Journal of Applied Clinical Medical Physics最新文献

{"title":"RTPhy-ChatBot: A RAG-Based intelligent assistant for radiotherapy physics using LLaMA3 and AAPM reports","authors":"Shuoyang Wei,&nbsp;Ankang Hu,&nbsp;Zhiqun Wang,&nbsp;Xiangyin Meng,&nbsp;Lang Yu,&nbsp;Bo Yang,&nbsp;Jie Qiu","doi":"10.1002/acm2.70263","DOIUrl":"10.1002/acm2.70263","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Medical physics plays a crucial role in radiotherapy, with ongoing technological advancements aimed at improving treatment outcomes. However, the rapid pace of innovation presents challenges for medical physicists, who must continuously acquire and integrate complex information for effective decision-making and communication.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>To support efficient knowledge acquisition, we developed RTPhy-ChatBot, an intelligent assistant tailored to radiotherapy physics. The objective was to create a reliable and precise tool to assist medical physicists in their daily work.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>The knowledge base for RTPhy-ChatBot was constructed from publications by the American Association of Physicists in Medicine (AAPM), which were converted into markdown format, segmented, and embedded using the bge-base-en-v1.5 model. RTPhy-ChatBot employed the Meta-LLaMA3-8B-Instruct model for response generation. We compared its performance with several commercial large language models (LLMs) across 20 template questions and evaluated the impact of zero-shot chain-of-thought (CoT) reasoning. In addition to expert scoring by senior medical physicists, we conducted Rouge score analysis against synthesized reference answers.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>RTPhy-ChatBot demonstrated strong performance in answering radiotherapy physics questions. Across 20 questions, it achieved an average score of 4.0 ± 0.9, compared to 3.9 ± 1.1 for Gemini-2.0-Flash, 4.0 ± 1.4 for GPT-4o, and 3.8 ± 1.2 for Moonshot-v1. It excelled in questions involving specific quality assurance standards. Rouge analysis yielded scores of 0.5127 (Rouge-1), 0.2119 (Rouge-2), and 0.2748 (Rouge-L), closely matching commercial LLMs.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>RTPhy-ChatBot proved to be an effective intelligent assistant for radiotherapy physics, delivering accurate, referenced responses grounded in AAPM publications. Despite lacking online access, it matched or exceeded the performance of commercial LLMs in domain-specific tasks. This pilot study highlights the potential of domain-specific assistants in supporting clinical workflows.</p>\u0000 </section>\u0000 </div>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":"26 10","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aapm.onlinelibrary.wiley.com/doi/epdf/10.1002/acm2.70263","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145251266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating surface-guided radiation therapy and continuous positive airway pressure for breast cancer: Improving reproducibility and efficacy","authors":"Jin Dong Cho,&nbsp;Su Chul Han,&nbsp;Jason Joon Bock Lee,&nbsp;Hyebin Lee,&nbsp;Heerim Nam","doi":"10.1002/acm2.70284","DOIUrl":"10.1002/acm2.70284","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;The utility of surface-guided radiation therapy (SGRT) with continuous positive airway pressure (CPAP) remains underexplored compared to its application with deep inspiratory breath hold (DIBH). This study investigates the integration of CPAP and SGRT, focusing on positional reproducibility and treatment efficiency.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Purpose&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;This study evaluated the impact of patient surface displacement during breast cancer radiation therapy using optical and thermal SGRT monitoring and compared treatment time characteristics between patients undergoing SGRT, either with or without CPAP, and a cohort of patients undergoing treatment without SGRT.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;The SGRT cohort comprised thirty patients: 15 with CPAP (CPAP + SGRT) and 15 without CPAP (SGRT-only). The surface displacement was monitored using an advanced optical and thermal SGRT system with thresholds of 3 mm for translational and 2.5° for rotational displacement. Treatment workflow metrics and positional deviations were assessed across 16 fractions. A comparative analysis included a cohort of 27 free-breathing (FB) patients who did not receive SGRT.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Positional reproducibility was similar in both SGRT groups, with translation vectors of 1.46 ± 0.98 mm (CPAP + SGRT) and 1.37 ± 0.80 mm (SGRT-only) and rotation vectors of 0.57 ± 0.40° and 0.57 ± 0.39°, respectively. Despite comparable displacement control, treatment delivery time variability was highest in the CPAP + SGRT group (normalized standard deviation: 0.16), followed by the SGRT-only (0.11) and FB groups (0.03). The broader time distributions in the SGRT group were attributed to beam-hold activations exceeding the displacement thresholds, whereas total treatment time did not differ significantly between groups.