[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-339014-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-339014-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","mri-based-radiomic-features-for-identifying-recurrent-prostate-cancer-after-proton-radiation-therapy","MRI-based radiomic features for identifying recurrent prostate cancer after proton radiation therapy","","Magnetic resonance imaging evaluation of recurrent prostate cancer after proton beam therapy is difficult because radiation-induced tissue changes can obscure lesion interpretation. This retrospective study assessed MRI-based radiomic features to identify recurrent prostate cancer following proton therapy. Twelve patients with biochemical recurrence were analyzed, with lesions and contralateral control ROIs segmented from mpMRI. Features from T2WI and ADC images were selected using RFE-CV and classified using a multilayer perceptron model trained on biopsy-confirmed segmentations. The results support feasibility for differential diagnosis, pending larger validation.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/mri-based-radiomic-features-for-identifying-recurrent-prostate-cancer-after-proton-radiation-therapy/339014/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/mri-based-radiomic-features-for-identifying-recurrent-prostate-cancer-after-proton-radiation-therapy/339014.png","ImageObject",300,407,{"name":42,"@type":43},"Finn","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is identifying recurrent prostate cancer after proton therapy challenging on MRI?","Question",{"text":63,"@type":64},"Radiation can produce biological and structural tissue changes, including fibrosis and altered signal patterns on T2WI and ADC images, which makes interpretation difficult for radiologists and may increase inter-observer variability.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How were radiomic features selected and used for classification?",{"text":68,"@type":64},"Radiomic features were extracted from T2-weighted and ADC series within lesion and contralateral control ROIs. Recursive Feature Elimination with Cross-Validation (RFE-CV) selected 10 informative features, which were used to train a multilayer perceptron to classify cancerous, benign, and healthy tissue.",{"name":70,"@type":61,"acceptedAnswer":71},"What performance metrics did the radiomics classifier achieve?",{"text":72,"@type":64},"The model reached an accuracy of 0.83 for distinguishing cancerous, benign, and healthy tissue, with sensitivity 0.80 and specificity 0.85. It also produced an AUC of 0.87 (95% CI [0.72–1.00]) for differentiating cancer from benign and healthy tissues.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},339014,1790733961,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":106,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":144,"preview_page_count":33,"preview_urls":145},34359740700684,"https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487","DOI: 10.1002/acm2.14293  \nMEDICAL IMAGING  \nMRI-based radiomic features for identifying recurrent prostate cancer after proton radiation therapy  \nKazim Z. Gumus1   Samuel Serrano Contreras2  Mohammed Al-Toubat2  Ira Harmon3  Mauricio Hernandez1  Savas Ozdemir1  Sindhu Kumar1  Nurcan Yuruk4  Mutlu Mete5  K. C. Balaji2  Mark Bandyk2   \nDheeraj R. Gopireddy1  \n1 Department of Radiology, University of Florida College of Medicine-Jacksonville, Jacksonville, Florida, USA  \n2 Department of Urology, University of Florida College of Medicine-Jacksonville, Jacksonville, Florida, USA  \n3 Center for Data Solutions, University of Florida College of Medicine-Jacksonville, Jacksonville, Florida, USA  \n4 Department of Computer Science, Southern Methodist University, Dallas, Texas, USA  \n5 Department of Computer Science and Information Systems, Texas A&M University-Commerce, Commerce, Texas, USA  \nCorrespondence  \nKazim Z. Gumus, Department of Radiology, University of Florida College of  \nMedicine-Jacksonville, Jacksonville, FL 32209, USA.  \nEmail: [kzgumus@gmail.com](kzgumus@gmail.com)  \nFunding information  \nUniversity of Florida College of  \nMedicine-Jacksonville Launchpad Initiative  \nAbstract  \nPurpose: Magnetic Resonance Imaging (MRI) evaluation of recurrent prostate cancer (PCa) following proton beam therapy is challenging due to radiationinduced tissue changes. This study aimed to evaluate MRI-based radiomic features so as to identify the recurrent PCa after proton therapy.  \nMethods: We retrospectively studied 12 patients with biochemical recurrence (BCR) following proton therapy. Two experienced radiologists identiﬁed prostate lesions from multi-parametric MRI (mpMRI) images post-proton therapy and marked control regions of interest (ROIs) on the contralateral side of the prostate gland. A total of 210 radiomic features were extracted from lesions and control regions on the T2-weighted (T2WI) and Apparent Diffusion Coefﬁcient (ADC) image series. Recursive Feature Elimination with Cross-Validation method (RFE-CV) was used for feature selection. A Multilayer Perceptron (MLP) neural network was developed to classify three classes: cancerous, benign, and healthy tissue. The 12-core biopsy results were used as the gold standard for the segmentations. The classiﬁer performance was measured using speciﬁcity, sensitivity, the area under receiver operating characteristic curve (AUC), and other statistical indicators.  \nResults: Based on biopsy results, 10 lesions were identiﬁed as PCa recurrence while eight lesions were conﬁrmed to be benign. Ten radiomic features (10/210) were selected to build the multi-class classiﬁer. The radiomics classiﬁer gave an accuracy of 0.83 in identifying cancerous, benign,and healthy tissue with a sensitivity of 0 .80 and speciﬁcity of 0 .85. The model yielded an AUC of 0.87, 95% CI [0.72–1.00] in differentiating cancer from the benign and healthy tissues.  \nConclusions: Our proof-of-concept study demonstrates the potential of using radiomic features as part of the differential diagnosis of PCa on mpMRI following proton therapy. The results need to be validated in a larger cohort.  \nKEYWORDS  \nMRI, prostate cancer, proton therapy, radiomics, recurrence  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \n© 2024 The Authors. Journal of Applied Clinical Medical Physics is published by Wiley Periodicals, Inc. on behalf of The American Association of Physicists in Medicine.  \nJAppl Clin Med Phys. 2024;25:e14293 .  \n[https://doi.org/10.1002/acm2.14293](https://doi.org/10.1002/acm2.14293)  \n[wileyonlinelibrary.com/journal/acm2](wileyonlinelibrary.com/journal/acm2)  \n1  \nof 7  \n1  INTRODUCTION  \nAccurate and early detection of recurrent prostate cancer (PCa) after radiation treatment has critical importance to guide salvage therapy.1,2 Currently, multi-parametric magn","cbCaiu2ku3gLW5nd","https://ap.wps.com/l/cbCaiu2ku3gLW5nd","pdf",2685660,"English","# Abstract\n## Purpose\n## Methods\n## Results\n## Conclusions\n# Introduction\n## Clinical importance of detecting recurrence\n## Role and limitations of mpMRI after proton therapy\n## Radiomics background and rationale\n# Methods Overview","[{\"question\":\"Why is identifying recurrent prostate cancer after proton therapy challenging on MRI?\",\"answer\":\"Radiation can produce biological and structural tissue changes, including fibrosis and altered signal patterns on T2WI and ADC images, which makes interpretation difficult for radiologists and may increase inter-observer variability.\"},{\"question\":\"How were radiomic features selected and used for classification?\",\"answer\":\"Radiomic features were extracted from T2-weighted and ADC series within lesion and contralateral control ROIs. Recursive Feature Elimination with Cross-Validation (RFE-CV) selected 10 informative features, which were used to train a multilayer perceptron to classify cancerous, benign, and healthy tissue.\"},{\"question\":\"What performance metrics did the radiomics classifier achieve?\",\"answer\":\"The model reached an accuracy of 0.83 for distinguishing cancerous, benign, and healthy tissue, with sensitivity 0.80 and specificity 0.85. It also produced an AUC of 0.87 (95% CI [0.72–1.00]) for differentiating cancer from benign and healthy tissues.\"}]","MRI-based radiomic features for identifying recurrent prostate cancer after proton radiation therapy | PDF",1790027336,18,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d08e2d6e897cae2f2860c8712ef80780.webp",983,1291,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/7d120aa547bf7460d8f2d998f48e70b4.webp",982,1290,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f08c77e9b8a6d4ce558b3efc125d3ed7.webp",981,1289,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6855e182bca53a30a13db9b59b6183f7.webp",980,1287]