Details of the Researcher

PHOTO

Zeng Yuwen
Section
Advanced Institute of So-Go-Chi (Convergence Knowledge) Informatics
Job title
Assistant Professor
e-Rad No.
80994813

Research History 5

  • 2025/04 - Present
    Tohoku University

  • 2023/10 - Present
    Tohoku University　Graduate School of Medicine

  • 2022/05 - 2023/03
    東北大学大学院医工学研究科　知能システム医工学分野　リサーチ・アシスタント（RA）

  • 2022/07 - 2022/09
    アイシン・ソフトウェア株式会社　盛岡開発センター　研究開発インター

  • 2022/01 - 2022/03
    東北大学大学院医工学研究科　知能システム医工学分野　リサーチ・アシスタント（RA）

Education 5

  • Tohoku University

    2021/04 - 2023/09

  • Tohoku University　Graduate School of Biomedical Engineering　Department of Biomedical Engineering

    2020/10 - 2023/09

  • University of South Bohemia in Ceske Budejovice

    2023/04 - 2023/07

  • Beijing Institute of Technology　Graduate school of biomedical engineering　Biomedical engineering

    2017/09 - 2020/08

  • Beijing Institute of Technology　Faculty of Science　Biomedical Engineering

    2013/09 - 2017/07

Committee Memberships 1

  • 計測自動制御学会 システム・情報部門 学術講演会（SSI2025）　現地実行委員（会場担当）

    2024/11 - 2025/11

Professional Memberships 1

  • IEEE

    2023/12 - Present

Research Interests 4

  • 人工知能

  • 説明可能なAI

  • コンピュータ支援診断

  • 医用画像診断システム

Research Areas 2

  • Informatics / Intelligent informatics /

  • Life sciences / Medical systems /

Awards 4

  1. 医学部奨学賞 銀賞

    2023/12　東北大学大学院医学系研究科・医学部　深層学習による死後CT画像を用いた死因鑑別 支援システムに関する研究

  2. 若手奨励研究

    2023/01　東北大学 創生応用医学研究センター AI応用医学部門

  3. IEEE Sendai Section, Student Award, The Best Paper Prize

    2021/12　Proceedings of the 2021 Tohoku-Section Joint Convention of Institutes of Electrical Information Engineers　An Interpretable Deep Learning Method for Forensic Diagnosis of Drowning

  4. SICE 2021 Annual Conference Young Author’s Award

    2021/10　Deep Learning-Based Interpretable Computer- Aided Diagnosis of Drowning for Forensic Radiology

Papers 17

  1. Transformer-based Deep Learning Models with Shape Guidance for Predicting Breast Cancer in Mammography Images

    Kengo Takahashi, Yuwen Zeng, Zhang Zhang, Kei Ichiji, Takuma Usuzaki, Ryusei Inamori, Haoyang Liu, Noriyasu Homma

    Journal of Imaging Informatics in Medicine　2025/12/19

    DOI： 10.1007/s10278-025-01773-3 　

  2. Modality-Guided Edge Fusion and Semantic Enhancement for Multi-Modal Brain Tumor Segmentation Peer-reviewed

    Wentong Zhou, Yuwen Zeng, Xiaoyong Zhang, Ruili Li, Arata Nagai, Masayuki Kanamori, Hidenori Endo, Kuniyasu Niizuma, Noriyasu Homma

    2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)　6668-6675　2025/12/15

    Publisher: IEEE

    DOI： 10.1109/bibm66473.2025.11356218 　

  3. Bilateral Information-Guided Diagnosis of Breast Masses in Mammography Using Vision Transformer Peer-reviewed

    Tianyu Zeng, Yuwen Zeng, Zhang Zhang, Xiaoyong Zhang, Kei Ichiji, Shuo-Yan Chou, Ivo Bukovsky, Jan Vrba, Noriyasu Homma