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Conclusions&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;SGRT effectively minimized displacement-related uncertainties during breast cancer radiation therapy with and without CPAP. Although CPAP provides additional internal stabilization and its integration with SGRT increased treatment delivery time variability, the total treatment time remained comparable across all groups. These findings underscore the potential of SGRT and CPAP as complementary tools to enhance precision and safety, particularly for techniques requiring high positional accuracy.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 &lt;/d","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":"26 10","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aapm.onlinelibrary.wiley.com/doi/epdf/10.1002/acm2.70284","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145251283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating the use of ionization chamber and solid-state detectors to evaluate kerma-area product meter accuracy under TG-125 geometry across variable field of views","authors":"Atsushi Fukuda,&nbsp;Pei-Jan Paul Lin","doi":"10.1002/acm2.70281","DOIUrl":"10.1002/acm2.70281","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;A kerma-area product (KAP) meter has been installed in a fluoroscopic system, and its accuracy has been evaluated in task group (TG)-190 geometry using an external detector. However, it is unclear that external detectors could evaluate the KAP meter accuracy under the TG-125 geometry.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Purpose&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;This study investigated whether the reference air kerma rate (&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;msub&gt;\u0000 &lt;mover&gt;\u0000 &lt;mi&gt;K&lt;/mi&gt;\u0000 &lt;mo&gt;̇&lt;/mo&gt;\u0000 &lt;/mover&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;a&lt;/mi&gt;\u0000 &lt;mo&gt;,&lt;/mo&gt;\u0000 &lt;mi&gt;r&lt;/mi&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;/msub&gt;\u0000 &lt;annotation&gt;${dot{K} _{a,r}}$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;) values of the KAP meter increase with increasing field of view (FOV) and whether an external ionization chamber and solid-state detector (SSD) could be used to evaluate KAP meter accuracy in TG-125 geometry.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;An ionization chamber and three different SSDs (Radcal AGMS-DM+, Raysafe X2 R/F sensor, and RTI Dose Probe) were placed at the patient entrance reference point in a C-arm fluoroscopic system, and measurements were taken at FOV settings of 18, 25, 34, and 42 cm using both the TG-190 and TG-125 geometries. The &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;msub&gt;\u0000 &lt;mover&gt;\u0000 &lt;mi&gt;K&lt;/mi&gt;\u0000 &lt;mo&gt;̇&lt;/mo&gt;\u0000 &lt;/mover&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;a&lt;/mi&gt;\u0000 &lt;mo&gt;,&lt;/mo&gt;\u0000 &lt;mi&gt;r&lt;/mi&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;/msub&gt;\u0000 &lt;annotation&gt;$dot{K} _{a,r}$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;, incident air kerma rate (&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msub&gt;\u0000 &lt;mover&gt;\u0000 &lt;mi&gt;K&lt;/mi&gt;\u0000 &lt;mo&gt;̇&lt;/mo&gt;\u0000 &lt;/mover&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;a&lt;/mi&gt;\u0000 &lt;mo&gt;,&lt;/mo&gt;\u0000 &lt;mi&gt;i&lt;/mi&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;/msub&gt;\u0000 ","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":"26 10","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aapm.onlinelibrary.wiley.com/doi/epdf/10.1002/acm2.70281","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145251221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PlanAct: An eclipse scripting API-based module embedding clinical optimization strategies for automated planning in locally advanced non-small cell lung cancer","authors":"Hao Guo,&nbsp;Tenzin Kunkyab,&nbsp;Yang Lei,&nbsp;Kenneth Rosenzweig,&nbsp;Robert Samstein,&nbsp;Ming Chao,&nbsp;Tian Liu,&nbsp;Junyi Xia,&nbsp;Jiahan Zhang","doi":"10.1002/acm2.70304","DOIUrl":"10.1002/acm2.70304","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Manual intensity-modulated radiotherapy (IMRT) planning for locally advanced non-small cell lung cancer (LA-NSCLC) is labor-intensive and time-consuming. Knowledge-based planning (e.g., RapidPlan) improves consistency but commonly falls short in fully meeting clinical objectives in LA-NSCLC cases, requiring iterative manual adjustments.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>To develop and validate PlanAct, an Eclipse Scripting API (ESAPI)-based module for optimizing automated IMRT planning in LA-NSCLC, and to compare its performance against clinical and RapidPlan-generated plans across a retrospective patient cohort.