Abstract Early regression—the regression in tumor volume during the initial phase of radiotherapy (approximately 2 weeks after treatment initiation)—is a common occurrence during radiotherapy. This rapid radiation-induced tumor regression may alter target coordinates, necessitating adaptive radiotherapy (ART). We developed a deep learning-based radiomics (DLR) approach to predict early head and neck tumor regression and thereby facilitate ART. Primary gross tumor volume (GTVp) was monitored in 96 patients and nodal GTV (GTVn) in 79 patients during treatment. All patients underwent two computed tomography (CT) scans: one before the start of radiotherapy for initial planning and one during radiotherapy for boost planning. Patients were assigned to regression and nonregression groups according to their median tumor regression rate (ΔGTV/treatment day from initial to boost CT scan). We input a GTV image into the convolutional neural network model, which was pretrained using natural image datasets, via transfer learning. The deep features were extracted from the last fully connected layer. To clarify the prognostic power of the deep features, machine learning models were trained. The models then predicted the regression and nonregression of GTVp and GTVn and evaluated the predictive performance by 0.632 + bootstrap area under the curve (AUC). Predictive performance for GTVp regression was highest using the InceptionResNetv2 model (mean AUC = 0.75) and that for GTVn was highest using NASNetLarge (mean AUC = 0.73). Both models outperformed the handcrafted radiomics features (mean AUC = 0.63 for GTVp and 0.61 for GTVn) or clinical factors (0.64 and 0.67, respectively). DLR may facilitate ART for improved radiation side-effects and target coverage.

Radiotherapy for esophageal cancer entails high-dose irradiation of the myocardium owing to its close anatomical proximity to the esophagus. This study aimed to evaluate the dosimetric impact of functional avoidance planning for the myocardium with volumetric-modulated arc therapy (VMAT) in patients with esophageal cancer and determine the feasibility of functional planning. Ten patients with early stage esophageal cancer were included in this study. The prescribed dose was 60 Gy administered in 30 fractions. An experienced physician contoured the left ventricle (LV) of the myocardium. For each patient, an anatomical plan (non-LV-sparing plan) and a functional plan (LV-sparing plan) were created using the VMAT. In the functional plan, the mean percentage of LV volume receiving a dose of ≥ 30 and ≥ 40 Gy was 6.0% ± 6.7% and 2.4% ± 2.7%, respectively, whereas in the anatomical plan, they were 11.7% ± 13.1% and 4.9% ± 6.5%, respectively. There were no significant differences with respect to the dose to the hottest 1 cm3 of the planning target volume (PTV) and the minimum dose of the gross tumor volume and the dosimetric parameters of other normal tissues between the anatomical and functional plans. We compared the anatomical and functional plans of patients with esophageal cancer undergoing VMAT. Our results demonstrated that the functional plan reduced the dose to the LV with no significant differences in the organs at risk and PTV, indicating that avoidance planning can be safely performed when administering VMAT in patients with esophageal cancer.

Abstract Large language models (LLMs) have recently gained attention for their potential. However, concerns remain regarding their reliability due to limitations such as hallucinations and insufficient domain-specific knowledge. Retrieval-augmented generation (RAG) has emerged as a promising approach, enabling LLMs to reference external knowledge sources and generate accurate outputs. We aimed to clarify the potential of RAG-enhanced LLMs with Japanese input in the field of radiotherapy. This was assessed by evaluating performance on three certification examinations in Japan: the Japanese Medical Physicist Examination, the Japanese Board Examination for Radiologists, and the Japanese Board Examination for Radiation Oncologists. In this study, we constructed a RAG system named Rad-Hub, consisting of a Japanese Radiotherapy Knowledge Database (JRKD) and a retrieval framework built on Microsoft Azure. The JRKD was populated with 32 Japanese radiotherapy textbooks and clinical guidelines. We assessed its utility by inputting all multiple-choice questions from the three examinations into ChatGPT-4o, both with and without Rad-Hub, and recording the answers. They were then compared with reference answers determined by experienced medical physicists and radiation oncologists. Rad-Hub improved accuracy across all examinations. Accuracy increased from 77.0% ± 2.6% to 84.6% ± 1.5% in the Medical Physicist examination, from 74.9% ± 2.0% to 82.1% ± 1.1% in the Radiologist examination, and from 55.6% ± 4.4% to 71.7% ± 4.5% in the Radiation Oncologist examination. Performance gains ranged from 7.2% to 16.1%. These findings highlight the potential of RAG-enhanced LLMs, particularly ChatGPT-4o with Rad-Hub, for integration into radiotherapy applications, such as educational and clinical decision assistance.

