TOHOKU UNIVERSITY Researchers

Details of the Researcher

Home

日本語 English

Noriyasu Homma

Section

Graduate School of Medicine

Job title

Professor

Degree

博士（工学）（東北大学）

researchmap

https://researchmap.jp/noriyasu_homma

J-GLOBAL ID

200901061502830497

Committee Memberships 24

計測自動制御学会　理事

2021/02 - Present
計測自動制御学会　東北支部顧問

2014/01 - Present
日本生体医工学会　東北支部幹事

2009/04 - Present
International Journal of Engineering Business Management　Editorial Board Member

2008/11 - Present
International Journal of Engineering Business Management　編集委員

2008/11 - Present
IEEE Computational Intelligence Society　Technical Committee Member

2007/04 - Present
IEEE Computational Intelligence Society　専門委員

2007/04 - Present
Artificial Life and Robotics　編集委員

2006/04 - Present
計測自動制御学会人工生命体システム部会　委員

2006/01 - Present
Intelligent and Fuzzy Systems　副編集長

2006/01 - Present
計測自動制御学会コンピューテーショナル・インテリジェンス（旧ニューラルネットワーク）部会　委員

2005/04 - Present
計測自動制御学会　東北支部支部長

2020/02 - 2021/02
計測自動制御学会　システム・情報部門部門長

2018/02 - 2019/02
計測自動制御学会　システム・情報部門副部門長

2017/02 - 2018/01
計測自動制御学会コンピューテーショナル・インテリジェンス部会　主査

2015/01 - 2016/12
計測自動制御学会コンピューテーショナル・インテリジェンス（旧ニューラルネットワーク）部会　副主査

2013/01 - 2014/12
計測自動制御学会　東北支部事業幹事

2010/01 - 2013/12
計測自動制御学会　東北支部事業幹事

2010/01 - 2013/12
計測自動制御学会人工生命体システム部会　主査

2008/01 - 2009/12
計測自動制御学会システムインテグレーション部門　表彰委員

2007/01 - 2008/12
計測自動制御学会　編集委員

2006/03 - 2008/02
計測自動制御学会　編集委員

2006/03 - 2008/02
計測自動制御学会人工生命体システム部会　副主査

2006/01 - 2007/12
計測自動制御学会人工生命体システム部会　副主査

2006/01 - 2007/12

Show all ︎Show first 5

Professional Memberships 4

日本放射線技術学会(1998/05-2008/10)
AAPM(2012/07-)
計測自動制御学会(1991/06-)
IEEE(1998/10-)

Research Interests 3

Chaos
Brain Functions
Complex Systems

Research Areas 4

Manufacturing technology (mechanical, electrical/electronic, chemical engineering) / Control and systems engineering /
Life sciences / Radiology /
Life sciences / Medical systems /
Informatics / Intelligent informatics /

Awards 23

SSI優秀論文賞

2020/11　計測自動制御学会システム・情報部門　肺がん放射線治療のための目標範囲提示型呼吸誘導システムによる呼吸動態再現性向上の試み
部門貢献表彰

2019/11　計測自動制御学会システム・情報部門
優秀論文発表賞A賞

2019/01　電気学会　マーカレス腫瘍追跡のための隠れマルコフモデルを用いたX線動画像からの物体輝度抽出
SSI Excellent Paper Award

2018/11　計測自動制御学会システム・情報部門　Computer-Aided Diagnosis of Micro-Calcification Clusters in Mammograms Using an Adaptive GMM
最優秀論文賞

2018/09　FANシンポジウム運営委員会　マーカレス腫瘍追跡のための隠れマルコフモデルを用いたX線動画像からの物体輝度抽出
SSI優秀論文賞

2017/11　計測自動制御学会システム・情報部門　肺がん放射線治療のためのX線動画像中の標的腫瘍のアフィン変換に基づく追跡法
SSI優秀発表賞

2017/11　計測自動制御学会システム・情報部門　乳がん病変検出のための深層学習を用いた計算機支援画像診断システム
FAN 2015 最優秀論文賞

2015/09/25　FANシンポジウム運営委員会
2014年度SICE学術奨励賞

2015/02/20　計測自動制御学会　構造情報に基づく乳房X線画像上の腫瘤陰影検出法
生体医工学シンポジウムベストリサーチアワード

2014/09/26　日本生体医工学会　Pilot study on evaluation of baroreflex function using green light photoplethysmogram
2013年度SICE学術奨励賞

2014/02/21　計測自動制御学会　画像解剖学的な乳腺異常推定による乳房X線画像上の構築の乱れ病変検出法
平成２５年電気学会優秀論文発表A賞

2014/02/05　電気学会　呼吸性位置変動時系列予測の性能改善のための知的モデル化の試み
生体医工学シンポジウムベストリサーチアワード

2013/09/21　日本生体医工学会　生理的指標を用いた3次元映像の生体影響評価における心理的影響の減衰
Finalist of SICE Annual Conf. 2013 International Award

2013/09/17　SICE　A Kernel-Based Method for Real-Time Markerless Tumor Tracking in Fluoroscopic Image Sequence
生体医工学シンポジウムベストリサーチアワード

2012/09/08　日本生体医工学会　Physiological Evaluation of Visually-Induced Motion Sickness Using Independent Component Analysis of Photoplethysmogram
Finalist of SICE Annual Conference Young Authors Award

2012/08/23　SICE
生体医工学シンポジウムベストリサーチアワード

2011/09/16　日本生体医工学会　植込み型除細動器用致死性不整脈検出アルゴリズムの高速・高精度化
7.American Association of Medical Physics, John R. Cameron Young Investigator Competition Finalists

2010/07　American Association of Medical Physics
Finalist of SICE Annual Conf. Young Author's Award

2005/08　SICE
Finalist of SICE Annual Conference Young Authors Award

2004/08/06　SICE
Finalist of SICE Annual Conference International Award

2002/08　SICE
KACC Best Paper Award

2000/10　Institute of Control, Automation, and Systems Engineering
Finalist of Best Poster Award at 14th IFAC World Congress

1999/07　IFAC

Show all ︎Show 5

Papers 237

Reproducible Machine Learning-Based Voice Pathology Detection: Introducing the Pitch Difference Feature. International-journal

Jan Vrba, Jakub Steinbach, Tomáš Jirsa, Laura Verde, Roberta De Fazio, Yuwen Zeng, Kei Ichiji, Lukáš Hájek, Zuzana Sedláková, Zuzana Urbániová, Martin Chovanec, Jan Mareš, Noriyasu Homma

Journal of voice : official journal of the Voice Foundation　2025/04/11

DOI： 10.1016/j.jvoice.2025.03.028 　

More details Close

PURPOSE: We introduce a novel methodology for voice pathology detection using the publicly available Saarbrücken Voice Database and a robust feature set combining commonly used acoustic handcrafted features with two novel ones: pitch difference (relative variation in fundamental frequency) and NaN feature (failed fundamental frequency estimation). METHODS: We evaluate six machine learning (ML) algorithms-support vector machine, k-nearest neighbors, naive Bayes, decision tree, random forest, and AdaBoost-using grid search for feasible hyperparameters and 20 480 different feature subsets. Top 1000 classification models-feature subset combinations for each ML algorithm are validated with repeated stratified cross-validation. To address class imbalance, we apply k-means synthetic minority oversampling technique to augment the training data. RESULTS: Our approach achieves 85.61%, 84.69%, and 85.22% unweighted average recall for females, males, and combined results, respectively. We intentionally omit accuracy as it is a highly biased metric for imbalanced data. CONCLUSION: Our study demonstrates that by following the proposed methodology and feature engineering, there is a potential in detection of various voice pathologies using ML models applied to the simplest vocal task, a sustained utterance of the vowel /a:/. To enable easier use of our methodology and to support our claims, we provide a publicly available GitHub repository with DOI 10.5281/zenodo.13771573. Finally, we provide a REFORMS checklist to enhance readability, reproducibility, and justification of our approach.
Vision Transformer-Based Breast Mass Diagnosis in Mammography Using Bilateral Information

Tianyu Zeng, Zhang Zhang, Yuwen Zeng, Xiaoyong Zhang, Kei Ichiji, Noriyasu Homma

2024 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)　147-152　2024/08/26
Publisher: IEEE
DOI： 10.1109/iicaiet62352.2024.10730097 　
Attention Optimization in AI-Aided Drowning Diagnosis Using Post-Mortem CT to Mitigate Overfitting with Limited Training Data

Zhang Zhang, Xiaoyong Zhang, Taihei Mizuno, Kei Ichiji, Noriyasu Homma

2024 International Joint Conference on Neural Networks (IJCNN)　32　1-6　2024/06/30
Publisher: IEEE
DOI： 10.1109/ijcnn60899.2024.10650327 　
Integration of Classification and Segmentation for Computer-Aided Diagnosis System of Drowning

Yuwen Zeng, Xiaoyong Zhang, Kei Ichiji, Noriyasu Homma

2024 International Joint Conference on Neural Networks (IJCNN)　1-7　2024/06/30
Publisher: IEEE
DOI： 10.1109/ijcnn60899.2024.10650202 　
Inconsistency between Human Observation and Deep Learning Models: Assessing Validity of Postmortem Computed Tomography Diagnosis of Drowning. International-journal

Yuwen Zeng, Xiaoyong Zhang, Jiaoyang Wang, Akihito Usui, Kei Ichiji, Ivo Bukovsky, Shuoyan Chou, Masato Funayama, Noriyasu Homma

Journal of imaging informatics in medicine　2024/02/09

DOI： 10.1007/s10278-024-00974-6 　

More details Close

Drowning diagnosis is a complicated process in the autopsy, even with the assistance of autopsy imaging and the on-site information from where the body was found. Previous studies have developed well-performed deep learning (DL) models for drowning diagnosis. However, the validity of the DL models was not assessed, raising doubts about whether the learned features accurately represented the medical findings observed by human experts. In this paper, we assessed the medical validity of DL models that had achieved high classification performance for drowning diagnosis. This retrospective study included autopsy cases aged 8-91 years who underwent postmortem computed tomography between 2012 and 2021 (153 drowning and 160 non-drowning cases). We first trained three deep learning models from a previous work and generated saliency maps that highlight important features in the input. To assess the validity of models, pixel-level annotations were created by four radiological technologists and further quantitatively compared with the saliency maps. All the three models demonstrated high classification performance with areas under the receiver operating characteristic curves of 0.94, 0.97, and 0.98, respectively. On the other hand, the assessment results revealed unexpected inconsistency between annotations and models' saliency maps. In fact, each model had, respectively, around 30%, 40%, and 80% of irrelevant areas in the saliency maps, suggesting the predictions of the DL models might be unreliable. The result alerts us in the careful assessment of DL tools, even those with high classification performance.
Attention Optimization in AI-Aided Drowning Diagnosis Using Post-Mortem CT to Mitigate Overfitting with Limited Training Data.

Zhang Zhang, Xiaoyong Zhang 0002, Taihei Mizuno, Kei Ichiji, Noriyasu Homma

IJCNN　1-6　2024

DOI： 10.1109/IJCNN60899.2024.10650327 　
Integration of Classification and Segmentation for Computer-Aided Diagnosis System of Drowning.

Yuwen Zeng, Xiaoyong Zhang 0002, Kei Ichiji, Noriyasu Homma

IJCNN　1-7　2024

DOI： 10.1109/IJCNN60899.2024.10650202 　
How intra-source imbalanced datasets impact the performance of deep learning for COVID-19 diagnosis using chest X-ray images

Zhang Zhang, Xiaoyong Zhang, Kei Ichiji, Ivo Bukovský, Noriyasu Homma

Scientific Reports　13　(1)　2023/11/03
Publisher: Springer Science and Business Media LLC
DOI： 10.1038/s41598-023-45368-w 　

eISSN： 2045-2322

More details Close

Abstract Over the past decade, the use of deep learning has been widely increasing in the medical image diagnosis field. Deep learning-based methods’ (DLMs) performance strongly relies on training data. Therefore, researchers often focus on collecting as much data as possible from different medical facilities or developing approaches to avoid the impact of inter-category imbalance (ICI), which means a difference in data quantity among categories. However, due to the ICI within each medical facility, medical data are often isolated and acquired in different settings among medical facilities, known as the issue of intra-source imbalance (ISI) characteristic. This imbalance also impacts the performance of DLMs but receives negligible attention. In this study, we study the impact of the ISI on DLMs by comparison of the version of a deep learning model that was trained separately by an intra-source imbalanced chest X-ray (CXR) dataset and an intra-source balanced CXR dataset for COVID-19 diagnosis. The finding is that using the intra-source imbalanced dataset causes a serious training bias, although the dataset has a good inter-category balance. In contrast, the deep learning model performed a reliable diagnosis when trained on the intra-source balanced dataset. Therefore, our study reports clear evidence that the intra-source balance is vital for training data to minimize the risk of poor performance of DLMs.
Comprehensive evaluation of machine learning algorithms for predicting sleep–wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability

Xue Li, Chiaki Ono, Noriko Warita, Tomoka Shoji, Takashi Nakagawa, Hitomi Usukura, Zhiqian Yu, Yuta Takahashi, Kei Ichiji, Norihiro Sugita, Natsuko Kobayashi, Saya Kikuchi, Ryoko Kimura, Yumiko Hamaie, Mizuki Hino, Yasuto Kunii, Keiko Murakami, Mami Ishikuro, Taku Obara, Tomohiro Nakamura, Fuji Nagami, Takako Takai, Soichi Ogishima, Junichi Sugawara, Tetsuro Hoshiai, Masatoshi Saito, Gen Tamiya, Nobuo Fuse, Susumu Fujii, Masaharu Nakayama, Shinichi Kuriyama, Masayuki Yamamoto, Nobuo Yaegashi, Noriyasu Homma, Hiroaki Tomita

Frontiers in Psychiatry　14　2023/06/06
Publisher: Frontiers Media SA
DOI： 10.3389/fpsyt.2023.1104222 　

eISSN： 1664-0640

More details Close

Introduction Perinatal women tend to have difficulties with sleep along with autonomic characteristics. This study aimed to identify a machine learning algorithm capable of achieving high accuracy in predicting sleep–wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability (HRV). Methods Nine HRV indicators (features) and sleep–wake conditions of 154 pregnant women were measured for 1 week, from the 23rd to the 32nd weeks of pregnancy. Ten machine learning and three deep learning methods were applied to predict three types of sleep–wake conditions (wake, shallow sleep, and deep sleep). In addition, the prediction of four conditions, in which the wake conditions before and after sleep were differentiated—shallow sleep, deep sleep, and the two types of wake conditions—was also tested. Results and Discussion In the test for predicting three types of sleep–wake conditions, most of the algorithms, except for Naïve Bayes, showed higher areas under the curve (AUCs; 0.82–0.88) and accuracy (0.78–0.81). The test using four types of sleep–wake conditions with differentiation between the wake conditions before and after sleep also resulted in successful prediction by the gated recurrent unit with the highest AUC (0.86) and accuracy (0.79). Among the nine features, seven made major contributions to predicting sleep–wake conditions. Among the seven features, “the number of interval differences of successive RR intervals greater than 50 ms (NN50)” and “the proportion dividing NN50 by the total number of RR intervals (pNN50)” were useful to predict sleep–wake conditions unique to pregnancy. These findings suggest alterations in the vagal tone system specific to pregnancy.
How Different Data Sources Impact Deep Learning Performance in COVID-19 Diagnosis using Chest X-ray Images.

Zhang Zhang, Xiaoyong Zhang 0002, Kei Ichiji, Ivo Bukovsky, Shuo-Yan Chou, Noriyasu Homma

IIAI-AAI　508-513　2023

DOI： 10.1109/IIAI-AAI59060.2023.00103 　
How Different Data Sources Impact Deep Learning Performance in COVID-19 Diagnosis using Chest X-ray Images

Zhang Zhang, Xiaoyong Zhang, Kei Ichiji, Ivo Bukovsky, Shuoyan Chou, Noriyasu Homma

Proceedings - 2023 14th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2023　508-513　2023

DOI： 10.1109/IIAI-AAI59060.2023.00103 　
Risk Analysis of Breast Cancer by Using Bilateral Mammographic Density Differences: A Case-Control Study

Zhang Zhang, Xiaoyong Zhang, Jiaqi Chen, Yumi Takane, Satoru Yanagaki, Naoko Mori, Kei Ichiji, Katsuaki Kato, Mika Yanagaki, Akiko Ebata, Minoru Miyashita, Takanori Ishida, Noriyasu Homma

The Tohoku Journal of Experimental Medicine　261　(2)　139-150　2023
Publisher: Tohoku University Medical Press
DOI： 10.1620/tjem.2023.j066 　

ISSN： 0040-8727

eISSN： 1349-3329
Deep Learning-Based Diagnosis of Fatal Hypothermia Using Post-Mortem Computed Tomography

Yuwen Zeng, Xiaoyong Zhang, Issei Yoshizumi, Zhang Zhang, Taihei Mizuno, Shota Sakamoto, Yusuke Kawasumi, Akihito Usui, Kei Ichiji, Ivo Bukovsky, Masato Funayama, Noriyasu Homma

The Tohoku Journal of Experimental Medicine　260　(3)　253-261　2023
Publisher: Tohoku University Medical Press
DOI： 10.1620/tjem.2023.j041 　

ISSN： 0040-8727

eISSN： 1349-3329
Improved Tumor Image Estimation in X-Ray Fluoroscopic Images by Augmenting 4DCT Data for Radiotherapy

Takumi Shinohara, Kei Ichiji, Jiaoyang Wang, Noriyasu Homma, Xiaoyong Zhang, Norihiro Sugita, Makoto Yoshizawa

Journal of Advanced Computational Intelligence and Intelligent Informatics　26　(4)　471-482　2022/07/20
Publisher: Fuji Technology Press Ltd.
DOI： 10.20965/jaciii.2022.p0471 　

ISSN： 1343-0130

eISSN： 1883-8014

More details Close

Measurement of tumor position is important for the radiotherapy of lung tumors with respiratory motion. Although tumors can be observed using X-ray fluoroscopy during radiotherapy, it is often difficult to measure tumor position from X-ray image sequences accurately because of overlapping organs. To measure tumor position accurately, a method for extracting tumor intensities from X-ray image sequences using a hidden Markov model (HMM) has been proposed. However, the performance of tumor intensity extraction depends on limited knowledge regarding the tumor motion observed in the four-dimensional computed tomography (4DCT) data used to construct the HMM. In this study, we attempted to improve the performance of tumor intensity extraction by augmenting 4DCT data. The proposed method was tested using simulated datasets of X-ray image sequences. The experimental results indicated that the HMM using the augmentation method could improve tumor-tracking performance when the range of tumor movement during treatment differed from that in the 4DCT data.
[A Review of Current Knowledge for X-ray Energy in CT: Practical Guide for CT Technologist].

Kazutaka Hoyoshi, Tomomi Ohmura, Shingo Kayano, Mitsunori Goto, Shun Muramatsu, Noriyasu Homma

Nihon Hoshasen Gijutsu Gakkai zasshi　78　(5)　449-463　2022/05/20

DOI： 10.6009/jjrt.2022-1238 　

More details Close

In computed tomography (CT) systems, the optimal X-ray energy in imaging depends on the material composition and the subject size. Among the parameters related to the X-ray energy, we can arbitrarily change only the tube voltage. For years, the tube voltage has often been set at 120 kVp. However, since about 2000, there has been an increasing interest in reducing radiation dose, and it has led to the publication of various reports on low tube voltage. Furthermore, with the spread of dual-energy CT, virtual monochromatic X-ray images are widely used since the contrast can be adjusted by selecting the optional energy. Therefore, because of the renewed interest in X-ray energy in CT imaging, the issue of energy and imaging needs to be summarized. In this article, we describe the basics of physical characteristics of X-ray attenuation with materials and its influence on the process of CT imaging. Moreover, the relationship between X-ray energy and CT imaging is discussed for clinical applications.
A 2.5D Deep Learning-Based Method for Drowning Diagnosis Using Post-Mortem Computed Tomography

Yuwen Zeng, Xiaoyong Zhang, Yusuke Kawasumi, Akihito Usui, Kei Ichiji, Masato Funayama, Noriyasu Homma

IEEE Journal of Biomedical and Health Informatics　27　(2)　1-10　2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
DOI： 10.1109/jbhi.2022.3225416 　

ISSN： 2168-2194

eISSN： 2168-2208
A cloud system for extraction of autonomic nervous system indices and blood pressure variabilities from video images

Makoto Yoshizawa, Norihiro Sugita, Akira Tanaka, Noriyasu Homma, Tomoyuki Yambe

Proceedings of the International Display Workshops　27　983-984　2021/12/09

ISSN： 1883-2490
Remote, Non-Contact and Continuous Extraction of Multiple Peoples’ Autonomic Nervous System Indices from One Fish-Eye Camera

Makoto Yoshizawa, Norihiro Sugita, Akira Tanaka, Noriyasu Homma, Emi Yuda, Tomoyuki Yambe

Proceedings of the International Display Workshops　573-573　2021/12/02
Publisher: International Display Workshops General Incorporated Association
DOI： 10.36463/idw.2021.0573 　

ISSN： 1883-2490
Letter on Convergence of In-Parameter-Linear Nonlinear Neural Architectures With Gradient Learnings. International-journal

Ivo Bukovsky, Gejza Dohnal, Peter M Benes, Kei Ichiji, Noriyasu Homma

IEEE transactions on neural networks and learning systems　PP　2021/11/17

DOI： 10.1109/TNNLS.2021.3123533 　

More details Close

This letter summarizes and proves the concept of bounded-input bounded-state (BIBS) stability for weight convergence of a broad family of in-parameter-linear nonlinear neural architectures (IPLNAs) as it generally applies to a broad family of incremental gradient learning algorithms. A practical BIBS convergence condition results from the derived proofs for every individual learning point or batches for real-time applications.
Comments on ``Convergence Analysis of Adaptive Exponential Functional Link Network''. International-journal

Ivo Bukovsky, Gejza Dohnal, Noriyasu Homma

IEEE transactions on neural networks and learning systems　PP　2021/11/11

DOI： 10.1109/TNNLS.2021.3123540 　

More details Close

This article is to comment on the derivation of the weight-update stability of in-parameter-linear nonlinear learning system with the gradient descent learning rule in the above article. Our comments are not to disqualify the commented article's whole contribution; however, the issues should be pointed out to avoid their proliferation.
Deep Learning-Based Interpretable Computer-Aided Diagnosis of Drowning for Forensic Radiology

Yuwen Zeng, Xiaoyong Zhang, Yusuke Kawasumi, Akihito Usui, Kei Ichiji, Masato Funayama, Noriyasu Homma

2021 60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021　820-824　2021/09/08
Publisher: Institute of Electrical and Electronics Engineers Inc.
An interpretable DL-based method for diagnosis of H.Pylori infection using gastric X-ray images

Reima Ishii, Xiaoyong Zhang, Noriyasu Homma

LifeTech 2021 - 2021 IEEE 3rd Global Conference on Life Sciences and Technologies　6-7　2021/03/09
Publisher: Institute of Electrical and Electronics Engineers Inc.
DOI： 10.1109/LifeTech52111.2021.9391979 　
Manganese Dynamics in Mouse Brain After Systemic MnCl2 Administration for Activation-Induced Manganese-Enhanced MRI. International-journal

Hiroki Tanihira, Tomonori Fujiwara, Satomi Kikuta, Noriyasu Homma, Makoto Osanai

Frontiers in neural circuits　15　787692-787692　2021

DOI： 10.3389/fncir.2021.787692 　

More details Close

Activation-induced manganese-enhanced MRI (AIM-MRI) is an attractive tool for non-invasively mapping whole brain activities. Manganese ions (Mn2+) enter and accumulate in active neurons via calcium channels. Mn2+ shortens the longitudinal relaxation time (T1) of H+, and the longitudinal relaxation rate R1 (1/T1) is proportional to Mn2+ concentration. Thus, AIM-MRI can map neural activities throughout the brain by assessing the R1 map. However, AIM-MRI is still not widely used, partially due to insufficient information regarding Mn2+ dynamics in the brain. To resolve this issue, we conducted a longitudinal study looking at manganese dynamics after systemic administration of MnCl2 by AIM-MRI with quantitative analysis. In the ventricle, Mn2+ increased rapidly within 1 h, remained high for 3 h, and returned to near control levels by 24 h after administration. Microdialysis showed that extracellular Mn returned to control levels by 4 h after administration, indicating a high concentration of extracellular Mn2+ lasts at least about 3 h after administration. In the brain parenchyma, Mn2+ increased slowly, peaked 24-48 h after administration, and returned to control level by 5 days after a single administration and by 2 weeks after a double administration with a 24-h interval. These time courses suggest that AIM-MRI records neural activity 1-3 h after MnCl2 administration, an appropriate timing of the MRI scan is in the range of 24-48 h following systemic administration, and at least an interval of 5 days or a couple of weeks for single or double administrations, respectively, is needed for a repeat AIM-MRI experiment.
Heart Rate Information-Based Machine Learning Prediction of Emotions Among Pregnant Women. International-journal