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>PlanAct was developed with modular functions to automate key tasks in IMRT plan generation and optimization. PlanAct was manually executed on 56 anonymized retrospective LA-NSCLC cases using a standardized nine-beam geometry. Plans were normalized to ensure 95% planning target volume (PTV) coverage. The PlanAct-optimized plans were evaluated against RapidPlan-generated plans and clinically approved plans using institutional plan quality metrics, including dose-volume constraints for the esophagus, spinal cord, lungs, heart, larynx, and PTV. Statistical comparisons were performed to assess differences in plan quality and unmet dosimetric requirements.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>PlanAct-optimized plans demonstrated significant improvement in plan quality compared to RapidPlan, with fewer unmet clinical requirements and better organ-at-risk sparing, particularly for the lungs (<i>p</i> &lt; 0.001 for V₂₀ and D_mean). Only one PlanAct-optimized plan failed to meet all dose constraints (in this case, lungs D_mean) due to a large PTV volume, compared to 18 RapidPlan and 10 clinical plans. Even in anatomically challenging cases, PlanAct produced more favorable dose distributions, with superior hotspot control.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>PlanAct is an effective tool to optimize automated IMRT planning in LA-NSCLC. It produced plans comparable to or better than clinical plans, even in challenging cases. Its modular architecture makes it promising for integration into future fully autonomous, patient-specific radiotherapy treatment planning systems.</p>\u0000 </section>\u0000 </div>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":"26 10","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aapm.onlinelibrary.wiley.com/doi/epdf/10.1002/acm2.70304","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145251244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dosimetric evaluation of surface-guided tattoo-free approach for right sided whole-breast irradiation","authors":"Xinxin Zhang,&nbsp;Chengzhu Zhang,&nbsp;Swati Mamidanna,&nbsp;Yin Zhang,&nbsp;Xiao Wang,&nbsp;Ning J Yue,&nbsp;Shicha Kumar,&nbsp;Maria J Kowzun,&nbsp;Lindsay Potdevin,&nbsp;Mridula George,&nbsp;Lara Hathout,&nbsp;Bruce Haffty,&nbsp;Nisha Ohri","doi":"10.1002/acm2.70294","DOIUrl":"10.1002/acm2.70294","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background and purpose&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;In preparation for adjuvant breast radiation therapy (RT), permanent skin tattoo marks are often placed on the patient's skin to assist patient positioning on the treatment couch. However, those marks are often undesirable, in particular, for breast cancer patients due to various cosmetic and psychological concerns and other drawbacks. With surface-guided radiation therapy (SGRT) being readily available, it becomes possible to adopt a “tattoo-free” approach for patient setup. This study evaluates the efficacy and dosimetric implications of a tattoo-free setup technique.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Thirty right-sided breast cancer patients were included in this retrospective study. All patients received an initial course of whole breast treatment of 42.56 Gy in 16 fractions using a tangential 3D conformal technique, followed by a 10 Gy boost to the lumpectomy site in four fractions. SGRT was used in daily setup to reproduce patient's positioning between the simulation and treatment. The patient's breast surface was aligned with the corresponding reference breast surface generated from the planning computed tomography (CT) images via AlignRT system. To evaluate the feasibility and accuracy of the new tattoo-free approach, at the beginning of the program and for this group of patients, daily orthogonal kV imaging pair was performed to confirm the treatment positioning by verifying the bony landmarks, and the translational couch shifts were recorded for every fraction. Those shifts were applied to the isocenter positions of the original corresponding clinical treatment plans, and dose distributions were re-computed. The dosimetric evaluation between the two setup methods, that is, the breast surface alignment versus the bony landmark alignment, were then assessed on the original clinical plan. New plan sums were obtained from the 16 fractions, where each one was recalculated based on the new isocenter positions determined with the kV imaging shifts. Boost fractions were excluded in this study, as setup was verified using surgical clips as the matching reference.