Abstract Background Automatic contouring can reduce the time required for delineating organs at risk (OARs) in brachytherapy planning and minimize interobserver variability. Purpose This study aimed to develop and evaluate a deep learning‐based automatic contouring model for OARs in three‐dimensional image‐guided brachytherapy (3D‐IGBT) for cervical and endometrial cancer, including cases with interstitial needles. Methods The dataset comprised 100 patients (140 cases) with cervical or endometrial cancer who underwent 3D‐IGBT. Interstitial needles were used in 74 cases. The nnU‐Net model was trained (80 patients, 80 cases) and tested (20 patients, 60 cases). The OARs considered were the bladder, small bowel, rectum, and sigmoid. Ground truth (GT) contours were manually delineated by radiation oncologists and medical physicists. Evaluation included measuring inference time and assessing geometric agreement using dice similarity coefficient (DSC), surface DSC (sDSC), Hausdorff distance (HD), and 95th percentile HD (95HD). These metrics were also calculated for a combined structure of the rectum and sigmoid (Rec+Sig). Furthermore, D _2cc was calculated based on both the GT and predicted contours using the clinical dose distribution, and the difference between them (ΔD _2cc ) was evaluated. Differences in accuracy with or without interstitial needles were compared using Welch's t ‐test (significance level: p  < 0.05). Results Mean processing time was 30.3 s per case. Mean DSC values for the bladder, small bowel, rectum, sigmoid, and Rec+Sig were 0.96, 0.79, 0.83, 0.76, and 0.87, respectively. Mean 95HD values (mm) were 4.01, 18.8, 13.6, 25.5, and 17.8, respectively; ΔD _2cc values (Gy) were 0.17, 0.53, 0.014, −0.073, and −0.045, respectively. No significant accuracy differences related to interstitial needles were observed for any of the OARs. Conclusions The proposed deep learning model demonstrated potential for application in cases involving interstitial needles and may contribute to improving the efficiency of the treatment planning workflow.

This study aimed to evaluate the clinical validity of a dose-mimicking automated planning for volumetric-modulated arc therapy (VMAT) in patients with stage III non-small cell lung cancer (NSCLC), through direct comparison with a commercial dose volume histogram (DVH)-predicted system. We retrospectively analyzed volumetric-modulated arc therapy plans from 75 patients with stage III NSCLC treated at our institution (60 for training, 15 for testing). The dose-mimicking method was implemented using RatoGuide, and the DVH-predicted method was implemented using RapidPlan. The RatoGuide 3D dose-prediction model was trained on the 60 training cases. For each test case, a predicted dose distribution was generated and converted to a deliverable plan (RGDose) in Eclipse using vendor-provided objective functions. A RapidPlan model trained and generated deliverable plans (RPDose) for the same dataset. The clinical plan dose distribution (CliDose) was the reference. We compared dose distributions and DVH parameters among RGDose, RPDose and CliDose. Mean absolute errors (MAEs) relative to CliDose were 0.83 ± 0.66% (targets) and 2.06 ± 3.14% (organs at risk [OARs]) for RGDose, and 0.88 ± 0.66% (targets) and 2.49 ± 3.63% (OARs) for RPDose. There were no significant differences in OAR DVH parameters between RGDose and CliDose. In contrast, compared to CliDose, RPDose showed a significant reduction in the Esophagus D1cc and a significant increase in the Lungs V5Gy. The dose-mimicking method more faithfully reproduced the original clinical plans than the conventional DVH-predicted system, suggesting that dose-mimicking method can capture complex inter-OAR trade-offs and consistently reflect planner intent.

Abstract Large language models (LLMs), such as ChatGPT and Grok, have rapidly advanced in natural language understanding and are increasingly being applied to specialized fields, including medicine. In this study, we evaluated the domain-specific knowledge of LLMs in radiotherapy by assessing their performance on three certification examinations in Japan: the Japanese Medical Physicist Examination, the Japanese Board Examination for Radiologists and the Japanese Board Examination for Radiation Oncologists. We assessed five LLMs—ChatGPT-5, ChatGPT-5 Pro, Grok 4, Grok 4 heavy and Gemini 2.5 Pro—by inputting all multiple-choice questions from these exams into each model and recording their responses. The AI-generated answers were compared with reference answers determined by experienced medical physicists and radiation oncologists. The results demonstrated average accuracies of 84.7 ± 2.0% (ChatGPT-5), 94.7 ± 2.1% (ChatGPT-5 Pro), 78.4 ± 1.2% (Grok 4), 81.6 ± 2.2% (Grok 4 heavy) and 88.9 ± 1.2% (Gemini 2.5 Pro). All models achieved over 75% accuracy, with ChatGPT-5 Pro consistently outperforming others, attaining an average accuracy exceeding 90% across all examinations. These findings highlight the strong potential of advanced LLMs, particularly ChatGPT-5 Pro, for future integration into radiotherapy-related applications such as automated contouring and treatment planning support.

