{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T16:09:10Z","timestamp":1774886950421,"version":"3.50.1"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"AngioGenesis Analytics"},{"DOI":"10.13039\/100020631","name":"European Innovation Council and Small and Medium-sized Enterprises Executive Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020631","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction and objectives<\/jats:title>\n                    <jats:p>An AI model that performs well during training does not guarantee similar performance in clinical practice and should be carefully evaluated before implementation. We aimed to evaluate a voxel-level trained AI model (AUROC 0.87), which utilizes a three-dimensional multiparametric transrectal prostate ultrasound (3D mpUS) to identify clinically significant prostate cancer (csPCa).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>We included patients with csPCa (Grade Group \u2265 2 and scheduled for radical prostatectomy (RP)) and without csPCa (PI-RADS\u2009\u2264\u20092 and\/or negative systematic biopsies). Histopathology of RP specimens provided the csPCa reference standard. 3D mpUS consisted of grayscale, contrast-enhanced ultrasound, and shear-wave elastography using automated acquisition. We assessed patient-level diagnostic accuracy by comparing the results of simulated targeted biopsies based on the AI model with the reference standard in internal and external evaluation. Patients without csPCa and RP reference standard were used to determine specificity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Based on internal evaluation of 250 patients, a sensitivity of 0.82 (CI 0.75 to 0.87) and specificity of 0.43 (CI 0.32 to 0.55) was reached for ISUP\u2009\u2265\u20092. For ISUP\u2009\u2265\u20093, this was 0.90 (CI 0.83\u20130.95) and 0.39 (CI 0.31\u20130.47). In the external evaluation of 77 patients, the sensitivity for ISUP\u2009\u2265\u20092 was 0.81 (CI 0.65\u20130.90), with a specificity of 0.42 (CI 0.28\u20130.57). For ISUP\u2009\u2265\u20093, this was 0.96 (CI 0.78\u20130.99) and 0.42 (CI 0.30\u20130.55).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The AI model based on 3D mpUS showed consistent patient-level performance for csPCa detection in internal and external evaluation, comparable to voxel-level analysis. These suggest strong generalizability and support prospective clinical trials.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Trial registration<\/jats:title>\n                    <jats:p>NCT04605276.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Question<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Does the diagnostic performance of a 3D multiparametric ultrasound-based AI model translate from voxel-level training to patient-level biopsy simulation?<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Simulated biopsy performance aligned with voxel-level results, showing robust csPCa detection and supporting the model\u2019s generalizability across independent datasets.<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Clinical relevance<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>The AI model\u2019s consistent biopsy simulation performance confirms its readiness for clinical evaluation and suggests diagnostic value in MRI-constrained settings.<\/jats:italic>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-025-12114-x","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T15:59:29Z","timestamp":1762444769000},"page":"3043-3049","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Evaluation of an artificial intelligence model based on multiparametric transrectal ultrasound for localizing clinically significant prostate cancer by simulation of targeted biopsies"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8448-4193","authenticated-orcid":false,"given":"Daniel L.","family":"van den Kroonenberg","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Delberghe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Auke","family":"Jager","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnoud W.","family":"Postema","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katelijne C. C.","family":"de Bie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes B.","family":"Reitsma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marije","family":"Zwart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hessel","family":"Wijkstra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Garrido-Utrilla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joost","family":"de Baaij","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Paul A.","family":"van Basten","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henk G.","family":"van der Poel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harrie P.","family":"Beerlage","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Massimo","family":"Mischi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jorg R.","family":"Oddens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,6]]},"reference":[{"key":"12114_CR1","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, Israel 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-naive men with elevated prostate-specific antigen: a large prospective multicenter clinical study. Eur Urol 