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Translational shifts for the 30 patients (&lt;i&gt;N&lt;/i&gt; = 480) were reviewed. The mean absolute shift resulted from the orthogonal kV imaging-based setup following the SGRT setup, in lateral, vertical and longitudinal directions, were 0.20 cm (ranged from 0 to 1.98 cm with 95% confidence interval (CI) of 0.18–0.22 cm), 0.23 cm (ranged from 0–1.25 cm with 95% CI of 0.21–0.25 cm), and 0.22 cm (ranged from 0 to 1.35 cm with 95% CI of 0.19–0.24 cm), respectively. The average change in V95%","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":"26 10","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aapm.onlinelibrary.wiley.com/doi/epdf/10.1002/acm2.70294","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145251263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AAPM WGTEACH Report 366: Best practices in the teaching and mentoring of medical physics","authors":"Victor J. Montemayor,&nbsp;Elizabeth L. Bossart,&nbsp;Jay W. Burmeister,&nbsp;Ashley Cetnar,&nbsp;Matthew A. Deeley,&nbsp;Jessica M. Fagerstrom,&nbsp;Joanna M. Harper,&nbsp;Kenneth L. Homann,&nbsp;Judy Rose James,&nbsp;Tae Kyu Lee,&nbsp;Harish K. Malhotra,&nbsp;Maria Mamalui,&nbsp;Marija Popovic,&nbsp;Dennis N. Stanley","doi":"10.1002/acm2.70259","DOIUrl":"10.1002/acm2.70259","url":null,"abstract":"<p>Working Group on Teaching Educators and Clinicians How (WGTEACH) has been charged with writing a report to review best, evidence-based practices in various aspects of the teaching of medical physics. These aspects include not only didactic teaching and mentoring in the classroom and clinic, but also teaching K-12 and undergraduate students and interacting with the public, including patients. This report also touches on virtual and remote learning, adult learning theory, implications for teaching from neuroscience research on learning, and the role of accrediting and governing agencies in education.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":"26 10","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aapm.onlinelibrary.wiley.com/doi/epdf/10.1002/acm2.70259","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145251260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Response prediction of radiotherapy in lung cancer patients using multimodal data","authors":"Xiaojuan Duan,&nbsp;Yushun Gong,&nbsp;Liang Wei,&nbsp;Lu Chen,&nbsp;Xin Song,&nbsp;Yongqin Li","doi":"10.1002/acm2.70277","DOIUrl":"10.1002/acm2.70277","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background and Purpose&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Radiotherapy (RT) is a critical treatment for lung cancer; however, individual responses vary significantly. Pre-treatment prediction of RT response could guide clinical decision-making and identify patients unlikely to benefit. This study aims to predict RT response in lung cancer patients using multimodal data.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Patients diagnosed with lung cancer and scheduled to undergo RT at a single institution between May 2022 and October 2024 were selected. Multimodal data, encompassing demographic, radiological, biological, and physiological characteristics, were collected 1 week before RT initiation. Treatment plans followed the International Commission on Radiation Units and Measurements (ICRU) Report 83 guidelines, developed using a commercial treatment planning system and delivered via a linear accelerator with 6 MV photon beams. Radiological and biological data were reassessed 4 weeks after completion of RT, with treatment response classified according to Response Evaluation Criteria in Solid Tumors (RECIST). The dataset was split into training (70%), validation (15%), and testing (15%) sets using a stratified random sampling approach. A back propagation neural network (BPNN) was trained on the training set, and model performance was validated on the testing set.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;A total of 120 patients were analyzed. Of these, 41 were classified as having partial response (PR), 69 as stable disease (SD), and 10 as progressive disease (PD). Significant differences were observed among the groups in 58 characteristics, including 2 demographic, 5 radiological, 1 biological, and 50 physiological. Among the 34 features analyzed for PR prediction, the maximum vertical tumor diameter achieved an AUC of 0.699 (95% CI: 0.630–0.757). In contrast, the comprehensive BPNN model incorporating all characteristics showed an AUC of 0.855 (95% CI: 0.843-0.875), with a prediction mean squared error (MSE) of 0.07. Similarly, among the 36 features analyzed for PD prediction, the zero-crossing ratio of surface electromyography signals achieved an AUC of 0.750 (95% CI: 0.648–0.841). The comprehensive model further increased AUC to 0.929 (95% CI: 0.900–0.960), with a prediction MSE of 0.01.