Physics and Imaging in Radiation Oncology最新文献

{"title":"The value of post radiotherapy prostate specific antigen dynamics for prostate cancer risk stratification models","authors":"Jane Shortall ,&nbsp;Eliana Vasquez Osorio ,&nbsp;Andrew Green ,&nbsp;Kimberley Reeves ,&nbsp;David Wong ,&nbsp;Tanuj Puri ,&nbsp;Peter Hoskin ,&nbsp;Ananya Choudhury ,&nbsp;Marcel van Herk ,&nbsp;Alan McWilliam","doi":"10.1016/j.phro.2025.100787","DOIUrl":"10.1016/j.phro.2025.100787","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Risk-stratification at diagnosis of prostate cancer does not always predict risk of biochemical recurrence (BCR). Fully utilizing post-radiotherapy follow-up Prostate Specific Antigen (PSA) data could offer earlier and higher prognostic value than pre-treatment risk-stratification.</div><div>We investigate whether PSA dynamics in the first three-years of follow-up can re-stratify risk of treatment failure after radical radiotherapy, allowing for targeted intervention.</div></div><div><h3>Materials and methods</h3><div>Retrospective analysis of repeat follow-up PSA measurements from men with mixed-risk prostate cancer treated in two separate radical radiotherapy techniques (n = 446, 2005–2007). PSA trajectories were modelled between zero and three-years follow-up using Gaussian Process regression. Models were sampled and clustered using hierarchical clustering to define characteristic post-radiotherapy PSA trajectories.</div><div>Kaplan-Meier analysis compared dichotomising by pre-treatment risk-group and characteristic PSA trajectory. Cox proportional-hazard models with and without follow-up PSA information compared using Akaike Information Criterion (AIC).</div></div><div><h3>Results</h3><div>PSA trajectories were characterized as stable, steady-rise, and unstable. Kaplan-Meier analysis showed that pre-treatment risk-group was not prognostic of BCR (p &gt; 0.05), however characteristic PSA trajectory was (p &lt; 0.001). PSA trajectory improved multivariable model performance when added to baseline prognostic variables. Unstable PSA had highest BCR.</div><div>Results were validated across two cohorts and sensitivity analysis, suggesting results were robust. However, analysis excluded patients with BCR within three-years follow-up due to lack of data.</div></div><div><h3>Conclusion</h3><div>PSA dynamics within the first three-years of post-radiotherapy follow-up for prostate cancer were more prognostic of BCR than pre-treatment risk-groups, suggesting PSA dynamics could be used to re-stratify BCR risk during early follow-up.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"34 ","pages":"Article 100787"},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144134589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spot-optimization reduces beam delivery time in liver breath hold intensity modulated proton therapy","authors":"Michael Butkus ,&nbsp;Daniel Bastawros ,&nbsp;Yunze Yang ,&nbsp;Roberto Cassetta ,&nbsp;Roni Hytonen ,&nbsp;Robert Kaderka","doi":"10.1016/j.phro.2025.100763","DOIUrl":"10.1016/j.phro.2025.100763","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Liver irradiations with intensity-modulated proton therapy (IMPT) often require motion mitigation techniques that prolong treatment. A prototype spot-optimization algorithm was tested to evaluate whether plan delivery time could be reduced while preserving quality.</div></div><div><h3>Methods and materials</h3><div>Fifteen patients previously treated with liver IMPT using breath-hold were re-planned with nominal treatment planning system (TPS) settings and using a prototype spot-optimization algorithm in which combinations of minimum Monitor Unit (MU) and layer-spacing settings were tested: 1MU/1MeV, 3MU/3MeV, 1MU/5MeV, 5MU/3MeV. Spot-optimized and nominals plans were compared using standard dose-volume histogram (DVH) metrics for targets and organs-at-risk. A Wilcoxon signed-rank test was applied (p &lt; 0.05). Delivery time for all plans were measured by creating and delivering IMPT quality assurance (QA) plans. Gamma analyses were performed on all plans to test deliverability. Plans were considered deliverable if &gt;90 % of points passed a gamma criterion of 3 %/3mm.</div></div><div><h3>Results</h3><div>Minimal DVH differences were observed between nominal and spot-optimized plans. For the 3MU/3MeV setting, no DVH metrics were significantly different. Median and interquartile range (IQR) delivery times for these plans were 40 % (38 %<strong>–</strong>44 %) faster than nominal plans. 