Xue Li, Chiaki Ono, Noriko Warita, Tomoka Shoji, Takashi Nakagawa, Hitomi Usukura, Zhiqian Yu, Yuta Takahashi, Kei Ichiji, Norihiro Sugita, Natsuko Kobayashi, Saya Kikuchi, Yasuto Kunii, Keiko Murakami, Mami Ishikuro, Taku Obara, Tomohiro Nakamura, Fuji Nagami, Takako Takai, Soichi Ogishima, Junichi Sugawara, Tetsuro Hoshiai, Masatoshi Saito, Gen Tamiya, Nobuo Fuse, Shinichi Kuriyama, Masayuki Yamamoto, Nobuo Yaegashi, Noriyasu Homma, Hiroaki Tomita

Frontiers in psychiatry　12　799029-799029　2021

DOI： 10.3389/fpsyt.2021.799029 　

More details Close

In this study, the extent to which different emotions of pregnant women can be predicted based on heart rate-relevant information as indicators of autonomic nervous system functioning was explored using various machine learning algorithms. Nine heart rate-relevant autonomic system indicators, including the coefficient of variation R-R interval (CVRR), standard deviation of all NN intervals (SDNN), and square root of the mean squared differences of successive NN intervals (RMSSD), were measured using a heart rate monitor (MyBeat) and four different emotions including "happy," as a positive emotion and "anxiety," "sad," "frustrated," as negative emotions were self-recorded on a smartphone application, during 1 week starting from 23rd to 32nd weeks of pregnancy from 85 pregnant women. The k-nearest neighbor (k-NN), support vector machine (SVM), logistic regression (LR), random forest (RF), naïve bayes (NB), decision tree (DT), gradient boosting trees (GBT), stochastic gradient descent (SGD), extreme gradient boosting (XGBoost), and artificial neural network (ANN) machine learning methods were applied to predict the four different emotions based on the heart rate-relevant information. To predict four different emotions, RF also showed a modest area under the receiver operating characteristic curve (AUC-ROC) of 0.70. CVRR, RMSSD, SDNN, high frequency (HF), and low frequency (LF) mostly contributed to the predictions. GBT displayed the second highest AUC (0.69). Comprehensive analyses revealed the benefits of the prediction accuracy of the RF and GBT methods and were beneficial to establish models to predict emotions based on autonomic nervous system indicators. The results implicated SDNN, RMSSD, CVRR, LF, and HF as important parameters for the predictions.
Human ability enhancement for reading mammographic masses by a deep learning technique

Noriyasu Homma, Kyohei Noro, Xiaoyong Zhang, Yutaro Kon, Kei Ichiji, Ivo Bukovsky, Akiko Sato, Naoko Mori

Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020　2962-2964　2020/12/16
Publisher: IEEE
DOI： 10.1109/BIBM49941.2020.9313564 　
シミュレーション画像を用いたダークバンドアーチファクト評価

保吉和貴, 佐藤和宏, 菊地雄歩, 松岡真由, 本間経康

日本CT技術学会雑誌　第8回学術大会予稿集　6-6　2020/10
Publisher: (NPO)日本CT技術学会
ISSN： 2434-2769

eISSN： 2434-2750
Learning entropy of adaptive filters via clustering techniques

Ivo Bukovsky, Gejza Dohnal, Pavel Steinbauer, Ondrej Budik, Kei Ichiji, Homma Noriyasu

2020 Sensor Signal Processing for Defence Conference, SSPD 2020　2020/09/01
Publisher: Institute of Electrical and Electronics Engineers Inc.
DOI： 10.1109/SSPD47486.2020.9272138 　
A Deep Learning Aided Drowning Diagnosis for Forensic Investigations using Post-Mortem Lung CT Images International-journal

Noriyasu Homma, Xiaoyong Zhang, Amber Qureshi, Takuya Konno, Yusuke Kawasumi, Akihito Usui, Masato Funayama, Ivo Bukovsky, Kei Ichiji, Norihiro Sugita, Makoto Yoshizawa

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS　2020-July　1262-1265　2020/07

DOI： 10.1109/EMBC44109.2020.9175731 　

ISSN： 1557-170X
Adaptive Gaussian Mixture Model-Based Statistical Feature Extraction for Computer-Aided Diagnosis of Micro-Calcification Clusters in Mammograms

ZHANG Zhang, ZHANG Xiaoyong, ICHIJI Kei, TAKANE Yumi, YANAGAKI Satoru, KAWASUMI Yusuke, ISHIBASHI Tadashi, HOMMA Noriyasu

SICE Journal of Control, Measurement, and System Integration　13　(4)　183-190　2020
Publisher: The Society of Instrument and Control Engineers
DOI： 10.9746/jcmsi.13.183 　

ISSN： 1882-4889

More details Close

In mammography, detection and categorization of micro-calcification clusters (MCCs) using computer-aided diagnosis (CAD) systems are very important tasks because MCCs are important signs at an early stage of breast cancer. However, the conventional methods of CAD only classify MCCs into benign and malignant types, and no method has been developed for a medical requirement to classify the MCCs into more detailed categories according to the spatial distribution of MCCs. To provide a cogent second opinion, we specifically focus on analyzing MCCs' spatial distribution and propose an adaptive Gaussian mixture model-based method to extract the statistical features of the spatial distribution in this study. By mimicking the radiologists' workflow, the proposed method used the main feature of each spatial distributions to classify the MCCs and then provide a cogent second opinion to increase the confidence level of diagnosis decisions. The experiments have been performed on 100 mammographic images with MCCs from a clinical dataset. The experimental results showed that the proposed method was able to detect the MCCs and classify the spatial distribution of the MCCs effectively.
Comparison of Visible and Infrared Video Plethysmography Captured from Different Regions of the Human Face. International-journal

Norihiro Sugita, Tomoya Matsuzaki, Makoto Yoshizawa, Kei Ichiji, Shunsuke Yamaki, Noriyasu Homma

42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society(EMBC)　2020　4187-4190　2020
Publisher: IEEE
DOI： 10.1109/EMBC44109.2020.9176138 　

More details Close

Recently, video plethysmography (VPG) - a heart rate estimation technique using a video camera - has gained significant attention. Most studies of VPG have used a visible RGB camera; only a limited number of studies investigating near-infrared light (wavelength 750-2500 nm), which can be used even in a dark environment, have been performed. The purpose of this study was to investigate the differences between VPG data collected using visible light (VPGVIS) or near-infrared light (VPGNIR) from four facial areas (forehead, right cheek, left cheek, and nose). An experiment was conducted to obtain both VPGVIS and VPGNIR simultaneously by alternately irradiating the face with NIR and VIS lights. Experimental results showed that the root mean squared error of heart rate estimated using VPGNIR was 1 bpm higher than that of VPGVIS. However, contrary to our expectations, the power of the heartbeat-related component included in VPGNIR was not reduced despite the absorbance of hemoglobin in the NIR light range being 1/100 of that in the VIS light range. This result supports the hypothesis that a main factor in the generation of VPG waves was change in the optical properties caused by blood vessels compressing the subcutaneous tissue and the venous bed. Additionally, the accuracy of the heart rate estimation using VPG tended to be high when the nose was set as the ROI. This result was likely associated with the anatomical structure of the nose.
Hidden Markov Model-based Extraction of Target Objects in X-ray Image Sequence for Lung Radiation Therapy Peer-reviewed

Masahiro Shindo, Kei Ichiji, Noriyasu Homma, Xiaoyong Zhang, Shungo Okuda, Norihiro Sugita, Shunsuke Yamaki, Yoshihiro Takai, Makoto Yoshizawa

IEEJ Transactions on Electronics, Information and Systems　140　(1)　49-60　2020/01
Estimation of Absolute Blood Pressure using Video Images Captured at Different Heights from the Heart International-journal Peer-reviewed

Norihiro Sugita, Taihei Noro, Makoto Yoshizawa, Kei Ichiji, Shunsuke Yamaki, Noriyasu Homma

Proc. 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society　2019　4458-4461　2019/07
Publisher: IEEE
DOI： 10.1109/embc.2019.8856362 　

More details Close

The risk of cardiovascular diseases is related to the absolute level of blood pressure as well as its fluctuation while sleeping or during daily activities. To assess the risk, a simpler method to monitor daily blood pressure is desirable. In recent years, there has been a focus on developing a method to obtain pulse waves from video images of the human body. This is a promising technique to acquire biometric information without contact. In this study, we propose a new method to estimate the absolute level of blood pressure by using two video images of human hands captured at different heights from the heart. We focus on the amplitude difference of pulse waves obtained from the video images and derive an equation to estimate blood pressure based on the relationship between the internal pressure and the cross-sectional area of the blood vessel. The accuracy of the estimation was evaluated using data obtained from 5 healthy subjects performing cycling exercises that change their blood pressure. The average value of the root mean square error between the real value and the estimated value was 25.7 mmHg, while that of correlation coefficient was 0.66. There were large individual differences, particularly in the estimation of the absolute value of blood pressure. This result suggests the need for individual correction of the compliance curve, which represents the relationship between the internal pressure and the cross-sectional area of the blood vessel.
Effect of viewing a three-dimensional movie with vertical parallax Peer-reviewed

Norihiro Sugita, Katsuhiro Sasaki, Makoto Yoshizawa, Kei Ichiji, Makoto Abe, Noriyasu Homma, Tomoyuki Yambe

Displays　58　20-26　2019/07
Publisher: Elsevier BV
DOI： 10.1016/j.displa.2018.10.007 　

ISSN： 0141-9382
A method to measure slice sensitivity profiles of CT images under low-contrast and high-noise conditions. International-journal Peer-reviewed

Goto M, Tominaga C, Taura M, Azumi H, Sato K, Homma N, Mori I

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)　60　100-110　2019/04

DOI： 10.1016/j.ejmp.2019.03.010 　

ISSN： 1120-1797

More details Close

Noise reduction features of iterative reconstruction (IR) methods in computed tomography might accompany the sacrifice of the longitudinal resolution, or slice sensitivity profile (SSP), at low contrast-to-noise ratio (CNR) conditions. To assess the benefit of IR methods correctly, the difference of SSP between IR methods and filtered-backprojection (FBP) must be taken into account. Therefore, SSP measurement under low-CNR conditions is necessary. Although edge methods are predominantly used, their performance under low-CNR conditions appears to be not fully established. We developed a method that is compatible with extremely low-CNR conditions. Thin plastic disk-shaped sheets embedded in acrylic resin were used as low-contrast test objects. The lowest peak contrast used was approximately 17 [HU]. We assessed the performance of our method by using FBP images. We identified a source of measurement instability aside from noise: the measured thin-slice SSP is dependent on the orbital phase of helical scan, presumably because of cone-beam artifacts. This impediment to high accuracy is manageable using phase-controlled scans. We confirmed that table position repeatability is much better than the value of the specifications, and therefore the ensemble-averaged images of multiple scans can be used for SSP measurement. Accurate measurement of SSP under extremely low-CNR conditions is possible, even when the test object is visually indiscernible from the noisy background. Low-contrast SSP behavior is elucidated for IR methods (AIDR-3D, FIRST, and AiSR-V) by using this measurement method.
Learning Entropy as a Learning-Based Information Concept International-journal Peer-reviewed

Bukovsky Ivo, Kinsner Witold, Homma Noriyasu

ENTROPY　21　(2)　2019/02

DOI： 10.3390/e21020166 　

ISSN： 1099-4300
[Tilted-wire method to measure resolution properties of CT images at extremely low-contrast and high-noise conditions].

Chiaki Tominaga, Hiroki Azumi, Mitsunori Goto, Masaaki Taura, Noriyasu Homma, Issei Mori

Igaku butsuri : Nihon Igaku Butsuri Gakkai kikanshi = Japanese journal of medical physics : an official journal of Japan Society of Medical Physics　39　(3)　69-69　2019

DOI： 10.11323/jjmp.39.3_69 　
A key-point based real-time tracking of lung tumor in x-ray image sequence by using difference of Gaussians filtering and optical flow. Peer-reviewed

Ichiji K, Yoshida Y, Homma N, Zhang X, Bukovsky I, Takai Y, Yoshizawa M

Physics in medicine and biology　63　(18)　185007　2018/09

DOI： 10.1088/1361-6560/aada71 　

ISSN： 0031-9155
Probabilistic Decomposition of X-Ray Image Sequence to Extract Obscure Target Objects for Monitoring Intrafractional Organ Motion Peer-reviewed

Masahiro Shindo, Kei Ichiji, Noriyasu Homma, Xiaoyong Zhang, Yoshihiro Takai, Makoto Yoshizawa

American Association of Physicists in Medicine 60th Annual Meeting　(TU-AB-205-3)　2018/07
Extraction of Blood Pressure Information from Video Plethysmography Invited Peer-reviewed

Norihiro Sugita, Makoto Yoshizawa, Akira Tanaka, Makoto Abe, Noriyasu Homma, Tomoyuki Yambe

40th Annual Conference of IEEE Engineering in Medicine Biology Society 2018　2018/07
Tilted-wire method for measuring resolution properties of CT images under extremely low-contrast and high-noise conditions. Peer-reviewed

Tominaga C, Azumi H, Goto M, Taura M, Homma N, Mori I

Radiological physics and technology　11　(2)　125-137　2018/06

DOI： 10.1007/s12194-018-0443-8 　

ISSN： 1865-0333

More details Close

Edge methods are predominantly used for modulation transfer function (MTF) measurements in computed tomography (CT) images reconstructed using iterative methods. However, edge methods employ a relatively large and distinct test object, which is intended to simulate relatively large and distinct clinical organs. If one wants to assess the image quality of a small low-contrast object that is visually indistinct against a noisy background, a small and indistinct test object is desired. Another concern is that information related to the signal amount is discarded during MTF measurements. Choosing a weak impulse as the ultimately small test object, we have developed a tilted-wire method, which is a type of point spread function (PSF) method compatible with extremely low contrast-to-noise ratio (CNR) conditions. The signal amount is measured as the PSF volume. We used two commercial CT systems to evaluate the measurement accuracy of the tilted-wire method. When ensemble-averaged images are used, one can measure the MTF even when the wire is indiscernible from noise. The measurement error under such conditions is a few percent for both the MTF and signal amount. We also applied the tilted-wire method to two hybrid iterative reconstruction methods, namely AIDR-3D and ASiR. The results show that the MTF of ASiR is completely CNR-dependent, but that of AIDR-3D is noise-dependent. The signal amount obtained with ASiR is unchanged from that obtained through filtered back-projection (FBP). The signal amount obtained with AIDR-3D is less than that obtained through FBP, depending on the noise level.
Potential improvements of lung and prostate MLC tracking investigated by treatment simulations. International-journal Peer-reviewed

Toftegaard J, Keall PJ, O'Brien R, Ruan D, Ernst F, Homma N, Ichiji K, Poulsen PR

Medical physics　45　(5)　2218-2229　2018/05

DOI： 10.1002/mp.12868 　

ISSN： 0094-2405

More details Close

PURPOSE/OBJECTIVES: Intrafraction tumor motion during external radiotherapy is a challenge for the treatment accuracy. A novel technique to mitigate the impact of tumor motion is real-time adaptation of the multileaf collimator (MLC) aperture to the motion, also known as MLC tracking. Although MLC tracking improves the dosimetric accuracy, there are still residual errors. Here, we investigate and rank the performance of five prediction algorithms and seven improvements of an MLC tracking system by extensive tracking treatment simulations. MATERIALS AND METHODS: An in-house-developed MLC tracking simulator that has been experimentally validated against an electromagnetic-guided MLC tracking system was used to test the prediction algorithms and tracking system improvements. The simulator requires a Dicom treatment plan and a motion trajectory as input and outputs all motion of the accelerator during MLC tracking treatment delivery. For lung tumors, MLC tracking treatments were simulated with a low and a high modulation VMAT plan using 99 patient-measured lung tumor trajectories. For prostate, tracking was also simulated with a low and a high modulation VMAT plan, but with 695 prostate trajectories. For each simulated treatment, the tracking error was quantified as the mean MLC exposure error, which is the sum of the overexposed area (irradiated area that should have been shielded according to the treatment plan) and the underexposed area (shielded area that should have been irradiated). First, MLC tracking was simulated with the current MLC tracking system without prediction, with perfect prediction (Perfect), and with the following five prediction algorithms: linear Kalman filter (Kalman), kernel density estimation (KDE), linear adaptive filtering (LAF), wavelet-based multiscale autoregression (wLMS), and time variant seasonal autoregression (TVSAR). Next, MLC tracking was simulated using the best prediction algorithm and seven different tracking system improvements: no localization signal latency (a), doubled maximum MLC leaf speed (b), halved MLC leaf width (c), use of Y backup jaws to track motion perpendicular to the MLC leaves (d), dynamic collimator rotation for alignment of the MLC leaves with the dominant target motion direction (e), improvements 4 and 5 combined (f), and all improvements combined (g). RESULTS: All results are presented as the mean residual MLC exposure error compared to no tracking. In the prediction study, the residual MLC exposure error was 47.0% (no prediction), 45.1% (Kalman), 43.8% (KDE), 43.7% (LAF), 42.1% (wLMS), 40.1% (TVSAR), and 36.5% (Perfect) for lung MLC tracking. For prostate MLC tracking, it was 66.0% (no prediction), 66.9% (Kalman), and 63.4% (Perfect). For lung with TVSAR prediction, the residual MLC exposure error for the seven tracking system improvements was 37.2%(1), 38.3%(2), 37.4%(3), 34.2%(4), 30.6%(5), 27.7%(6), and 20.7%(7). For prostate with no prediction, the residual MLC exposure error was 61.7%(1), 61.4%(2), 55.4%(3), 57.2%(4), 47.5%(5), 43.7%(6), and 38.7%(7). CONCLUSION: For prostate, MLC tracking was slightly better without prediction than with linear Kalman filter prediction. For lung, the TVSAR prediction algorithm performed best. Dynamic alignment of the collimator with the dominant motion axis was the most efficient MLC tracking improvement except for lung tracking with the low modulation VMAT plan, where jaw tracking was slightly better.
Contactless Technique for Measuring Blood-Pressure Variability from One Region in Video Plethysmography Peer-reviewed

Norihiro Sugita, Makoto Yoshizawa, Makoto Abe, Akira Tanaka, Noriyasu Homma, Tomoyuki Yambe

Journal of Medical and Biological Engineering　1-10　2018/03
Remote and non-contact extraction techniques of autonomic nervous system indices and blood pressure variabilities from video images

Makoto Yoshizawa, Norihiro Sugita, Akira Tanaka, Noriyasu Homma, Tomoyuki Yambe

Proceedings of the International Display Workshops　2　968-971　2018
Publisher: International Display Workshops
ISSN： 1883-2490
An Optimization Technique to Extract Video Pulse Wave for Non-Contact Remote Monitoring of Autonomic Nervous System and Blood Pressure Variability. Peer-reviewed

Makoto Yoshizawa, Norihiro Sugita, Akira Tanaka, Kei Ichiji, Noriyasu Homma, Tomoyuki Yambe

IEEE 7th Global Conference on Consumer Electronics, GCCE 2018, Nara, Japan, October 9-12, 2018　425-428　2018
Publisher: IEEE
DOI： 10.1109/GCCE.2018.8574732 　
Development of System to Reproduce Outside Environments when Driving with Cycling Wheelchair

杉田典大, 小川健太, 吉澤誠, 本間経康, 関和則, 半田康延

日本バーチャルリアリティ学会論文誌(Web)　23　(1)　3‐11(J‐STAGE)　2018

DOI： 10.18974/tvrsj.23.1_3 　

ISSN： 2423-9593
A Deep Learning-based Computer-aided Diagnosis System for Mammographic Lesion Detection

鈴木真太郎, ZHANG Xiaoyong, 本間経康, 市地慶, 高根侑美, 柳垣聡, 川住祐介, 石橋忠司, 吉澤誠

計測自動制御学会論文集　54　(8)　659‐669(J‐STAGE)　2018

DOI： 10.9746/sicetr.54.659 　

ISSN： 0453-4654
Dosimetric evaluation of MLC-based dynamic tumor tracking radiotherapy using digital phantom: Desired setup margin for tracking radiotherapy. Peer-reviewed

Kadoya N, Ichiji K, Uchida T, Nakajima Y, Ikeda R, Uozumi Y, Zhang X, Bukovsky I, Yamamoto T, Takeda K, Takai Y, Jingu K, Homma N

Medical dosimetry : official journal of the American Association of Medical Dosimetrists　43　(1)　74-81　2018

DOI： 10.1016/j.meddos.2017.08.005 　

ISSN： 0958-3947
Classification of Mammographic Masses by Deep Learning Peer-reviewed

Zhang, Xiaoyong Sasaki, Takuya Suzuki, Shintaro Takane, Yumi Kawasumi, Yusuki Ishibashiz, Tadashi Homma, Noriyasu Yoshizawa, Makoto

2017 56TH ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS OF JAPAN (SICE)　793-796　2017/09/19

DOI： 10.23919/SICE.2017.8105545 　
An Approach to Stable Gradient-Descent Adaptation of Higher Order Neural Units International-journal Peer-reviewed

Bukovsky, Ivo Homma, Noriyasu

IEEE Trans. Neural Netw. Learn. Syst.　28　(9)　2022-2034　2017/09

DOI： 10.1109/TNNLS.2016.2572310 　

More details Close

Stability evaluation of a weight-update system of higher order neural units (HONUs) with polynomial aggregation of neural inputs (also known as classes of polynomial neural networks) for adaptation of both feedforward and recurrent HONUs by a gradient descent method is introduced. An essential core of the approach is based on the spectral radius of a weight-update system, and it allows stability monitoring and its maintenance at every adaptation step individually. Assuring the stability of the weight-update system (at every single adaptation step) naturally results in the adaptation stability of the whole neural architecture that adapts to the target data. As an aside, the used approach highlights the fact that the weight optimization of HONU is a linear problem, so the proposed approach can be generally extended to any neural architecture that is linear in its adaptable parameters.
最大リャプノフ指数推定に基づく呼吸性移動時系列の予測可能性の検討 Peer-reviewed

市地慶, 本間経康, 張曉勇, 武田賢, 髙井良尋, 杉田典大, 吉澤誠

東北医学雑誌　129　(1)　47-47　2017/08
Higher order neural units for efficient adaptive control of weakly nonlinear systems

Ivo Bukovsky, Jan Voracek, Kei Ichiji, Homma Noriyasu

IJCCI 2017 - Proceedings of the 9th International Joint Conference on Computational Intelligence　149-157　2017

DOI： 10.5220/0006557301490157 　
Framework for Discrete-Time Model Reference Adaptive Control of Weakly Nonlinear Systems with HONUs. Peer-reviewed

Peter Mark Benes, Array,Martin Vesely, Jan Vorácek, Kei Ichiji, Noriyasu Homma

Computational Intelligence - 9th International Joint Conference, IJCCI 2017 Funchal-Madeira, Portugal, November 1-3, 2017 Revised Selected Papers　829　239-262　2017
Publisher: Springer
DOI： 10.1007/978-3-030-16469-0_13 　

ISSN： 1860-949X
Modulation transfer function measurement method using extremely noisy tilted-wire images Peer-reviewed

Proceedings of JSCT　4　(2)　23-26　2016/12
A Real-Time Homography-Based Tracking Method for Tracking Deformable Tumor Motion in Fluoroscopy Peer-reviewed

Zhang, Xiaoyong Homma, Noriyasu Ichiji, Kei Sugita, Norihiro Takai, Yoshihiro Yoshizawa, Makoto

2016 55TH ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS OF JAPAN (SICE)　1673-1677　2016/09/20

DOI： 10.1109/SICE.2016.7749183 　
Mass Detection Using Deep Convolutional Neural Network for Mammographic Computer-Aided Diagnosis Peer-reviewed

Suzuki, Shintaro Zhang, Xiaoyong Homma, Noriyasu Ichiji, Kei Sugita, Norihiro Kawasumi, Yusuke Ishibashi, Tadashi Yoshizawa, Makoto

2016 55TH ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS OF JAPAN (SICE)　1382-1386　2016/09/20

DOI： 10.1109/SICE.2016.7749265 　
Evaluation of the Amount of the Manganese Entry in the Neurons for Activity-Induced Manganese-Enhanced MRI Peer-reviewed

Kikuta, Satomi Yanagawa, Yuchio Homma, Noriyasu Osanai, Makoto

Electr. Commun. Jpn.　99　(8)　48-53　2016/08

DOI： 10.1002/ecj.11838 　
Easy Extraction of Blood Pressure Variability from Body Video Images Using Simulink Peer-reviewed

Makoto Yoshizawa, Norihiro Sugita, Makoto Abe, Kazuma Obara, Akira Tanaka, Noriyasu Homma, Tomoyuki Yambe

Proc. 37th Annual Conference of IEEE Engineering in Medince Biology Society　2016/08
A Remote and Non-Contact Monitoring System of Physiological Indices to Cope with Visually Induced Motion Sickness Peer-reviewed

Makoto Yoshizawa, Norihiro Sugita, Makoto Abe, Akira Tanaka, Noriyasu Homma, Tomoyuki Yambe