Cone-beam computed tomography-based online adaptive radiotherapy (CBCT-based online ART) is currently used in clinical practice; however, deep learning-based segmentation of CBCT images remains challenging. Previous studies generated CBCT datasets for segmentation by adding contours outside clinical practice or synthesizing tissue contrast-enhanced diagnostic images paired with CBCT images. This study aimed to improve CBCT segmentation by matching the treatment planning CT (tpCT) image quality to CBCT images without altering the tpCT image or its contours. A deep-learning-based CBCT segmentation model was trained for the male pelvis using only the tpCT dataset. To bridge the quality gap between tpCT and routine CBCT images, an artificial pseudo-CBCT dataset was generated using Gaussian noise and Fourier domain adaptation (FDA) for 80 tpCT datasets (the hybrid FDA method). A five-fold cross-validation approach was used for model training. For comparison, atlas-based segmentation was performed with a registered tpCT dataset. The Dice similarity coefficient (DSC) assessed contour quality between the model-predicted and reference manual contours. The average DSC values for the clinical target volume, bladder, and rectum using the hybrid FDA method were 0.71 ± 0.08, 0.84 ± 0.08, and 0.78 ± 0.06, respectively. Conversely, the values for the model using plain tpCT were 0.40 ± 0.12, 0.17 ± 0.21, and 0.18 ± 0.14, and for the atlas-based model were 0.66 ± 0.13, 0.59 ± 0.16, and 0.66 ± 0.11, respectively. The segmentation model using the hybrid FDA method demonstrated significantly higher accuracy than models trained on plain tpCT datasets and those using atlas-based segmentation.

BACKGROUND: Stereotactic radiotherapy (SRT) for kidney cancer, particularly when tumours are situated near critical organs-at-risk (OARs), presents significant challenges in achieving optimal dose delivery. MR-guided online adaptive radiotherapy (MRgoART) offers a promising solution by allowing real-time anatomical modification and plan reoptimisation. However, the ideal strategy for prescription dose selection and reoptimisation remains unclear. METHODS: This single-centre planning study evaluated kidney tumours located within 1 cm of gastrointestinal OARs. In Step 1, prescription doses for MRgoART were compared: the target dose (26 Gy) versus the planned dose (adjusted during pre-treatment planning to satisfy OAR constraints). In Step 2, two optimisation strategies were assessed: (1) covering 99% of the planning target volume (PTV) with the prescription dose (99%_xGy_Plan) and (2) delivering the full target dose with acceptable partial PTV coverage accepting dose heterogeneity (26Gy_x%_Plan), both respecting OAR constraints. Dose-volume parameters and blinded expert preferences were evaluated. RESULTS: Of 22 patients assessed, 14 patients with 18 tumours met the inclusion criteria. Among these, 36 MRgoART plans for 12 tumours were analysed in Step 1. Reoptimisation using the target dose resulted in significantly higher mean tumour doses, improved dose gradients, and PTV coverage metrics compared to reoptimisation based on the planned dose. In Step 2, 54 plans were assessed. Although the 26Gy_x%_Plan demonstrated superior mean tumour and PTV dose, it exhibited lower conformity. Radiation oncologists preferred the 26Gy_x%_Plan in 48% of cases, following 26% deemed almost equal, indicating its clinical advantage. CONCLUSION: For kidney tumours adjacent to gastrointestinal OARs, MRgoART planning should favour reoptimisation based on the target dose. A high-dose strategy with partial PTV coverage (26Gy_x%_Plan) was generally preferred by radiation oncologists, balancing therapeutic effectiveness with OAR protection.

PURPOSE: This study aimed to investigate changes in target coverage using magnetic resonance-guided online adaptive radiotherapy (MRgoART) for kidney tumors and to evaluate the suitable timing of treatment. MATERIALS AND METHODS: Among patients treated with 3-fraction MRgoART for kidney cancer, 18 tumors located within 1 cm of the gastrointestinal tract were selected. Stereotactic radiosurgery planning with a prescription dose of 26 Gy was performed using pretreatment simulation and three MRgoART timings with an adapt-to-shape method. The best MRgoART plan was defined as the plan achieving the highest percentage of planning target volume (PTV) coverage of 26 Gy. In clinical scenario simulation, MRgoART plans were evaluated in the order of actual treatment. Waiting for the next timing was done when the PTV coverage of 26 Gy did not achieve 95%-99% or did not increase by 5% or more compared to the pretreatment plan. RESULTS: The median percentages of PTV receiving 26 Gy in pretreatment and the first, second, and third MRgoART were 82% (range, 19%), 63% (range, 7% to 99%), 88% (range, 31% to 99%), and 95% (range, 3% to 99%), respectively. Comparing pretreatment simulation plans with the best MRgoART plans showed a significant difference (p = 0.025). In the clinical scenario simulation, 16 of the 18 planning series, including nine plans with 95%-99% PTV coverage of 26 Gy and seven plans with increased PTV coverage by 5% or more, would be irradiated at a good timing. CONCLUSION: MRgoART revealed dose coverage differences at each MRgoART timing. Waiting for optimal irradiation timing could be an option in case of suboptimal timing.