5MU/3MeV plans had median (IQR) delivery times 59 % (52 %<strong>–</strong>61 %) faster than nominal plans but had a small but significant increase in Liver_Eff D_mean with a median (IQR) difference of 0.2 Gy(RBE) (0.0<strong>–</strong>0.4 Gy(RBE)). QA analysis showed all spot-optimized plans were deliverable.</div></div><div><h3>Conclusions</h3><div>The spot-optimization algorithm produced clinically deliverable plans with negligible DVH differences to nominal plans and reduced delivery time of liver IMPT by over one-third.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"34 ","pages":"Article 100763"},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cost-effectiveness of personalized policies for implementing organ-at-risk sparing adaptive radiation therapy in head and neck cancer","authors":"Seyedmohammadhossein Hosseinian ,&nbsp;Daniel Suarez-Aguirre ,&nbsp;Cem Dede ,&nbsp;Raul Garcia ,&nbsp;Lucas McCullum ,&nbsp;Mehdi Hemmati ,&nbsp;Aysenur Karagoz ,&nbsp;Abdallah S.R. Mohamed ,&nbsp;Stephen Y. Lai ,&nbsp;Katherine A. Hutcheson ,&nbsp;Amy C. Moreno ,&nbsp;Kristy K. Brock ,&nbsp;Fatemeh Nosrat ,&nbsp;Clifton D. Fuller ,&nbsp;Andrew J. Schaefer","doi":"10.1016/j.phro.2025.100772","DOIUrl":"10.1016/j.phro.2025.100772","url":null,"abstract":"<div><h3>Background and Purpose</h3><div>The principle of adaptive radiation therapy (ART) is to adjust radiation plans in response to anatomical changes during treatment. The purpose of this study was to develop a decision-making model for implementation of personalized ART that balances the costs and clinical benefits of radiation plan adaptations in head and neck cancer (HNC).</div></div><div><h3>Materials and Methods</h3><div>Using retrospective imaging data from 52 HNC patients, a Markov decision process (MDP) model was developed to determine optimal timing for plan adaptations based on the difference in normal tissue complication probability (ΔNTCP) between planned and delivered doses to organs-at-risk. To capture the trade-off between the costs and benefits of plan adaptations, the end-treatment ΔNTCPs were converted to Quality Adjusted Life Years (QALYs) and then to equivalent monetary values using a willingness-to-pay per QALY parameter.</div></div><div><h3>Results</h3><div>The optimal policies were derived for 96 combinations of willingness-to-pay per QALY (W) and re-planning cost (RC) and validated using Monte Carlo simulation for two representative scenarios: (1) W = $200,000, RC = $1,000; (2) W = $100,000, RC = $2,000. In scenario (1), the MDP model’s policy reduced the probability of excessive toxicity (ΔNTCP ≥ 5 %) to zero (from 0.21 without re-planning) at an average cost of $380 per patient. In scenario (2), it reduced this probability to 0.02 at an average cost of $520 per patient.</div></div><div><h3>Conclusions</h3><div>The MDP model’s policies outperformed the current fixed-time (one-size-fits-all) approaches in both clinical and financial outcomes in the simulations.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"34 ","pages":"Article 100772"},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A 0.05 mm3 diode-based single charged-particle real-time radiation detector for electron radiotherapy","authors":"Kyoungtae Lee ,&nbsp;Rahul Lall ,&nbsp;Michel M. Maharbiz ,&nbsp;Mekhail Anwar","doi":"10.1016/j.phro.2025.100762","DOIUrl":"10.1016/j.phro.2025.100762","url":null,"abstract":"<div><div>Real-time radiation monitoring at the single-particle level is an unmet need for electron radiotherapy, especially for dose deposition to targets in motion or critical OARs. We have developed a first-in-class CMOS-based 0.05 mm³ single electron sensitive detector. The chiplet integrates all the requisite electronics. The functionality of the system is verified under 6 and 9 MeV clinical electron beams. Percentage depth vs. pulse-width curves for 6 and 9 MeV beams are measured and verified using Monte-Carlo simulations. The proposed system has the potential to enhance the electron radiotherapy quality and safety, providing real-time dosimetry from multiple sites simultaneously.