The International Society of Electrophysiology and Kinesiology 2016 (ISEK 2016)　2016/07/08
A Tele-Electrocardiographic Monitoring System for Patients with Chronic Diseases at Home Peer-reviewed

Yoshizawa M, Ohuchi H, Nunokawa K, Taniuchi K, Okaniwa T, Sugita N, Abe M, Homma N, Yambe T

Austin Emergency Medicine　2　(6)　2016/06
Detection of Masses On Mammograms Using Deep Convolutional Neural Network: A Feasibility Study Peer-reviewed

Suzuki, S. Zhang, X. Homma, N. Ichiji, K. Kawasumi, Y. Ishibashi, T. Yoshizawa, M

Med. Phys.　43　(6 40)　3817　2016/06

DOI： 10.1118/1.4957862 　
Dosimetric Evaluation of Dynamic Tumor Tracking Radiation Therapy Using Digital Phantom: A Study On Margin and Desired Accuracy of Tracking Peer-reviewed

Uchida, T. Kadoya, N. Ichiji, K. Nakajima, Y. Jingu, K. Osanai, M. Takeda, K. Takai, Y. Homma, N

Med. Phys.　43　(6 25)　3638　2016/06

DOI： 10.1118/1.4956939 　
Study of Learning Entropy for Onset Detection of Epileptic Seizures in EEG Time Series Peer-reviewed

Ivo Bukovsky, Matous Cejnek, Jan Vrba, Noriyasu Homma

2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)　3302-3305　2016

ISSN： 2161-4393
Blood Perfusion Display Based on Video Pulse Wave International-journal Peer-reviewed

Makoto Yoshizawa, Norihiro Sugita, Makoto Abe, Akira Tanaka, Kazuma Obara, Tsuyoshi Yamauchi, Noriyasu Homma, Tomoyuki Yambe

2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)　2016　4763-4767　2016

DOI： 10.1109/EMBC.2016.7591792 　

ISSN： 1557-170X
Estimation of heart rate variability using a compact radiofrequency motion sensor International-journal Peer-reviewed

Sugita, Norihiro Matsuoka, Narumi Yoshizawa, Makoto Abe, Makoto Homma, Noriyasu Otake, Hideharu Kim, Junghyun Ohtaki, Yukio

Med. Eng. Phys.　37　(12)　1146-1151　2015/12

DOI： 10.1016/j.medengphy.2015.09.008 　

More details Close

Physiological indices that reflect autonomic nervous activity are considered useful for monitoring peoples' health on a daily basis. A number of such indices are derived from heart rate variability, which is obtained by a radiofrequency (RF) motion sensor without making physical contact with the user's body. However, the bulkiness of RF motion sensors used in previous studies makes them unsuitable for home use. In this study, a new method to measure heart rate variability using a compact RF motion sensor that is sufficiently small to fit in a user's shirt pocket is proposed. To extract a heart rate related component from the sensor signal, an algorithm that optimizes a digital filter based on the power spectral density of the signal is proposed. The signals of the RF motion sensor were measured for 29 subjects during the resting state and their heart rate variability was estimated from the measured signals using the proposed method and a conventional method. A correlation coefficient between true heart rate and heart rate estimated from the proposed method was 0.69. Further, the experimental results showed the viability of the RF sensor for monitoring autonomic nervous activity. However, some improvements such as controlling the direction of sensing were necessary for stable measurement.
Remote Monitoring of Autonomic Nervous System Indices Using Video Peer-reviewed

Yoshizawa, Makoto Sugita, Norihiro Abe, Makoto Obara, Kazama Tanaka, Akira Homma, Noriyasu Yambe, Tomoyuki

2015 IEEE 4TH GLOBAL CONFERENCE ON CONSUMER ELECTRONICS (GCCE)　670-671　2015/10

DOI： 10.1109/GCCE.2015.7398691 　
A Real-Time Homography-Based Algorithm for Markerless Deformable Lung Tumor Motion Tracking Using KV X-Ray Fluoroscopy Peer-reviewed

X. Zhang, N. Homma, Y. Takai, K. Ichiji, N. Sugita, M. Abe, M. Yoshizawa

MEDICAL PHYSICS　42　(6)　3656-3656　2015/06

DOI： 10.1118/1.4925867 　

ISSN： 0094-2405
Tracking tumor boundary in MV-EPID images without implanted markers: A feasibility study. International-journal Peer-reviewed

Zhang, Xiaoyong Homma, Noriyasu Ichiji, Kei Takai, Yoshihiro Yoshizawa, Makoto

Med Phys　42　(5)　2510-2523　2015/05
Publisher: Wiley
DOI： 10.1118/1.4918578 　

ISSN： 0094-2405

More details Close

PURPOSE: To develop a markerless tracking algorithm to track the tumor boundary in megavoltage (MV)-electronic portal imaging device (EPID) images for image-guided radiation therapy. METHODS: A level set method (LSM)-based algorithm is developed to track tumor boundary in EPID image sequences. Given an EPID image sequence, an initial curve is manually specified in the first frame. Driven by a region-scalable energy fitting function, the initial curve automatically evolves toward the tumor boundary and stops on the desired boundary while the energy function reaches its minimum. For the subsequent frames, the tracking algorithm updates the initial curve by using the tracking result in the previous frame and reuses the LSM to detect the tumor boundary in the subsequent frame so that the tracking processing can be continued without user intervention. The tracking algorithm is tested on three image datasets, including a 4-D phantom EPID image sequence, four digitally deformable phantom image sequences with different noise levels, and four clinical EPID image sequences acquired in lung cancer treatment. The tracking accuracy is evaluated based on two metrics: centroid localization error (CLE) and volume overlap index (VOI) between the tracking result and the ground truth. RESULTS: For the 4-D phantom image sequence, the CLE is 0.23 ± 0.20 mm, and VOI is 95.6% ± 0.2%. For the digital phantom image sequences, the total CLE and VOI are 0.11 ± 0.08 mm and 96.7% ± 0.7%, respectively. In addition, for the clinical EPID image sequences, the proposed algorithm achieves 0.32 ± 0.77 mm in the CLE and 72.1% ± 5.5% in the VOI. These results demonstrate the effectiveness of the authors' proposed method both in tumor localization and boundary tracking in EPID images. In addition, compared with two existing tracking algorithms, the proposed method achieves a higher accuracy in tumor localization. CONCLUSIONS: In this paper, the authors presented a feasibility study of tracking tumor boundary in EPID images by using a LSM-based algorithm. Experimental results conducted on phantom and clinical EPID images demonstrated the effectiveness of the tracking algorithm for visible tumor target. Compared with previous tracking methods, the authors' algorithm has the potential to improve the tracking accuracy in radiation therapy. In addition, real-time tumor boundary information within the irradiation field will be potentially useful for further applications, such as adaptive beam delivery, dose evaluation.
Target Extraction from X-ray Image Sequence by using Gaussian Mixture Model for Lung Tumor Tracking

SHIBUSAWA Naoki, ICHIJI Kei, YOSHIDA Yusuke, ZHANG Xiaoyang, HOMMA Noriyasu, TAKAI Yoshihiro, YOSHIZAWA Makoto

IEICE technical report.　114　(482)　277-282　2015/03
Publisher: 一般社団法人電子情報通信学会
ISSN： 0913-5685

More details Close

During treatment fraction, accurate tracking of moving tumor by using X-ray imaging is important for radiation therapy. However, superimposition of tumor and other structure in X-ray image can reduce tracking accuracy. In this study, a moving target extraction method taken into account the transparent characteristic of X-ray by using Gaussian mixture model (GMM) was evaluated by using an X-ray image sequence of a 3D printed dynamic phantom based on clinical CT volume data. In comparison with other method, the moving target extracted by the GMM-based method was similar to the original phantom and improved tracking accuracy.
肺腫瘍追跡のためのX線画像シーケンスの混合正規分布モデル近似に基づく対象輝度成分抽出 Peer-reviewed

澁澤直樹, 市地慶, 張曉勇, 本間経康, 高井良尋, 吉田裕輔, 吉澤誠

電子情報通信学会技報　2015/03
Type-one fuzzy logic for quantitatively defining imprecise linguistic terms in politics and public policy Peer-reviewed

Ashu M. G. Solo, Noriyasu Homma, Madan M. Gupta, Zeng-Guang Hou

Research Methods: Concepts, Methodologies, Tools, and Applications　1-4　67-83　2015/01/31
Publisher: IGI Global
DOI： 10.4018/978-1-4666-7456-1.ch004 　
ADAPTIVE POLYNOMIAL FILTERS WITH INDIVIDUAL LEARNING RATES FOR COMPUTATIONALLY EFFICIENT LUNG TUMOR MOTION PREDICTION Peer-reviewed

Matous Cejnek, Ivo Bukovsky, Noriyasu Homma, Ondrej Liska

2015 INTERNATIONAL WORKSHOP ON COMPUTATIONAL INTELLIGENCE FOR MULTIMEDIA UNDERSTANDING (IWCIM)　2015
Evaluation of Baroreflex Function Using Green Light Photople-thysmogram in Consideration of Resistance to Artifacts Peer-reviewed

Makoto Abe, Makoto Yoshizawa, Kazuma Obara, Norihiro Sugita, Noriyasu Homma, Tomoyuki Yambe

Advanced Biomedical Engineering　4　1-6　2015
Publisher: Japanese Society for Medical and Biological Engineering
DOI： 10.14326/abe.4.1 　

ISSN： 2187-5219

More details Close

The maximum cross-correlation coefficient (ρ_max) between blood pressure (BP) and heart rate (HR) variability for frequency components limited to the Mayer wave-related band is useful for the evaluation of baroreflex function. However, continuous BP measurement with an expensive and bulky measuring device is required to calculate ρ_max. This study proposes a simpler method to obtain ρ_max using a green light photoplethysmogram (PPG). A green PPG sensor is less affected by motion artifacts than a near-infrared PPG sensor. In this study, an electrocardiogram, continuous BP, green PPG, and near-infrared PPG were obtained from the subjects. HR, mean BP, and pulse transit time were estimated from the signals, and ρ_max was subsequently calculated. Compared to the ρ_max obtained from the near-infrared PPG signal, the ρ_max obtained from the green PPG signal is closer in value to the ρ_max obtained from mean BP. These results show that the green PPG sensor can be used to estimate baroreflex function instead of using continuous BP measurement.
Evaluation of the amount of the manganese entry in the neurons for activity-induced manganese-enhanced MRI Peer-reviewed

Kikuta, S., Yanagawa, Y., Homma, N., Osanai, M.

IEEJ Transactions on Electronics, Information and Systems　135　(3)　280-284　2015

DOI： 10.1541/ieejeiss.135.280 　
乳房密度は日本人女性でも乳がん罹患危険因子か(Is Mammographic Breast Density a Risk Factor for Breast Cancer in Japanese Women?) Peer-reviewed

張暁勇, 筑島徳政, 渡邉篤俊, 大橋悠二, 長谷川奈保, 市地慶, 田村篤史, 小山内実, 本間経康

東北大学医学部保健学科紀要　24　(1)　45-51　2015/01
Publisher: 東北大学医学部保健学科
ISSN： 1348-8899
Aliased noise in X-ray CT images and band-limiting processing as a preventive measure Peer-reviewed

Kazuhiro Sato, Miho Shidahara, Mitsunori Goto, Isao Yanagawa, Noriyasu Homma, Issei Mori

Radiological Physics and Technology　2015/01

DOI： 10.1007/s12194-015-0306-5 　
Techniques for estimating blood pressure variation using video images International-journal Peer-reviewed

Norihiro Sugita, Kazuma Obara, Makoto Yoshizawa, Makoto Abe, Akira Tanaka, Noriyasu Homma

2015 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)　2015　4218-4221　2015

DOI： 10.1109/EMBC.2015.7319325 　

ISSN： 1557-170X
A REAL-TIME FEATURE-BASED MARKERLESS TUMOR TRACKING METHOD USING X-RAY IMAGE SEQUENCE FOR RADIOTHERAPY Peer-reviewed

Yusuke Yoshida, Kei Ichiji, Xiaoyong Zhang, Noriyasu Homma, Yoshihiro Takai, Makoto Yoshizawa

2015 INTERNATIONAL WORKSHOP ON COMPUTATIONAL INTELLIGENCE FOR MULTIMEDIA UNDERSTANDING (IWCIM)　2015

DOI： 10.1109/IWCIM.2015.7347086 　
TUMOR MOTION TRACKING USING KV/MV X-RAY FLUOROSCOPY FOR ADAPTIVE RADIATION THERAPY Peer-reviewed

Xiaoyong Zhang, Noriyasu Homma, Kei Ichiji, Makoto Abe, Norihiro Sugita, Ivo Bukovsky, Yoshihiro Takai, Makoto Yoshizawa

2015 INTERNATIONAL WORKSHOP ON COMPUTATIONAL INTELLIGENCE FOR MULTIMEDIA UNDERSTANDING (IWCIM)　2015

DOI： 10.1109/IWCIM.2015.7347084 　
Quantitative activation-induced manganese-enhanced MRI reveals severity of Parkinson's disease in mice. International-journal Peer-reviewed

Kikuta, Satomi Nakamura, Yukiyo Yamamura, Yukio Tamura, Atsushi Homma, Noriyasu Yanagawa, Yuchio Tamura, Hajime Kasahara, Jiro Osanai, Makoto

Sci Rep　5　12800-12800　2015

DOI： 10.1038/srep12800 　

eISSN： 2045-2322
A Fast Neural Network Approach to Predict Lung Tumor Motion during Respiration for Radiation Therapy Applications Peer-reviewed

Ivo Bukovsky, Noriyasu Homma, Kei Ichiji, Matous Cejnek, Matous Slama, PeterM. Benes, Jiri Bila

BioMed Research International　2014/09

DOI： 10.1155/2015/489679 　
Tele-healthcare systems for end-of-life decision at home Peer-reviewed

Makoto Yoshizawa, Hitoshi Ohuchi, Kenji Nunokawa, Kouichi Taniuchi, Norihiro Sugita, Makoto Abe, Noriyasu Homma, Tomoyuki Yambe

Transactions of Japanese Society for Medical and Biological Engineering　52　15-SY-16　2014/08/17
Publisher: Japan Soc. of Med. Electronics and Biol. Engineering
DOI： 10.11239/jsmbe.52.SY-15 　

ISSN： 1347-443X 1881-4379
Tracking Tumor's Boundary in MV Image Sequences for Image-Guided Radiation Therapy Peer-reviewed

X. Zhang, N. Homma, Y. Narita, Y. Takai, K. Ichiji, M. Abe, N. Sugita, M. Yoshizawa

Medical Physics　41　(6)　574　2014/07
A kernel-based method for markerless tumor tracking in kV fluoroscopic images Peer-reviewed

Xiaoyong Zhang, Noriyasu Homma, Kei Ichiji, Makoto Abe, Norihiro Sugita, Yoshihiro Takai, Yuichiro Narita, Makoto Yoshizawa

Physics in Medicine and Biology　59　4897-4911　2014/07

DOI： 10.1088/0031-9155/59/17/4897 　
在宅看取り用遠隔医療システム

吉澤誠, 杉田典大, 阿部誠, 本間経康, 大内仁, 布川憲司, 山家智之

生体医工学　52　2014/06

More details Close

SY-15-SY-16
Type-one fuzzy logic for quantitatively defining imprecise linguistic terms in politics and public policy Peer-reviewed

Ashu M.G. Solo, Madan M. Gupta, Noriyasu Homma, Zeng-Guang Hou

Political Campaigning in the Information Age　239-255　2014/05/31
Publisher: IGI Global
DOI： 10.4018/978-1-4666-6062-5.ch015 　
A Faster 1-D Phase-Only Correlation-Based Method for Estimations of Translations, Rotation and Scaling in Images Peer-reviewed

X. Zhang, N. Homma, K. Ichiji, M. Abe, N. Sugita, M. Yoshizawa

IEICE Trans. Fundamentals　E97-A　(3)　809-819　2014/03
Publisher: Institute of Electronics, Information and Communication Engineers
DOI： 10.1587/transfun.E97.A.809 　

ISSN： 0916-8508
Heart Rate Reliability Prediction for the Estimated Value from Sheet-shaped Microdisplacement Sensor Signal Peer-reviewed

Ken Ogihara, Norihiro Sugita, Makoto Yoshizawa, Noriyasu Homma, Makoto Abe, Kazuma Obara, Narumi Matsuoka, Koichi Saito, Atushi Goto

Transactions of the Japanese Society for Medical and Biological Engineering　52　(1)　18-23　2014/02
Publisher:
DOI： 10.11239/jsmbe.52.18 　

ISSN： 1347-443X

eISSN： 1881-4379
Change of psychological effects in assessment of biological effects of three-dimensional scenography based on a physiological index Peer-reviewed

Makoto Abe, Daiki Niinuma, Makoto Yoshizawa, Norihiro Sugita, Noriyasu Homma, Tomoyuki Yambe, Shin-Ichi Nitta

Transactions of Japanese Society for Medical and Biological Engineering　52　(1)　11-16　2014/02
Publisher:
DOI： 10.11239/jsmbe.52.11 　

ISSN： 1347-443X

eISSN： 1881-4379
Verification of a Method of Detecting Life-threatening Arrhythmias from Human Data for Use in Implantable Cardioverter- Defibrillator Peer-reviewed

Makoto ABE, Makoto YOSHIZAWA, Norihiro SUGITA, Noriyasu HOMMA, Kazuo SHIMIZU, Moe GOTO, Masashi INAGAKI, Masaru SUGIMACHI, Kenji SUNAGAWA

Advanced Biomedical Engineering　3　(0)　59-64　2014
Publisher: Japanese Society for Medical and Biological Engineering
DOI： 10.14326/abe.3.59 　

eISSN： 2187-5219
Study of Learning Entropy for Novelty Detection in Lung Tumor Motion Prediction for Target Tracking Radiation Therapy Peer-reviewed

Ivo Bukovsky, Noriyasu Homma, Matous Cejnek, Kei Ichiji

PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)　3124-3129　2014

DOI： 10.1109/IJCNN.2014.6889834 　

ISSN： 2161-4393
Discrimination Ability and Reproducibility of a New Index Reflecting Autonomic Nervous Function Based on Pulsatile Amplitude of Photoplethysmography Peer-reviewed

Yusuke Kano, Makoto Yoshizawa, Norihiro Sugita, Makoto Abe, Noriyasu Homma, Akira Tanaka, Tsuyoshi Yamauchi, Hidekazu Miura, Yasuyuki Shiraishi, Tomoyuki Yambe

2014 36TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)　1794-1800　2014

DOI： 10.1109/EMBC.2014.6943957 　

ISSN： 1557-170X
Improving the Detection Algorithm for Life-Threatening Arrhythmias: Implementation in Implantable Cardioverter-Defibrillator Peer-reviewed

Makoto Abe, Makoto Yoshizawa, Telma Keiko Sugai, Noriyasu Homma, Norihiro Sugita, Kazuo Shimizu, Moe Goto, Masashi Inagaki, Masaru Sugimachi, Kenji Sunagawa

Electronics and Communications in Japan　96　(12)　1-8　2013/12

DOI： 10.1002/ecj.11585 　
Evaluation of Motor Performances of Hemiplegic Patients Using a Virtual Cycling Wheelchair: An Exploratory Trial Peer-reviewed

Norihiro Sugita, Makoto Yoshizawa, Yoshihisa Kojima, Makoto Abe, Noriyasu Homma, Kazunori Seki, Nobuyasu Handa

Computational and Mathematical Methods in Medicine　2013　2013/11

DOI： 10.1155/2013/512965 　
Tele-Echographic Image Archiving System Using a Tablet Computer and a Virtual Probe Peer-reviewed

Norihiro Sugita, Makoto Yoshizawa, Makoto Abe, Noriyasu Homma, Tomoyuki Yambe, Yoshifumi Saij

Transactions of Japanese Society for Medical and Biological Engineering　51　(Vol.51)　p.M-10-10-M-10　2013/09
Publisher: Japanese Society for Medical and Biological Engineering
DOI： 10.11239/jsmbe.51.M-10 　

ISSN： 1347-443X
"A Kernel-Based Method for Real-Time Markerless Tumor Tracking in Fluoroscopic Image Sequence Peer-reviewed

X. Zhang, N. Homma, Y. Takai, N. Yuichiro, K. Ichiji, M. Abe, N. Sugita, M. Yoshizawa

SICE Annual Conference 2013　828-832　2013/09
次世代デジタルマンモグラフィ総合ビューアシステムの開発

高根侑美, 川住祐介, 本間経康, 伊藤典明, 大友祐司, 紺野純, 石橋忠司

日本乳癌学会総会プログラム抄録集　21回　270-270　2013/06
Publisher: (一社)日本乳癌学会
Physiological Evaluation of Visually Induced Motion Sickness Using Independent Component Analysis of Photoplethysmogram Peer-reviewed

Makoto Abe, Makoto Yoshizawa, Norihiro SUGITA, Akira TANAKA, Noriyasu HOMMA, Tomoyuki YAMBE, Shin-ichi NITTA

Advanced Biomedical Engineering　2　(0)　25-31　2013/05
Publisher: Japanese Society for Medical and Biological Engineering
DOI： 10.14326/abe.2.25 　

eISSN： 2187-5219
A Time Varying Seasonal Autoregressive Model Based Prediction of Respiratory Motion for Tumor Following Radiotherapy Peer-reviewed

Kei Ichiji, Noriyasu Homma, Masao Sakai, Yuichiro Narita, Yoshihiro Takai, Xiaoyong Zhang, Makoto Abe, Norihiro Sugita, Makoto Yoshizawa

Computational and Mathematical Methods in Medicine　2013　2013/05

DOI： 10.1155/2013/390325 　
A Hybrid Image Filtering Method for Computer-Aided Detection of Microcalcification Clusters in Mammograms Peer-reviewed

Xiaoyong Zhang, Noriyasu Homma, Shotaro Goto, Yosuke Kawasumi, Tadashi Ishibashi, Makoto Abe, Norihiro Sugita, Makoto Yoshizawa

Journal of Medical Engineering　2013　1-8　2013/04
Publisher: Hindawi Limited
DOI： 10.1155/2013/615254 　

ISSN： 2314-5129

eISSN： 2314-5137

More details Close

The presence of microcalcification clusters (MCs) in mammogram is a major indicator of breast cancer. Detection of an MC is one of the key issues for breast cancer control. In this paper, we present a highly accurate method based on a morphological image processing and wavelet transform technique to detect the MCs in mammograms. The microcalcifications are firstly enhanced by using multistructure elements morphological processing. Then, the candidates of microcalcifications are refined by a multilevel wavelet reconstruction approach. Finally, MCs are detected based on their distributions feature. Experiments are performed on 138 clinical mammograms. The proposed method is capable of detecting 92.9% of true microcalcification clusters with an average of 0.08 false microcalcification clusters detected per image.
A Great Impact of Green Video Signals on Tele-Healthcare in Daily Life, Especially for Rural or Disaster Areas

Yoshizawa Makoto, Tanaka Akira, Sugita Norihiro, Abe Makoto, Homma Noriyasu, Obara Kazuma, Yambe Tomoyuki

BME　51　M-55-M-55　2013
Publisher: Japanese Society for Medical and Biological Engineering
DOI： 10.11239/jsmbe.51.M-55 　

ISSN： 1347-443X
Evaluation of Baroreflex System for Elderly People in Disaster Areas Using Electrocardiogram and Plethysmogram

Yoshizawa Makoto, Tanaka Akira, Sugita Norihiro, Abe Makoto, Homma Noriyasu, Konno Satoshi, Yambe Tomoyuki

BME　51　M-9-M-9　2013
Publisher: Japanese Society for Medical and Biological Engineering
DOI： 10.11239/jsmbe.51.M-9 　

ISSN： 1347-443X
Evaluation of Navigation Skill of Elderly People Using the Cycling Wheel Chair in a Virtual Environment Peer-reviewed

Norihiro Sugita, Makoto Yoshizawa, Yoshihisa Kojima, Akira Tanaka, Makoto Abe, Noriyasu Homma, Toshitsugu Kikuchi, Kazunori Seki, Yasunobu Handa

2013 IEEE VIRTUAL REALITY CONFERENCE (VR)　125-+　2013

DOI： 10.1109/VR.2013.6549394 　

ISSN： 1087-8270
Volume Registration Based on 3-D Phase Correlation for Tumor Motion Estimation in 4-D CT Peer-reviewed

Xiaoyong Zhang, Noriyasu Homma, Makoto Abe, Norihiro Sugita, Yoshihiro Takai, Yuichiro Narita, Makoto Yoshizawa

2013 35TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)　5095-5098　2013

DOI： 10.1109/EMBC.2013.6610694 　

ISSN： 1557-170X
WE‐A‐134‐03: A Kernel‐Based Method for Non‐Rigid Tumor Tracking in KV Image Sequence Peer-reviewed

X. Zhang, N. Homma, K. Ichiji, Y. Takai, Y. Narita, M. Abe, N. Sugita, M. Yoshizawa

Medical Physics　40　(6)　469-469　2013

DOI： 10.1118/1.4815509 　

ISSN： 0094-2405
Moving Object Segmentation in Surveillance Video Based on Adaptive Mixtures Peer-reviewed

