{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T07:24:30Z","timestamp":1789802670224,"version":"4.0.1"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T00:00:00Z","timestamp":1749254400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T00:00:00Z","timestamp":1749254400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Health~Holland and Siemens Healthineers","award":["LSHM20103"],"award-info":[{"award-number":["LSHM20103"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"Abstract<\/jats:title>\n \n Objectives<\/jats:title>\n This study compared two uncertainty quantification (UQ) metrics to rule out prostate MRI scans with a high-confidence artificial intelligence (AI) prediction and investigated the resulting potential radiologist\u2019s workload reduction in a clinically significant prostate cancer (csPCa) detection pathway.<\/jats:p>\n <\/jats:sec>\n \n Materials and methods<\/jats:title>\n This retrospective study utilized 1612 MRI scans from three institutes for csPCa (Gleason Grade Group\u2009\u2265\u20092) assessment. We compared the standard diagnostic pathway (radiologist reading) to an AI-based rule-out pathway in terms of efficacy and accuracy in diagnosing csPCa. In the rule-out pathway, 15 AI submodels (trained on 7756 cases) diagnosed each MRI scan, and any prediction deemed uncertain was referred to a radiologist for reading. We compared the mean (meanUQ) and variability (varUQ) of predictions using the DeLong test on the area under the receiver operating characteristic curves (AUROC). The level of workload reduction of the best UQ method was determined based on a maintained sensitivity at non-inferior specificity using the margins 0.05 and 0.10.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The workload reduction of the proposed pathway was institute-specific: up to 20% at a 0.10 non-inferiority margin (\n p<\/jats:italic>\n \u2009<\u20090.05) and non-significant workload reduction at a 0.05 margin. VarUQ-based rule out gave higher but non-significant AUROC scores than meanUQ in certain selected cases (+0.05 AUROC,\n p<\/jats:italic>\n \u2009>\u20090.05).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n MeanUQ and varUQ showed promise in AI-based rule-out csPCa detection. Using varUQ in an AI-based csPCa detection pathway could reduce the number of scans radiologists need to read. The varying performance of the UQ rule-out indicates the need for institute-specific UQ thresholds.<\/jats:p>\n <\/jats:sec>\n \n Key Points<\/jats:title>\n \n \n Question<\/jats:italic>\n <\/jats:bold>\n AI can autonomously assess prostate MRI scans with high certainty at a non-inferior performance compared to radiologists, potentially reducing the workload of radiologists<\/jats:italic>\n .\n <\/jats:p>\n \n \n Findings<\/jats:italic>\n <\/jats:bold>\n The optimal ratio of AI-model and radiologist readings is institute-dependent and requires calibration<\/jats:italic>\n .\n <\/jats:p>\n \n \n Clinical relevance<\/jats:italic>\n <\/jats:bold>\n Semi-autonomous AI-based prostate cancer detection with variational UQ scores shows promise in reducing the number of scans radiologists need to read<\/jats:italic>\n .\n <\/jats:p>\n <\/jats:sec>\n \n Graphical Abstract<\/jats:title>\n <\/jats:sec>","DOI":"10.1007\/s00330-025-11727-6","type":"journal-article","created":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T08:08:25Z","timestamp":1749283705000},"page":"7821-7831","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Simulating workload reduction with an AI-based prostate cancer detection pathway using a prediction uncertainty metric"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5454-5052","authenticated-orcid":false,"given":"Stefan J.","family":"Fransen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joeran S.","family":"Bosma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quintin","family":"van Lohuizen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Roest","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank F. J.","family":"Simonis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas C.","family":"Kwee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derya","family":"Yakar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henkjan","family":"Huisman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,7]]},"reference":[{"key":"11727_CR1","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1016\/S0140-6736(16)32401-1","volume":"389","author":"HU Ahmed","year":"2017","unstructured":"Ahmed HU, El-Shater Bosaily A, Brown LC et al (2017) Diagnostic accuracy of multi-parametric MRI and TRUS biopsy in prostate cancer (PROMIS): a paired validating confirmatory study. Lancet 389:815\u2013822. https:\/\/doi.org\/10.1016\/S0140-6736(16)32401-1","journal-title":"Lancet"},{"key":"11727_CR2","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1016\/j.eururo.2018.11.023","volume":"75","author":"M van der Leest","year":"2019","unstructured":"van der Leest M, Cornel E, Isra\u00ebl B et al (2019) Head-to-head comparison of transrectal ultrasound-guided prostate biopsy versus multiparametric prostate resonance imaging with subsequent magnetic resonance-guided biopsy in biopsy-na\u00efve men with elevated prostate-specific antigen: a large prospective multicenter clinical study (figure presented.). Eur Urol 75:570\u2013578. https:\/\/doi.org\/10.1016\/j.eururo.2018.11.023","journal-title":"Eur Urol"},{"key":"11727_CR3","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.1016\/S0140-6736(24)00651-2","volume":"403","author":"ND James","year":"2024","unstructured":"James ND, Tannock I, N\u2019Dow J et al (2024) The Lancet Commission on prostate cancer: planning for the surge in cases. Lancet 403:1683\u20131722. https:\/\/doi.org\/10.1016\/S0140-6736(24)00651-2","journal-title":"Lancet"},{"key":"11727_CR4","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1097\/RLI.0000000000000780","volume":"56","author":"DJ Winkel","year":"2021","unstructured":"Winkel DJ, Tong A, Lou B et al (2021) A novel deep learning based computer-aided diagnosis system improves the accuracy and efficiency of radiologists in reading biparametric magnetic resonance images of the prostate: results of a multireader, multicase study. Invest Radiol 56:605\u2013613. https:\/\/doi.org\/10.1097\/RLI.0000000000000780","journal-title":"Invest Radiol"},{"key":"11727_CR5","doi-asserted-by":"publisher","first-page":"1814","DOI":"10.1038\/s41591-023-02437-x","volume":"29","author":"K Dvijotham","year":"2023","unstructured":"Dvijotham K, Winkens J, Barsbey M et al (2023) Enhancing the reliability and accuracy of AI-enabled diagnosis via complementarity-driven deferral to clinicians. Nat Med 29:1814\u20131820. https:\/\/doi.org\/10.1038\/s41591-023-02437-x","journal-title":"Nat Med"},{"key":"11727_CR6","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1016\/S1470-2045(23)00298-X","volume":"24","author":"K L\u00e5ng","year":"2023","unstructured":"L\u00e5ng K, Josefsson V, Larsson A-M et al (2023) Artificial intelligence-supported screen reading versus standard double reading in the mammography screening with artificial intelligence trial (MASAI): a clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study. Lancet Oncol 24:936\u2013944. https:\/\/doi.org\/10.1016\/S1470-2045(23)00298-X","journal-title":"Lancet Oncol"},{"key":"11727_CR7","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1148\/radiol.210948","volume":"304","author":"AD Lauritzen","year":"2022","unstructured":"Lauritzen AD, Rodr\u00edguez-Ruiz A, von Euler-Chelpin MC et al (2022) An artificial intelligence\u2013based mammography screening protocol for breast cancer: outcome and radiologist workload. Radiology 304:41\u201349. https:\/\/doi.org\/10.1148\/radiol.210948","journal-title":"Radiology"},{"key":"11727_CR8","doi-asserted-by":"publisher","first-page":"e230031","DOI":"10.1148\/ryai.230031","volume":"5","author":"JS Bosma","year":"2023","unstructured":"Bosma JS, Saha A, Hosseinzadeh M et al (2023) Semisupervised learning with report-guided pseudo labels for deep learning\u2013based prostate cancer detection using biparametric MRI. Radiol Artif Intell 5:e230031. https:\/\/doi.org\/10.1148\/ryai.230031","journal-title":"Radiol Artif Intell"},{"key":"11727_CR9","doi-asserted-by":"publisher","first-page":"102155","DOI":"10.1016\/j.media.2021.102155","volume":"73","author":"A