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Conclusion&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Pretreatment demographic, radiological, and physiological characteristics were associated with RT response in lung cancer patients. The developed BPNN models leveraging multimodal data effectively predicted PR and PD","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":"26 10","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12504048/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145244594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantification of dose accumulation using deformable image registration: Application in re-irradiation of liver metastases using robotic radiosurgery","authors":"Ahamed Badusha Mohamed Yoosuf,&nbsp;Mohd Zahri Abdul Aziz,&nbsp;Mohd Syahir Mansoor,&nbsp;Gokula Kumar Appalanaido,&nbsp;Salem Alshehri,&nbsp;Mamdouh Alqathami","doi":"10.1002/acm2.70278","DOIUrl":"10.1002/acm2.70278","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>This study evaluates cumulative dose estimations using deformable image registration (DIR) in robotic stereotactic ablative radiotherapy (SABR)-based multiple re-irradiations for liver metastases. It highlights DIR's role and accuracy in adaptive radiotherapy to enhance treatment precision and reduce toxicity.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Materials &amp; Methods</h3>\u0000 \u0000 <p>A retrospective analysis was conducted on 22 patients (age: 42–80, median: 61 years) with liver metastases re-irradiated using CyberKnife SABR (54 treatments) between June 2016 and February 2024. A comparative analysis of organs-at-risk (OAR) volumes was performed using contours derived from DIR and physical summation method to evaluate consistency between the two approaches. Dosimetric analysis involved accumulating doses to organs at risk using physical dose summation and DIR-based dose summation. To standardize dose assessments, all radiation doses were converted into equivalent doses in 2 Gy fractions (EQD2) and biologically effective doses (BED). The DIR algorithm was quantitatively assessed using similarity indices, including Dice similarity coefficient (DSC) and Jaccard (JD) index.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The findings demonstrated that organs susceptible to motion, such as the liver and large bowel, exhibited greater variability in volume measurements when evaluated using physical summation. A significant reduction in maximum dose for the liver (<i>p</i> = 0.00) and chest wall (<i>p</i> = 0.05) was observed under DIR-based dose accumulation (liver-83.2 ± 28.0 Gy; chest wall-66.9 ± 18.6 Gy) compared to physical summation (liver-123.8 ± 55.6 Gy; chest wall-82.9 ± 22.4 Gy), suggesting overestimation using physical summation. Among the analyzed structures, DIR showed high spatial accuracy for the heart, liver, and external body with Dice scores &gt; 0.90 and Jaccard indices &gt; 0.84, while lower agreement was noted for deformable organs such as the bowel with Dice scores &lt; 0.43 and Jaccard indices &lt; 0.29.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>DIR improved anatomical alignment and provides more anatomically consistent cumulative dose estimation in SABR re-irradiation, particularly for OARs that are prone to deform. Integrating DIR into adaptive radiotherapy workflows can improve the estimation of dose to OARs while minimizing toxicity risks.</p>\u0000 </section>\u0000 </div>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":"26 10","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12504063/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145244590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of a novel quantitative multiparametric MR sequence for radiation therapy treatment response assessment","authors":"Yuhao Yan,&nbsp;R. Adam Bayliss,&nbsp;Adam R. Burr,&nbsp;Andrew M. Baschnagel,&nbsp;Brett A. Morris,&nbsp;Florian Wiesinger,&nbsp;Jose de Arcos Rodriguez,&nbsp;Carri K. Glide-Hurst","doi":"10.1002/acm2.70274","DOIUrl":"10.1002/acm2.70274","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Multiparametric MRI has shown great promise to derive multiple quantitative imaging biomarkers for treatment response assessment.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Purpose&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;To evaluate a novel deep-learning-enhanced MUlti-PArametric MR sequence (DL-MUPA) for treatment response assessment for brain metastases patients treated with stereotactic radiosurgery (SRS) and head-and-neck (HN) cancer patients undergoing conventionally fractionation adaptive radiation therapy.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;DL-MUPA derives quantitative T1 and T2 relaxation time maps from a single 4–6-min scan denoised via DL method using least-squares dictionary fitting. Longitudinal phantom benchmarking was performed on a NIST-ISMRM phantom over 1 year. In patients, longitudinal DL-MUPA data were acquired on a 1.5T MR-simulator, including pretreatment (PreTx) and every ∼3 months after SRS (PostTx) in brain, and PreTx, mid-treatment and 3 months PostTx in HN. Delta analysis was performed calculating changes of mean T1 and T2 values within gross tumor volumes (GTVs), residual disease (RD, HN), parotids, and submandibular glands (HN) for treatment response assessment. Uninvolved normal tissues (normal appearing white matter in brain, masseter in HN) were evaluated for within-subject repeatability.