Xiaoyong Zhang, Noriyasu Homma, Kei Ichiji, Makoto Abe, Norihiro Sugita, Makoto Yoshizawa

2013 PROCEEDINGS OF SICE ANNUAL CONFERENCE (SICE)　1322-1325　2013

ISSN： 1550-0322
Markerless Lung Tumor Motion Tracking by Dynamic Decomposition of X-Ray Image Intensity. International-journal Peer-reviewed

Noriyasu Homma, Yoshihiro Takai, Haruna Endo, Kei Ichiji, Yuichiro Narita, Xiaoyong Zhang, Masao Sakai, Makoto Osanai, Makoto Abe, Norihiro Sugita, Makoto Yoshizawa

Journal of medical engineering　2013　340821-340821　2013

DOI： 10.1155/2013/340821 　

More details Close

We propose a new markerless tracking technique of lung tumor motion by using an X-ray fluoroscopic image sequence for real-time image-guided radiation therapy (IGRT). A core innovation of the new technique is to extract a moving tumor intensity component from the fluoroscopic image intensity. The fluoroscopic intensity is the superimposition of intensity components of all the structures passed through by the X-ray. The tumor can then be extracted by decomposing the fluoroscopic intensity into the tumor intensity component and the others. The decomposition problem for more than two structures is ill posed, but it can be transformed into a well-posed one by temporally accumulating constraints that must be satisfied by the decomposed moving tumor component and the rest of the intensity components. The extracted tumor image can then be used to achieve accurate tumor motion tracking without implanted markers that are widely used in the current tracking techniques. The performance evaluation showed that the extraction error was sufficiently small and the extracted tumor tracking achieved a high and sufficient accuracy less than 1 mm for clinical datasets. These results clearly demonstrate the usefulness of the proposed method for markerless tumor motion tracking.
スマートエイジングのためのバーチャル散歩システム Peer-reviewed

杉田典大, 杉原僚太, 吉澤誠, 本間経康, 阿部誠, 川嶋隆太

日本バーチャルリアリティ学会論文誌　17　(4)　497-504　2012/12/31
Publisher: THE VIRTUAL REALITY SOCIETY OF JAPAN
DOI： 10.18974/tvrsj.17.4_497 　

ISSN： 1344-011X

More details Close

In this study, a novel virtual walking system has been developed for putting the concept of advocating a positive acceptance of the later stages of life or aging, called smart aging, into practice. An essential core of the system can be found in striking the right balance between virtual and real worlds for old people to use pleasantly and safely. The system consists of a laptop computer, micro-projectors, and a completely new screen system mounted on the walking frame, called "walking frame mounted display (WFMD)." Users can physically walk with pleasure by the virtual reality technology and safely by the WFMD in the virtual environment. Furthermore, the WFMD does not require any sensors to be worn and is sufficiently inexpensive for home use. Comparison of experimental results clearly demonstrates that the real walking in a virtual environment using the WFMD is easier to use for old people than stamping their feet on the "Wii balance board" in the same environment.
Lung Tumor Motion Estimation Using 3-D Phase Correlation for Radiotherapy Treatment Peer-reviewed

Xiaoyong ZHANG, Noriyasu HOMMA, Yoshihiro TAKAI, Yuichiro NARITA, Makoto ABE, Norihiro SUGITA, Makoto YOSHIZAWA

Proc. SICE Annual Conference 2012　754-758　2012/08
DoG-Based Detection of Architectural Distortion in Mammographic Images for Computer-Aided Detection Peer-reviewed

Takeshi Handa, Xiaoyong Zhang, Noriyasu Homma, Tadashi, Ishibashi, Yusuke Kawasumi, Makoto Abe, Norihiro Sugita, Makoto Yoshizawa

Proc. SICE Annual Conference 2012　762-767　2012/08
Evaluation of autonomic nervous function for elderly people using electrocardiogram and plethysmogram Invited Peer-reviewed

Yoshizawa M, Sugita N, Abe M, Homma N, Konno S, Yambe T, Nitta S

Proceedings of SICE Annual Conference 2012　1665-1668　2012/08
Design of an Error-Based Adaptive Controller for a Flexible Robot Arm using Dynamic Pole Motion Approach Peer-reviewed

Ki-Young Song, Madan M. Gupta, Noriyasu Homma

Journal of Robotics　2011　2012/03
Tumor image extraction from fluoroscopy for a markerless lung tumor motion tracking and prediction Peer-reviewed

Noriyasu Homma, Keita Ishihara, Yoshihiro Takai, Haruna Endo, Kei Ichiji, Masao~Sakai, Yuichiro Narita, Makoto Abe, Norihiro Sugita, Makoto Yoshizawa

Proc. SPIE Medical Imaging　8316　391-397　2012/02

DOI： 10.1117/12.911960 　
Fundamentals of higher order neural networks for modeling and simulation Peer-reviewed

Madan M. Gupta, Ivo Bukovsky, Noriyasu Homma, Ashu M. G. Solo, Zeng-Guang Hou

Artificial Higher Order Neural Networks for Modeling and Simulation　103-133　2012
Publisher: IGI Global
DOI： 10.4018/978-1-4666-2175-6.ch006 　
Intelligent sensing and monitoring : respiratory motion prediction for tumor following radiotherapy. Peer-reviewed

K. Ichiji, N. Homma, M. Sakai, I. Bukovsky, X. Zhang, M. Osanai, M. Abe, N. Sugita, M. Yoshizawa

Journal of Artificial Intelligence and Soft Computing Research　2　(4)　331-342　2012
Application of a Telemedical Tool in an Isolated Island and a Disaster Area of the Great East Japan Earthquake Invited Peer-reviewed

Makoto Yoshizawa, Tomoyuki Yambe, Norihiro Sugita, Satoshi Konno, Makoto Abe, Noriyasu Homma, Futoshi Takei, Katsuhiko Yokota, Yoshifumi Saijo, Shin-ichi Nitta

IEICE Trans. Fundamentals/Commun./Electron./Inf. & Syst.　E85-A/B/C/D/　(10)　3067-3073　2012
Publisher: The Institute of Electronics, Information and Communication Engineers
DOI： 10.1587/transcom.E95.B.3067 　

ISSN： 0916-8516

More details Close

The present paper has reported a case study of the "Electronic Doctor's Bag" which is a telemedical tool for home-visit medical services using the mobile communications environment in an isolated island and a disaster area hit by the tsunami. Clinical trials performed for 20 patients around a clinic in Miyako Island indicated that the communication functions of the proposed system were highly evaluated by patients as well as medical staffs. However, the system still has room for further improvement in operability, portability and mobile communication environment. The experience at the shelter in Kesennuma City suggested that mobile healthcare tools such as the proposed system will be strongly required when there are no or only paramedical staffs after leaving of emergency medical staffs.
SU‐E‐J‐135: 3‐D Fourier‐Based Volumetric Registration for Estimating Intra‐Fractional Lung Tumor Motion Peer-reviewed

X. Zhang, N. Homma, Y. Takai, Y. Narita, M. Yoshizawa

Medical Physics　39　(6)　3683　2012

DOI： 10.1118/1.4734971 　

ISSN： 0094-2405
SU‐D‐BRA‐02: An Extended Time‐Variant Seasonal Autoregressive Model‐Based Prediction for Irregular Breathing Motion Tracking Peer-reviewed

K. Ichiji, N. Homma, M. Sakai, Y. Narita, Y. Takai, M. Yoshizawa

Medical Physics　39　(6)　3616　2012

DOI： 10.1118/1.4734680 　

ISSN： 0094-2405
Respiratory Motion Prediction for Tumor Following Radiotherapy by using Time-variant Seasonal Autoregressive Techniques Invited Peer-reviewed

Kei Ichiji, Noriyasu Homma, Masao Sakai, Yoshihiro Takai, Yuichiro Narita, Mokoto Abe, Norihiro Sugita, Makoto Yoshizawa

2012 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)　6028-6031　2012

ISSN： 1557-170X
Development of a Virtual Reality System to Evaluate Skills Needed to Drive a Cycling Wheel-Chair Invited Peer-reviewed

Norihiro Sugita, Yoshihisa Kojima, Makoto Yoshizawa, Akira Tanaka, Makoto Abe, Noriyasu Homma, Kazunori Seki, Nobuyasu Handa

2012 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)　6019-6022　2012

ISSN： 1557-170X
Telemedicine System Necessary in Disaster Areas Invited Peer-reviewed

Norihiro Sugita, Makoto Yoshizawa, Hitoshi Kawata, Tomoyuki Yambe, Satoshi Konno, Yoshifumi Saijo, Makoto Abe, Noriyasu Homma, Shin-ichi Nitta

2012 PROCEEDINGS OF SICE ANNUAL CONFERENCE (SICE)　1661-1664　2012
Improving detection algorithm of life-threatening arrhythmias for implementation of implantable cardioverter-defibrillators Peer-reviewed

Makoto Abe, Makoto Yoshizawa, Telma Keiko Sugai, Noriyasu Homma, Norihiro Sugita, Kazuo Shimizu, Moe Goto, Masashi Inagaki, Masaru Sugimachi, Kenji Sunagawa

IEEJ Transactions on Electronics, Information and Systems　132　(12)　1943-1948　2012
Publisher: Institute of Electrical Engineers of Japan
DOI： 10.1541/ieejeiss.132.1943 　

ISSN： 1348-8155 0385-4221
植込み型除細動器用致死性不整脈検出アルゴリズムの高速・高精度化 Peer-reviewed

阿部誠, テルマケイコスガイ, 吉澤誠, 本間経康, 杉田典大, 清水一夫, 後藤萌, 稲垣正司, 杉町勝, 砂川賢二

生体医工学　49　(6)　932-938　2011/12
Publisher: Japanese Society for Medical and Biological Engineering
DOI： 10.11239/jsmbe.49.932 　

ISSN： 1347-443X

More details Close

The implantable cardioverter-defibrillator (ICD) is an effective therapeutic device for rescuing patients with cardiac diseases from death caused by life-threatening arrhythmias. The authors previously have proposed a detection algorithm of life-threatening arrhythmia with a multiple regression model. In this research, we have developed the algorithm so as to accurately classify cardiac rhythms and to reduce in the computational time with a microcontroller used in the ICD. The experimental results showed that the proposed method kept a high accuracy to detect cardiac rhythms. In addition, the validation of implementation of the proposed algorithm in the microcontroller indicated that the result of detection of cardiac rhythms could be attained within computational time of 60 ms. For the practical application, it is necessary to evaluate the power consumption of the ICD working with the proposed method.
“Evaluation of temporal relationship between a physiological index and a subjective score using average mutual information Peer-reviewed

Norihiro Sugita, Makoto Yoshizawa, Akira Tanaka, Makoto Abe, Noriyasu Homma, Shigeru Chiba, Tomoyuki Yambe, Shin-ichi Nitta

Displays　32　(4)　201-208　2011/10

DOI： 10.1016/j.displa.2011.04.003 　
Potentials of Quadratic Neural Unit for Applications Peer-reviewed

Ricardo Rodriguez, Ivo Bukovsky, Noriyasu Homma

Int'l. J. of Software Science and Computational Intelligence　3　(3)　1-12　2011/09
Intelligent sensing of biomedical signals - Lung tumor motion prediction for accurate radiotherapy Peer-reviewed

Kei Ichiji, Noriyasu Homma, Ivo Bukovsky, Makoto Yoshizawa

IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CompSens 2011: 2011 IEEE Workshop on Merging Fields of Computational Intelligence and Sensor Technology　35-41　2011

DOI： 10.1109/MFCIST.2011.5949518 　
Methods for Assessment of Effects of Habitual Exercise on the Autonomic Nervous Function Using Plethysmogram Peer-reviewed

Makoto Yoshizawa, Norihiro Sugita, Tomoyuki Yambe, Satoshi Konno, Telma Keiko Sugai, Makoto Abe, Noriyasu Homma

2011 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)　1157-1160　2011

DOI： 10.1109/IEMBS.2011.6090271 　

ISSN： 1557-170X
Estimation of baroreflex function using independent component analysis of photoplethysmography Peer-reviewed

Makoto Abe, Makoto Yoshizawa, Norihiro Sugita, Akira Tanaka, Noriyasu Homma, Tomoyuki Yambe, Shin-Ichi Nitta

IEEJ Transactions on Electronics, Information and Systems　131　(9)　4-1546　2011
Publisher: Institute of Electrical Engineers of Japan
DOI： 10.1541/ieejeiss.131.1540 　

ISSN： 1348-8155 0385-4221
Sensitivity improvement of automatic pulmonary nodules detection in chest X-ray CT images Peer-reviewed

Noriyasu Homma, Satoshi Shimoyama, Tadashi Ishibashi, Yusuke Kawazumi, Makoto Yoshizawa

Artificial Life and Robotics　15　526-529　2010/12

DOI： 10.1007/s10015-010-0860-1 　
Extraction of the Mayer wave component in blood pressure from the instantaneous phase difference between electrocardiograms and photoplethysmograms Peer-reviewed

Norihiro Sugita, Makoto Yoshizawa, Masanori Murakoshi, Makoto Abe, Noriyasu Homma, Tomoyuki Yambe, Shinichi Nitta

Artificial Life and Robotics　15　522-525　2010/12

DOI： 10.1007/s10015-010-0861-0 　
Lung Tumor Motion Prediction Based on Multiple Time-Variant Seasonal Autoregressive Model for Tumor Following Radiotherapy Peer-reviewed

Kei Ichiji, Makao Sakai, Noriyasu Homma, Yoshihiro Takai, Makoto Yoshizawa

Proc. SII 2010　353-358　2010/12

DOI： 10.1109/SII.2010.5708351 　
Quadratic Neural Unit is a Good Compromise between Linear Models and Neural Networks for Industrial Applications Peer-reviewed

Ivo Bukovsky, Noriyasu Homma, Ladislav Smetana, Ricardo Rodriguez, Martina Mironovova, Stanislav Vrana

Proc. 9th IEEE Int'l. Conf. Cognitive Informatics　2010/07

DOI： 10.1109/COGINF.2010.5599677 　
Adaptive Seasonal Autoregressive Model Based Intrafractional Lung Tumor Motion Prediction for Continuously Irradiation Peer-reviewed

Kei Ichiji, Makao Sakai, Noriyasu Homma, Yoshihiro Takai, Makoto Yoshizawa

Medical Physics　37　(6)　3331-3332　2010/07
How can brain learn to control a nonholonomic system? Peer-reviewed

Noriyasu Homma, Shinpei Kato, Takakuni Goto, Ivo Bukovsky, Ryuta Kawashima, Makoto Yoshizawa

Journal of Robotics　2010　2010/06
Lung motion prediction by static neural networks Peer-reviewed

Ricardo Rodriguez, Kei Ichiji, Ivo Bukovsky, Jiri Bila, Noriyasu Homma

Proc. (IMEKO TC 18) 4th Int’l. Symp. Measurement, Analysis and Modelling of Human Functions　2010/06
Estimation of Blood Pressure Variability from the Temporal Difference Peer-reviewed

Norihiro Sugita, Makoto Yoshizawa, Masayuki Murakoshi, Makoto Abe, Noriyasu Homma, Tomoyuki Yambe, Shin-ichi Nitta

5th International Symposium on Medical, Bio- and Nano-Electronics　23-27　2010/02
Prediction Methods of Unsteady Periodic Tumour Motion for Radiotherapy Peer-reviewed

Masao SAKAI Kei ICHIJI, Noriyasu HOMMA, Yoshihiro TAKAI, Makoto YOSHIZAWA

5th International Symposium on Medical, Bio- and Nano-Electronics　75-78　2010/02
Development of a Prediction System for Lung Tumor Motion for Radiation Therapy Peer-reviewed

Kei ICHIJI, Masao SAKAI, Noriyasu HOMMA, Yoshihiro TAKAI, Makoto YOSHIZAWA

5th International Symposium on Medical, Bio- and Nano-Electronics　109-110　2010/02
A time variant seasonal ARIMA model for lung tumor motion prediction Peer-reviewed

K. Ichiji, M. Sakai, N. Homma, Y. Takai, M. Yoshizawa

Proc. AROB 10　485-488　2010/02
Pulse Transmission Time Based on Temporal Difference in the Instantaneous Phase Between Electrocardiogram and Photoplethysmogram Signals Peer-reviewed

M. Murakoshi, M. Yoshizawa, N. Sugita, M. Abe, N. Homma, T. Yambe, S. Nitta

Proc. AROB 10　489-492　2010/02
Dynamic Backpropagation and Prediction Peer-reviewed

Ivo Bukovsky, Noriyasu Homma

Automation　53　(1-2)　61-66　2010/02
Higher order neural networks: Fundamental theory and applications Peer-reviewed

Madan M. Gupta, Noriyasu Homma, Zeng-Guang Hou, Ashu M. G. Solo, Ivo Bukovsky

Artificial Higher Order Neural Networks for Computer Science and Engineering: Trends for Emerging Applications　396-422　2010
Publisher: IGI Global
DOI： 10.4018/978-1-61520-711-4.ch017 　
Testing Potentials of Dynamic Quadratic Neural Unit for Prediction of Lung Motion during Respiration for Tracking Radiation Therapy Peer-reviewed

Ivo Bukovsky, Kei Ichiji, Noriyasu Homma, Makoto Yoshizawa, Ricardo Rodriguez

2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010　2010

DOI： 10.1109/IJCNN.2010.5596748 　

ISSN： 2161-4393
SU‐GG‐J‐55: Simultaneous Estimation of Lung Tumor Image and Intrafractional Motion without Implanted Markers Using KV‐X‐Ray Fluoroscopy for Image‐Guided Radiotherapy Peer-reviewed

H. Endo, N. Homma, Y. Takai, M. Yoshizawa

Medical Physics　37　(6)　3157　2010

DOI： 10.1118/1.3468279 　

ISSN： 0094-2405
Human Brain Activities Related to Manual Control of a Nonholonomic System: An f-MRI Study Peer-reviewed

Noriyasu Homma, Shinpei Kato, Takakuni Goto, Masao Sakai, Norihiro Sugita, Makoto Yoshizawa, Y. Yomogida, Y. Sassa, M. Sugiura, J. Riera, R. Kawashima

International Journal of Advanced Computer Engineering　2　(2)　129-133　2009/12
A Study on Effect of Morphological Filters on Computer-aided Medical Image Diagnosis Invited Peer-reviewed

Noriyasu Homma, Yuko Kawai, Satoshi Shimoyama, Tadashi Ishibashi, Makoto Yoshizawa

Artificial Life and Robotics　14　(2)　191-194　2009/11

DOI： 10.1007/s10015-009-0651-8 　
Dynamic Backpropagation Peer-reviewed

Ivo Bukovsky, Noriyasu Homma

Automatizace　52　(10)　586-590　2009/10
放射線治療のための肺腫瘍位置変動の周期ダイナミクス予測に関する一考察 Peer-reviewed

市地慶, 酒井正夫, 本間経康, 高井良尋, 吉澤誠, 竹田宏

計測自動制御学会東北支部45周年記念学術講演会講演論文集　1202　23-26　2009/09/01
Manual control of a nonholonomic system by multiple predictor-controller pair architecture Peer-reviewed

S. Kato, T. Goto, N. Homma, M. Yoshizawa

Proc. ICROS-SICE 2009　5036-5039　2009/08
Auto-Detection of Non-Isolated Pulmonary Nodules Connected to The Chest Walls in X-ray CT images Peer-reviewed

S. Shimoyama, N. Homma, M. Sakai, T. Ishibashi, M. Yoshizawa

Proc. ICROS-SICE 2009　3672-3675　2009/08
Obama, McCain, and Warren Needed Fuzzy Logic to Define 'Rich' by Income Peer-reviewed

Solo, A. M. G, Gupta, M. M, Homma, N, Hou, Z.-G

Proceedings of the 2009 International e-Learning, e-Business, Enterprise Information Systems, and e-Government　265-270　2009/07
Solving Convex Optimization Problems Using Recurrent Neural Networks in Finite Time Peer-reviewed

Long Cheng, Zeng-Guang Hou, Noriyasu Homma, Min Tan, Madam M. Gupta

Proc. International Joint Conference on Neural Networks　2009/06

DOI： 10.1109/IJCNN.2009.5178723 　
Lung Area Extraction from X-ray CT Images for Computer-aided Diagnosis of Pulmonary Nodules by using Active Contour Model Peer-reviewed

Noriyasu Homma, Satoshi Shimoyama, Tadashi Ishibashi, Makoto Yoshizawa

WSEAS Trans. Information Science & Applications,　6　(5)　746-755　2009/05
A New Motion Management Method for Lung Tumor Tracking Radiation Therapy Peer-reviewed

Noriyasu Homma, Masao Sakai, Haruna Endo, Masatoshi Mitsuya, Yoshihiro Takai, Makoto Yoshizawa

WSEAS Trans. Systems　8　(4)　471-480　2009/04
Multiple Model-based Reinforcement learning of a Nonholonomic Control System Peer-reviewed

Shinpei Kato, Takakuni Goto, Noriyasu Homma, Makoto Yoshizawa

4th International Symposium on Medical, Bio- and Nano-Electronics　85-86　2009/03

More details Close

Sendai, Japan
心血管IVR用X線装置の空間散乱X線量の装置間比較 Peer-reviewed

稲葉洋平, 江端綾子, 田浦将明, 結城裕子, 竹川弥香, 梁川功, 田村元, 町田好男, 小倉隆英, 森一生, 本間経康, 石橋忠司, 齋藤春夫, 高井良尋, 佐藤行彦, 仲田栄子, 丸岡伸, 細貝良行, 千田浩一

東北大学医学部保健学科紀要　18　(1)　45-51　2009/02
Auto-Detection of Non-Isolated Pulmonary Nodules in X-ray CT Images Peer-reviewed

Noriyasu Homma, Satoshi Shimoyama, Masao Sakai, Tadashi Ishibashi, Makoto Yoshizawa

PROCEEDINGS OF THE 8TH WSEAS INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, KNOWLEDGE ENGINEERING AND DATA BASES　396-+　2009
Time Series Prediction of Respiratory Motion for Lung Tumor Tracking Radiation Therapy Peer-reviewed

Noriyasu Homma, Masao Sakai, Yoshihiro Takai

NN'09: PROCEEDINGS OF THE 10TH WSEAS INTERNATIONAL CONFERENCE ON NEURAL NETWORKS　126-+　2009
Combinatorial Effect of Various Features Extraction on Computer Aided Detection of Pulmonary Nodules in X-ray CT Images Peer-reviewed

Noriyasu Homma, Kazunori Takei, Tadashi Ishibashi

WSEAS Trans. Information Science & Applications,　5　(7)　1127-1136　2008/07
Natural Intelligence: Noise-Resistance of Neural Spike Communication Peer-reviewed

N. Homma, K. Fuchigami, M, Sakai, T. Goto, K. Abe

Int. J. Artificial Life and Robotics　12　295-300　2008/03

DOI： 10.1007/s10015-007-0485-1 　
形状的特徴量抽出に基づく胸部X線CT画像における肺結節陰影パターンの自動鑑別 Peer-reviewed

武井一典, 本間経康, 石橋忠司, 酒井正夫, 後藤太邦, 吉澤誠, 阿部健一

知能と情報（日本知能情報ファジィ学会誌）　20　(1)　108-116　2008/02
Publisher: Japan Society for Fuzzy Theory and intelligent informatics
DOI： 10.3156/jsoft.20.108 　

ISSN： 1347-7986

More details Close

In this paper, we propose a new diagnosis method of pulmonary nodules in CT images to reduce false positive(FP) rate under high true positive (TP) rate conditions. An essential core of the method is to extract two novel and effective features from the raw CT images: One is orientation features of nodules in a region of interest (ROI) extracted by a gabor filter, while the other is variation of CT values of the ROI in the direction along body axis. Simulation results show that the discrimination rate of the proposed method is extremely improved compared with that by the conventional method.
ＣＴによる動きの描出 Peer-reviewed

齋藤春夫, 千田浩一, 細貝良行, 森一生, 町田好男, 田村元, 丸岡伸, 高井良尋, 大石幹雄, 佐藤行彦, 本間経康, 小倉隆英, 仲田栄子, 石橋忠司

東北大学医学部保健学科紀要　17　(1)　9-13　2008/02
Fundamental theory of artificial higher order neural networks Peer-reviewed

Madan M. Gupta, Noriyasu Homma, Zeng-Guang Hou, Ashu M. G. Solo, Takakuni Goto

Artificial Higher Order Neural Networks for Economics and Business　368-388　2008
Publisher: IGI Global
DOI： 10.4018/978-1-59904-897-0.ch017 　
A new method for computer aided detection of pulmonary nodules in X-ray CT images Peer-reviewed

Noriyasu Homma, Kazunori Takei, Tadashi Ishibashi

ADVANCES ON ARTIFICIAL INTELLIGENCE, KNOWLEDGE ENGINEERING AND DATA BASES, PROCEEDINGS　379-+　2008
Shape Features Extraction from Pulmonary Nodules in X-ray CT Images Peer-reviewed

Noriyasu Homma, Kazuhisa Saito, Tadashi Ishibashi, Madan M. Gupta, Zeng-Guang Hou, Ashu M. G. Solo