Saha","year":"2021","unstructured":"Saha A, Hosseinzadeh M, Huisman H (2021) End-to-end prostate cancer detection in bpMRI via 3D CNNs: effects of attention mechanisms, clinical priori and decoupled false positive reduction. Med Image Anal 73:102155. https:\/\/doi.org\/10.1016\/j.media.2021.102155","journal-title":"Med Image Anal"},{"key":"11727_CR10","doi-asserted-by":"publisher","first-page":"959","DOI":"10.3390\/diagnostics11060959","volume":"11","author":"JJ Twilt","year":"2021","unstructured":"Twilt JJ, van Leeuwen KG, Huisman HJ et al (2021) Artificial intelligence based algorithms for prostate cancer classification and detection on magnetic resonance imaging: a narrative review. Diagnostics (Basel) 11:959. https:\/\/doi.org\/10.3390\/diagnostics11060959","journal-title":"Diagnostics"},{"key":"11727_CR11","doi-asserted-by":"publisher","first-page":"e230275","DOI":"10.1148\/radiol.230275","volume":"308","author":"N Alves","year":"2023","unstructured":"Alves N, Bosma JS, Venkadesh KV et al (2023) Prediction variability to identify reduced AI performance in cancer diagnosis at MRI and CT. Radiology 308:e230275. https:\/\/doi.org\/10.1148\/radiol.230275","journal-title":"Radiology"},{"key":"11727_CR12","doi-asserted-by":"publisher","first-page":"e223128","DOI":"10.1148\/radiol.223128","volume":"307","author":"B Turkbey","year":"2023","unstructured":"Turkbey B, Purysko AS (2023) PI-RADS: Where next? Radiology 307:e223128. https:\/\/doi.org\/10.1148\/radiol.223128","journal-title":"Radiology"},{"key":"11727_CR13","doi-asserted-by":"publisher","first-page":"1740","DOI":"10.1016\/j.ejrad.2014.06.026","volume":"83","author":"R Itatani","year":"2014","unstructured":"Itatani R, Namimoto T, Atsuji S et al (2014) Negative predictive value of multiparametric MRI for prostate cancer detection: outcome of 5-year follow-up in men with negative findings on initial MRI studies. Eur J Radiol 83:1740\u20131745. https:\/\/doi.org\/10.1016\/j.ejrad.2014.06.026","journal-title":"Eur J Radiol"},{"key":"11727_CR14","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.1007\/s00330-021-08320-y","volume":"32","author":"M Hosseinzadeh","year":"2022","unstructured":"Hosseinzadeh M, Saha A, Brand P et al (2022) Deep learning-assisted prostate cancer detection on bi-parametric MRI: minimum training data size requirements and effect of prior knowledge. Eur Radiol 32:2224\u20132234. https:\/\/doi.org\/10.1007\/s00330-021-08320-y","journal-title":"Eur Radiol"},{"key":"11727_CR15","doi-asserted-by":"publisher","first-page":"6526","DOI":"10.1007\/s00330-022-08712-8","volume":"32","author":"J Bleker","year":"2022","unstructured":"Bleker J, Kwee TC, Rouw D et al (2022) A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics. Eur Radiol 32:6526\u20136535. https:\/\/doi.org\/10.1007\/s00330-022-08712-8","journal-title":"Eur Radiol"},{"key":"11727_CR16","doi-asserted-by":"publisher","first-page":"745657","DOI":"10.3389\/fonc.2021.745657","volume":"11","author":"B Kr\u00fcger-Stokke","year":"2021","unstructured":"Kr\u00fcger-Stokke B, Bertilsson H, Lang\u00f8rgen S et al (2021) Multiparametric prostate MRI in biopsy-na\u00efve men: a prospective evaluation of performance and biopsy strategies. Front Oncol 11:745657. https:\/\/doi.org\/10.3389\/fonc.2021.745657","journal-title":"Front Oncol"},{"key":"11727_CR17","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s00330-022-09032-7","volume":"33","author":"C Roest","year":"2023","unstructured":"Roest C, Kwee TC, Saha A et al (2023) AI-assisted biparametric MRI surveillance of prostate cancer: feasibility study. Eur Radiol 33:89\u201396. https:\/\/doi.org\/10.1007\/s00330-022-09032-7","journal-title":"Eur Radiol"},{"key":"11727_CR18","doi-asserted-by":"publisher","unstructured":"Isensee F, Jaeger PF, Kohl SAA et al (2021) nnU-Net: a self-configuring method for deep learning-based biomedical medical image segmentation. Nat Methods 18:203\u2013211. https:\/\/doi.org\/10.1038\/s41592-020-01008-z","DOI":"10.1038\/s41592-020-01008-z"},{"key":"11727_CR19","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","volume":"3","author":"WJ Youden","year":"1950","unstructured":"Youden