75:570\u2013578","journal-title":"Eur Urol"},{"key":"12114_CR2","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1056\/NEJMoa1801993","volume":"378","author":"V Kasivisvanathan","year":"2018","unstructured":"Kasivisvanathan V, Rannikko AS, Borghi M et al (2018) MRI-targeted or standard biopsy for prostate-cancer diagnosis. N Engl J Med 378:1767\u20131777","journal-title":"N Engl J Med"},{"key":"12114_CR3","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/S1470-2045(18)30569-2","volume":"20","author":"O Rouviere","year":"2019","unstructured":"Rouviere O, Puech P, Renard-Penna R et al (2019) Use of prostate systematic and targeted biopsy on the basis of multiparametric MRI in biopsy-naive patients (MRI-FIRST): a prospective, multicentre, paired diagnostic study. Lancet Oncol 20:100\u2013109","journal-title":"Lancet Oncol"},{"key":"12114_CR4","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.1001\/jamaoncol.2018.4160","volume":"4","author":"SJ Kim","year":"2018","unstructured":"Kim SJ, Vickers AJ, Hu JC (2018) Challenges in adopting level 1 evidence for multiparametric magnetic resonance imaging as a biomarker for prostate cancer screening. JAMA Oncol 4:1663\u20131664","journal-title":"JAMA Oncol"},{"key":"12114_CR5","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1016\/j.ultrasmedbio.2018.02.014","volume":"44","author":"D Rohrbach","year":"2018","unstructured":"Rohrbach D, Wodlinger B, Wen J, Mamou J, Feleppa E (2018) High-frequency quantitative ultrasound for imaging prostate cancer using a novel micro-ultrasound scanner. Ultrasound Med Biol 44:1341\u20131354","journal-title":"Ultrasound Med Biol"},{"key":"12114_CR6","doi-asserted-by":"publisher","first-page":"2811","DOI":"10.1007\/s00345-020-03103-4","volume":"38","author":"AW Postema","year":"2020","unstructured":"Postema AW, Gayet MCW, van Sloun RJG et al (2020) Contrast-enhanced ultrasound with dispersion analysis for the localization of prostate cancer: correlation with radical prostatectomy specimens. World J Urol 38:2811\u20132818","journal-title":"World J Urol"},{"key":"12114_CR7","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1097\/JU.0000000000000415","volume":"202","author":"CK Mannaerts","year":"2019","unstructured":"Mannaerts CK, Wildeboer RR, Remmers S et al (2019) Multiparametric ultrasound for prostate cancer detection and localization: correlation of B-mode, shear wave elastography and contrast enhanced ultrasound with radical prostatectomy specimens. J Urol 202:1166\u20131173","journal-title":"J Urol"},{"key":"12114_CR8","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1111\/bju.15093","volume":"126","author":"CK Mannaerts","year":"2020","unstructured":"Mannaerts CK, Engelbrecht MRW, Postema AW et al (2020) Detection of clinically significant prostate cancer in biopsy-naive men: direct comparison of systematic biopsy, multiparametric MRI- and contrast-ultrasound-dispersion imaging-targeted biopsy. BJU Int 126:481\u2013493","journal-title":"BJU Int"},{"key":"12114_CR9","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1016\/S1470-2045(22)00016-X","volume":"23","author":"ADR Grey","year":"2022","unstructured":"Grey ADR, Scott R, Shah B et al (2022) Multiparametric ultrasound versus multiparametric MRI to diagnose prostate cancer (CADMUS): a prospective, multicentre, paired-cohort, confirmatory study. Lancet Oncol 23:428\u2013438","journal-title":"Lancet Oncol"},{"key":"12114_CR10","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.euros.2022.12.018","volume":"49","author":"A Jager","year":"2023","unstructured":"Jager A, Postema AW, Mischi M, Wijkstra H, Beerlage HP, Oddens JR (2023) Clinical trial protocol: developing an image classification algorithm for prostate cancer diagnosis on three-dimensional multiparametric transrectal ultrasound. Eur Urol Open Sci 49:32\u201343","journal-title":"Eur Urol Open Sci"},{"key":"12114_CR11","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.eururo.2023.02.025","volume":"84","author":"AW Postema","year":"2023","unstructured":"Postema AW, Jager A, Mischi M, Salomon G (2023) Re: Multiparametric ultrasound versus multiparametric MRI to diagnose prostate cancer (CADMUS): a prospective, multicentre, paired-cohort, confirmatory study. Eur Urol 84:140\u2013141","journal-title":"Eur Urol"},{"key":"12114_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/s40134-021-00382-6","volume":"9","author":"FA Carpagnano","year":"2021","unstructured":"Carpagnano FA, Eusebi L, Carriero S, Giannubilo W, Bartelli F, Guglielmi G (2021) Prostate cancer ultrasound: is still a valid tool? Curr Radiol Rep 9:7","journal-title":"Curr Radiol Rep"},{"key":"12114_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105316","volume":"189","author":"RR Wildeboer","year":"2020","unstructured":"Wildeboer RR, van Sloun RJG, Wijkstra H, Mischi M (2020) Artificial intelligence in multiparametric prostate cancer imaging with focus on deep-learning methods. Comput Methods Programs Biomed 189:105316","journal-title":"Comput Methods Programs Biomed"},{"key":"12114_CR14","volume":"211","author":"DL van den Kroonenberg","year":"2024","unstructured":"van den Kroonenberg DL, Jager A, Postema AW, de Bie K, Hagens MJ, Wijkstra H (2024) Development of a computer aided diagnosis system using multiparametric transrectal ultrasound for the localization of clinically significant