[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-353430-105":59,"doc-detail-353430-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","artificial-intelligence-in-prostate-mri-comparative-diagnostic-performance-in-a-high-prevalence-cohort","Artificial intelligence in prostate MRI - Comparative diagnostic performance in a high-prevalence cohort","","Artificial intelligence is increasingly integrated into prostate cancer diagnostic workflows, yet validation in high-prevalence clinical cohorts remains insufficient. This retrospective study compared a licensed AI software with routine radiologist readings of prostate MRI, using histopathology as the reference standard. In 1000 patients undergoing prostate MRI for suspected cancer, diagnostic performance was evaluated across PI-RADS thresholds with sensitivity, specificity, PPV, NPV, accuracy, ROC analysis, inter-rater agreement, and McNemar’s test.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/artificial-intelligence-in-prostate-mri-comparative-diagnostic-performance-in-a-high-prevalence-cohort/353430/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/artificial-intelligence-in-prostate-mri-comparative-diagnostic-performance-in-a-high-prevalence-cohort/353430.png","ImageObject",300,407,{"name":92,"@type":93},"acoobca","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-07","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What was the study purpose comparing AI and radiologists?","Question",{"text":112,"@type":113},"The study compared the diagnostic performance of a licensed AI software against routine radiologist readings of prostate MRI, with histopathology as the reference standard.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How was diagnostic performance assessed in the study?",{"text":117,"@type":113},"Performance was evaluated using sensitivity, specificity, PPV, NPV, and accuracy across PI-RADS thresholds, along with ROC analysis, Cohen’s kappa for inter-rater agreement, and paired McNemar’s test.",{"name":119,"@type":110,"acceptedAnswer":120},"What were the key findings at the PI-RADS ≥3 threshold?",{"text":121,"@type":113},"Radiologists had higher sensitivity but much lower specificity than AI; overall accuracy and PPV were higher for radiologists, while NPV differed between methods, with statistically significant differences reported.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},353430,1790588248,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":19,"preview_urls":145},3985747870733,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Artiﬁcial intelligence in prostate MRI: Comparative diagnostic performance in a high-prevalence cohort  \nActa Radiologica 2026, Vol. 67(9) 765–774 © The Foundation Acta Radiologica 2026  \nArticle reuse guidelines:  \n[sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/02841851261470455](DOI: 10.1177/02841851261470455)[ ](DOI: 10.1177/02841851261470455)[journals.sagepub.com/home/acr](journals.sagepub.com/home/acr)  \nNádia Gonçalves Ferreira 1,2 , Owen Matthew Truscott Thomas3  , Kjell-Inge Gjesdal2,4 , Stig Müller 1,5 , Jan Oldenburg 1,6  ,  \nIngrid Framås Syversen2 , Anders Christian Hansen7 and Jonn Terje Geitung2,8   \nAbstract  \nBackground: Artiﬁcial intelligence (AI) is increasingly used in prostate cancer diagnostic workﬂows but remains insufﬁciently validated in high-prevalence cohorts often encountered in academic referral centers.  \nPurpose: To compare the diagnostic performance of licensed AI software with routine radiologist readings of prostate MRI, using histopathology as the reference standard.  \nMaterial and Methods: In this retrospective study, 1000 patients underwent prostate MRI for suspected prostate cancer (between May 2020 and December 2024), followed by transperineal biopsy; 391 subsequently underwent radical prostatectomy. Diagnostic performance was assessed using sensitivity, speciﬁcity, positive predictive value (PPV), negative predictive value (NPV), and accuracy across PI-RADS thresholds. Receiver operating characteristic (ROC) analysis, Cohen’s kappa for inter-rater agreement, and paired McNemar’s test were performed.  \nResults: In total, 959 patients (mean age = 69.7 ± 8.4 years) were included; clinically signiﬁcant prostate cancer (csPCa) was found in 830 (86.5%) patients. AI assigned more cases to PI-RADS 1–2 and fewer to PI-RADS 3 (κ = 0.388; P \u003C.001). At the PI-RADS ≥3 threshold, radiologists showed sensitivity 96.0%, speciﬁcity 20.9%, accuracy 85.9%, PPV 88.7%, and NPV 45.0%, compared with 91.3%, 37.2%, 84.0%, 90.3%, and 40.0% for AI (P \u003C.001). ROC performance was comparable (AUC 0.763 vs. 0.739; P = .28). In the prostatectomy subgroup, AI demonstrated a higher false-negative rate (8.4% vs. 4.1%; odds ratio = 3.83, 95% conﬁdence interval [CI] = 1.52–11.51).  \nConclusion: AI showed diagnostic performance comparable to that of radiologists for csPCa detection, with no signiﬁcant difference in AUC. AI reduced indeterminate PI-RADS 3 scores but missed more signiﬁcant cancers.  \nKeywords  \nGenital/reproductive, magnetic resonance imaging, prostate, adults, computer applications-detection, diagnosis  \nReceived: 25 March 2026; accepted: 4 July 2026  \n1 Medical Faculty, University of Oslo, Oslo, Norway  \n2Department of Radiology, Akershus Univesity Hospital, Lørenskog, Norway  \n3Health Services Research Unit, Akershus University Hospital, Lørenskog, Norway  \n4Sunnmære MR-Klinikk, Ålesund, Norway  \n5Department of Urology, Akershus University Hospital, Lørenskog, Norway  \n6Department of Oncology, Akershus University Hospital, Lørenskog, Norway  \n7Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Centre for Mathematical Sciences, Cambridge, UK 8Institute of Clincal Medicine, University of Oslo, Oslo, Norway  \nCorresponding author:  \nNádia Gonçalves Ferreira, Department of Radiology, Akershus Univesity Hospital, Lørenskog, Norway.  \nEmail: [nadiago@uio.no](nadiago@uio.no)  \nIntroduction  \nWorldwide, prostate cancer (PCa) is the second leading cancer diagnosis in men.1 Its incidence continues to rise, and the number of affected individuals is expected to reach approximately 2 .9 million by 2040 .2  \nSince its ﬁrst use in 1983, magnetic resonance imaging (MRI) has undergone signiﬁcant technological and clinical advancements, establishing itself as a crucial tool for diagnosing PCa.3,4 Current guidelines recommend performing MRI before biopsy to select patients for further diagnostic conﬁrmation and to minimize ","cbCaiaYez1u8TbOe","https://ap.wps.com/l/cbCaiaYez1u8TbOe","pdf",1259636,"English","# Abstract\n## Background\n## Purpose\n## Material and Methods\n## Results\n## Conclusion\n# Introduction\n## Prostate cancer burden and MRI role\n## PI-RADS limitations\n## AI as an adjunct and clinical evidence gap\n## mdprostate software rationale and study aim\n# Material and Methods\n## Patients","[{\"question\":\"What was the study purpose comparing AI and radiologists?\",\"answer\":\"The study compared the diagnostic performance of a licensed AI software against routine radiologist readings of prostate MRI, with histopathology as the reference standard.\"},{\"question\":\"How was diagnostic performance assessed in the study?\",\"answer\":\"Performance was evaluated using sensitivity, specificity, PPV, NPV, and accuracy across PI-RADS thresholds, along with ROC analysis, Cohen’s kappa for inter-rater agreement, and paired McNemar’s test.\"},{\"question\":\"What were the key findings at the PI-RADS ≥3 threshold?\",\"answer\":\"Radiologists had higher sensitivity but much lower specificity than AI; overall accuracy and PPV were higher for radiologists, while NPV differed between methods, with statistically significant differences reported.\"}]","Artificial intelligence in prostate MRI - Comparative diagnostic performance in a high-prevalence cohort | PDF",1790105345,25,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/75889cfd1ab804a38720d8d415a0caba.webp",983,1310,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5646858844ff38d4747a39ba0bb89aea.webp",982,1309,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/cddd13e105ea3087d8ce1dc6094a7e30.webp",981,1308,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e59ebca6b09e067e13211b82c2ddd2d5.webp",980,1306]