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"34 ","pages":"Article 100762"},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Partial adaptation for online-adaptive proton therapy triggered by during-delivery treatment verification: Feasibility study on prostate cancer treatments","authors":"Virginia Gambetta ,&nbsp;Victoria Pieta ,&nbsp;Jonathan Berthold ,&nbsp;Tobias Hölscher ,&nbsp;Albin Fredriksson ,&nbsp;Christian Richter ,&nbsp;Kristin Stützer","doi":"10.1016/j.phro.2025.100755","DOIUrl":"10.1016/j.phro.2025.100755","url":null,"abstract":"<div><h3>Background and Purpose</h3><div>Online treatment verification during proton therapy delivery may detect deviations due to anatomical changes occurring along the treatment course and trigger immediate intervention, if necessary. We investigated the potential of partial plan adaptation in two-field prostate cancer treatments as a solution for online-adaptive proton therapy (OAPT) after the detection of relevant treatment deviations during the first field delivery.</div></div><div><h3>Materials and Methods</h3><div>In a retrospective study, ten fractions from eight prostate cancer patients with prompt gamma imaging (PGI) detected treatment deviations, which were confirmed on respective in-room control computed tomography (cCT) scans, were considered. For each cCT, a dose-mimicking-based robust partial adaptation reoptimized the second field by considering the suboptimal dose delivery of the first non-adapted, PGI-monitored field. The results were compared to the non-adapted scenario and upfront full adaptation (both fields) in terms of achievable target coverage (prescription: 48 Gy/60 Gy to low-risk/high-risk target) and organ-at-risk (OAR) sparing.</div></div><div><h3>Results</h3><div>Partially adapted plans showed comparable target coverage (median <em>D</em>_98%: 99.9%/98.0% for low-/high-risk target) to fully adapted plans (100.3%/98.7%) and were superior to non-adapted plans (98.7%/94.5%). Achievable OAR sparing was patient-specific depending on the proximity to the target region, but within clinical goals for the partially and fully adapted plans.</div></div><div><h3>Conclusions</h3><div>Partial adaptation triggered mid-delivery of a fraction can still generate plans of comparable conformity to full adaptation, even in the case of plans with only two, opposing fields. A verification-triggered OAPT may therefore become an alternative to upfront OAPT, saving time and imaging dose in fractions without relevant anatomy changes.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"34 ","pages":"Article 100755"},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of Grade 4 radiation-induced lymphopenia during chemoradiation therapy for lung cancer patients: Insights from two past trials","authors":"Serena Monti ,&nbsp;Giuseppe Palma ,&nbsp;Ting Xu ,&nbsp;Radhe Mohan ,&nbsp;Zhongxing Liao ,&nbsp;Laura Cella","doi":"10.1016/j.phro.2025.100782","DOIUrl":"10.1016/j.phro.2025.100782","url":null,"abstract":"<div><h3>Background and Purpose</h3><div>Radiation-induced lymphopenia (RIL) is a significant side effect associated with radiation therapy (RT) with important prognostic implications. We developed and tested a normal tissue complication probability (NTCP) model for Grade 4 (G4) RIL in patients with locally advanced Non-Small-Cell Lung Cancer (NSCLC) who underwent concurrent chemotherapy and RT, analyzing data from patients enrolled in two clinical trials.</div></div><div><h3>Materials and Methods</h3><div>We retrospectively analyzed the data from NCT00915005 (MDA-cohort) and NCT00533949 (RTOG0617-cohort) trials. After finding the candidate predictors of G4-RIL, defined as absolute lymphocyte count (ALC) at nadir &lt; 0.2*10⁹ cells/l during RT, we trained an NTCP model on the MDA-cohort and tested it on the RTOG-cohort, based on common available variables in the two cohorts. Model performance was assessed in terms of discrimination and calibration.</div></div><div><h3>Results</h3><div>In the MDA-cohort, 55 out of 161 (34%) patients developed G4-RIL, while in the RTOG-cohort 16 out of 227 (7%) developed this condition. The relative volume of healthy lungs receiving at least 5 Gy (V_5Gy) and baseline ALC were selected as predictors in an NTCP model, with good discriminative performances (cross validated ROC-AUC: 0.68). The predictive value of V_5Gy was confirmed in the RTOG0917-cohort (ROC-AUC: 0.67), although its validation was limited with suboptimal calibration, potentially due to discrepancies between cohorts.</div></div><div><h3>Conclusions</h3><div>Baseline ALC and lung V_5Gy were identified as predictors for G4-RIL, consistent with findings from previous studies. Treatment plan optimization aiming at reducing low-dose bath in the lungs could be an effective strategy for severe RIL mitigation.