Lung function assessment is essential for determining the optimal treatment strategy for radiation therapy in patients with lung tumors. This study aimed to develop radiomics and dosiomics approaches to estimate pulmonary function test (PFT) results in post-stereotactic body radiation therapy (SBRT). Sixty-four patients with lung tumors who underwent SBRT were included. Models were created to estimate the PFT results at 0-6 months (Cohort 1) and 6-24 months (Cohort 2) after SBRT. Radiomics and dosiomics features were extracted from the computed tomography (CT) images and dose distributions, respectively. To estimate the PFT results, Models A (dose-volume histogram [DVH] + radiomics features) and B (DVH + radiomics + dosiomics features) were created. In the PFT results, the forced expiratory volume in one second (FEV1) and forced vital capacity (FVC) were estimated using each model, and the ratio of FEV1 to FVC (FEV1/FVC) was calculated. The Pearson's correlation coefficient (Pearson r) and area under the curve (AUC) for FEV1/FVC (< 70%) were calculated. The models were evaluated by comparing them with the conventional calculation formulae (Conventional). The Pearson r (FEV1/FVC) values were 0.30, 0.64, and 0.69 for Conventional and Models A and B (Cohort 2), respectively, and the AUC (FEV1/FVC < 70%) values were 0.63, 0.80, and 0.78, respectively. This study demonstrates the possibility of estimating lung function after SBRT using radiomics and dosiomics features based on planning CT images and dose distributions.

This study aimed to evaluate the performance for answering the Japanese medical physicist examination and providing the benchmark of knowledge about medical physics in language-generative AI with large language model. We used questions from Japan's 2018, 2019, 2020, 2021 and 2022 medical physicist board examinations, which covered various question types, including multiple-choice questions, and mainly focused on general medicine and medical physics. ChatGPT-3.5 and ChatGPT-4.0 (OpenAI) were used. We compared the AI-based answers with the correct ones. The average accuracy rates were 42.2 ± 2.5% (ChatGPT-3.5) and 72.7 ± 2.6% (ChatGPT-4), showing that ChatGPT-4 was more accurate than ChatGPT-3.5 [all categories (except for radiation-related laws and recommendations/medical ethics): p value < 0.05]. Even with the ChatGPT model with higher accuracy, the accuracy rates were less than 60% in two categories; radiation metrology (55.6%), and radiation-related laws and recommendations/medical ethics (40.0%). These data provide the benchmark for knowledge about medical physics in ChatGPT and can be utilized as basic data for the development of various medical physics tools using ChatGPT (e.g., radiation therapy support tools with Japanese input).

BACKGROUND AND OBJECTIVE: In the field of radiation therapy, image-guided radiotherapy (IGRT) technology has been gradually improving and highly accurate radiation treatment has been possible. Research on IGRT using 1.5 Tesla magnetic resonance imaging (MRI) began in 1999, and a radiation therapy device called 1.5 Tesla magnetic resonance linear accelerator (MR-Linac), which combines a linear accelerator with 1.5 Tesla MRI, was developed in Europe. The aim of this review is to present an overview of 1.5 Tesla MR-Linac with a review of the literature and our experience. METHODS: Reports related to 1.5 Tesla MR-Linac were searched for in PubMed and are discussed in relation to our experience. KEY CONTENT AND FINDINGS: The 1.5 Tesla MR-Linac enables IGRT using 1.5 Tesla MRI, further enhancing the precision of radiation therapy. Position verification by cone-beam computed tomography (CBCT) is performed in many institutions, but soft tissue contrast is often unclear in CBCT images of the abdomen and mediastinal organs. Since the 1.5 Tesla MR-Linac allows position verification using MRI, position verification can be performed using clear MRI even in regions where CBCT is unclear. With the 1.5 Tesla MR-Linac, it is possible to perform online adaptive radiotherapy (ART) using 1.5 Tesla MRI. Online ART is a method in which images are acquired while the patient is on the treatment table. The method is based on the current condition of the organs in the body on that day and an optimal treatment field is recreated. Additionally, it allows monitoring of tumor motion using cine images obtained by 1.5 Tesla MRI during the delivery of X-ray radiation. A previous report showed that patients with prostate cancer who received radiotherapy by MR-Linac had fewer side effects than those in patients who received conventional CBCT radiation therapy. CONCLUSIONS: The 1.5 Tesla MR-Linac obtained CE-mark certification in Europe in August 2018 and it has been used for clinical treatment. In Japan, clinical treatment using this device started in 2021. By using 1.5 Tesla MR-Linac, patients can be provided with higher precision radiotherapy. In this review, we provide an overview of 1.5 Tesla MR-Linac.

This study aims to evaluate the dosimetric accuracy of a deep learning (DL)-based deliverable volumetric arc radiation therapy (VMAT) plan generated using DL-based automated planning assistant system (AIVOT, prototype version) for patients with prostate cancer. The VMAT data (cliDose) of 68 patients with prostate cancer treated with VMAT treatment (70-74 Gy/28-37 fr) at our hospital were used (n = 55 for training and n = 13 for testing). First, a HD-U-net-based 3D dose prediction model implemented in AIVOT was customized using the VMAT data. Thus, a predictive VMAT plan (preDose) comprising AIVOT that predicted the 3D doses was generated. Second, deliverable VMAT plans (deliDose) were created using AIVOT, the radiation treatment planning system Eclipse (version 15.6) and its vender-supplied objective functions. Finally, we compared these two estimated DL-based VMAT treatment plans-i.e. preDose and deliDose-with cliDose. The average absolute dose difference of all DVH parameters for the target tissue between cliDose and deliDose across all patients was 1.32 ± 1.35% (range: 0.04-6.21%), while that for all the organs at risks was 2.08 ± 2.79% (range: 0.00-15.4%). The deliDose was superior to the cliDose in all DVH parameters for bladder and rectum. The blinded plan scoring of deliDose and cliDose was 4.54 ± 0.50 and 5.0 ± 0.0, respectively (All plans scored ≥4 points, P = 0.03.) This study demonstrated that DL-based deliverable plan for prostate cancer achieved the clinically acceptable level. Thus, the AIVOT software exhibited a potential for automated planning with no intervention for patients with prostate cancer.