2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8　3396-+　2008

DOI： 10.1109/IJCNN.2008.4634280 　

ISSN： 2161-4393
Quantification of radial organization in a dysplastic cerebral cortex with diffusion tensor imaging Peer-reviewed

Masahiro MURASAKI, Tatsuo NAGASAKA, Shin MARUOKA, Yoshihiro TAKAI, Yukihiko SATO, Yoshiyuki HOSOKAI, Takahide OGURA, Issei MORI, Tadashi ISHIBASHI, Koichi CHIDA, Eiko NAKATA, Yoshio MACHIDA, Noriyasu HOMMA, Haruo SAITO, Hajime TAMURA

Bulletin of School of Health Sciences, Tohoku University　17　(2)　127-134　2008
Publisher:
ISSN： 1348-8899

More details Close

Radial organization of dysplastic cerebral cortices was hypothesized and magnetic resonance diffusion tensor imaging was performed for an infant who had a dysplasia in the right cerebral cortex. Absolute value of the inner product of the normal vector to the cerebral surface and the first eigen vector (that depicts the direction of the largest eigen value of diffusion tensor) was calculated for each pixel. The absolute value of the inner product was significantly larger for the dysplastic side than for the contralateral normal side of the brain.
F-MRI analysis of the human brain activities during manual control of a nonholonomic system Peer-reviewed

Shinpei Kato, Takakuni Goto, Noriyasu Homma, Makoto Yoshizawe, Yukihito Yomogida, Yuko Sassa, Motoaki Sugiura, Jorge Riera, Ryuta Kawashima

2008 PROCEEDINGS OF SICE ANNUAL CONFERENCE, VOLS 1-7　1895-+　2008
A Phased Reinforcement Learning Algorithm for Complex Control Problems Peer-reviewed

Takakuni Goto, Noriyasu Homma Makoto Yoshizawa, Kenichi Abe

Int. J. Artificial Life and Robotics　11　(2)　190-196　2007/07

DOI： 10.1007/s10015-007-0427-y 　
Development of the displacement amplification mechanism for myocardial assist device

Watabe Tomoki, Shiraishi Yasuyuki, Wada Yumiko, Sakata Ryo, Saijo Yoshifumi, Yambe Tomoyuki, Homma Dai, Shibata Souichi, Umezu Mitsuo

Journal of Life Support Technology　19　192-192　2007
Publisher: The Society of Life Support Engineering
DOI： 10.5136/lifesupport.19.Supplement_192 　

ISSN： 1341-9455
Computer Aided Diagnosis System for Pulmonary Nodules Using Hierarchical Feature Extraction Peer-reviewed

K. Takei, N. Homma, T. Ishibashi, M. Sakai, M. Yoshizawa, K. Abe

Proc. 12th AROB ‘07　390-393　2007/01
Computer aided diagnosis for pulmonary nodules by shape feature extraction Peer-reviewed

Kazunori Takei, Noriyasu Homma, Tadashi Ishibashi, Masao Sakai, Makoto Yoshizawa

PROCEEDINGS OF SICE ANNUAL CONFERENCE, VOLS 1-8　1959-+　2007
Indoor mobile robot navigation using doorplate landmarks Peer-reviewed

An-Min Zou Zeng-Guang Hou Min Tan Madan M. Gupta Peter, N. Nikiforuk, Noriyasu Homma

Int. J. Vehicle Autonomous Systems　4　(2-4)　143-155　2006/12
An Analysis of the Learning Process on Manual Control of Nonholonomic Systems Peer-reviewed

後藤, 本間吉澤

人間工学　42　(5)　285-294　2006/10
Publisher: Japan Ergonomics Society
DOI： 10.5100/jje.42.287 　

ISSN： 0549-4974

More details Close

This paper describes analysis on human operator's trial and error learning process to control a nonholonomic system. A novel analysis technique using the value function of reinforcement learning is proposed. According to the transition of the value function, human operators tend to explore an objective trajectory first, then shift to the tracking control of the trajectory, and accelerate the tracking scheme simultaneously. This acceleration disturbs the objective trajectory, and inducts another exploration phase to converge on the better solution. These results of the stepped approach of human learning may inspire an improvement to reinforcement learning.
複雑系モデルを用いた生体循環系ダイナミクスの解析 Peer-reviewed

成田,本間, 酒井,田中, 吉澤,阿部

東北大学医学部保健学科紀要　15　(2)　125-135　2006/07
Noise resistance and enhancement of neural performance by using spike signals

Noriyasu Homma, Madan M. Gupta, Zeng-Guang Hou

IEEE International Conference on Neural Networks - Conference Proceedings　3868-3873　2006
Publisher: Institute of Electrical and Electronics Engineers Inc.
DOI： 10.1109/ijcnn.2006.246883 　

ISSN： 1098-7576
Fuzzy neural networks

Madan M. Gupta, Noriyasu Homma, Zeng-Guang Hou

Studies in Fuzziness and Soft Computing　207　205-233　2006
Publisher: Springer Verlag
DOI： 10.1007/978-3-540-35488-8_9 　

ISSN： 1434-9922
Natural Intelligence: Noise-resistance of Neural Spike Communication Invited Peer-reviewed

Noriyasu Homma, Koh Fuchigami, Masao Sakai, Kenichi Abe

Proc. 11th Int'l. Symp. AROB　1　(1)　504-507　2006/01
価値関数を用いた非線形手動制御系の学習過程に関する考察 Peer-reviewed

後藤, 本間, 吉澤, 阿部

東北大学医学部保健学科紀要　15　(1)　17-28　2006/01
Self-Organizing Neural Networks for Incremental Category Learning Peer-reviewed

Masao Sakai, K. Takei, Noriyasu Homma, Y. Koyanaka, Kenichi Abe

Proc. 11th AROB ‘06　7599-7604　2006/01
Noise resistance and enhancement of neural performance by using spike signals Peer-reviewed

Noriyasu Homma, Madan M. Gupta, Zeng-Guang Hou

2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10　3868-+　2006

ISSN： 2161-4393
Analysis of human learning process on manual control of complex systems Peer-reviewed

Takakuni Goto, Noriyasu Homma, Makoto Yoshizawa, Kenichi Abe

2006 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-6, PROCEEDINGS　1648-+　2006

DOI： 10.1109/ICSMC.2006.384955 　

ISSN： 1062-922X
Phased learning with hierarchical reinforcement learning in nonholonomic motion control Peer-reviewed

Takaknuni Goto, Noriyasu Homma, Makoto Yoshizawa, Kenichi Abe

2006 SICE-ICASE INTERNATIONAL JOINT CONFERENCE, VOLS 1-13　2200-+　2006
Self-organizing neural networks using discontinuous teacher data for incremental category learning Peer-reviewed

Masao Sakai, Noriyasu Homma, Kenichi Abe

2006 SICE-ICASE INTERNATIONAL JOINT CONFERENCE, VOLS 1-13　3870-+　2006
Is Neural Firing Frequency an Informational Carrier in Neural Systems? Invited Peer-reviewed

Koh Fuchigami, Noriyasu Homma, Masao Sakai, Kenichi Abe

Proc. SICE Annual Conference 2005 in Okayama　1　(1)　2067-2072　2005/08
Nonlinear Analysis of Chaotic Dynamics in Human Circulatory Systems Peer-reviewed

Taiki Narita, Noriyasu Homma, Masao Sakai, A. Tanaka, Makoto Yoshizawa, Kenichi Abe

Proc. SICE Annual Conference 2005　CD　488-493　2005/08
Multilayer Self-Organizing Category Formation Networks Peer-reviewed

Masao Sakai, Noriyasu Homma, Y. Koyanaka, Kenichi Abe

Proc. SICE Annual Conference 2005　CD　2895-2900　2005/08
Chaotic Mode Transition Dynamics in Human Circulatory Systems Peer-reviewed

Taiki Narita, Noriyasu Homma, Masao Sakai, Makoto Yoshizawa, Kenichi Abe

Proc. 16th IFAC World Congress　CD　1-6　2005/07
Neural Network Methods for the Localization and Navigation of Mobile Robots Peer-reviewed

Hou, Z.G, Tan, M, Gupta, M.M, Nikiforuk, P.N, Homma, N

Proceedings of the IEEE 18th CCECE　2005/05

DOI： 10.1109/CCECE.2005.1557158 　
脳内神経活動の電磁界解析手法の比較・検討 Peer-reviewed

武井一典, 本間経康, 酒井正夫, 吉澤誠, 阿部健一

東北大学医学部保健学科紀要　14　(2)　81-91　2005/04
508 Development of a totally implantable artificial myocardial assist system : Preliminary study of the hemodynamic effect in the mock circulatory system and in animal experiment

AOKI Hidetaka, NITTA Shin-ichi, OKAMOTO Eiji, OGAWA Daisnke, YOSHIZAWA Makoto, TANAKA Akira, TANAKA Takashi, SASADA Hiroshi, TABAYASHI Koichi, HOMMA Dai, NAGATOSHI Jun, ITOH Shinji, SUDO Tomohiro, UMEZU Mitsuo, SHIRAISHI Yasuyuki, SEKINE Kazumitsu, SAIJO Yoshifumi, YAMBE Tomoyuki

Proceedings of the JSME Bioengineering Conference and Seminar　2004　(0)　191-192　2005
Publisher: 一般社団法人日本機械学会
DOI： 10.1299/jsmebs.2004.17.0_191 　
Neural spike communication under noisy environments Peer-reviewed

N Homma, K Fuchigami, MM Gupta

Proceedings of the 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology　165-171　2005
Superimposing Neural Learning by Dynamic and Spatial Changing Weights Peer-reviewed

N. Homma, M. M. Gupta

Artificial Life and Robotics　7　(4)　151-155　2004/04

DOI： 10.1007/BF02471197 　
Speech Recognition using Pulse Coupled Neural Networks with a Radial Basis Function Peer-reviewed

T. Sugiyama, N. Homma, K. Abe, M. Sakai

Artificial Life and Robotics　7　(4)　156-159　2004/04

DOI： 10.1007/BF02471198 　
血管造影・ＩＶＲ時における皮膚被曝線量計算シミュレータの試作 Peer-reviewed

小野寺, 小川, 多田, 富樫, 千田, 立花, 中田, 本間

東北大学医学部保健学科紀要　13　(2)　93-100　2004/04
カオス的遍歴現象を呈するモード遷移ダイナミクスモデル Peer-reviewed

成田, 本間, 酒井, 吉澤, 阿部

東北大学医学部保健学科紀要　13　(2)　101-112　2004/04
2重フィードバック型ニューロンモデルの発火ダイナミクス解析 Peer-reviewed

渕上, 本間, 酒井, 阿部

東北大学医学部保健学科紀要　13　(1)　33-41　2004/04
ニューラルネットワークを用いた顔表情認識 Peer-reviewed

小谷中, 本間, 酒井, 阿部

東北大学医学部保健学科紀要　13　(1)　23-32　2004/04
Face recognition by concept formation neural structure Peer-reviewed

Y Koyanaka, N Homma, M Sakai, K Abe

SICE 2004 ANNUAL CONFERENCE, VOLS 1-3　2130-2134　2004
Chaotic itinerancy model for human circulatory systems dynamics Peer-reviewed

T Narita, M Sakai, N Homma, M Yoshizawa, K Abe

SICE 2004 ANNUAL CONFERENCE, VOLS 1-3　2124-2129　2004
Dynamic neural structure for long-term memory formation Peer-reviewed

N Homma, M Sakai, K Abe, H Takeda

SICE 2004 ANNUAL CONFERENCE, VOLS 1-3　2272-2277　2004
A simple spike neural network can generate complex firing patterns Peer-reviewed

K Fuchigami, N Homma, M Sakai, K Abe

SICE 2004 ANNUAL CONFERENCE, VOLS 1-3　2149-2152　2004
Self-Organizing Neural Networks for Concept Formation Peer-reviewed

Noriyasu Homma, Masao Sakai, Kenichi Abe

Proc. 9th Int'l. Symp. AROB　1　(1)　347-350　2004/01
Fuzzy self-organizing map in cerebral cortical structure for pattern recognition Peer-reviewed

N Homma, MM Gupta

NAFIPS 2004: ANNUAL MEETING OF THE NORTH AMERICAN FUZZY INFORMATION PROCESSING SOCIETY, VOLS 1AND 2　1　539-544　2004
パルス結合RBFネットワークにおける音素認識 Peer-reviewed

酒井, 杉山, 本間, 阿部

東北大学医療技術短期大学部紀要　12　(1)　35-41　2003/04
Memory Superimposition by Backpropagation Neural Networks Peer-reviewed

N. Homma, M. M. Gupta

Bull. College of Medical Sciences, Tohoku University　12　(2)　111-120　2003/04
同時リカレントネットワークによる不連続な非線形関数の統計的近似学習法 Peer-reviewed

酒井, 本間, 阿部

計測自動制御学会論文集　39　(6)　600-606　2003/04
Publisher: The Society of Instrument and Control Engineers
DOI： 10.9746/sicetr1965.39.600 　

ISSN： 0453-4654

More details Close

In this paper, a statistical approximation learning (SAL) method is proposed for training a new type of neural networks which is known as simultaneous recurrent networks (SRNs). SRNs have the capability to approximate non-smooth functions which cannot be approximated by using conventional feedforward neural networks. However, most of learning methods for SRNs are computationally expensive due to their inherent recursive calculations. To solve this problem, a statistical relation between the time-series of the network outputs and the network configuration parameters is used in the proposed SAL method. Simulation results show that the SAL method can learn a strongly nonlinear function efficiently.
A self-organizing concept formation network Peer-reviewed

N Homma, M Sakai, K Abe, H Takeda

SICE 2003 ANNUAL CONFERENCE, VOLS 1-3　2337-2341　2003
Analysis of electromagnetic field of nerve impulses in brain using FDTD method Peer-reviewed

K Sasaki, N Homma, M Sakai, K Abe

SICE 2003 ANNUAL CONFERENCE, VOLS 1-3　502-507　2003
Lyapunov spectrum analysis of reconstructed attractors from observed time series Peer-reviewed

M Sakai, N Homma, M Yano, K Abe

SICE 2003 ANNUAL CONFERENCE, VOLS 1-3　3347-3352　2003
Self-organizing neural networks by dynamic and spatial changing weights Peer-reviewed

N Homma, MM Gupta, M Yoshizawa, K Abe

ISUMA 2003: FOURTH INTERNATIONAL SYMPOSIUM ON UNCERTAINTY MODELING AND ANALYSIS　129-134　2003
A self-organizing neural structure for concept formation from incomplete observation Peer-reviewed

N Homma, MM Gupta

PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4　1　2615-2618　2003

ISSN： 1098-7576
A General Second-order Neural Unit Peer-reviewed

N. Homma, M. M. Gupta

Bull. College of Medical Sciences, Tohoku University　11　(1)　1-6　2002/04
Complexity Control Method of Chaos Dynamics in Recurrent Neural Networks Peer-reviewed

M. Sakai, N. Homma, K. Abe

ICASE　4　(2)　124-129　2002/04
Superimposing Learning for Backpropagation Neural Networks Peer-reviewed

N. Homma, M. M. Gupta

Bull. College of Medical Sciences, Tohoku University　11　(2)　253-259　2002/04
Incremental Neural Learning by Dynamic and Spatial Changing Weights Peer-reviewed

N. Homma, M. M. Gupta

Proc. of the 15th IFAC World Congress on Automatic Control　CD　CD　2002/04
A Statistical Approximation Learning Method for Simultaneous Recurrent Networks Peer-reviewed

M. Sakai, N. Homma, K. Abe

Proc. of the 15th IFAC World Congress on Automatic Control　CD　CD　2002/04
Study on general Second-Order Neural Units (SONUs)

Noriyasu Homma, Madan M. Gupta

Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002　13　177-182　2002
Phase-space reconstruction from observed time series using Lyapunov spectrum analysis Peer-reviewed

M Yano, N Homma, M Sakai, K Abe

SICE 2002: PROCEEDINGS OF THE 41ST SICE ANNUAL CONFERENCE, VOLS 1-5　701-706　2002
Statistical learning method of discontinuous functions using simultaneous recurrent networks Peer-reviewed

M Sakai, N Homma, K Abe

SICE 2002: PROCEEDINGS OF THE 41ST SICE ANNUAL CONFERENCE, VOLS 1-5　3110-3115　2002
Statistical approximation learning of discontinuous functions using simultaneous recurrent neural networks Peer-reviewed

M Sakai, N Homma, MI Gupta, K Abe

PROCEEDINGS OF THE 2002 IEEE INTERNATIONAL SYMPOSIUM ON INTELLIGENT CONTROL　CD　434-439　2002
Control of Chaos Dynamics in Recurrent Neural Networks Peer-reviewed

Masao Sakai, Noriyasu Homma, Kenichi Abe

Proc. of the ICCAS 2001　292-295　2001/12
Stochastic Analysis of Chaos Dynamics in Recurent Neural Networks Peer-reviewed

N. Homma, M. Sakai, M. M. Gupta, K. Abe

Proc. of Joint 9th IFSA / NAFIPS International Conference '01　1　298-303　2001/07
神経回路網におけるカオスダイナミクスの制御 Peer-reviewed

酒井, 本間, 阿部

計測自動制御学会論文集　37　(3)　250-254　2001/03
Publisher: The Society of Instrument and Control Engineers
DOI： 10.9746/sicetr1965.37.250 　

ISSN： 0453-4654

More details Close

This paper demonstrates that the Lyapunov exponents of recurrent neural networks can be controlled by our proposed methods. One of the control methods minimizes a squared error e_λ=(λ-λ^obj)²/2 by a gradient method, where λ is the largest Lyapunov exponent of the network and λ^obj is a desired exponent. λ implying the dynamical complexity is calculated by observing the state transition for a long-term period. This method is, however, computationally expensive for large-scale recurrent networks and the control is unstable for recurrent networks with chaotic dynamics since a gradient collection through time diverges due to the chaotic instability. We also propose an approximation method in order to reduce the computational cost and realize a "stable" control for chaotic networks. The new method is based on a stochastic relation which allows us to calculate the collection through time in a fashion without time evolution. Simulation results show that the approximation method can control the exponent for recurrent networks with chaotic dynamics under a restriction.
Chaos control by stochastic analysis on recurrent neural networks Peer-reviewed

Masao Sakai, Noriyasu Homma, Kenichi Abe

Proc. of AROB 6th 2001　2　(1)　478-481　2001
Complexity Control Method of Chaos Dynamics in Recurrent Neural Networks Peer-reviewed

Masao Sakai, Noriyasu Homma, Kenichi Abe

Proc. of KACC 2000　494-497　2000/10

More details Close

2000 KACC Best Paper Award 受賞
動的ネットワークの励起アトラクタと認識能力の関係に関する一考察 Peer-reviewed

本間, 鎌内

東北大学医療技術短期大学部紀要　9　(2)　223-228　2000/04
Complexity Control Method by Stochastic Analysis for Recurrent Neural Networks Peer-reviewed

Masao Sakai, Noriyasu Homma, Kenichi Abe

Proc. of AROB 5th 2000　1　281-284　2000/01
Complexity Control Method for Recurrent Neural Networks Peer-reviewed

Masao Sakai, Noriyasu Homma, Kenichi Abe

Proc. of IEEE SMC 1999　1　484-489　1999/10
Control method of the Lyapunov exponents for recurrent neural networks Peer-reviewed

Noriyasu Homma, Masao Sakai, Kenichi Abe

Proc. of the 14th World Congress of IFAC　K　51-56　1999/07
生物的な認識機構をもつ文字認識ニューラルネット Peer-reviewed

本間経康, 鎌内俊行, 阿部健一, 竹田宏

計測自動制御学会論文集　35　(4)　568-573　1999/04
Publisher: The Society of Instrument and Control Engineers
DOI： 10.9746/sicetr1965.35.568 　

ISSN： 0453-4654

More details Close

This paper demonstrates that a recognition mechanism based on a biological one can be useful for recognizing "unknown" patterns, and also useful for self-learning of them. An essential point of our proposed mechanism is a dynamical recognition using chaotic dynamics of recurrent neural networks. Harnessing the complex dynamics, the networks can recognize the "known" patterns and their neighbors as the conventional recognition methods are possible. We present some simulation results illustrating that our networks are able to decide whether input patterns are "known" or "unknown" by observing temporal stability of output patterns. In addition, it is shown that recognition of "unknown" patterns makes it possible the networks to learn the new patterns automatically.
神経回路網ダイナミクスの複雑さの制御法 Peer-reviewed

本間経康, 酒井正夫, 阿部健一, 竹田宏

計測自動制御学会論文集　35　(1)　138-143　1999/01
Publisher: The Society of Instrument and Control Engineers
DOI： 10.9746/sicetr1965.35.138 　

ISSN： 0453-4654

More details Close

The paper demonstrates that a complexity of dynamics in recurrent networks with N neurons can be controlled by our gradient methods. The complexity, i.e. the Lyapunov exponent, is calculated by observing the state transition for a long-term period T. One of the control methods is based on the conventional learning algorithms for the recurrent networks. This is the method with high-precision, but it requires O(N⁵T) expected time. To reduce the expensive run time, we propose another method based on the approximate relation between the complexity and a new parameter of the network configuration reported in our previous papers. This approximation requires only O(N²) run time. Simulation results show that the first method can control the exponent and that the approximation one can control the exponent under a restriction. The networks can learn not only the target time series, but also the exponent of the target by a combination method which is incorporated the proposed control method into the conventional learning algorithm.
Effect of Complexity on Learning Ability of Recurrent Neural Networks Peer-reviewed

N. Honma, K. Kitagawa, K. Abe

Artificial Life and Robotics　2　(2)　97-101　1998/07

DOI： 10.1007/BF02471163 　
Adaptive evolution of holon networks by an autonomous decentralized method Peer-reviewed

N Honma, K Abe, M Sato, H Takeda

APPLIED MATHEMATICS AND COMPUTATION　91　(1)　43-61　1998/04

DOI： 10.1016/S0096-3003(97)10008-X 　

ISSN： 0096-3003
リカレントニューラルネットワークの創発的学習手法 Peer-reviewed

喜多川健, 本間経康, 阿部健一

計測自動制御学会論文集　33　(11)　1093-1098　1997/11
Publisher: The Society of Instrument and Control Engineers
DOI： 10.9746/sicetr1965.33.1093 　

ISSN： 0453-4654

More details Close

We propose a learning method for recurrent neural networks with dynamics. The core of this method is to keep a complexity of the network dynamics in the vicinity of the edge of chaos. To investigate the properties of the dynamics effectively and explicitly, novel stochastic parameters defined by combinations of the standard parameters such as individual connection strengths and thresholds are introduced, and then relations between complexities of the dynamics and the stochastic parameters are revealed. The standard parameters are changed by the core part based on the relations and also according to the global error measure. Some examples suggest that the method is practical one for temporal supervised learning tasks and therefore the dynamics of the edge of chaos are effectual for learning of the recurrent networks.
ホロンネットワークの創発的進化による非線形システムのダイナミクス推定 Peer-reviewed

本間経康, 佐藤光男, 阿部健一, 竹田宏

計測自動制御学会論文集　31　(10)　1739-1745　1995/10
Publisher: The Society of Instrument and Control Engineers
DOI： 10.9746/sicetr1965.31.1739 　

ISSN： 0453-4654

More details Close

The paper demonstrates that holon networks can be used effectively for the identification of nonlinear dynamical systems. The emphasis of the paper is on modeling of complicated systems which have a great deal of uncertainty and unknown interactions between their elements and parameters. The concept of applying a quantitative model building, for example, to environmental or ecological systems is not new. In a previous paper we presented a holon network model as an another alternative to quantitative modeling. Holon networks have a hierarchical construction where each level of hierarchy consists of networks with reciprocal actions among their elements. The networks are able to evolve by self-organizing their structure and adapt their parameters to environments. This was achived by an autonomous decentralized adaptation method. Holon networks, being constructed by a number of elements and hence having high degree of parameter freedom, have great flexibility of their functions. But, at the same time, such networks are computationally expensive. In this paper we propose a new emergent evolution method to reduce the computation times. In this new evolution method the initial holon networks consists of only a few elements and it grows gradually with each new observation and autonomous criterion in order to fit their function to the environment. Some examples show that this method can lead to network structures which have sufficient flexibility and adapt well to various environments.
自律分散的適応手法によるホロンネットワークの進化について Peer-reviewed

本間経康, 佐藤光男, 阿部健一, 竹田宏

計測自動制御学会論文集　31　(7)　908-915　1995/07
Publisher: The Society of Instrument and Control Engineers
DOI： 10.9746/sicetr1965.31.908 　