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"34 ","pages":"Article 100782"},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144123137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving outcome prediction in oropharyngeal carcinoma through the integration of diffusion-weighted magnetic resonance imaging radiomics","authors":"Heleen Bollen ,&nbsp;Rüveyda Dok ,&nbsp;Frederik De Keyzer ,&nbsp;Sarah Deschuymer ,&nbsp;Annouschka Laenen ,&nbsp;Johannes Devos ,&nbsp;Vincent Vandecaveye ,&nbsp;Sandra Nuyts","doi":"10.1016/j.phro.2025.100759","DOIUrl":"10.1016/j.phro.2025.100759","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Locoregional recurrence (LRR) is the primary pattern of failure in head and neck cancer (HNC) following radiation treatment (RT). Predicting an individual patient’s LRR risk is crucial for pre-treatment risk stratification and treatment adaptation during RT. This study aimed to evaluate the feasibility of integrating pre-treatment and mid-treatment diffusion-weighted (DW)-MRI radiomic parameters into multivariable prognostic models for HNC.</div></div><div><h3>Materials and methods</h3><div>A total of 178 oropharyngeal cancer (OPC) patients undergoing (chemo)radiotherapy (CRT) were analyzed on DW-MRI scans. 105 radiomic features were extracted from ADC maps. Cox regression models incorporating clinical and radiomic parameters were developed for pre-treatment and mid-treatment phases. The models’ discriminative ability was assessed with the Harrel C-index after 5-fold cross-validation.</div></div><div><h3>Results</h3><div>Gray Level Co-occurrence Matrix (GLCM)-correlation emerged as a significant pre-treatment radiomic predictor of locoregional control (LRC) with a C-index (95 % CI) of 0.66 (0.57–0.75). Significant clinical predictors included HPV status, stage, and alcohol use, yielding a C-index of 0.70 (0.62–0.78). Combining clinical and radiomic data resulted in a C-index of 0.72 (0.65–0.80), with GLCM-correlation, disease stage and alcohol use as significant predictors. The mid-treatment model, which included delta (Δ) mean ADC, stage, and additional chemotherapy, achieved a C-index of 0.74 (0.65–0.82). Internal cross-validation yielded C-indices of 0.60 (0.51–0.69), 0.56 (0.44–0.66), and 0.63 (0.54–0.73) for the clinical, combined, and mid-treatment models, respectively.</div></div><div><h3>Conclusion</h3><div>The addition of Δ ADC improves the clinical model, highlighting the potential complementary value of radiomic features in prognostic modeling.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"34 ","pages":"Article 100759"},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143767653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Organs at risk proximity in central lung stereotactic ablative radiotherapy: A comparison of four-dimensional computed tomography and magnetic resonance-guided breath-hold delivery techniques","authors":"Nicolas Giraud ,&nbsp;Hilâl Tekatli ,&nbsp;Famke L. Schneiders ,&nbsp;John R. van Sornsen de Koste ,&nbsp;Marco Marzo ,&nbsp;Miguel A. Palacios ,&nbsp;Suresh Senan","doi":"10.1016/j.phro.2025.100761","DOIUrl":"10.1016/j.phro.2025.100761","url":null,"abstract":"<div><div>Higher toxicity rates are associated with stereotactic ablative radiotherapy (SABR) to central lung tumors. Breath-hold (BH) magnetic resonance-guided SABR (MR-SABR) can reduce doses to organs at risk (OAR). We quantified the planning target volumes (PTV) to OAR distance in 45 lesions treated using MR-SABR and generated a corresponding four-dimensional computed tomography (4D-CT) based PTV (motion-encompassing internal target volume plus 5 mm). For lesions located ≦3 cm from airways, BH MR-SABR increased the median PTV distance to OAR by 3.7 mm. For lesions ≦3 cm from pericardium, median PTV-OAR separation increased by 2.0 mm with BH. These findings highlight the advantage of BH SABR for central lung tumors.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"34 ","pages":"Article 100761"},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multicentre prospective risk analysis of a fully automated radiotherapy workflow","authors":"Geert De Kerf ,&nbsp;Ana Barragán-Montero ,&nbsp;Charlotte L. Brouwer ,&nbsp;Pietro Pisciotta ,&nbsp;Marie-Claude Biston ,&nbsp;Marco Fusella ,&nbsp;Geoffroy Herbin ,&nbsp;Esther Kneepkens ,&nbsp;Livia Marrazzo ,&nbsp;Joshua Mason ,&nbsp;Camila Panduro Nielsen ,&nbsp;Koen Snijders ,&nbsp;Stephanie Tanadini-Lang ,&nbsp;Aude Vaandering ,&nbsp;Tomas M. Janssen","doi":"10.1016/j.phro.2025.100765","DOIUrl":"10.1016/j.phro.2025.100765","url":null,"abstract":"<div><h3>Background and Purpose</h3><div>Fully automated workflows (FAWs) for radiotherapy treatment preparation are feasible, but remain underutilized in clinical settings. A multicentre prospective risk analysis was conducted to support centres in managing FAW-related risks and to identify workflow steps needing improvement.