BACKGROUND: Megavoltage computed tomography (MVCT) images acquired during each radiotherapy session may be useful for delta radiomics. However, no studies have examined whether the MVCT-based radiomics has prognostic power. Therefore, the purpose of this study was to examine the prognostic power of the MVCT-based radiomics for head and neck squamous cell carcinoma (HNSCC) patients. METHODS: 100 HNSCC patients who received definitive radiotherapy were analyzed and divided into two groups: training (n = 70) and test (n = 30) sets. MVCT images obtained using TomoTherapy for the first fraction of radiotherapy and planning kilovoltage CT (kVCT) images obtained using Aquilion LB CT scanner were analyzed. Primary gross tumor volume (GTV) was propagated from kVCT to MVCT images using rigid registration, and 107 radiomic features were extracted from the GTV in MVCT and kVCT images. Least absolute shrinkage and selection operator (LASSO) Cox regression model was used to examine the association between overall survival (OS) and rad score calculated for each patient by weighting the feature value through the coefficient when features were selected. Then, the predictive values of MVCT-based and kVCT-based rad score and patient-, treatment-, and tumor-specific factors were evaluated. RESULTS: C-indices of the rad score for MVCT- and kVCT-based radiomics were 0.667 and 0.685, respectively. The C-indices of 6 clinical factors were 0.538-0.622. The 3-year OS was significantly different between high- and low-risk groups according to the MVCT-based rad score (50% vs. 83%; p < 0.01). CONCLUSIONS: Our results suggested that MVCT-based radiomics had stronger prognostic power than any single clinical factor and was a useful prognostic factor when predicting OS in HNSCC patients.

Abstract This study aimed to develop and validate a collapsed cone convolution for magnetic resonance-guided radiotherapy (CCCMR). The 3D energy deposition kernels (EDKs) were generated in water in a 1.5-T transverse magnetic field. The CCCMR corrects the inhomogeneity in simulation geometry by referring to the EDKs according to the mass density between the interaction and energy deposition points in addition to density scaling. Dose distributions in a water phantom and in slab phantoms with inserted inhomogeneities were calculated using the Monte Carlo (MC) and CCCMR. The percentage depth dose (PDD) and off-axis ratio (OAR) were compared, and the gamma passing rate (3%/2 mm) was evaluated. The CCCMR simulated asymmetric dose distributions in the simulation phantoms, especially the water phantom, and all PDD and OAR profiles were in good agreement with the findings of the MC. The gamma passing rates were &amp;gt;99% for each field size and for the entire region. In the inhomogeneity phantoms, although the CCCMR underestimated dose in the low mass density regions, it could reconstruct dose changes at mass density boundaries. The gamma passing rate for the entire region was &amp;gt;95% for the field size of 2 × 2 cm2, but it was 68.9–86.7% for the field sizes of ≥5 × 5 cm2. Conclusively, in water, the CCCMR can obtain dose distributions comparable to those with the MC. Although the dose differences between them were mainly in inhomogeneity regions, the possibility of the effective use of the CCCMR in small field sizes was demonstrated.

PURPOSE: To study the dosimetry impact of deformable image registration (DIR) using radiophotoluminescent glass dosimeter (RPLD) and custom developed phantom with various inserts. METHODS: The phantom was developed to facilitate simultaneous evaluation of geometric and dosimetric accuracy of DIR. Four computed tomography (CT) images of the phantom were acquired with four different configurations. Four volumetric modulated arc therapy (VMAT) plans were computed for different phantom. Two different patterns were applied to combination of four phantom configurations. RPLD dose measurement was combined between corresponding two phantom configurations. DIR-based dose accumulation was calculated between corresponding two CT images with two commercial DIR software and various DIR parameter settings, and an open source software. Accumulated dose calculated using DIR was then compared with measured dose using RPLD. RESULTS: The mean ± standard deviation (SD) of dose difference was 2.71 ± 0.23% (range, 2.22%-3.01%) for tumor-proxy and 3.74 ± 0.79% (range, 1.56%-4.83%) for rectum-proxy. The mean ± SD of target registration error (TRE) was 1.66 ± 1.36 mm (range, 0.03-4.43 mm) for tumor-proxy and 6.87 ± 5.49 mm (range, 0.54-17.47 mm) for rectum-proxy. These results suggested that DIR accuracy had wide range among DIR parameter setting. CONCLUSIONS: The dose difference observed in our study was 3% for tumor-proxy and within 5% for rectum-proxy. The custom developed physical phantom with inserts showed potential for accurate evaluation of DIR-based dose accumulation. The prospect of simultaneous evaluation of geometric and dosimetric DIR accuracy in a single phantom may be useful for validation of DIR for clinical use.