prostate cancer. J Urol 211:e491","journal-title":"J Urol"},{"key":"12114_CR15","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.euros.2025.03.005","volume":"75","author":"DL van den Kroonenberg","year":"2025","unstructured":"van den Kroonenberg DL, Delberghe FT, Jager A et al (2025) Development and validation of an algorithm for segmentation of the prostate and its zones from three-dimensional transrectal multiparametric ultrasound images. Eur Urol Open Sci 75:48\u201354","journal-title":"Eur Urol Open Sci"},{"key":"12114_CR16","doi-asserted-by":"publisher","first-page":"1701","DOI":"10.1001\/jama.2024.21772","volume":"332","author":"MR Patel","year":"2024","unstructured":"Patel MR, Balu S, Pencina MJ (2024) Translating AI for the clinician. JAMA 332:1701\u20131702","journal-title":"JAMA"},{"key":"12114_CR17","doi-asserted-by":"publisher","first-page":"3089","DOI":"10.1038\/s41388-023-02826-z","volume":"42","author":"I El Naqa","year":"2023","unstructured":"El Naqa I, Karolak A, Luo Y et al (2023) Translation of AI into oncology clinical practice. Oncogene 42:3089\u20133097","journal-title":"Oncogene"},{"key":"12114_CR18","doi-asserted-by":"publisher","DOI":"10.1148\/rg.220105","volume":"43","author":"Y Choi","year":"2023","unstructured":"Choi Y, Yu W, Nagarajan MB et al (2023) Translating AI to clinical practice: overcoming data shift with explainability. Radiographics 43:e220105","journal-title":"Radiographics"},{"key":"12114_CR19","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.eururo.2021.12.007","volume":"81","author":"PM Willemse","year":"2022","unstructured":"Willemse PM, Davis NF, Grivas N et al (2022) Systematic review of active surveillance for clinically localised prostate cancer to develop recommendations regarding inclusion of intermediate-risk disease, biopsy characteristics at inclusion and monitoring, and surveillance repeat biopsy strategy. Eur Urol 81:337\u2013346","journal-title":"Eur Urol"},{"key":"12114_CR20","volume":"4","author":"FH Drost","year":"2019","unstructured":"Drost FH, Osses DF, Nieboer D et al (2019) Prostate MRI, with or without MRI-targeted biopsy, and systematic biopsy for detecting prostate cancer. Cochrane Database Syst Rev 4:CD012663","journal-title":"Cochrane Database Syst Rev"},{"key":"12114_CR21","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.euros.2024.06.012","volume":"66","author":"DL van den Kroonenberg","year":"2024","unstructured":"van den Kroonenberg DL, Jager A, Garrido-Utrilla A et al (2024) Clinical validation of multiparametric ultrasound for detecting clinically significant prostate cancer using computer-aided diagnosis: a direct comparison with the magnetic resonance imaging pathway. Eur Urol Open Sci 66:60\u201366","journal-title":"Eur Urol Open Sci"},{"key":"12114_CR22","doi-asserted-by":"publisher","first-page":"e230397","DOI":"10.1001\/jamahealthforum.2023.0397","volume":"4","author":"JM Teno","year":"2023","unstructured":"Teno JM (2023) Garbage in, garbage out-words of caution on big data and machine learning in medical practice. JAMA Health Forum 4:e230397","journal-title":"JAMA Health Forum"},{"key":"12114_CR23","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1038\/s41391-023-00714-x","volume":"27","author":"MJ Hagens","year":"2024","unstructured":"Hagens MJ, Ribbert LLA, Jager A et al (2024) Histopathological concordance between prostate biopsies and radical prostatectomy specimens-implications of transrectal and transperineal biopsy approaches. Prostate Cancer Prostatic Dis 27:312\u2013317","journal-title":"Prostate Cancer Prostatic Dis"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-12114-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-025-12114-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-12114-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T15:19:44Z","timestamp":1774883984000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-025-12114-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,6]]},"references-count":23,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["12114"],"URL":"https:\/\/doi.org\/10.1007\/s00330-025-12114-x","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,6]]},"assertion":[{"value":"3 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 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 D. L. van den Kroonenberg.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"The authors of this manuscript declare relationships with the following companies: Arnoud W. Postema, Auke Jager, and Johannes B. Reitsma are scientific advisors for Angiogenesis Analytics, for which they receive compensation. Anna Garrido-Utrilla is a full-time employee of Angiogenesis Analytics. Harrie P. Beerlage is chief of the clinical board for Angiogenesis Analytics.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Johannes B. Reitsma kindly provided statistical advice for this manuscript.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"Written informed consent was obtained from all subjects (patients) in this study, which explicitly included consent for both the training phase and the retrospective testing phase (the present study).","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"There is no overlap in patient population with previously published studies.","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}