ISSN： 0453-4654

More details Close

For a control problem of a complicated nonlinear system with unknown dynamics, system identification method is a useful method, because the method makes clear the properties of the system. But this method with usual linear approximation model is not useful enough for the properties of natural phenomena, for instance atmospheric phenomena, earthquakes, etc., and of biological behaviors, for instance brain action, an organic action, etc. When such a complicated system is analyzed, it is not able to make precisely clear the properties of the system by analyzing properties of individual elements separated from the whole system, because such elements of such a complicated system have polysemy. In other words, in such a system, complicated interaction among the elements exerts an influence upon the system behavior. For this problem, in this paper, a new model of complicated nonlinear systems with unknown dynamics is proposed, and an adaptation algorithm using the new model is presented. The model consists of a holon network in which the reciprocal action among the elements (holon) exists, and which is able to realize evolution of its performance adapting to its environment by changing network parameters. In this adaptation algorithm, the network structure is reconstructed by autonomous decentralized adaptation of the parameters keeping balance of two properties of holon, which are properties as the whole to the parts and as the parts to the whole. It is shown for some examples that this algorithm leads to a network structure adapting to the environment and that this model has sufficient generalization ability.
最適制御入力の学習的ランダム探索アルゴリズム Peer-reviewed

本間経康, 佐藤光男, 竹田宏

計測自動制御学会論文集　29　(9)　1086-1093　1993/09
Publisher:
DOI： 10.9746/sicetr1965.29.1086 　

ISSN： 0453-4654
Classification of Masses in Mammogram: A Comparison Study of State-Of-The-Art Deep Learning Technologies Peer-reviewed

Hiroki Takano, Xiaoyong Zhang, Noriyasu Homma, Makoto Yoshizawa

American Association of Physicists in Medicine 60th Annual Meeting　(TU-I345-GePD-F1-2)

Show all ︎Show first 5

Misc. 91

Examination of multimodal deep learning model for predicting recurrence of non-small cell lung cancer

稲森瑠星, 臼崎琢磨, 市地慶, 市地慶, 市地慶, 張暁勇, 本間経康

日本診療放射線技師会誌　71　(10)　2024

ISSN： 2187-2538
Indoor localization by passively using Bluetooth radio waves without wearing a device

梅原優佑, 杉田典大, 市地慶, 本間経康

電子情報通信学会大会講演論文集(CD-ROM)　2023　2023

ISSN： 1349-144X
Performance improvement on deep-learning model-based lung tumor motion prediction by respiratory motion data augmentation for radiotherapy

石井万結, 市地慶, 淡路樹, 篠原唯, ZHANG Xiaoyong, 本間経康

インテリジェント・システム・シンポジウム(CD-ROM)　31st　2023
Saliency Map Visualization of Deep Learning for Alzheimer’s Disease Diagnosis Using PET Images

水野泰平, ZHANG X., ZHANG X., 市地慶, 杉田典大, 本間経康

インテリジェント・システム・シンポジウム(CD-ROM)　30th　2022
Estimation of organ motion from X-ray image sequences using particle filter for lung cancer radiotherpy

篠原匠, 市地慶, ZHANG X., ZHANG X., 杉田典大, 本間経康

インテリジェント・システム・シンポジウム(CD-ROM)　30th　2022
Possibilities and Limitations of Video Plethysmography as Wear ”less”-Monitoring

吉澤誠, 杉田典大, 湯田恵美, 田中明, 本間経康, 山家智之

日本生体医工学会大会プログラム・抄録集(Web)　59th　2020
溺死例の肺CT画像をAI(人工知能)で解析する

舟山眞人, 舟山眞人, 今野拓哉, AMBER Qureshi, 佐藤亮太, 臼井章仁, 臼井章仁, 川住祐介, 小河原輝正, 猪狩由, 張暁勇, 本間経康

日本法医学雑誌　74　(1)　82-82　2020
Publisher: (NPO)日本法医学会
ISSN： 0047-1887
活動依存性マンガン造影MRIの実験プロトコルの問題点

谷平大樹, 菊田里美, 藤原智徳, 本間経康, 小山内実

日本生理学雑誌　81　(1)　12-12　2019/02
Publisher: (一社)日本生理学会
ISSN： 0031-9341
活動依存性マンガン造影MRIの実験プロトコルの問題点

谷平大樹, 菊田里美, 藤原智徳, 本間経康, 小山内実

日本生理学雑誌　81　(1)　12-12　2019/02
Publisher: (一社)日本生理学会
ISSN： 0031-9341
映像脈波を用いた血圧推定の可能性

杉田典大, 吉澤誠, 野呂泰平, 八巻俊輔, 市地慶, 本間経康, 山家智之

日本生体医工学会大会プログラム・抄録集(Web)　58th　2019
マルチカメラ映像を用いた生体情報抽出に関する研究

戸沼大, 吉澤誠, 杉田典大, 本間経康

計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)　2019　2019
隠れマルコフモデルを用いたX線動画像からの腫瘍像抽出法の先験情報導入による性能向上の試み

奥田隼梧, 市地慶, 本間経康, 張曉勇, 吉澤誠

計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)　2019　2019
深層学習は乳癌画像をどう読むか

本間経康, 本間経康, 張暁勇, 張暁勇, 高野寛己, 野呂恭平, 張彰, 陳家旗, 市地慶, 市地慶, 杉田典大, 酒井正夫, 吉澤誠, 川住祐介, 石橋忠司

日本乳癌画像研究会プログラム・抄録集　28th　35　2019
マーカレス腫瘍追跡のための隠れマルコフモデルを用いたX線動画像からの物体輝度抽出—Hidden Markov model-based extraction of tumor target in X-ray image sequence for markerless tumor tracking—システム研究会インテリジェント・システム(FAN2018)

新藤雅大, 市地慶, 本間経康, 張曉勇, 杉田典大, 八巻俊輔, 髙井良尋, 吉澤誠

電気学会研究会資料. ST / システム研究会 [編]　2018　(39-54・56-78・80-84)　37-42　2018/09
Publisher: 電気学会
乳房X線画像における良悪性鑑別が難しい腫瘤に対する深層学習の性能評価

野呂恭平, 張暁勇, 高野寛己, 市地慶, 柳垣聡, 高根侑美, 石橋忠司, 本間経康

日本放射線技術学会雑誌　74　(9)　1091-1092　2018/09
Publisher: (公社)日本放射線技術学会
ISSN： 0369-4305
乳房X線画像における良悪性鑑別が難しい腫瘤に対する深層学習の性能評価

野呂恭平, 張暁勇, 高野寛己, 市地慶, 柳垣聡, 高根侑美, 石橋忠司, 本間経康

日本放射線技術学会雑誌　74　(9)　1091-1092　2018/09
Publisher: (公社)日本放射線技術学会
ISSN： 0369-4305

eISSN： 1881-4883
呼吸性移動対策のための肺腫瘍位置の時系列成分分離に基づく予測

佐藤雄介, 市地慶, 新藤雅大, 張暁勇, 角谷倫之, 小山内実, 高井良尋, 本間経康

日本放射線技術学会雑誌　74　(9)　1092-1093　2018/09
Publisher: (公社)日本放射線技術学会
ISSN： 0369-4305
活動依存性マンガン造影MRIのための撮影パラメータの検討

谷平大樹, 菊田里美, 藤原智徳, 本間経康, 小山内実

日本放射線技術学会雑誌　74　(9)　1092-1092　2018/09
Publisher: (公社)日本放射線技術学会
ISSN： 0369-4305

eISSN： 1881-4883
死人の脈を診る「魔法の鏡」―ビデオカメラによる遠隔・非接触生体情報抽出技術―

吉澤誠, 杉田典大, 田中明, 本間経康, 山家智之

光学シンポジウム講演予稿集　43rd　65‐68　2018/06/21
Imaging analysis of the input-output characteristics of the striatal projection

笹川正人, 菊田里美, 小林和人, 本間経康, 小山内実

電気学会研究会資料　(MBE-18-001-031)　27‐30　2018/03/20
Neural network(NN)を用いたHolter ECGのwideおよびnarrow QRSの識別についての検討―NNは従来法よりもQRS識別能を改善させるか?―

橋本英樹, 田中充, 鎌田弘之, 松田神一, 庄野逸, 本間経康, 本間経康, 吉澤誠

心電図　38　(Suppl.1)　S-62　2018/03
Publisher: (一社)日本不整脈心電学会
ISSN： 0285-1660

eISSN： 1884-2437
活動依存性マンガン造影MRIによる神経活動計測タイミングの検討

谷平大樹, 菊田里美, 菊田里美, 本間経康, 本間経康, 小山内実, 小山内実

日本生理学雑誌(Web)　80　(1)　24-25　2018/02
Publisher: (一社)日本生理学会
ISSN： 0031-9341
関心領域の画素数が映像からの心拍数推定精度に及ぼす影響に関する研究

戸沼大, 吉澤誠, 杉田典大, 本間経康

計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)　2018　2018
Hidden Markov model-based extraction of tumor target in X-ray image sequence for markerless tumor tracking

新藤雅大, 市地慶, 本間経康, ZHANG Xiaoyong, 杉田典大, 八巻俊輔, 高井良尋, 吉澤誠

電気学会研究会資料　(ST-18-039-054.056-078.080-084)　37‐42　2018
Non-contact blood pressure estimation using video pulse waves for ubiquitous health monitoring

Makoto Yoshizawa, Norihiro Sugita, Makoto Abe, Akira Tanaka, Noriyasu Homma, Tomoyuki Yambe

2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017　2017-January　1-3　2017/12/19
Publisher: Institute of Electrical and Electronics Engineers Inc.
DOI： 10.1109/GCCE.2017.8229429 　
マーカレス腫瘍追跡のためのX線動画像の物体輝度の重畳状態を考慮した動体抽出の検討

新藤雅大, 市地慶, 張暁勇, 本間経康, 齊藤望, 高井良尋, 吉澤誠

計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)　2017　ROMBUNNO.SS12‐11　2017/11/25
肺がん放射線治療のためのX線動画像中の標的腫瘍のアフィン変換に基づく追跡法

齊藤望, 市地慶, 張暁勇, 本間経康, 新藤雅大, 高井良尋, 吉澤誠

計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)　2017　ROMBUNNO.SS12‐4　2017/11/25
乳がん病変検出のための深層学習を用いた計算機支援画像診断システム

鈴木真太郎, 張暁勇, 高根侑美, 川住祐介, 石橋忠司, 本間経康, 吉澤誠

計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)　2017　ROMBUNNO.SS12‐5　2017/11/25
全脳神経活動履歴計測法であるマンガン造影MRIの定量的発展とパーキンソン病モデル動物への応用

菊田里美, 菊田里美, 中村幸代, 山村行生, 本間経康, 柳川右千夫, 笠原二郎, 小山内実

計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)　2017　ROMBUNNO.SS12‐6　2017/11/25
Involvement of the store operated calcium entry in the long-lasting calcium transient in the striatal GABAergic neuron.

Kikuta S, Yanagawa Y, Homma N, Takada M, Osanai M

Neuroscience 2017(2017/11/13,Washington, DC, USA)　2017/11
Possibility of Games Using a Blood Perfusion Display: "The Mirror Magical"

2017　287-291　2017/09/09
活動依存性マンガン造影MRIのための脳内マンガン動態の検討

谷平大樹, 菊田里美, 菊田里美, 菊田里美, 本間経康, 小山内実

電気学会電子・情報・システム部門大会講演論文集(CD-ROM)　2017　ROMBUNNO.TC6‐11　2017/09/06
線条体投射ニューロンの入出力特性のイメージング解析

笹川正人, 菊田里美, 菊田里美, 菊田里美, 本間経康, 本間経康, 小林和人, 小山内実, 小山内実

電気学会電子・情報・システム部門大会講演論文集(CD-ROM)　2017　ROMBUNNO.TC6‐5　2017/09/06
マーカレス追尾照射に必要な数理技術

本間経康, 髙井良尋, 張曉勇, 市地慶, 魚住洋佑, 酒井正夫, 吉澤誠

医学物理 Supplement　37　(Suppl.2)　7-16　2017/04
Publisher: (公社)日本医学物理学会
ISSN： 1345-5354

eISSN： 2186-9634
Multi-scale imaging for unraveling the brain functions

小山内実, 菊田里美, 本間経康

電気学会医用・生体工学研究会資料　MBE-17　(15-41)　137‐140　2017/03/20
逐次近似応用再構成における信号量の測定について

富永千晶, 後藤光範, 安海弘樹, 田浦将明, 本間経康, 森一生

日本放射線技術学会総会学術大会予稿集　73回　250-250　2017/03
Publisher: (公社)日本放射線技術学会
ISSN： 1884-7846
ビデオカメラによる遠隔・非接触的血圧変動推定

吉澤誠, 杉田典大, 阿部誠, 田中明, 本間経康, 山家智之

日本生体医工学会大会プログラム・抄録集(Web)　56th　2017
映像脈波によるサイバー健康管理

吉澤誠, 杉田典大, 阿部誠, 田中明, 本間経康, 山家智之

日本生体医工学会大会プログラム・抄録集(Web)　56th　2017
Deep learning for medical big data and computer-aided diagnosis

本間経康, 張暁勇, 鈴木真太郎, 魚住洋佑, 市地慶, 柳垣聡, 高根侑美, 川住祐介, 石橋忠司, 吉澤誠

Transactions of Japanese Society for Medical and Biological Engineering　56th　(3)　228-228　2017
Publisher: 公益社団法人日本生体医工学会
ISSN： 1347-443X

More details Close

In recent years, deep convolutional neural network (DCNN) has attracted great attention due to its outstanding performance in recognition of natural images. However, its performance for medical image recognition is still uncertain because collecting a large-scale medical training data is difficult. To solve this shortage of training data problem, we propose a transfer learning strategy for mass detection in mammograms. We firstly train a DCNN using a large-scale natural image dataset for classification of 1,000 classes. Then, we modify a fully-connected output layer of the DCNN and subsequently train the DCNN using a relatively small-scale mammogram dataset for two classes classification: mass and normal. The experimental results showed that sensitivity of the mass detection was about 90% and false positive was 20 %. In addition, we discuss another solution for the shortage of training data by collecting a medical big data in way of an autonomous decentralized system.
Classification of Benign and Malignant Masses in Mammogram by Using Deep Convolutional Neural Network

高野寛己, 張曉勇, 本間経康, 吉澤誠

Tohoku-Section Joint Convention Record of Institutes of Electrical and Information Engineers, Japan　2017　(0)　153-153　2017
Publisher: Organizing Committee of Tohoku-Section Joint Convention of Institutes of Electrical and Information Engineers, Japan
DOI： 10.11528/tsjc.2017.0_153 　
活動依存性マンガン造影MRIのための脳内マンガン動態の検討

谷平大樹, 菊田里美, 稲波千尋, 大澤匡弘, 本間経康, 小山内実

計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)　2017　ROMBUNNO.SS12‐8　2017
qAIM‐MRIによるD1ドーパミン受容体コンディショナルノックダウンマウスの全脳神経活動解析

小山内実, 小山内実, 菊田里美, 菊田里美, 菊田里美, 谷平大樹, 本間経康, 本間経康, 中尾聡宏, 小田佳奈子, 笹岡俊邦, 南部篤

日本大脳基底核研究会　32nd　20　2017
PSF法におけるMTFの位置依存性とその改善

安海弘樹, 富永千晶, 後藤光範, 田浦将明, 本間経康, 森一生

日本放射線技術学会総会学術大会予稿集　72回　280-280　2016/02
Publisher: (公社)日本放射線技術学会
ISSN： 1884-7846
低CNR条件のMTF測定における加算平均方法の比較

富永千晶, 安海弘樹, 後藤光範, 本間経康, 森一生

日本放射線技術学会総会学術大会予稿集　72回　280-281　2016/02
Publisher: (公社)日本放射線技術学会
ISSN： 1884-7846
Design and evaluation of a newly developed Fontan clip

Ikeda Jumpei, Yambe Tomoyuki, Shiraishi Yasuyuki, Yamada Akihiro, Tsuboko Yusuke, Taira Yasunori, Suzuki Takuji, Inoue Yusuke, Homma Dai, Yamagishi Masaaki

Transactions of Japanese Society for Medical and Biological Engineering　54　(26)　S16-S16　2016
Publisher: Japanese Society for Medical and Biological Engineering
DOI： 10.11239/jsmbe.54Annual.S16 　

ISSN： 1347-443X
A Mammographic Mass Detection Method Based on Transfer Learning of Deep Convolutional Neural Network

鈴木真太郎, 張曉勇, 本間経康, 吉澤誠

Tohoku-Section Joint Convention Record of Institutes of Electrical and Information Engineers, Japan　2016　(0)　1-1　2016
Publisher: 電気関係学会東北支部連合大会実行委員会
DOI： 10.11528/tsjc.2016.0_1 　
大脳皮質‐基底核‐視床ループにおけるパーキンソン病責任領野の同定

菊田里美, 中村幸代, 山村行生, 本間経康, 柳川右千夫, 田村元, 笠原二郎, 小山内実

日本生理学雑誌(Web)　78　(1)　12-12　2016/01
Publisher: (一社)日本生理学会
ISSN： 0031-9341
MRIを用いた全脳神経活動履歴計測法によりパーキンソン病の病態を可視化する

菊田里美, 菊田里美, 中村幸代, 山村行生, 本間経康, 柳川右千夫, 田村元, 笠原二郎, 小山内実

インテリジェント・システム・シンポジウム(CD-ROM)　25th　ROMBUNNO.B101　2015/09/24
活動依存性マンガン造影MRIを用いたパーキンソン病モデルマウスの神経活動履歴計測

菊田里美, 中村幸代, 山村行生, 田村篤史, 本間経康, 柳川右千夫, 田村元, 笠原二郎, 小山内実

日本生理学雑誌　77　(2)　48-48　2015/03
Publisher: (一社)日本生理学会
ISSN： 0031-9341
大脳皮質内神経回路ダイナミクスにおける興奮性・抑制性ニューロンの活動の時間的関係

田村篤史, 菊田里美, 柳川右千夫, 本間経康, 小山内実

日本生理学雑誌　77　(2)　49-49　2015/03
Publisher: (一社)日本生理学会
ISSN： 0031-9341
Examination of pediatric pulmonary circulation assist device based on Fontan circulation animal experimental model

YAMADA AKIHIRO, Shiraisihi Yasuyuki, Miura Hidekazu, Tsuboko Yusuke, Taira Yasunori, Sano Kyosuke, Yamagishi Masaaki, Homma Dai, Yambe Tomoyuki

Transactions of Japanese Society for Medical and Biological Engineering　53　(0)　S201_01-S201_01　2015
Publisher: Japanese Society for Medical and Biological Engineering
DOI： 10.11239/jsmbe.53.S201_01 　

ISSN： 1347-443X

More details Close

Fontan procedure is the final palliative surgical operation in pediatric patients with congenital heart disease. After Fontan procedure, there is non-pulsatile flow in the pulmonary circulation. We have been developing the pulmonary circulation assist device for the Fontan circulation using shape memory alloy fibers. The device structure is mechanically contraction from the outside of the extracardiac conduit. For clinical application of the device, we have been also developing the animal experimental model for in vivo examination of the Fontan circulation assist device. In this study, we examined the hemodynamics change in the device driving the animal experimental model. The animal experimental model was constructed in four adult goats (45.8±15.6 kg). The right heart bypass of inferior vena cava to pulmonary artery was constructed by using extracardiac conduit, and the left ventricular assist device was connected to reduce of left ventricular load. The device could be mounted easily to the conduit in the thoracic cavity. The pulsatile flow could be generated in the pulmonary circulation by the device contraction. We performed the evaluation of the pediatric pulmonary circulatory assist device in the animal experimental model.
Noise Power Spectrum in PROPELLER MR Imaging Peer-reviewed

Sato K, Shidahara M, Goto M, Yanagawa I, Homma N, Mori I

Magn Reson Med Sci,　14　(3)　235-242　2015

DOI： 10.2463/mrms.2014-0071 　

More details Close

The noise power spectrum (NPS), an index for noise evaluation, represents the frequency characteristics of image noise. We measured the NPS in PROPELLER (Periodically Rotated Overlapping ParallEL Lines with Enhanced Reconstruction) magnetic resonance (MR) imaging, a nonuniform data sampling technique, as an initial study for practical MR image evaluation using the NPS. The 2-dimensional (2D) NPS reflected the k-space sampling density and showed agreement with the shape of the k-space trajectory as expected theoretically. Additionally, the 2D NPS allowed visualization of a part of the image reconstruction process, such as filtering and motion correction.
Circular edge MTF measurement: Its problems Peer-reviewed

MORI Issei

Proceedings of JSCT　3　64-66　2015
乳房密度は日本人女性でも乳がん罹患危険因子か

張暁勇, 筑島徳政, 渡邉篤俊, 大橋悠二, 長谷川奈保, 市地慶, 田村篤史, 小山内実, 本間経康

東北大学医学部保健学科紀要　24　(1)　45-51　2015
人知を超える電脳出現の展望と医学応用

本間経康

東北医学雑誌　126　(2)　167-168　2014/12
Publisher: 東北医学会
ISSN： 0040-8700
パーキンソン病の病態は背外側線条体の神経活動と相関している

菊田里美, 中村幸代, 山村行生, 柳川右千夫, 田村篤史, 本間経康, 田村元, 笠原二郎, 小山内実

電気学会電子・情報・システム部門大会講演論文集(CD-ROM)　2014　ROMBUNNO.TC4-8　2014/09/03
逐次近似再構成の体軸方向解像度測定を目的とした新しい手法の検討

後藤光範, 田浦正将, 佐藤和宏, 佐藤益弘, 本間経康, 森一生

日本放射線技術学会雑誌　70　(9)　1001-1001　2014/09
Publisher: (公社)日本放射線技術学会
ISSN： 0369-4305

eISSN： 1881-4883
低コントラスト円形エッジ法によるCTのMTF測定の問題について

富永千晶, 後藤光範, 佐藤和宏, 本間経康, 森一生

日本放射線技術学会雑誌　70　(9)　1079-1079　2014/09
Publisher: (公社)日本放射線技術学会
ISSN： 0369-4305

eISSN： 1881-4883
MLC Trackingのための呼吸性肺腫瘍移動の予測法

本間経康, 髙井良尋, 市地慶, 張暁勇, 成田雄一郎

Rad Fan　12　(3)　97-100　2014/03
Publisher: 株式会社メディカルアイ
Target Tracking in Medical Images Using Template Matching

Xiaoyong Zhang, Noriyasu Homma

Bulletin of School of Health Sciences Tohoku University　23　(1)　9-15　2014/01/31
テンプレートマッチングを用いた医用画像の目標追跡

張暁勇, 本間経康

東北大学医学部保健学科紀要　23　(1)　9-15　2014
MRIを用いた神経活動履歴計測

菊田里美, 中村幸代, 山村行生, 柳川右千夫, 本間経康, 笠原二郎, 小山内実

日本生理学雑誌　76　(1)　34-35　2014/01
Publisher: (一社)日本生理学会
ISSN： 0031-9341
Intelligent Modeling of Respiratory-induced Tumor Motion for Improving Prediction Accuracy

市地慶, 本間経康, 張曉勇

電気学会研究会資料. ST　2013　(29)　85-90　2013/09/25
Publisher: 電気学会
Development of Computer-Aided Diagnosis Systems for Detection of Architectural Distortion in Mammograms

Noriyasu Homma

Bulletin of School of Health Sciences Tohoku University　22　(2)　67-77　2013/07/31
Publisher: 東北大学医学部保健学科
ISSN： 1348-8899
Dosimetric Impact in Moving Tumor Under Irradiation Dose by Chasing Its Motion with DMLC

Y. Narita, N. Homma, K. Ichiji, Y. Takai

MEDICAL PHYSICS　40　(6)　2013/06

DOI： 10.1118/1.4814588 　

ISSN： 0094-2405
Methods for Estimating a Cross-Correlation Index of the Baroreflex System by using a Plethysmography

Makoto Yoshizawa, Norihiro Sugita, Tomoyuki Yambe, Satoshi Konno, Telma Keiko Sugai, Makoto Abe, Noriyasu Homma, Shin-ichi Nitta

Nano-Biomedical Engineering 2012　566-576　2012
情報通信技術（ＩＣＴ）は医療福祉問題の救世主か？

吉澤誠, 杉田典大, 阿部誠, 西條芳文, 本間経康, 金野敏, 山家智之, 仁田新一

生体医工学　49　(2)　387-389　2011/04
Publisher: Japanese Society for Medical and Biological Engineering
DOI： 10.11239/jsmbe.49.387 　

ISSN： 1347-443X
Quantification of Radial Prganization in a Dysplastic Cerebral Cortex with Diffusion Tensor Imaging

村崎晶洋, 永坂, 竜男, 丸岡, 伸, 高井, 良尋, 佐藤, 行彦, 細貝, 良行, 小倉, 隆英, 森, 一生, 石橋, 忠司, 千田, 浩一, 仲田, 栄子, 町田, 好男, 本間, 経康, 齋藤, 春夫, 田村元

東北大学医学部保健学科紀要　17　(2)　127-134　2011
Virtual Walking System for Smart Aging

SUGIHARA Ryouta, SUGITA Norihiro, HOMMA Noriyasu, YOSHIZAWA Makoto

IEICE technical report　110　(294)　37-42　2010/11/11
Publisher: The Institute of Electronics, Information and Communication Engineers
ISSN： 0913-5685