    IEEE Journal of Biomedical and Health Informatics　1-13　2025/11

    Publisher: Institute of Electrical and Electronics Engineers (IEEE)

    DOI： 10.1109/jbhi.2025.3626200 　

    ISSN： 2168-2194

    eISSN： 2168-2208

  4. Deep learning-based dual-energy subtraction synthesis from single-energy kV x-ray fluoroscopy for markerless tumor tracking. International-journal

    Jiaoyang Wang, Kei Ichiji, Yuwen Zeng, Xiaoyong Zhang, Yoshihiro Takai, Noriyasu Homma

    Medical & biological engineering & computing　2025/08/27

    DOI： 10.1007/s11517-025-03432-9 　

    More details Close

    Markerless tumor tracking in x-ray fluoroscopic images is an important technique for achieving precise dose delivery for moving lung tumors during radiation therapy. However, accurate tumor tracking is challenging due to the poor visibility of the target tumor overlapped by other organs such as rib bones. Dual-energy (DE) x-ray fluoroscopy can enhance tracking accuracy with improved tumor visibility by suppressing bones. However, DE x-ray imaging requires special hardware, limiting its clinical use. This study presents a deep learning-based DE subtraction (DES) synthesis method to avoid hardware limitations and enhance tracking accuracy. The proposed method employs a residual U-Net model trained on a simulated DES dataset from a digital phantom to synthesize DES from single-energy (SE) fluoroscopy. Experimental results using a digital phantom showed quantitative evaluation results of synthesis quality. Also, experimental results using clinical SE fluoroscopic images of ten lung cancer patients showed improved tumor tracking accuracy using synthesized DES images, reducing errors from 1.80 to 1.68 mm on average. The tracking success rate within a 25% movement range increased from 50.2% (SE) to 54.9% (DES). These findings indicate the feasibility of deep learning-based DES synthesis for markerless tumor tracking, offering a potential alternative to hardware-dependent DE imaging.

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

    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.

  6. Adaptive region-oriented masked vision retentive network for predicting macrovascular invasion in hepatocellular carcinoma Peer-reviewed

    Kengo Takahashi, Ryusei Inamori, Kei Ichiji, Zhang Zhang, Zeng Yuwen, Noriyasu Homma

    Medical Imaging 2025: Computer-Aided Diagnosis　65-65　2025/04/04

    Publisher: SPIE

    DOI： 10.1117/12.3045625 　

  7. MGG-Net: A Multi-modal Feature Extraction and Global-Aware Feature Graph-Based Deep Learning Network for MGMT Status Classification in Glioma Peer-reviewed

    Haoyang Liu, Yuwen Zeng, Xiaoyong Zhang, Wentong Zhou, Arata Nagai, Masayuki Kanamori, Hidenori Endo, Noriyasu Homma

    International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025)　2025

    DOI： 10.1007/978-3-032-04947-6_34 　

  8. Vision Transformer-Based Breast Mass Diagnosis in Mammography Using Bilateral Information Peer-reviewed

    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 　

  9. Integration of Classification and Segmentation for Computer-Aided Diagnosis System of Drowning Peer-reviewed

    Y. Zeng, X. Zhang, M. Funayama, A. Usui, K, Ichiji, N. Homma

    IEEE World Congress on Computational Intelligence (IEEE WCCI 2024)　2024/07

  10. Inconsistency between Human Observation and Deep Learning Models: Assessing Validity of Postmortem Computed Tomography Diagnosis of Drowning Peer-reviewed

    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 　

  11. A 2.5D Deep Learning-Based Method for Drowning Diagnosis Using Post-Mortem Computed Tomography Peer-reviewed

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

    IEEE Journal of Biomedical and Health Informatics　2023/02

    DOI： 10.1109/JBHI.2022.3225416 　

  12. Deep Learning-Based Diagnosis of Fatal Hypothermia Using Post-Mortem Computed Tomography Peer-reviewed

    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

  13. Deep Learning-Based Interpretable Computer-Aided Diagnosis of Drowning for Forensic Radiology Peer-reviewed

    Y. Zeng, X. Zhang, Y. Kawasumi, A. Usui, K. Ichiji, M, Funayama, N. Homma

    2021 60th Annual Conference of the Society of Instrument and Control Engineers of Japan,　2021/11