The purpose of this study was to compare acute gastrointestinal (GI) toxicities in patients who underwent 3-dimensional conformal radiotherapy (3DCRT) and intensity-modulated radiotherapy (IMRT) in chemoradiotherapy (CRT) with S-1 including prophylactic regions for pancreatic cancer. We also investigated the predictive factor of acute GI toxicities in dose volume histogram (DVH) parameters. Patients who received CRT with S-1 for pancreatic cancer between January 2014 and March 2021 were included. Radiotherapy (RT) with a total dose of 50-54 Gy was delivered. We examined the differences in the frequencies of acute GI toxicity of grade 2 or higher and DVH parameters of the stomach (ST) and duodenum (DU) between the 3DCRT group and the IMRT group. The RT-related predictive factors of acute GI toxicities were investigated by univariate and multivariate analyses. There were 25 patients in the 3DCRT group and 31 patients in the IMRT group. The frequencies of acute GI toxicity of G2 or higher were 36% in the 3DCRT group and 9.7% in the IMRT group (p = 0.035). ST V50 was the most predictive factor (p = 0.001), and the incidences of acute GI toxicity of G2 or higher in ST V50 ≥ 4.1 cc and < 4.1cc were 43.7% and 7.7%, respectively. ST V40 was also a significant predictive factor of acute GI toxicity (p = 0.002). IMRT could reduce acute GI toxicities in CRT with S-1 including prophylactic regions for pancreatic cancer. Acute GI toxicities may be affected by moderate to high doses to the ST.

PURPOSE: We aimed to assess radiomics approaches for estimating three pulmonary function test (PFT) results (forced expiratory volume in one second [FEV1], forced vital capacity [FVC], and the ratio of FEV1 to FVC [FEV1/FVC]) using data extracted from chest computed tomography (CT) images. METHODS: This retrospective study included 85 lung cancer patients (mean age, 75 years ±8; 69 men) who underwent stereotactic body radiotherapy between 2012 and 2020. Their pretreatment chest breath-hold CT and PFT data before radiotherapy were obtained. A total of 107 radiomics features (Shape: 14, Intensity: 18, Texture: 75) were extracted using two methods: extraction of the lung tissue (<-250 HU) (APPROACH 1), and extraction of small blood vessels and lung tissue (APPROACH 2). The PFT results were estimated using the least absolute shrinkage and selection operator regression. Pearson's correlation coefficients (r) were determined for all PFT results, and the area under the curve (AUC) was calculated for FEV1/FVC (<70 %). Finally, we compared our approaches with the conventional formula (Conventional). RESULTS: For the estimated FEV1/FVC, the Pearson's r were 0.21 (P =.06), 0.69 (P <.01), and 0.73 (P <.01) for Conventional, APPROACH 1, and APPROACH 2, respectively; the AUCs for FEV1/FVC (<70 %) were 0.67 (95 % confidence interval [CI]: 0.55, 0.79), 0.82 (CI: 0.72, 0.91; P =.047) and 0.86 (CI: 0.78, 0.94; P =.01), respectively. CONCLUSIONS: The radiomics approach performed better than the conventional equation and may be useful for assessing lung function based on CT images.

This study evaluated accuracy of deformable image registration (DIR) with twelve parameter settings for thoracic images. We used peak-inhale and peak-exhale images for ten patients provided by DIR-lab. We used a prototype version of iCView software (ITEM Corporation) with DIR to perform intensity, structure, and hybrid-based DIR with the twelve parameter settings. DIR accuracy was evaluated by a target registration error (TRE) using 300 bronchial bifurcations and the Dice similarity coefficient (DSC) of the lungs. For twelve parameter settings, TRE ranged from 2.83 mm to 5.27 mm, whereas DSC ranged from 0.96 to 0.98. These results demonstrated that DIR accuracy differed among parameter settings and show that appropriate parameter settings are required for clinical practice.

Radiation therapy (RT) is one of the definitive treatments for early-stage nasal vestibular carcinoma and has similar local control rates to resection surgery. There are various methods, including external beam RT and brachytherapy. This report describes a case who showed local control for more than 5 years after brachytherapy alone using Au-198 grains for nasal vestibular carcinoma. A 68-year-old Japanese man complained of swelling and pain in his left nasal cavity. He was diagnosed with squamous cell carcinoma (SCC) (cT1N0M0, stage I). An elevated mass of 8 mm in long diameter was found inside the left nasal cavity. Since the patient selected brachytherapy, nine Au-198 grains 185 mBq were permanently injected percutaneously under local anesthesia, and 85 Gy was prescribed. Grade three dermatitis was observed as an acute adverse event. After 2 years, mild telangiectasia of the left nasal skin and epilation of nasal hair in the left nasal cavity was regarded as late adverse events. The patient continues to keep a complete response for 5 years. For small nasal vestibular SCC, brachytherapy with Au-198 grains might be a good option.