More details Close

In this study, a novel virtual walking system has been developed for putting the concept of advocating a positive acceptance of the later stages of life or aging, called smart aging, into practice. An essential core of the system can be found in balancing between virtual and real worlds for old people to use pleasantly and safely. The system consists of a laptop computer, micro-projectors, and a completely new screen system mounted on the walking frame, called "walking frame mounted display (WFMD)." Users can physically walk with pleasure by the virtual reality technology and safely by the WFMD in the virtual world. Furthermore, by using the video game controller "Wii Remote" as the sensor, the system is sufficiently inexpensive for home use. Experimental results clearly demonstrate the effectiveness of the system compared to the virtual reality system with conventional head mounted display.
遠隔医療のための心電図・脈波信号解析手法に関する研究(3.2 第8回情報シナジー研究会, 3. 研究活動報告)

村越政之, 吉澤誠, 杉田典大, 阿部誠, 本間経康

年報　9　109-114　2010/07
Publisher: 東北大学サイバーサイエンスセンター
胸部X線CT画像における肺結節陰影の自動検出法の開発(3.2 第7回情報シナジー研究会, 3. 研究活動報告)

本間経康, 下山聡, 石橋忠司, 吉澤誠

年報　8　109-113　2009/07
Publisher: 東北大学サイバーサイエンスセンター
運動制御動作の獲得過程における自発的拘束と機能創発

後藤太邦, 本間経康, 川島隆太

2009/01
The 11th International Symposium on Artificial Life and Robotics (AROB 11th'06)

HOMMA Noriyasu

45　(5)　465-465　2006/05/10

ISSN： 0453-4662
Fuzzy-Neural Computing Systems (Proc. World Automation Congress )

M. M. Gupta, N. Homma

Proc. World Automation Congress　CD　CD　2002/04
Phoneme Recognition using Pulse Coupled Neural Networks with a Radial Basis Function

SUGIYAMA Taiji, HOMMA Noriyasu, ABE Kenichi

14　141-144　2002/01/25
<Original Papers>Short-term Prediction of Chaotic Time Series by Intermittent Observation

Noriyasu HONMA, Takeshi HASEGAWA, Dept of Radiological Tech Coll of Medical Sciences Tohoku University, NEC Corporation

Bulletin of College of Medical Sciences,Tohoku University　9　(1)　37-41　2000/01/31
Publisher: 東北大学医療技術短期大学部
ISSN： 0917-4435
Study on Excited Attractors of Recurrent Neural Networks for Dynamical Recognition

HOMMA Noriyasu, KAMAUCHI Toshiyuki, ABE Kenichin, TAKEDA Hiroshi

12　199-204　2000/01/21
Synchronization of Chaotic Systems by Intermittent Driving Signals

Noriyasu HONMA, Takeshi HASEGAWA, Department of Radiological Technology College of Medical Sciences Tohoku University, NEC Corporation

8　(2)　197-201　1999/07/31

ISSN： 0917-4435
The Accumulation Effect of the Digital Radiography System Using a Cooled CCD Camera and Its Clinical Applicability

Mikio OISHI, Masayuki ZUGUCHI, Yoshiyuki HOSOKAI, Yosirou SEISYOU, Haruo OBARA, Noriyasu HONMA, Shin MARUOKA

東北大学医療技術短期大学部紀要　8　(2)　203-210　1999/07/31
Publisher: 東北大学医療技術短期大学部
ISSN： 0917-4435
X-Ray Multi-Layer Imaging Using Both a General X-Ray Equipment and a Digital Radiography System with a Cooled CCD Camera

Yosirou SEISYOU, Mikio OISHI, Masayuki ZUGUCHI, Yoshiyuki HOSOKAI, Noriyasu HONMA, Haruo OBARA

東北大学医療技術短期大学部紀要　8　(2)　211-218　1999/07/31
Publisher: 東北大学医療技術短期大学部
ISSN： 0917-4435
Control of the Complexity in Recurrent Neural Networks

Noriyasu HONMA, Department of Radiological Technology College of Medical Sciences Tohoku University

8　(1)　23-30　1999/01/31

ISSN： 0917-4435
Study of Dynamical Complexities in Fully Connected Recurrent Neural Networks

Noriyasu HONMA, Ken KITAGAWA, Department of Radiological Technology College of Medical Sciences Tohoku University, NTT DATA Corporation

8　(1)　11-16　1999/01/31

ISSN： 0917-4435
冷却CCDカメラを用いたIV－DSAシステムの基礎的研究

洞口正之, 斉藤春夫, 大石幹雄, 鈴木正吾, 本間経康

メディカルトレンド’99　14　(8)　52　1999
Publisher: Innervision
A Neural Network for Character Recognition Based on a Dynamical Recognition Mechanism

Noriyasu HONMA, Toshiyuki KAMAUCHI, Department of Radiological Technology College of Medical Sciences Tohoku University, Toyota Motor Corporation

7　(2)　137-142　1998/09/01

ISSN： 0917-4435
An Approximate Partitioning Algorithm for Traveling Salesman Problems

Noriyasu HONMA, Daisuke UCHIDA, Department of Radiological Technology College of Medical Sciences Tohoku University, Toyota Moter Corporation

7　(2)　109-114　1998/09/01

ISSN： 0917-4435
Nonlinear Observers for Unknown Chaotic Systems via Neural Networks

Noriyasu HONMA, Takeshi HASEGAWA, Department of Radiological Technology College of Medical Sciences Tohoku University, Graduate School of Engineering Tohoku university

7　(2)　123-128　1998/09/01

ISSN： 0917-4435
Construction of Transverse Image under X-ray Fluoroscopic Condition

Yoshiyuki HOSOKAI, Mikio OISHI, Haruo OBARA, Masatoshi SASAKI, Noriyasu HONMA, Masayuki ZUGUCHI

東北大学医療技術短期大学部紀要　7　(2)　129-136　1998/09/01
Publisher: 東北大学医療技術短期大学部
ISSN： 0917-4435
A Neural Network for Character Recognition Based on the Dynamics of Biological Recognition

KAMAUCHI Toshiyuki, HOMMA Noriyasu, ABE Kenichin

10　13-16　1998/01/20
An Approximate Partitioning Algorithm for Traveling Salesman Problem by Using Total Information

UCHIDA Daisuke, HONMA Noriyasu, ABE Kenichi

9　319-322　1997/01/16
An Autonomous Decentralized Heuristic Algorithm for Traveling Salesman Problems Using Holon Networks

HONMA Noriyasu, ABE Kenichi, SATO Mitsuo, TAKEDA Hiroshi

8　29-32　1996/01/17
ホロンネットワークモデルを用いた自律分散的適応法による非線形システムの同定

本間

第36回自動制御連合講演会前刷　141-142　1993

Show all ︎Show first 5

Books and Other Publications 17

放射線治療AIと外科治療AI

有村, 秀孝, 諸岡, 健一

オーム社　2020/04

ISBN: 9784274225475
Political Campaigning in the Information Age

Ashu M. G. Solo, Madan M. Gupta, Noriyasu Homma, Zeng-Guang Hou

IGI Global　2014/05

ISBN: 9781466660625
Frontiers in Radiation Oncology

Kei Ichiji, Noriyasu Homma, Masao Sakai, Makoto Abe, Norihiro Sugita, Makoto Yoshizawa

In-Tech　2013/07
Artificial Higher Order Neural Networks for Modeling and Simulation

Madan M. Gupta, Ivo Bukovsky, Noriyasu Homma, Ashu M. G. Solo, Zeng-Guang Hou

Information Science Reference　2012/10
Cognitive and Neural Aspects in Robotics with Applications 2011, Special Issue of Journal of Robotics

Madan M. Gupta, Ivo Bukovsky, Noriyasu Homma, Zeng-Guang Hou, Ashu M. G. Solo

Hindawi Publishing Corp　2012/04
CT Image Based Computer-Aided Lung Cancer Diagnosis

Noriyasu Homma

In-Tech　2011/04
Theory and Applications of CT Images

Noriyasu Homma

In-Tech　2011/04
Cognitive and Neural Aspects in Robotics with Applications, Special Issue of Journal of Robotics

Madan M. Gupta, Noriyasu Homma, Zeng-Guang Hou, Ivo Bukovsky

Hindawi Publishing Corp　2011/01
Artificial Higher Order Neural Networks for Computer Science and Engineering

Madan M. Gupta, Noriyasu Homma, Zeng-Guang Hou, Ashu M. G. Solo, Ivo Bukovsky

Information Science Reference　2010/02
Discoveries and Breakthroughs in Cognitive Informatics and Natural Intelligence

Bukovsky, I, Bila. J, Gupta, M, M, Hou, Z-G, Homma, N

IGI Publishing　2009/11

ISBN: 9781605669021
Pattern Recognition

Noriyasu Homma

In-Tech　2009/10
Artificial Higher-Order Neural Networks for Economics and Business

Ming Zhang ed. Madan, M. Gupta, Noriyasu Homma, Zeng-Guang Hou, Ashu M. G. Solo

Information Science Reference　2008/07

ISBN: 9781599048970
診療画像マスター・テキスト下巻

梁川, 高井, 石橋 eds, 本間経康, 酒井正夫

メジカルビュー社　2008/03
Feature Extraction, Foundations and Applications

L. Zadeh, e, al. ed. M, M. Gupta, N. Homma, Z, G. Hou

Springer　2006/07
Applied Research in Uncertainty Modeling and Analysis

A. Okine Ayyub ed, N. Homma

Springer　2005/04
Static and Dynamic Neural Networks, From Fundamentals to Advanced Theory

M. M. Gupta, L. Jin, N. Homma

IEEE Press & Wiley　2003/04
Soft Computing, Multimedia, Biomedicine, Image Processing and Financial Engineering

M.Jamshidi et, al ed, N. Homma, M, M. Gupta

TSI Press　2002/04

Show all Show first 5

Presentations 31

深層学習は乳癌画像をどう読むか Invited

本間経康

第28回日本乳癌画像研究会　2019/02/10
医療と深層学習の共進化 Invited

本間経康

第8回次世代医療開発セミナー　2019/02/07
海外企業との産学連携 Invited

本間経康

第五回東北大学スマート・エイジング学際重点研究センターシンポジウム　2018/11/02
A stable gradient-descent adaptation of higher order neural units

第12回computational intelligence研究会　2017/12/15
マーカレス追尾照射に必要な数理技術

第113回日本医学物理学会学術大会　2017/04/15
マーカレス動態追尾放射線治療のための実時間照射制御の試み

第135回日本医学放射線学会北日本地方会・第80回日本核医学会北日本地方会　2016/10/28
Development of Markerless MLC Tracking Radiation Therapy International-presentation

6th DSP Seminar　2015/11/02
マーカーレスMLC 追尾照射の開発

東北大学医学物理セミナー　2015/10/24
安全で正確な追尾照射が拓く次世代放射線治療～医工連携開発の例

アカデミアから始まる医療機器開発　2015/02/28
マーカレス動体追尾照射システムの開発

酒井正夫, 張暁勇, 市地慶, 澁澤直樹, 吉田裕輔, 阿部誠, 杉田典大, 吉澤誠, 成田雄一郎, 高井良尋

日本放射線腫瘍学会第２７回日本高精度放射線外部照射研究会　2014/02/22
マーカレス動体追尾照射のための汎用型リニアック制御システムの開発に向けて

酒井正夫, 張暁勇, 市地慶, 澁澤直樹, 吉田裕輔, 阿部誠, 杉田典大, 吉澤誠, 成田雄一郎, 高井良尋

日本放射線腫瘍学会第26回学術大会　2013/10/18
汎用型放射線治療装置を用いたマーカレス動体追尾照射技術開発の試み

JRCランチョンセミナー31　2013/04/14
Entertainment and Virtual Reality - Recent Challenge: Virtual Walking System International-presentation

R. Sugihara, N. Sugita, M. Yoshizawa

Colloquium on Brain Fitness and Smart Aging Session　2010/09/29
Prediction Methods of Unsteady Periodic Tumor Motion for Radiotherapy International-presentation

M. Sakai, K. Ichiji, N. Homma, Y. Takai, M. Yoshizawa

5th International Symposium on Medical, Bio- and Nano-Electronics　2010/02
追跡照射放射線治療のための腫瘍位置の呼吸性変動予測法

遠藤春奈, 酒井正夫, 本間経康, 高井良尋, 吉澤誠

計測自動制御学会東北支部第２４９回研究集会　2009/03/12
胸部X線CT像における非孤立性肺結節陰影の自動検出

下山聡, 本間経康, 酒井正夫, 吉澤誠, 阿部健一

動的画像処理実用化ワークショップ　2009/03/05
Multiple Model-based Reinforcement learning of a Nonholonomic Control System International-presentation

Shinpei Kato, Takakuni Goto, Noriyasu Homma, Makoto Yoshizawa

4th Int. Symp. Bio & Nano-Electronics　2009/03/05
胸部X線CT像における肺結節陰影の自動検出法の開発

本間経康, 下山聡, 石橋忠司, 吉澤誠

第７回情報シナジー研究会　2009/02/17
追跡照射放射線治療のための肺腫瘍位置の呼吸性変動予測モデル

酒井正夫, 本間経康, 高井良尋

第５１回自動制御連合講演会　2008/11/22
Fuzzy Neural Computing Systems: Theory and Applications International-presentation

IEEE ICAL　2008/08
Ｘ線ＣＴ画像における肺結節陰影の統計的特徴量に関する一考察

齋藤和久, 本間経康, 石橋忠司, 山田隆之

計測自動制御学会東北支部第２４０回研究集会　2007/12/18
ガボールフィルタを用いた肺結節陰影診断支援システム

武井一典, 本間経康, 石橋忠司, 酒井正夫, 吉澤誠, 阿部健一

計測自動制御学会東北支部第２３３回研究集会　2006/12/18
Computer Aided Diagnosis System for Pulmonary Nodules Using Gabor Filter International-presentation

Kazunori Takei, Noriyasu Homma, Tadashi Ishibashi, Masao Sakai, Makoto Yoshizawa, Kenichi Abe

2nd Int. Symp. Bio & Nano-Electronics　2006/12/09
複雑系モデルを用いた生体循環系ダイナミクスの解析

成田, 本間, 酒井, 田中, 吉澤,阿部

計測自動制御学会東北支部第226回研究集会　2005/12/09
非ホロノミック系における手動制御の学習過程

後藤,本間, 吉澤,阿部

計測自動制御学会東北支部第225回研究集会　2005/11/11
複雑系の話-脳の計算原理を求めて-

本間経康

第７５回システム制御研究会　2005/05/28
Fuzzy Neural Computing Systems: Theory and Applications International-presentation

M. M. Gupta, N. Homma, Z.-G. Hou

IEEE CCECE 2005　2005/05/01
ニューラルネットによる概念表現とその形成過程のモデル化の試み

平成１６年度第１回ニューラルネットワークフォーラム　2004/08
Neural Computing Systems: Introduction, Theory and Applications International-presentation

M. M. Gupta

4th ISUMA　2003/09
Fuzzy-Neural Computing Systems International-presentation

M. M. Gupta

IEEE ISIC　2002/10
Fuzzy-Neural Computing Systems International-presentation

M. M. Gupta

World Automation Congress　2002/06

Show all Show first 5

Industrial Property Rights 13

生体情報計測装置、生体情報計測方法、生体情報表示装置及び生体情報表示方法

吉澤誠, 杉田典大, 阿部誠, 山家智之, 本間経康, 小原一誠, 田中明, 堀畑友希

Property Type: Patent
画像処理装置、画像処理方法、及び、画像処理プログラム

本間経康, 酒井正夫, 市地慶, 澁澤直樹, 張暁勇, 阿部誠, 杉田典大, 吉澤誠, 高▼井良尋

Property Type: Patent
乳房画像病変検出システム、乳房画像病変検出方法、乳房画像病変検出プログラムおよび乳房画像病変検出プログラムを記録したコンピュータ読み取り可能な記録媒体

本間経康, 半田岳志, 石橋忠司, 川住祐介, 吉澤誠

Property Type: Patent
脈波伝播速度の測定方法、その測定方法を用いた測定システムの作動方法及び脈波伝播速度の測定システム並びに撮像装置

高森哲弥, 吉澤誠, 本間経康, 杉田典大, 阿部誠, 田中明

Property Type: Patent
信号処理装置、信号処理プログラム及び信号処理プログラムを記録したコンピュータ読み取り可能な記録媒体

本間経康, 高井良尋, 遠藤春奈, 市地慶, 酒井正夫, 吉澤誠

Property Type: Patent
Signal processing for predicting an input time series signal and application thereof to predict position of an affected area during radiotherapy

Y. Takai, N. Homma, M. Sakai

US 8,751,200 B2

Property Type: Patent
信号処理装置、信号処理方法、信号処理プログラム及び信号処理プログラムを記録したコンピュータ読み取り可能な記録媒体並びに放射線治療装置

高井良尋, 本間経康, 酒井正夫

Property Type: Patent
画像診断支援システム、画像診断支援方法および画像診断支援プログラム

本間経康, 武井一典, 石橋忠司, 酒井正夫, 吉澤誠

Property Type: Patent
乳房画像病変検出システム、乳房画像病変検出方法、乳房画像病変検出プログラムおよび乳房画像病変検出プログラムを記録したコンピュータ読み取り可能な記録媒体

本間経康, 半田岳志, 石橋忠司, 川住祐介, 吉澤誠

特許第6256954号

Property Type: Patent
脈波伝播速度の測定方法、その測定方法を用いた測定システムの作動方法及び脈波伝播速度の測定システム並びに撮像装置

高森哲弥, 吉澤誠, 本間経康, 杉田典大, 阿部誠, 田中明

特許第6072893号

Property Type: Patent
信号処理装置、信号処理プログラム及び信号処理プログラムを記録したコンピュータ読み取り可能な記録媒体

本間経康, 高井良尋, 遠藤春奈, 市地慶, 酒井正夫, 吉澤誠

特許第5797197号

Property Type: Patent
Signal-processing device and computer-readable recording medium with signal-processing program recorded thereon

N. Homma, Y. Takai, H. Endo, K. Ichiji, M. Sakai, M. Yoshizawa

US 8,837,863 B2

Property Type: Patent
信号処理装置、信号処理方法、信号処理プログラム及び信号処理プログラムを記録したコンピュータ読み取り可能な記録媒体並びに放射線治療装置

高井良尋, 本間経康, 酒井正夫

特許第5604306号

Property Type: Patent

Show all Show first 5

Research Projects 30

放射線治療における高精度照射機構の開発 Competitive

2007/10 - Present
医用画像の計算機支援診断システムの開発 Competitive

2005/10 - Present
Study on human brain functions using engineering models Competitive

System: Grant-in-Aid for Scientific Research

1999/04 - Present
Study on Recognition Mechanisms using Neural Networks Competitive

System: Grant-in-Aid for Scientific Research

1997/04 - Present
Developing a platform for ultramicro breast cancer detection using AI image analysis and liquid biopsy.

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research

Category: Grant-in-Aid for Scientific Research (B)

Institution: Tohoku University

2025/04/01 - 2028/03/31
Diagnosis of Ai (postmortem images) using AI (artificial intelligence)

FUNAYAMA Masato

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research

Category: Grant-in-Aid for Scientific Research (B)

Institution: Tohoku University

2019/04/01 - 2022/03/31

More details Close

We evaluated the performance of AI in diagnosing drowning on postmortem CT images. The sample consisted of 153 drowned bodies and 160 non-drowned bodies taken at the University's Ai Center, with a slice thickness of 1.0 mm per body and 30 mm spacing, typically 7 levels, 4 images per level, 28 images in total. The "drowning probability" for each component image was calculated, and the arithmetic mean of all images was used for the final decision (0.5 or greater is drowning). Area under the receiver operating characteristic curve (AUC) analysis was performed for each of the 10 cross-validations to evaluate performance. The results yielded an arithmetic mean of 0.95. The AI was shown to be a useful and powerful complementary test for the diagnosis of drowning on postmortem lung CT images.
Development of beyond human-level AI for medical image diagnosis systems

HOMMA Noriyasu

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research

Category: Grant-in-Aid for Challenging Research (Exploratory)

Institution: Tohoku University

2018/06/29 - 2021/03/31

More details Close

In this research, next generation medical image diagnosis systems have been developed by using a deep learning based artificial intelligence (AI) that is capable of super-performance beyond human experts. The AI-aided (AID) systems have been applied for breast cancer screening using mammography exmas, gastric cancer screening using fluoroscopic stomac exams, and drowning diagnosis using forensic imaging (autopsy imaging) of x-ray computed tomography. Experimental results showed that the AID systems were able to achieve the human experts' level performance for the tasks. Specifically, the AID system for mammographic diagnosis demonstrated superior performance beyond human experts and further more, the system made human experts' performance even better. These results clearly demonstrated the usefulness and effectiveness of the proposed AID systems in clinical use.
Development of a novel X-ray fluoroscopic motion tomography system for real time image guided tumor following radiation therapy

Homma Noriyasu

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B)

Category: Grant-in-Aid for Scientific Research (B)

Institution: Tohoku University

2017/04/01 - 2020/03/31

More details Close

In radiation therapy, intra-fractional tumor motion and deformation significantly limits the efficiency of radiation delivery and brings potential risk for organs around the tumor such as organs at risk. Conformable tumor following beam control is an ideal solution for such intra-fractional motion problem. In this study, a new real-time image processing method for tracking tumor motion and deformation has been developed. The proposed method is based on x-ray fluoroscopy to take advantage of real-time imaging the target tumor inside the body. However, the image quality of x-ray fluoroscopy is often not sufficient for tracking tumor due to superposition of bones or the other organs. To address this issue, a new stochastic partial tomographic reconstruction has been developed. Experimental results demonstrate that the proposed method outperforms the conventional methods and more importantly, they can achieve clinically useful performance.
Development of digital mammography diagnostic support system

Ishibashi Tadashi

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

2016/04/01 - 2019/03/31

More details Close

Mammographic breast cancer screening is a cost-effective way to improve survival. However, diagnostic accuracy greatly varies depending on experience of the doctor. CAD using AI technology is attracting attention as a diagnostic support method for doctors. We constructed a database of over 20,000 normal breast and cancer cases and succeeded in developing CAD using deep learning. We made a diagnostic workstation equipped with this software, and confirmed that the detection rate of calcified lesions and mass lesions was superior to existing CAD. At the same time, we developed a report management support software that can accurately measure breast tissue and calculate breast cancer risk factors from past medical history and family history, with a view to future personalized medicine.
Development of evaluation method for MR images using non-linear reconstruction processing

Machida Yoshio

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

2015/04/01 - 2018/03/31

More details Close

Recently in the MR imaging area, MR fast imaging techniques and data image reconstruction techniques using new information technology including compression sensing (CS) are being introduced. Many of these techniques involve nonlinear calculation processing, and how to evaluate the image quality of the obtained images was a challenge. In this research, we aim to evaluate the image quality of nonlinearly processed MR images by utilizing conventional linear evaluation tools such as noise power spectrum (NPS) and modulation transfer function (MTF). We have tried to establish the measurement method and evaluate some nonlinear processed images.
Three-dimensionally consolidated reality of image quality of CT images reconstructed by iterative reconstruction methods

Mori Issei, HOMMA NORIYASU, GOTO MITSUNORI

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

2015/04/01 - 2018/03/31

More details Close

Iterative reconstruction (IR) methods is said to reduce radiation dose while maintaining image quality. Numerous task-based image quality assessment, which mimics clinical tasks, support the superiority of IR methods over existing filtered backprojection (FBP) method. However, the test object is visually too distinct: it does not reflect clinically difficult/important task. Further, it ignores slice sensitivity profile (SSP). We developed methods to measure in-plane resolution and SSP using indistinct test objects buried in noise. We also measured three-dimensional noise power spectrum (NPS) accurately. Using these methods, we evaluated matched filter SNR (MFSNR) of indistinct object for images of IR and FBP. Resultantly, none of three IR methods showed better MFSNR than FBP. Consequently, IR methods do not improve the detectability of indistinct object: radiation dose cannot be reduced. The predominant task-based evaluation method necessarily overvalues IR methods.
Development of a next-generation mammography CAD system by using diagnostic logic extraction from bigdata

Homma Noriyasu, ISHIBASHI Tadashi, KAWASUMI Yusuke, YOSHIZAWA Makoto, GUPTA Madan, HOU Zeng-Guang, BUKOVSKY Ivo, ZHANG Xiaoyong

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Challenging Exploratory Research

Category: Grant-in-Aid for Challenging Exploratory Research

Institution: Tohoku University

2014/04/01 - 2017/03/31

More details Close

In breast cancer screening using mammography, due to the increase of the number of examinees, reading a lot of mammograms became burden for doctors, and it might lead to false detection and unnecessary biopsies. For reducing the work burden of doctors and improving their diagnostic accuracy, computer-aided diagnosis (CAD) systems have been developed. However, it is difficult to design the quantitative features that sufficiently represent the characteristics of abnormalities in mammograms for accurate diagnosis. To solve this problem, we have developed a new CAD system based on a deep learning technique that can extract such features through learning massive data sets. The experimental results showed that diagnostic sensitivity of a typical abnormality was about 90 % and false positive was 20 %. The results demonstrated that the proposed deep learning technique has a potential to be a key strategy for mammographic CAD systems.
Establishment of completely new motion tracking prediction model using body surface myoelectric potential change

Akimoto Hiroyoshi, Hirose Katsumi, Takai Yoshihiro, Honma Noriyasu, Ichiji Kei

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Young Scientists (B)

Category: Grant-in-Aid for Young Scientists (B)

Institution: Hirosaki University

2014/04/01 - 2017/03/31

More details Close

In order to construct a system to improve the accuracy of radiotherapy for lung malignant tumors, we conducted a study to predict lung motion by measuring electrical signals of respiratory muscles on chest surface. The movement of lung was measured with a fluoroscopic image and the signal of respiratory muscles was measured by placing the electrode of the electromyogrammeter on chest surface, and the relationship between the two was analyzed. The results showed that the electric signals of respiratory muscles contain noise, and we could not construct a system that detects the electrical signal of respiratory muscles prior to respiratory movement. It seems that the system construction required more data volume than that was considered necessary at the time of research planning.
Development of precise real-time adaptive tumor following beam control for next generation of 4-dimensional image guided radiation therapy

Homma Noriyasu, TAKAI Yoshihiro, YOSHIZAWA Makoto, NARITA Yuichiro

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B)

Category: Grant-in-Aid for Scientific Research (B)

Institution: Tohoku University

2013/04/01 - 2016/03/31

More details Close

In radiation therapy, intra-fractional tumor motion significantly limits the efficiency of radiation delivery and brings potential risk for organs around the tumor. Conformable tumor following beam control is an ideal solution for such intra-fractional motion problem. In this study, two key techniques of real-time markerless tumor tracking and motion prediction have been developed for such accurate beam control that can be implemented on radiotherapy instruments widely used in clinic. Experimental results demonstrate that the proposed techniques outperform the conventional methods and more importantly, they can achieve clinically useful performance.
Study for digital mammography soft copy standardization

Tadashi Ishibashi, HOMMA Noriyasu, MORI Naoko

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

2013/04/01 - 2016/03/31

More details Close

The data size and the image processing of digital mammography differ from each other equipment, and are not unified. Therefore, in Japanese mammographic screening, introduction of soft copy interpretation is behind. This research was done for the purpose of developing the system for which every mammogram can display optimally. The research program document was submitted to the Ethics Committee of each institution in collection, and after recognition, mammograms are anonymized and collected as uncoupling data. After, we study the histogram analysis of each digital mammogram, it asked for the optimal main concentration of an image display, the gamma coefficient, the frequency emphasis function, etc. The digital mammography viewer with this software was developed, and that clinical evaluation was performed. As compared with the original soft-copy image, our soft-copy images can be displayed on 5M monitor without picture deterioration was checked.
Regional Myocardial 3-Dimensional Rotational Motion Analysis with Cine MRI, Cardiac MDCT, and Myocardial Tagging.

