Current status and future directions of AI in prostate cancer detection on MRI: a special report from the ESUR prostate MRI working group authors

{"This":[0,161],"report":[1,32,162],"from":[2],"the":[3,10,31,90,104,121,150,164,175],"ESUR":[4],"Prostate":[5],"MRI":[6,193],"Working":[7],"Group":[8],"assesses":[9],"current":[11],"role":[12],"of":[13,20,107,124,141],"artificial":[14],"intelligence":[15],"(AI)":[16],"in":[17,111],"MRI-based":[18],"detection":[19],"prostate":[21,129,192],"cancer.":[22],"While":[23],"deep":[24],"learning":[25],"tools":[26,110,187],"demonstrate":[27],"high":[28],"technical":[29],"accuracy,":[30],"emphasizes":[33],"a":[34,48,146],"significant":[35],"gap":[36,165],"between":[37,166],"research":[38,93,168],"achievements":[39],"and":[40,66,80,102,149,170,181],"actual":[41],"clinical":[42,122,171],"application.":[43],"Key":[44],"statements":[45],"include":[46,135],"promoting":[47],"\\"human-in-the-loop\\"":[49],"approach,":[50,148],"where":[51],"AI":[52,186],"supports":[53],"rather":[54],"than":[55],"replaces":[56],"radiological":[57],"expertise,":[58],"to":[59,85],"reduce":[60],"risks":[61],"such":[62],"as":[63,185],"automation":[64],"bias":[65],"legal":[67],"liability.":[68],"There":[69],"is":[70],"an":[71],"urgent":[72],"need":[73,151,176],"for":[74,81,128,152,156,177],"prospective":[75],"validation":[76],"across":[77],"multiple":[78],"vendors":[79],"implementing":[82],"post-market":[83,154,179],"surveillance":[84,155],"monitor":[86],"algorithmic":[87],"drift.":[88],"Finally,":[89],"group":[91],"identified":[92],"priorities":[94],"focused":[95],"on":[96],"cost-effectiveness,":[97],"transparency":[98],"via":[99],"explainable":[100],"AI,":[101],"addressing":[103],"unique":[105],"challenges":[106,119],"deploying":[108],"these":[109],"population-based":[112],"screening":[113],"programs.":[114],"KEY":[115],"POINTS:":[116],"Question":[117],"What":[118],"hinder":[120],"adoption":[123],"AI-based":[125],"medical":[126],"devices":[127],"cancer":[130],"detection?":[131],"Findings":[132],"Major":[133],"obstacles":[134],"insufficient":[136],"real-world":[137],"validation,":[138],"complex":[139],"dynamics":[140],"human-AI":[142],"interactions":[143],"that":[144],"require":[145],"human-in-the-loop":[147],"ongoing":[153],"oncologic":[157],"safety.":[158],"Clinical":[159],"relevance":[160],"highlights":[163],"AI's":[167],"promise":[169],"readiness.":[172],"It":[173],"underscores":[174],"localvalidation,":[178],"surveillance,":[180],"adequate":[182],"user":[183],"training":[184],"become":[188],"incorporated":[189],"into":[190],"diagnostic":[191],"workflows.":[194]}

Authors

Institutions

Publication Details

Journal
European Radiology
Published
2026-09-18
DOI
https://doi.org/10.1007/s00330-026-12836-6
Primary Topic
Prostate Cancer Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Current status and future directions of AI in prostate cancer detection on MRI: a special report from the ESUR prostate MRI working group authors

Tobias Penzkofer, Georgios Agrotis, Olivier Rouvière, Tristan Barrett et al.
European Radiology
Prostate Cancer Diagnosis and Treatment
article

Current status and future directions of AI in prostate cancer detection on MRI: a special report from the ESUR prostate MRI working group authors

Tobias Penzkofer, Georgios Agrotis, Olivier Rouvière, Tristan Barrett, Evis Sala, Raphaële Renard‐Penna, Charlie Alexander Hamm, Johannes Uhlig, Maarten de Rooij, Hanna Falińska, Giorgio Brembilla, on behalf of the ESUR Prostate MRI Working Group, Anwar R. Padhani, Luca Russo, Renato Cuocolo, Iztok Caglic, Emanuele Messina, Andrea Ponsiglione
article en

Abstract

This report from the ESUR Prostate MRI Working Group assesses the current role of artificial intelligence (AI) in MRI-based detection of prostate cancer. While deep learning tools demonstrate high technical accuracy, the report emphasizes a significant gap between research achievements and actual clinical application. Key statements include promoting a "human-in-the-loop" approach, where AI supports rather than replaces radiological expertise, to reduce risks such as automation bias and legal liability. There is an urgent need for prospective validation across multiple vendors and for implementing post-market surveillance to monitor algorithmic drift. Finally, the group identified research priorities focused on cost-effectiveness, transparency via explainable AI, and addressing the unique challenges of deploying these tools in population-based screening programs. KEY POINTS: Question What challenges hinder the clinical adoption of AI-based medical devices for prostate cancer detection? Findings Major obstacles include insufficient real-world validation, complex dynamics of human-AI interactions that require a human-in-the-loop approach, and the need for ongoing post-market surveillance for oncologic safety. Clinical relevance This report highlights the gap between AI's research promise and clinical readiness. It underscores the need for localvalidation, post-market surveillance, and adequate user training as AI tools become incorporated into diagnostic prostate MRI workflows.

European Radiology
Université Claude Bernard Lyon 1 (FR), Università Cattolica del Sacro Cuore (IT), University of Salerno (IT), University College London Hospitals NHS Foundation Trust (GB), Radboud University Nijmegen (NL), Vita-Salute San Raffaele University (IT), University of Cambridge (GB), Policlinico Umberto I (IT), Agostino Gemelli University Polyclinic (IT), Radboud University Medical Center (NL), The Netherlands Cancer Institute (NL), Maastricht University (NL), Humboldt-Universität zu Berlin (DE), Sorbonne Université (FR), Assistance Publique – Hôpitaux de Paris (FR), Hospices Civils de Lyon (FR), Mount Vernon Cancer Centre (GB), Oncode Institute (NL), Universitätsmedizin Göttingen (DE), Wojskowy Instytut Medycyny Lotniczej (PL), Pitié-Salpêtrière Hospital (FR), Hôpital Edouard Herriot (FR), University Children's Hospital Tübingen (DE), Berlin Institute of Health at Charité - Universitätsmedizin Berlin (DE), Istituti di Ricovero e Cura a Carattere Scientifico (IT), Addenbrooke's Hospital (GB), Istituto di Ricovero e Cura a Carattere Scientifico San Raffaele (IT), University College London (GB), University of Naples Federico II (IT), Freie Universität Berlin (DE), Charité - Universitätsmedizin Berlin (DE), University of Tübingen (DE), Sapienza University of Rome (IT)
Openalex Percentile: Top 11%
Prostate Cancer Diagnosis and Treatment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.