  14. Automatic Diagnosis Based on Spatial Information Fusion Feature for Intracranial Aneurysm Peer-reviewed

    Yuwen Zeng, Xinke Liu, Nan Xiao, Youxiang Li, Yuhua Jiang, Junqiang Feng, Shuxiang Guo

    IEEE Transactions on Medical Imaging　39　(5)　1448-1458　2020/05

    Publisher: Institute of Electrical and Electronics Engineers (IEEE)

    DOI： 10.1109/tmi.2019.2951439 　

    ISSN： 0278-0062

    eISSN： 1558-254X

  15. Real-Time Facial Expression Recognition Using Deep Convolutional Neural Network Peer-reviewed

    Y. Zeng, N. Xiao, K. Wang, H. Yuan

    IEEE International Conference on Mechatronics and Automation　2019/07

  16. A CNN-based prototype method of unstructured surgical state perception and navigation for an endovascular surgery robot Peer-reviewed

    Yan Zhao, Shuxiang Guo, Yuxin Wang, Jinxin Cui, Youchun Ma, Yuwen Zeng, Xinke Liu, Yuhua Jiang, Youxinag Li, Liwei Shi, Nan Xiao

    Medical & Biological Engineering & Computing　57　(9)　1875-1887　2019/06/20

    Publisher: Springer Science and Business Media LLC

    DOI： 10.1007/s11517-019-02002-0 　

    ISSN： 0140-0118

    eISSN： 1741-0444

  17. Catheter Tracking Based on Multi-scale Filter and Direction-oriented Method Peer-reviewed

    Y. Zeng, N. Xiao, K. Wang, H. Yuan

    IEEE International Conference on Mechatronics and Automation　2018/07

Show all ︎Show first 5

Misc. 9

  1. LLMを用いた放射線読影レポートの平易化における語彙頻度に基づく可読性評価の検討 Peer-reviewed

    総合大会電子情報通信学会総合大会　2026/03

  2. MRIモダリティを用いた2D／3D深層学習モデルによる脳腫瘍セグメンテーション性能の比較評価

    荒川侑輝, Yuwen Zeng, 張曉勇, 周雯童, 杉田典大, 本間経康

    計測自動制御学会東北支部 第357回研究集会　2026/03

  3. Data-Driven Investigation of Brain Mechanisms Underlying Self-Initiated Attention Shifts

    Yuwen Zeng, Dengzhe Hou, Yongsong Huang, Chia-huei Tseng, Shioiri Satoshi

    ヒューマン情報処理研究会（HIP）　2025/12

  4. 死後画像における深層学習を用いた溺死分類と異常所見のマルチラベル分類

    石川遥基, Yuwen Zeng, 張 暁勇, 臼井 章仁, 市地 慶, 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（SSI2025）　2025/11

  5. High-Resolution Abnormal Mammogram Generation from Normal Samples Using Density-Aware Dual-Mask CycleGAN for Imbalanced Dataset Augmentation