Saito Haruo, HONMA NORIYASU

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

2013/04/01 - 2016/03/31

More details Close

Regional myocardial rotational motion analyzed with cine MRI by following up the track of characteristic points on the intimal or the epicardial surface of left ventricle was almost equivalent to that with myocardial tagging images by following up the track of the intersections of grid-like tags on the left ventricular myocardium. Individual differences of longitudinal regional myocardial motion made it difficult to expand 2D motion analysis analyses to 3D ones. 2D regional myocardial motion analysis of patients with pulmonary hypertension demonstrated the presence of reduced regional myocardial motion segments even in the cases with normal global left ventricular motion.
Risk Determination of Artificial Stereoscopic Vision Based on Searching for Onset Condition of 3D Sickness

Yoshizawa Makoto, HOMMA Noriyasu, SUGITA Norihiro, YAMBE Tomoyuki, TANAKA Akira

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B)

Category: Grant-in-Aid for Scientific Research (B)

Institution: Tohoku University

2012/04/01 - 2016/03/31

More details Close

Three dimensional visualization in movies, televisions and video games has been advancing rapidly. However, physiological and psychological effects of artificial stereoscopic vision on humans have not sufficiently been clarified. This study aimed at elucidation of the onset condition of so-called 3D sickness which is caused by artificial stereoscopic vision and the relationship between 3D sickness and visual fatigues. The experimental results have shown the followings: 1) Physiological indices for evaluation of 3D sickness may include psychological disturbance but it can be suppressed by adaptation. 2) It is possible that the cause of visual fatigue in stereoscopic vision can be explained using the contradiction between convergence and accommodation mechanisms. 3) Vertical disparity caused by the tilt of the head should be less than about 0.6 degree to avoid 3D sickness.
Verification of role-sharing hypothesis of circulatory control and its application to health monitoring using sensors for video games

YOSHIZAWA Makoto, HOMMA Noriyasu, SUGITA Norihiro, YAMBE Tomoyuki, TANAKA Akira

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Challenging Exploratory Research

Category: Grant-in-Aid for Challenging Exploratory Research

Institution: Tohoku University

2012/04/01 - 2015/03/31

More details Close

This study aimed at developing an estimation system of the baroreflex function, which can be used in daily life using the photoplethysmogram based on dynamics between blood pressure and heart rate. First, it was revealed that two indices, i.e., CVRR defined as the standard deviation of heart rate normalized by its mean value and μPA defined as the natural logarithm of the ratio of low frequency components to high frequency components of the pulse wave amplitude, have high discrimination ability and high reproducibility. Secondly, it was shown that a subject’s age can be estimated with these two indices with the correlation coefficient of 0.774. Finally, it was suggested that the baroreflex function can be estimated by processing the video images of a human body taken with an ordinary video camera.
Development of tumor tracking radiotherapy by using a new algorithm for markerless MV-X ray imaging

TAKAI Yoshihiro, HOMMA Noriyasu, NARITA Yuichiro

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Challenging Exploratory Research

Category: Grant-in-Aid for Challenging Exploratory Research

Institution: Hirosaki University

2012/04/01 - 2014/03/31

More details Close

We developed a new algorithm to track lung tumor motion without implanted fiducial markers by using MV X-ray fluoroscopy for a real-time image-guided radiotherapy. A core innovation of the new algorithm is to extract or "de-superimpose" a moving tumor component from the MX X-ray fluoroscopic sequence. The fluoroscopic intensity is the superimposition of intensities caused by objects passed through by the X-ray. The de-superimposition problem for more than two objects is thus ill-posed, but it can be transformed into a well-posed one by temporally accumulating constraints that must be satisfied by the de-superimposed moving tumor component and the rest of the intensity components. We clarified that a low sampling rate of the MV X-ray imaging system affects badly on the imaging quality such as blurring when the tumor moves faster. To avoid such blurring, a de-blurring technique has been developed by using tumor motion prediction. 3-D tracking method were also developed using MV and kV.
Regional Myocardial Rotational Motion Analysis with Cine MRI, Cardiac MDCT, and Myocardial Tagging.

SAITO Haruo, ISHIBASHI Tadashi, HONMA Noriyasu

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

2010 - 2012

More details Close

Regional myocardial rotational motion analyzed with cine MRI by following up the track of characteristic points on the intimal or the epicardial surface of left ventricle was almost equivalent to that with myocardial tagging images by following up the track of the intersections of grid-like tags on the left ventricular myocardium. Angle of rotation or migration length on the approximated circle of the left ventricle in each successive images should be used for the regional myocardial rotational motion analysis. Some estimate methods of appropriate contrast injection rate and acquisition start timing forcardiac MDCT could be proposed.
Development of accurate computer-aided diagnosis of pulmonary nodules in x-ray CT images by using multi-scale morphological recognition

HOMMA Noriyasu, ISHIBASHI Tadashi, GUPTA Madan

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

2007 - 2009

More details Close

In this research project, we developed a new intelligent method for computer aided detection of pulmonary nodules in x-ray CT images. An essential core of the method is to use some pieces of radiologist's professional knowledge to achieve clinically demanded high detection accuracy. The results demonstrated that the method can improve 30% of true positive rate for hardly-detectable nodules and reduce 40% of false positive rate compared to previous ones.
Study on Emergent Functional Evolution and Heuristic Knowledge Acquisition by Neural Structural Development

HOMMA Noriyasu, YOSHIZAWA Makoto, SAKAI Masao

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

2005 - 2006

More details Close

In this research project, we analyze neural spike dynamics of a double feedback neural unit (DFNU) to clarify physiological microscopic mechanism of neural spike communication and functional formation. An essential emphasis of the analysis is on use of the DFNU's simple formulations that can provide quantitative analytic results. Comparing dynamics of Hodgkin-Huxley model to that of the DFNU, it is shown that dynamics of the DFNU is also physiologically plausible under a condition. The results suggest that high-frequency firings are relatively appropriate for a neural informational carrier due to the reliability and robustness to noisy inputs. To realize such reliable spike communication, we improved the DFNU's performance by using extra noisy inputs with appropriate amplitudes. Simulation studies show that there is optimal region of the amplitude that makes the DFNU possess the noise-enhanced reliable communication ability as similar to stochastic resonance phenomena. In addition to the microscopic analysis, we further conduct experimental analysis to investigate a key mechanism of emergent functional evolution from a viewpoint of macroscopic brain sciences. A phased reinforcement learning algorithm for controlling nonholonomic systems is proposed for this purpose. The key element of the proposed algorithm is a shaping function defined on a novel position-direction space. The shaping function is started to be constructed once the goal is reached and constrains the exploration strategy. The proposed method is applied to the positioning tasks of a 2-link planer underactuated manipulator. This manipulator has one passive joint and is difficult to control. As the result, the efficiency of the proposed shaping function was confirmed in learning speed and best policy.
Clinical Application of Flash X-ray System by High Energy Discharge

OBARA Haruo, OHISHI Mikiko, ZUGUCHI Masayuki, MARUOKA Shin, HONMA Noriyasu

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

2004 - 2006

More details Close

The x-ray tube used in the conventional medical x-ray generator is a hot cathode diode using thermionic emission, while we have developed a flash x-ray generator with a cold cathode diode driven by field emission. Flash x ray equipment by the high energy discharge is composed of a DC high-voltage power supply, a high voltage condenser, a cold cathode x-ray tube, an air gap switch, a trigger pulse generator, and a turbo-molecular pump, and a cold cathode x-ray tube is composed of an anode, negative electrode, trigger electrodes. Many characteristics of a flash x-ray generator occurring under a cold cathode diode are different by materials of an electrode (an anode, the cathode), distance between the anode-cathodes, distance between cathode-trigger electrodes, four factor of a turbo-molecular pump. For examination of materials of an electrode (Ce, Yb, W), but W compared it with other, under charge voltage 90kV, the condition of a pressure of 6.65×10^<-3>Pa, x-ray intensity of 1.3 time was provided. X-ray output pulse was detected using a combination of a plastic scintillator and a photomultiplier, and the pulse width and the maximum tube current were approximately 1.0 μ sec and 40 kA, respectively, with a charging voltage of 90 kV. In order to measure the dimensions of the focal spot, we employed a pinhole camera, and the dimension varied with changes in the electrode angles and the spaces between electrodes. But the spots had size of 2.0 X 2.3mm. In high speed radiography, we obtained stop motion images of various objects including plastic bullets and water flows. In summary, the flash x-ray generator developed in the research is useful to perform high speed radiographies of children, spinal cord injury or disabled persons, because the generator produces extremely short x-ray pulses.
Development and Implementation of Control Strategy for Artificial Hearts from the Aspect of Complex Systems and Artificial Life

ABE Ken-ichi, NITTA Shin-ichi, MATSUKI Hidetoshi, YOSHIZAWA Makoto, YAMBE Tomoyuki, HOMMA Tsuneyasu

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B)

Category: Grant-in-Aid for Scientific Research (B)

2003 - 2005

More details Close

Strictly speaking, the cardiovascular system is a complex system with large-scale, multivariate, nonlinear and nonstationary characteristics. The purpose of this study was to develop control strategies for artificial hearts in consideration of the characteristics of the cardiovascular system regarded as a living system. The fruits yielded by this study are shown below. First, we proposed a nonlinear model to simulate time trajectories of stroke volume and blood pressure by introducing a feedback effect reflecting autonomic nervous information based on heart rate variability. This model can generate a chaotic heart rate variability whose characteristic differs between rest and exercise conditions. The model seems to be adequate because responses of heart rate variability similar to the above one were found in a healthy human subject. Secondly, we discussed whether the cardiac function of the natural heart can be estimated even in a complex system such as a circulatory system assisted by a ventricular assist device (VAD) using continuous-flow pump in which the VAD and the natural heart are competing against each other. The results obtained from animal experiments showed that an index Emax could be estimated to some extent in such a complex situation. It was also suggested that a dynamic model based on differential equation should be considered for analysis rather than a static model even if a continuous-flow VAD is used because beating components caused by the natural heart cannot be ignored. Thirdly, we proposed a new method for estimating outflow of a continuous-flow VAD using an ARX model. It was ascertained that the accuracy of the proposed method remained on a practical level for two weeks in an animal experiment. Finally, we developed a transcutaneous energy and signal transmission system by using a new special type of coil with a good decoupled characteristic between energy and information. An in vitro experiment indicated that the system is useful for applying to clinical situations because of its robustness against positional deviation.
拡張Hebb則による神経回路網の構造的および機能的な自己組織化に関する研究

本間経康

Offer Organization: 日本学術振興会

System: 科学研究費助成事業若手研究(B)

Category: 若手研究(B)

Institution: 東北大学

2003 - 2004

More details Close

本研究課題では,生物脳のように変化する外部環境との相互作用を介して,構造的および機能的に柔軟に自己組織化する神経回路網モデルの構築を目標としているが,本年度は,はじめに,15年度に構築した構造改変に対応させた拡張Hebb則のプロトタイプを改良し,生理学的にもより妥当な結合構造の時空間改変を統合したモデルを構築した.つぎに,シミュレーションにより,改良モデルの能力を検証し,その理論的考察を行った. 1.プロトタイプ拡張Hebb則の改良ニューロンは主にシナプス結合を介して入力情報を受け取るが,シナプス結合を全く持たない新生ニューロンは入力がないため発火せず,したがって,Hebb則による学習が成立せずに新たな結合も形成されないという一種のジレンマがあった.従来のモデルでは,ランダムな初期結合構造を仮定するなど,不自然な解決法が用いられているが,15年度に提案したプロトタイプでも,ランダムな結合形成により便宜的に解決しており,その生理学的妥当性には疑問が残るなど,根本的な問題解決には至っていなかった.これに対し,本年度改良した学習則では,生理学的にもより妥当なニューロンの自発発火を構造改変のための信号として定式化することで,このジレンマを解決した. 2.シミュレーションによる能力検証と理論的考察改良したモデルを計算機上にインプリメントし,パターン認識問題に適用した結果,生理学的により妥当なシナプス結合を持たない新生ニューロンを用いても,認識に必要な対象の概念形成過程の幾つかの簡単な側面の再現が可能であるなど,その性能が確認された.また,理論的にも先に提案した概念(記憶)形成能力をより少ない計算コストで実現できることが証明された.
Development and Application of Flash X-ray System by High Energy Discharge

OBARA Haruo, MARUOKA Shin, ZUGUCHI Masayoshi, OHISHI Mikio, HONMA Noriyasu

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

2001 - 2003

More details Close

The, x-ray tube used in the conventional medical x-ray generator is a hot cathode diode using thermionic emission, while we have developed a flash x-ray generator with a cold cathode diode driven by field emission. The flash x rays are produced by the high energy vacuum discharge, and the generator consists of a DC high-voltage power supply, a high voltage condenser, a cold cathode x-ray tube, an air gap switch, a trigger pulse generator, and a vacuum pump. The x-ray tube is composed of an anode (target), cathode, and trigger electrodes. In this field emission tube, the anode and cathode electrodes can be changed, and the space between the anode and cathode electrodes is controlled in order to obtain optimum x-ray intensity. In addition, the space between the cathode and trigger electrodes should be decreased as much as possible to decrease the trigger voltage. In the tube, conical anode (1200) and cathode (500) electrodes are employed, and their elements are tungsten and carbon (graphite), respectively. The vacuum pump evacuates air from the tube with a pressure of 6.65 x 10^<-3> Pa, and the pulse width and the maximum tube current were approximately 300 ns and 40 kA, respectively, with a charging voltage of 80 kV. In order to measure the dimensions of the focal spot, we employed a pinhole camera, and the dimension varied with changes in the electrode angles and the spaces between electrodes. In high speed radiography, we obtained stop motion images of various objects including plastic bullets and water flows. In summary, the flash x-ray generator developed in the research is useful to perform high speed radiographies of children or disabled persons, because the generator produces extremely short x-ray pulses.
カオス的な時変ダイナミクスを利用した迅速な動的認識機構に関する研究

本間経康

Offer Organization: 日本学術振興会

System: 科学研究費助成事業

Category: 若手研究(B)

Institution: 東北大学

2001 - 2002

More details Close

本研究課題では,生物のような動的認識機構による柔軟で迅速な認識能力をもつモデルの構築を目標としているが,本年度は,昨年度開発した入力に応じてシステムパラメータを変化させる新しい時変モデルの性能を実験的,理論的に詳しく考察し,その性能向上を図った.とくに,ネットワーク構造の改変ルールと学習ルールのより自然な統合アルゴリズムを開発した. 1.新モデルの性能考察と改良: はじめに,昨年度開発した新モデルの追加学習性能を実験的,理論的に詳しく考察し,誤差逆伝播ネットワークに対する優位性を証明した.また,カオスダイナミクスと認識能力の関連を考察するために,リカレント型ネットワークのダイナミクスの統計的な特徴を明らかにし,新モデルの動的認識機構への拡張可能性について検討した.新モデルでは生物的な統一的ローカルルールで学習・適応させることを目指したが,昨年度のモデルは教師あり学習を用いたため,グローバル情報が必要であり,入力が未知か否かの判定にIF-THENではなく,放射基底関数(RBF)やファジィ推論を用いても,ローカル情報のみでは十分な性能が得られない問題点が明らかとなった.この問題を解決するため,つぎの教師なし学習則を導入したモデルを開発した. 2.Hebb則を用いた改良モデルの開発: 教師なし学習法の代表であり,生理学的にもその根拠が解明されつつあるHebb則を導入した改良モデルをパソコン上にインプリメントし,種々の計算機実験を通してその基礎的能力について検討した.とくに,従来固定構造下でのパラメータ改変に用いられてきたHebb則を構造改変にも適用できるように拡張した.これにより,ローカル情報のみを用いた統一的ルールによる自己組織的な学習・適応が可能となった.
動的認識ネットワークの励起アトラクタ解析と動きの検出・認識に関する研究

本間経康

Offer Organization: 日本学術振興会

System: 科学研究費助成事業

Category: 奨励研究(A)

Institution: 東北大学

2000 - 2000
Self-control of Memory Structure of Reinforcement Learning in Hidden Markov Environments

ABE Kenichi, HONMA Noriyasu

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research

Category: Grant-in-Aid for Scientific Research (C)

Institution: Tohoku University

1999 - 2000

More details Close

Recent research on reinforcement learning (RL) algorithms has concentrated on partially observable Markov decision problems (POMDPs). A possible solution to POMDPs is to use history information to estimate state. Q values must be updated in the form reflecting past history of observation/action pairs. In this study, we developed two methods of reinforcement learning, which can solve certain types of POMDPs. The results are summarized as follows : (1) As a result of last Grant-in-Aid for Scientific Research (C)(2), we proposed Labeling Q-learning (LQ-learning), which has a new memory architecture of handling past history. In this study, we established a general framework of the LQ-learning. Various algorithms in this framework were devised, and we gave comparative study between these through simulation. The above LQ-learning, however, has the drawback that we must predefine the labeling mechanism. To overcome this drawback, we further devised a SOM (self-organizing feature map) approach of labeling, in which past history of observation/action pairs are partitioned into classes. The SOM has one-dimensional structure and the output nodes of the SOM produce labels. (2) We proposed a new type of hierarchical RL, called Switching Q-learning (SQ-learning). The basic idea of SQ-learning is that non-Markovian tasks can be automatically decomposed into subtasks solvable by memoryless policies, without any other information leading to "good" subgoals. To deal with such decomposition, SQ-learning employs ordered sequences of Q-modules in which each module discovers a local control policy. SQ-learning uses a hierarchical system of learning automata for switching module. The simulation results demonstrate that SQ-learning has the ability to quickly learn optimal or near-optimal policies without huge computational burden. It is a future work to build a unified view by which LQ-learning and SQ-learning can be dealt with systematically.
A fundamental study for a newly devised DSA system consisted of cooled CCD camera.

ZUGUCHI Masayuki, SUZUKI Shogo, OOISHI Mikio, SAITOU Haruo, OGURA Takahide, HONMA Noriyasu, CHIDA Kouichi

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research

Category: Grant-in-Aid for Scientific Research (C)

Institution: TOHOKU UNIVERSITY

1997 - 1999

More details Close

An investigation of a newly devised DSA system consisted of a cooled CCD camera has been made from 1997 to 2000. Since the cooled CCD camera has markedly high contrast resolution, we have considered that the new system should be competent for IV-DSA. The DSA system had been constructed at first, which consisted of X-ray generator, optical unit and digital processing unit. Then the capability of the system for imaging bad been tested. According to the result of the practice examination using artificial blood vessel, we judged the contrast resolution of the image detected by our new system was better than that by the conventional DSA. Finally an animal experiment had been performed using rabbits, and the branches of the thoracic and abdominal aorta had been demonstrated clearly by the contrast medium administrated from their earlobe vein. Then we considered that this system might be available enough for IV-DSA for human beings.

Show all Show first 5

Social Activities 2

Varian Medical Systems to Exhibit TrueBeam™ System for Image-Guided Radiotherapy and Radiosurgery at ITEM Exhibition in Yokohama, Japan

2013/04/11 -

More details Close

Tumor Tracking Symposium Varian is also sponsoring a luncheon seminar on the topic of real-time tumor tracking without the use of implanted fiducial markers, as part of the 72nd Annual Meeting of the Japan Radiological Society (JRS), which meets during the ITEM exhibition event. Noriyasu Homma, Ph.D., associate professor at the Tohoku University Cyberscience Center, will talk about his efforts to develop a system that could augment the imaging capabilities of a linear accelerator to enable real-time tumor tracking during certain treatments. The International Technical Exhibition of Medical Imaging 2013 will be held from April 12-14 at the Pacifico Yokohama Exhibition Hall. This comprehensive academic exhibition, managed by the Japan Medical Imaging and Radiological Systems Industries Association (JIRA), has been held in conjunction with the Annual Meeting of the Japan Radiological Society (JRS), the Annual Scientific Congress of the Japanese Society of Radiological Technology (JSRT), and the Scientific Congress of the Japan Society of Medical Physics (JSMP), since 1988.
小田原高校進路講演会（出張講義）

2012/12/11 -

More details Close

世界の将来を支える研究」～時代に対応する東北大学の研究室～

Other 19

次世代デジタルマンモグラフィ総合ビューア・レポート支援システムの開発

More details Close

次世代デジタルマンモグラフィ総合ビューア・レポート支援システムの開発
残像効果モデルによる対象運動認識の正則化と医療画像計測への応用

More details Close

残像効果モデルによる対象運動認識の正則化と医療画像計測への応用に関する研究
次世代デジタルマンモグラフィ総合ビューアシステムの開発

More details Close

デジタルマンモグラフィ診断支援システムに関する研究
生体情報センサ

More details Close

秘匿事項
低侵襲腫瘍位置計測と変動予測による汎用型超高精度リアルタイム追尾照射技術の開発

More details Close

放射線治療における安全かつ高精度な照射技術に関する研究
生体情報センサ

More details Close

秘匿事項
生体情報センサ

More details Close

秘匿事項
スマート・エイジングのためのバーチャルリアリティを用いたエンタテイメントシステム開発

More details Close

サイバースマートエイジング機器の開発
Research on Computational Intelligence

More details Close

計算知能に関する研究
知的ロボットに関する研究

More details Close

知的ロボットに関する研究
医師の診断法に倣った胸部X線ＣＴ画像における肺結節診断支援システムの開発

More details Close

医師の診断法に倣った胸部X線ＣＴ画像における肺結節診断支援システムの開発
健康状態把握のための生体反応指標の検出技術とデータベース化

More details Close

健康状態把握のための生体反応指標の検出技術とデータベース化
胸部Ｘ線ＣＴ画像における肺結節陰影の計算機診断支援システムの開発とデータベースの構築

More details Close

胸部Ｘ線ＣＴ画像における肺結節陰影の計算機診断支援システムの開発とデータベースの構築
運動制御獲得過程の脳機能のモデル化に関する研究

More details Close

運動制御獲得過程の脳機能のモデル化に関する研究
放射線治療装置における体動推定システムの開発

More details Close

放射線治療装置における体動推定システムの開発
医用画像診断用計算機支援システムの開発

More details Close

医用画像診断用計算機支援システムの開発
脳が作る感覚世界-生体にセンサーはない-
主観的概念形成および認識のための自己組織化神経回路網モデル

More details Close

主観的概念形成および認識のための自己組織化神経回路網モデル
Research on Intelligent Systems

More details Close

知的システムに関する研究

Show all Show first 5