The purpose of this study is to introduce differential dose–volume histogram (dDVH) features into machine learning for radiation pneumonitis (RP) prediction and to demonstrate the predictive performance of the developed model based on integrated cumulative dose–volume histogram (cDVH) and dDVH features. Materials and methods: cDVH and dDVH features were calculated for 153 patients treated for non-small-cell lung cancer with 60–66 Gy and dose bins ranging from 2 to 8 Gy in 2 Gy increments. RP prediction models were developed with the least absolute shrinkage and selection operator (LASSO) through fivefold cross-validation. Results: Among the 152 patients in the patient cohort, 41 presented ≥grade 2 RP. The interdependencies between cDVH features evaluated by Spearman’s correlation were significantly resolved by the inclusion of dDVH features. The average area under curve for the RP prediction model using cDVH and dDVH model was 0.73, which was higher than the average area under curve using cDVH model for 0.62 with statistically significance (p &lt; 0.01). An analysis using the entire set of regression coefficients determined by LASSO demonstrated that dDVH features represented four of the top five frequently selected features in the model fitting, regardless of dose bin. Conclusions: We successfully developed an RP prediction model that integrated cDVH and dDVH features. The best RP prediction model was achieved using dDVH (dose bin = 4 Gy) features in the machine learning process.

Abstract In this article, we highlight the fundamental importance of the simultaneous use of dose-volume histogram (DVH) and dose-function histogram (DFH) features based on functional images calculated from 4-dimensional computed tomography (4D-CT) and deformable image registration (DIR) in developing a multivariate radiation pneumonitis (RP) prediction model. The patient characteristics, DVH features and DFH features were calculated from functional images by Hounsfield unit (HU) and Jacobian metrics, for an RP grade ≥ 2 multivariate prediction models were computed from 85 non-small cell lung cancer patients. The prediction model is developed using machine learning via a kernel-based support vector machine (SVM) machine. In the patient cohort, 21 of the 85 patients (24.7%) presented with RP grade ≥ 2. The median area under curve (AUC) was 0.58 for the generated 50 prediction models with patient clinical features and DVH features. When HU metric and Jacobian metric DFH features were added, the AUC improved to 0.73 and 0.68, respectively. We conclude that predictive RP models that incorporate DFH features were successfully developed via kernel-based SVM. These results demonstrate that effectiveness of the simultaneous use of DVH features and DFH features calculated from 4D-CT and DIR on functional image-guided radiotherapy.

PURPOSE: To evaluate the accuracy of electron transport in the magnetic field of Electron Gamma Shower version 5 (EGS5) by using the special Fano cavity test. METHODS: To simulate electron transport in the magnetic field, the trajectory of the electron was reconstructed with a short step length to restrict fractional energy loss, and the maximum user step length (mxustep) was set at 0.01 cm or 0.001 cm. For the special Fano cavity test, three-layer slab Fano test geometry was used, and uniform and isotropic per unit mass mono-energetic electrons with 0.01, 0.1, 1.0, and 10 MeV were permitted from the central axis of geometry in 0.35 T and 1.5 T. Furthermore, the magnetic field strength was scaled based on the mass density of the material. The relative difference between the calculated dose to gap and the theoretical value was evaluated. Furthermore, the special Fano cavity test was also performed using EGSnrc with the electron-enhanced electric and magnetic field macros under the same conditions, and the results were compared with those of EGS5. RESULTS: Deviations in 0.35 T were within 0.3% regardless of the parameter settings. In 1.5 T, stable results within 0.3% were obtained using 0.001 cm as the mxustep, except for one at 10 MeV. Further, the accuracy of EGSnrc was within 0.2%, except for 10 MeV for a 0.2-cm gap in 1.5 T. CONCLUSIONS: EGS5 with the appropriate parameter settings enable electron transport in magnetic fields similar with the accuracy of EGSnrc.

Abstract Background Radiomics is a new technology to noninvasively predict survival prognosis with quantitative features extracted from medical images. Most radiomics-based prognostic studies of non-small-cell lung cancer (NSCLC) patients have used mixed datasets of different subgroups. Therefore, we investigated the radiomics-based survival prediction of NSCLC patients by focusing on subgroups with identical characteristics. Methods A total of 304 NSCLC (Stages I–IV) patients treated with radiotherapy in our hospital were used. We extracted 107 radiomic features (i.e., 14 shape features, 18 first-order statistical features, and 75 texture features) from the gross tumor volume drawn on the free breathing planning computed tomography image. Three feature selection methods [i.e., test–retest and multiple segmentation (FS1), Pearson's correlation analysis (FS2), and a method that combined FS1 and FS2 (FS3)] were used to clarify how they affect survival prediction performance. Subgroup analysis for each histological subtype and each T stage applied the best selection method for the analysis of All data. We used a least absolute shrinkage and selection operator Cox regression model for all analyses and evaluated prognostic performance using the concordance-index (C-index) and the Kaplan–Meier method. For subgroup analysis, fivefold cross-validation was applied to ensure model reliability. Results In the analysis of All data, the C-index for the test dataset is 0.62 (FS1), 0.63 (FS2), and 0.62 (FS3). The subgroup analysis indicated that the prediction model based on specific histological subtypes and T stages had a higher C-index for the test dataset than that based on All data (All data, 0.64 vs. SCC_all, 060; ADC_all, 0.69; T1, 0.68; T2, 0.65; T3, 0.66; T4, 0.70). In addition, the prediction models unified for each T stage in histological subtype showed a different trend in the C-index for the test dataset between ADC-related and SCC-related models (ADC_T1–ADC_T4, 0.72–0.83; SCC_T1–SCC_T4, 0.58–0.71). Conclusions Our results showed that feature selection methods moderately affected the survival prediction performance. In addition, prediction models based on specific subgroups may improve the prediction performance. These results may prove useful for determining the optimal radiomics-based predication model.