</div></div><div><h3>Material and Methods</h3><div>Eight European radiotherapy centres performed a failure mode and effect analysis (FMEA) on a hypothetical FAW, with a manual review step at the end. Centres assessed occurrence, severity and detectability of provided, or newly added, failure modes to obtain a risk score. Quantitative analysis was performed on curated data, while qualitative analysis summarized free text comments.</div></div><div><h3>Results</h3><div>Manual review and auto-segmentation were identified as the highest-risk steps and the highest scoring failure modes were associated with inadequate manual review (high detectability and severity score), incorrect (i.e. outside of intended use) application of the FAW (high severity score) and protocol violations during patient preparation (high occurrence score). The qualitative analysis highlighted amongst others the risk of deviation from protocol and the difficulty for manual review to recognize automation errors. The risk associated with the technical parts of the workflow was considered low.</div></div><div><h3>Conclusions</h3><div>The FMEA analysis highlighted that points where people interact with the FAW were considered higher risk than lack of trust in the FAW itself. Major concerns were the ability of people to correctly judge output in case of low generalizability and increasing skill degradation. Consequently, educational programs and interpretative tools are essential prerequisites for widespread clinical application of FAWs.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"34 ","pages":"Article 100765"},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143791665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection of the failed-tolerance causes of electronic-portal-imaging-device-based in vivo dosimetry using machine learning for volumetric-modulated arc therapy: A feasibility study","authors":"Nipon Saiyo ,&nbsp;Hironori Kojima ,&nbsp;Kimiya Noto ,&nbsp;Naoki Isomura ,&nbsp;Kosuke Tsukamoto ,&nbsp;Shotaro Yamaguchi ,&nbsp;Yuto Segawa ,&nbsp;Junya Kohigashi ,&nbsp;Akihiro Takemura","doi":"10.1016/j.phro.2025.100785","DOIUrl":"10.1016/j.phro.2025.100785","url":null,"abstract":"<div><h3>Background and Purpose</h3><div>When electronic-portal-imaging-device (EPID)-based <em>in vivo</em> dosimetry (IVD) identifies dose tolerance failures, the cause of the failures should be evaluated. This study aimed to develop a machine-learning (ML) model to classify the cause of EPID-based IVD failures in volumetric-modulated arc therapy (VMAT) treatment.</div></div><div><h3>Materials and Methods</h3><div>Twenty-three prostate VMAT plans were used to recalculate the dose distribution in homogeneous phantom images as no-error (NE) plans. Errors in the randomized multileaf collimator (RMLC) position, monitor unit (MU) variation, lateral position, pitch rotation, and roll rotation were simulated. The IVD results of the NE plans and introduced errors were obtained using EPIgray software. Support vector machines (SVMs) were used to develop ML models for each error. The accuracy percentage, F1-score, and area under the receiver operating characteristic (ROC) curve (AUC) were used to evaluate models’ performances. The models were verified using five additional plans with an Alderson Rando phantom.</div></div><div><h3>Results</h3><div>The models obtained accuracies of over 90% and F1-scores of 0.9 for the RMLC position and MU variation. For lateral position, pitch rotation, and roll rotation errors, the accuracies were 66.1%, 65.2%, and 66.8%, and the F1-scores were 0.66, 0.65, and 0.67, respectively. The AUCs for all the errors were over 0.7. Additionally, the model verification results consistently classified EPIgray data for all the error types.</div></div><div><h3>Conclusion</h3><div>The developed ML models classified the causes of the failed tolerance of the EPID-based IVD.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"34 ","pages":"Article 100785"},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}