    計測自動制御学会 システム・情報部門 学術講演会（SSI2025）　2025/11

  6. Adversarial domain adaptation for breast cancer diagnosis in multi-center datasets

    Xinyang He, Yuwen Zeng, Zhang Zhang, Kei Ichiji, Xiaoyong Zhang, Noriyasu Homma

    計測自動制御学会 システム・情報部門 学術講演会（SSI2025）　2025/11

  7. Zero-shot and Few-shot Prompting for Radiology Report Simplification

    Mikami Mariko, Yuwen Zeng, Xiaoyang Zhang, Kei Ichiji, Noriyasu Homma

    2025年度電気関係学会 東北支部連合大会　2025/09

  8. データの施設多様性が乳房腫瘤検出モデルの性能に与える影響の分析 Peer-reviewed

    菅野真梨子, 張彰, Yuwen Zeng, 市地慶, 張暁勇, 本間経康

    第53回 日本放射線技術学会秋季学術大会　2025/09

  9. 乳房X線画像正常例で訓練した拡散モデル による異常検知に関する研究

    吉住壱成, 三上真理子, 類家朝陽, Yuwen Zeng, 張暁勇, 市地慶, 本間経康

    計測自動制御学会東北支部 第351回研究集会　2025/03

Show all ︎Show first 5

Presentations 10

  1. Adaptive region-oriented masked vision retentive network for predicting macrovascular invasion in hepatocellular carcinoma

    Kengo Takahashi, Ryusei Inamori, Kei Ichiji, Zhang Zhang, Zeng Yuwen, Noriyasu Homma

    Medical Imaging 2025: Computer-Aided Diagnosis　2025/04/04

  2. MGG-Net: A Multi-modal Feature Extraction and Global-Aware Feature Graph-Based Deep Learning Network for MGMT Status Classification in Glioma

    Haoyang Liu, Yuwen Zeng, Xiaoyong Zhang, Wentong Zhou, Arata Nagai, Masayuki Kanamori, Hidenori Endo, Noriyasu Homma

    International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025)　2025

  3. 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)　2024/08/26

  4. Integration of Classification and Segmentation for Computer-Aided Diagnosis System of Drowning

    Y. Zeng, X. Zhang, M. Funayama, A. Usui, K, Ichiji, N. Homma

    IEEE World Congress on Computational Intelligence (IEEE WCCI 2024)　2024/07

  5. Deep Learning-Based Explainable Computer-Aided Diagnosis System for Drowning

    Yuwen Zeng

    SCCH Explainable AI for Biomedical Workshop in Austria　2023/06

  6. Deep Learning-Based Explainable Computer-Aided Diagnosis System for Drowning

    Yuwen Zeng

    International Symposium on Human Welfare Engineering for Smart-Aging　2023/04

  7. Deep Learning-Based Interpretable Computer-Aided Diagnosis of Drowning for Forensic Radiology

    Y. Zeng, X. Zhang, Y. Kawasumi, A. Usui, K. Ichiji, M, Funayama, N. Homma

    2021 60th Annual Conference of the Society of Instrument and Control Engineers of Japan,　2021/11

  8. Learning-Based Interpretable Computer-Aided Diagnosis of Drowning for Forensic Radiology

    Yuwen Zeng

    東北大学MIRAI2.0 プロジェクト　2021/07

  9. Real-Time Facial Expression Recognition Using Deep Convolutional Neural Network

    Y. Zeng, N. Xiao, K. Wang, H. Yuan

    IEEE International Conference on Mechatronics and Automation　2019/07

  10. Catheter Tracking Based on Multi-scale Filter and Direction-oriented Method

    Y. Zeng, N. Xiao, K. Wang, H. Yuan

    IEEE International Conference on Mechatronics and Automation　2018/07

Show all Show first 5

Research Projects 2

  1. Heterogeneity-Aware, Cross-Domain Feature-Aligned Genetic Diagnosis System for Malignant Gliomas

    Yuwen Zeng

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業

    Category: 若手研究

    Institution: 東北大学

    2025/04 - 2028/03

  2. マルチモーダルAIによる術前MRIを用いた脳腫瘍遺伝子診断

    Offer Organization: 国立研究開発法人 日本医療研究開発機構AMED

    System: 橋渡し研究プログラム

    Category: 異分野融合型研究開発推進支援事業 (令和6年度Health Tech Colloquiumコンペ)

    Institution: 東北大学

    2024/10 - 2025/03