Abstract We compared predictive performance between dose volume histogram (DVH) parameter addition and deformable image registration (DIR) addition for gastrointestinal (GI) toxicity in cervical cancer patients. A total of 59 patients receiving brachytherapy and external beam radiotherapy were analyzed retrospectively. The accumulative dose was calculated by three methods: conventional DVH parameter addition, full DIR addition and partial DIR addition. ${D}_{2{cm}^3}$, ${D}_{1{cm}^3}$ and ${D}_{0.1{cm}^3}$ (minimum doses to the most exposed 2 cm3, 1cm3 and 0.1 cm3 of tissue, respectively) of the rectum and sigmoid were calculated by each method. V50, V60 and V70 Gy (volume irradiated over 50, 60 and 70 Gy, respectively) were calculated in full DIR addition. The DVH parameters were compared between toxicity (≥grade1) and non-toxicity groups. The area under the curve (AUC) of the receiver operating characteristic (ROC) curves were compared to evaluate the predictive performance of each method. The differences between toxicity and non-toxicity groups in ${D}_{2{cm}^3}$ were 0.2, 5.7 and 3.1 Gy for the DVH parameter addition, full DIR addition and partial DIR addition, respectively. The AUCs of ${D}_{2{cm}^3}$ were 0.51, 0.67 and 0.57 for DVH parameter addition, full DIR addition and partial DIR addition, respectively. In full DIR addition, the difference in dose between toxicity and non-toxicity was the largest and AUC was the highest. AUCs of V50, V60 and V70 Gy were 0.51, 0.63 and 0.62, respectively, and V60 and V70 were high values close to the value of ${D}_{2{cm}^3}$ of the full DIR addition. Our results suggested that the full DIR addition may have the potential to predict toxicity more accurately than the conventional DVH parameter addition, and that it could be more effective to accumulate to all pelvic irradiation by DIR.

PURPOSE: Radiomics is a new technique that enables noninvasive prognostic prediction by extracting features from medical images. Homology is a concept used in many branches of algebra and topology that can quantify the contact degree. In the present study, we developed homology-based radiomic features to predict the prognosis of non-small-cell lung cancer (NSCLC) patients and then evaluated the accuracy of this prediction method. METHODS: Four datasets were used: two to provide training and test data and two for the selection of robust radiomic features. All the datasets were downloaded from The Cancer Imaging Archive (TCIA). In two-dimensional cases, the Betti numbers consist of two values: b0 (zero-dimensional Betti number), which is the number of isolated components, and b1 (one-dimensional Betti number), which is the number of one-dimensional or "circular" holes. For homology-based evaluation, computed tomography (CT) images must be converted to binarized images in which each pixel has two possible values: 0 or 1. All CT slices of the gross tumor volume were used for calculating the homology histogram. First, by changing the threshold of the CT value (range: -150 to 300 HU) for all its slices, we developed homology-based histograms for b0 , b1 , and b1 /b0 using binarized images. All histograms were then summed, and the summed histogram was normalized by the number of slices. 144 homology-based radiomic features were defined from the histogram. To compare the standard radiomic features, 107 radiomic features were calculated using the standard radiomics technique. To clarify the prognostic power, the relationship between the values of the homology-based radiomic features and overall survival was evaluated using LASSO Cox regression model and the Kaplan-Meier method. The retained features with nonzero coefficients calculated by the LASSO Cox regression model were used for fitting the regression model. Moreover, these features were then integrated into a radiomics signature. An individualized rad score was calculated from a linear combination of the selected features, which were weighted by their respective coefficients. RESULTS: When the patients in the training and test datasets were stratified into high-risk and low-risk groups according to the rad scores, the overall survival of the groups was significantly different. The C-index values for the homology-based features (rad score), standard features (rad score), and tumor size were 0.625, 0.603, and 0.607, respectively, for the training datasets and 0.689, 0.668, and 0.667 for the test datasets. This result showed that homology-based radiomic features had slightly higher prediction power than the standard radiomic features. CONCLUSIONS: Prediction performance using homology-based radiomic features had a comparable or slightly higher prediction power than standard radiomic features. These findings suggest that homology-based radiomic features may have great potential for improving the prognostic prediction accuracy of CT-based radiomics. In this result, it is noteworthy that there are some limitations.