{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T14:16:49Z","timestamp":1788445009637,"version":"build-2803163510"},"reference-count":31,"publisher":"SAGE Publications","issue":"9","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Acta Radiol"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To compare the diagnostic performance of licensed AI software with routine radiologist readings of prostate MRI, using histopathology as the reference standard.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Material and Methods<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In total, 959 patients (mean age = 69.7 \u00b1 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\u20132 and fewer to PI-RADS 3 (\u03ba\u2009=\u20090.388;\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      \u2009&lt;.001). At the PI-RADS \u22653 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 (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      \u2009&lt;.001). ROC performance was comparable (AUC 0.763 vs. 0.739;\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      \u2009=\u2009.28). 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\u201311.51).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/02841851261470455","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T13:42:27Z","timestamp":1785159747000},"page":"765-774","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence in prostate MRI: Comparative diagnostic performance in a high-prevalence cohort"],"prefix":"10.1177","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7612-5137","authenticated-orcid":false,"given":"N\u00e1dia Gon\u00e7alves","family":"Ferreira","sequence":"first","affiliation":[{"name":"University of Oslo"},{"name":"Department of Radiology, Akershus Univesity Hospital, L\u00f8renskog, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5199-4269","authenticated-orcid":false,"given":"Owen Matthew Truscott","family":"Thomas","sequence":"additional","affiliation":[{"name":"Akershus University Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4568-762X","authenticated-orcid":false,"given":"Kjell-Inge","family":"Gjesdal","sequence":"additional","affiliation":[{"name":"Department of Radiology, Akershus Univesity Hospital, L\u00f8renskog, Norway"},{"name":"Sunnm\u00e6re MR-Klinikk, \u00c5lesund, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6749-0890","authenticated-orcid":false,"given":"Stig","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"University of Oslo"},{"name":"Akershus University Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4454-905X","authenticated-orcid":false,"given":"Jan","family":"Oldenburg","sequence":"additional","affiliation":[{"name":"University of Oslo"},{"name":"Akershus University Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5832-1702","authenticated-orcid":false,"given":"Ingrid Fram\u00e5s","family":"Syversen","sequence":"additional","affiliation":[{"name":"Department of Radiology, Akershus Univesity Hospital, L\u00f8renskog, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anders Christian","family":"Hansen","sequence":"additional","affiliation":[{"name":"University of Cambridge, Centre for Mathematical Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9259-1060","authenticated-orcid":false,"given":"Jonn Terje","family":"Geitung","sequence":"additional","affiliation":[{"name":"Department of Radiology, Akershus Univesity Hospital, L\u00f8renskog, Norway"},{"name":"University of Oslo"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,7,27]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(24)00651-2"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.141.6.1101"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)32401-1"},{"key":"e_1_3_2_6_2","unstructured":"EAU Guidelines. Edn. presented at the EAU Annual Congress London 2026. ISBN 978-94-92671-32-5."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2019.02.033"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2015.08.052"},{"key":"e_1_3_2_9_2","article-title":"Update on PI-RADS version 2.1 diagnostic performance benchmarks for prostate MRI: systematic review and meta-analysis","volume":"312","author":"Oerther B","year":"2024","unstructured":"Oerther B, Nedelcu A, Engel H, et al. Update on PI-RADS version 2.1 diagnostic performance benchmarks for prostate MRI: systematic review and meta-analysis. Radiology 2024; 312: e233337.","journal-title":"Radiology"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2020190646"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.euo.2020.02.005"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15111342"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.3390\/cancers17213503"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2025.103228"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240140"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2024.111790"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-024-10795-4"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13223488"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1097\/PAS.0000000000001497"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02295996"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"e_1_3_2_22_2","unstructured":"R Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical computing Vienna Austria 2025. https:\/\/www.R-project.org\/."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1466-8238.2007.00358.x"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(24)00220-1"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.euo.2024.11.001"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2020.03.048"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2014.08.079"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(18)30569-2"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1093\/ptj\/85.3.257"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-023-01386-w"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2019.12.017"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-025-11498-0"}],"container-title":["Acta Radiologica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02841851261470455","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02841851261470455","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02841851261470455","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T13:46:38Z","timestamp":1788443198000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02841851261470455"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":31,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1177\/02841851261470455"],"URL":"https:\/\/doi.org\/10.1177\/02841851261470455","relation":{},"ISSN":["0284-1851","1600-0455"],"issn-type":[{"value":"0284-1851","type":"print"},{"value":"1600-0455","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,27]]}}}