WJ (1950) Index for rating diagnostic tests. Cancer 3:32\u201335","journal-title":"Cancer"},{"key":"11727_CR20","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/s00134-009-1641-y","volume":"8","author":"N Turck","year":"2011","unstructured":"Turck N, Vutskits L, Sanchez-Pena P et al (2011) pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics 8:12\u201377. https:\/\/doi.org\/10.1007\/s00134-009-1641-y","journal-title":"BMC Bioinformatics"},{"key":"11727_CR21","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837. https:\/\/doi.org\/10.2307\/2531595","journal-title":"Biometrics"},{"key":"11727_CR22","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.eururo.2019.02.033","volume":"76","author":"B Turkbey","year":"2019","unstructured":"Turkbey B, Rosenkrantz AB, Haider MA et al (2019) Prostate imaging reporting and data system version 2.1: 2019 update of prostate imaging reporting and data system version 2. Eur Urol 76:340\u2013351. https:\/\/doi.org\/10.1016\/j.eururo.2019.02.033","journal-title":"Eur Urol"},{"key":"11727_CR23","doi-asserted-by":"publisher","unstructured":"Hering A, de Boer S, Saha A et al (2024) Deformable MRI sequence registration for AI-based prostate cancer diagnosis. International workshop on biomedical image registration. ACM, Morocco, pp 148\u2013162. https:\/\/doi.org\/10.1007\/978-3-031-73480-9_12","DOI":"10.1007\/978-3-031-73480-9_12"},{"key":"11727_CR24","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s13244-025-01905-x","volume":"16","author":"E Kotter","year":"2025","unstructured":"Kotter E, D\u2019Antonoli TA, Cuocolo R et al (2025) Guiding AI in radiology: ESR\u2019s recommendations for effective implementation of the European AI Act. Insights Imaging 16:33. https:\/\/doi.org\/10.1186\/s13244-025-01905-x","journal-title":"Insights Imaging"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-11727-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-025-11727-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-11727-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T11:44:28Z","timestamp":1763639068000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-025-11727-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,7]]},"references-count":24,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["11727"],"URL":"https:\/\/doi.org\/10.1007\/s00330-025-11727-6","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,7]]},"assertion":[{"value":"22 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 June 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The scientific guarantor of this publication is S.J. Fransen.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"D.Y. is a member of the Scientific Editorial Board of European Radiology (section: Imaging Informatics and Artificial Intelligence). As such, they have not participated in the selection nor review processes for this article. The remaining authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"No complex statistical methods were necessary for this paper.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"Written informed consent was waived by the Institutional Review Boards (center A: METc-2018\/597, center B: MEC-2019-056, and center C: 2017\/576).","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained (center A: METc-2018\/597, center B: MEC-2019-056, and center C: 2017\/576).","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Some study subjects or cohorts have been previously reported in previous studies, but with different purposes: deep learning prostate cancer detection (1\u20134), radiomics prostate cancer detection (5), csPCa biopsy detection efficacy (6), and prostate cancer follow-up detection (7). Our study uses a state-of-the-art AI system to investigate the potential for radiologists\u2019 workload reduction in a semi-autonomous AI-based prostate cancer detection pathway. 1 Alves et al [\n \n ];\n \n . 2. Bosma et al [\n \n ];\n \n . 3. Saha et al [\n \n ];\n \n . 4. Hosseinzadeh et al [\n \n ];\n \n . 5. Bleker et al [\n \n ];\n \n . 6. Kr\u00fcger-Stokke et al [\n \n ];\n \n . 7. Roest et al [\n \n ];\n \n .","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}