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Phantom benchmarking revealed excellent inter-session repeatability (coefficient of variation &lt; 0.9% for T1, &lt; 6.6% for T2), suggesting reliability for longitudinal studies with systematic bias adjustment. Uninvolved normal tissue suggested acceptable within-subject repeatability in the brain |ΔT1&lt;sub&gt;mean&lt;/sub&gt;| &lt; 36 ms (4.9%), |ΔT2&lt;sub&gt;mean&lt;/sub&gt;| &lt; 2 ms (6.1%) and HN |ΔT1&lt;sub&gt;mean&lt;/sub&gt;| &lt; 69 ms (7.0%), |ΔT2&lt;sub&gt;mean&lt;/sub&gt;| &lt; 4 ms (17.8%) with few outliers. In brain, remarkable changes were noted in a resolved metastasis (4-month PostTx ΔT1&lt;sub&gt;mean &lt;/sub&gt;= 155 ms (13.7%)) and necrotic settings (ΔT1&lt;sub&gt;mean &lt;/sub&gt;= 214-502 ms (17.6-39.7%), ΔT2&lt;sub&gt;mean &lt;/sub&gt;= 7-41 ms (8.7-41.4%), 6-month to 3-month PostTx). In HN, two base of tongue tumors exhibited T2 enhancement (PostTx GTV ΔT2&lt;sub&gt;mean &lt;/sub&gt;&gt; 7 ms (12.8%), RD ΔT2&lt;sub&gt;mean &lt;/sub&gt;&gt; 10 ms (18.1%)). A case with nodal disease resolved PostTx (GTV ΔT1&lt;sub&gt;mean &lt;/sub&gt;= -541 ms (-39.5%), ΔT2&lt;sub&gt;mean &lt;/sub&gt;= -24 ms (-32.7%), RD ΔT1&lt;sub&gt;mean &lt;/sub&gt;= -400 ms (-29.2%), ΔT2&lt;sub&gt;mean &lt;/sub&gt;= -25 ms (-35.3%)). Parotids (PostTx ΔT1&lt;sub&gt;mean &lt;/sub&gt;&gt; 82 ms (12.4%), ΔT2&lt;sub&gt;mean &lt;/sub&gt;&gt; 6 ms (13.4%)) and submand","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":"26 10","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12504055/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145244592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of a prostate SBRT planning workflow using auto-segmentation and knowledge-based planning","authors":"Trisha Jones,&nbsp;Kirk Luca,&nbsp;Mingdong Fan,&nbsp;Pretesh R. Patel,&nbsp;Ashesh B. Jani,&nbsp;Xiaofeng Yang,&nbsp;Justin Roper,&nbsp;Jie Ding","doi":"10.1002/acm2.70295","DOIUrl":"10.1002/acm2.70295","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Purpose&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;This study investigates a prostate stereotactic body radiotherapy (SBRT) planning workflow integrating commercial artificial intelligence (AI) contouring and knowledge-based planning (KBP). The purpose is to determine whether AI-generated contours are comparable to physician-delineated contours in achieving dosimetric goals.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;In this retrospective study, 20 patients with intact prostate cancer were included. A commercial AI contouring software was applied to computed tomography (CT) scans. Contouring accuracy for the prostate, rectum, and bladder was assessed against clinical contours using geometric metrics including Dice similarity coefficient (DSC), surface DSC (sDSC), and added path length (APL).&lt;/p&gt;\u0000 \u0000 &lt;p&gt;Volumetric modulated arc therapy plans were generated using an in-house prostate SBRT KBP model without user interaction. The prescribed dose was 36.25 Gy in 5 fractions to the planning target volume with a 40 Gy simultaneous integrated boost to the prostate. All plans were calculated using AcurosXB and normalized to cover 98% of the prostate. Given the high precision required for prostate SBRT, all plans used the physician-delineated (clinical) prostate contours. Three plans were generated for each patient: (1) a reference plan using clinical contours, (2) a plan using clinical prostate contour and AI organs at risk (OARs), and (3) a plan using clinical prostate contour and post-processed AI OARs that removed any overlap with the clinical prostate contour. The latter two plans were recalculated on clinical contours with fixed monitor units to evaluate the dosimetric impact of AI contouring. Plan quality was evaluated using NRG-GU013 criteria.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;The average DSC values were 0.83, 0.86, and 0.94 for prostate, rectum, and bladder, respectively, and the average sDSC values were 0.62, 0.81, and 0.85. AI prostate contours were clinically unacceptable. AI rectum and bladder contours overlapped the clinical prostate contour in 15 and 20 cases, respectively.&lt;/p&gt;\u0000 \u0000 &lt;p&gt;All reference plans using clinical contours met NRG criteria. Using AI OARs or post-processed AI OARs, only one case exceeded rectum V36Gy limits due to over-contouring, but it became clinically acceptable after recalculation on clinical contours. Plans using post-processed AI OARs yielded dosimetric results more comparable to reference plans for rectum and bladder sparing.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Conclusions&lt;/h3&gt;\u0000 \u0000 ","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":"26 10","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12504046/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145244610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}