{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T14:19:34Z","timestamp":1788272374978,"version":"build-2803163510"},"reference-count":51,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":2,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100011699","name":"Siemens Healthineers","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011699","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Deep\u2010learning neural network algorithms for detecting prostate cancer in MRI have proliferated in the literature. However, out of 30+ studies published since the PROSTATEx challenge, no studies tested the performance of their algorithm against using true external image data sets (studies came from an outside institution that did not supply any training data to the algorithm) while validating against MR\u2010US fusion biopsy or whole\u2010mount prostatectomy. Using true external data sets paints a much clearer picture of real\u2010world clinical performance of an algorithm.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This work will assess the performance of a published deep learning (DL) neural network algorithm to detect prostate cancer using external studies. The main difference from other studies is the combination of using only MR\u2010US fusion biopsy results as a gold standard; using test data from an institution that did not supply any training data for this version of the algorithm (including studies acquired with an endorectal coil, which were not in the original training set); and comparing the performance of algorithm\u2010generated regions\u2010of\u2010interest (ROIs) versus algorithm heat maps.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Patients were included in the study if they had a prostate MRI with at least one radiologist\u2010drawn target on MRI and underwent MR\u2010US fusion biopsy where the target was sampled for pathological analysis. Patients were excluded if they had any history of prostate cancer treatment, had previously undergone MR\u2010US fusion biopsy at our institution, were missing MRI acquisitions, had artifacts in image sets, or if the study had been shared for future algorithm development. MR image data was assessed using a DL research prototype (XProstate) from Siemens Healthineers that produced (a) ROIs in suspected cancer areas with a level of suspicion (LoS) score and (b) heat maps with LoS scores across the entire gland. The XProstate prototype had been trained with 2170 studies from eight different academic institutions. Clinical radiologist, XProstate ROI, and XProstate Heat Map scores were assessed with ROC analysis using pathology results from biopsy as a gold standard.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      202 unique patients were included for assessment of the XProstate research prototype. The ROC curve for the XProstate Heat Map LoS score generated the highest AUC (0.76, 95% CI: 0.70, 0.82) followed by clinical radiologist PI\u2010RADS score (0.73, 95% CI: 0.68, 0.79) and by XProstate ROI LoS score (0.71, 95% CI: 0.65, 0.77). Neither the XProstate Heat Map (AUC difference\u00a0=\u00a00.03, 95% CI: \u22120.04, 0.10,\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0=\u00a00.38) nor the XProstate ROI (AUC difference\u00a0=\u00a0\u22120.02, 95% CI: \u22120.09, 0.04,\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0=\u00a00.43) was significantly different from the radiologist PI\u2010RADS score.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The XProstate prototype demonstrated equivalent performance as clinical radiologists when presented with de novo cases that would mirror a real\u2010world clinical deployment. The automatic ROI delineation more closely matched clinical radiologist performance when using a cutoff of PI\u2010RADS 5 for annotating suspicious regions. Overall, the XProstate prototype provided reasonable clinical performance and this study demonstrated the need to assess Deep Learning prototypes with external institutional test data.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70614","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T12:45:06Z","timestamp":1785761106000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Real\u2010world assessment of a deep learning neural network algorithm for prostate cancer detection in MRI using true de novo data"],"prefix":"10.1002","volume":"53","author":[{"given":"Steven M.","family":"Shea","sequence":"first","affiliation":[{"name":"Department of Radiology &amp; Medical Imaging, Stritch School of Medicine Loyola University Chicago  Maywood Illinois USA"},{"name":"Parkinson School of Public Health Loyola University Chicago  Maywood Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Wesolowski","sequence":"additional","affiliation":[{"name":"Clinical Research Office, Stritch School of Medicine Loyola University Chicago  Maywood Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdulrahman","family":"Hashem","sequence":"additional","affiliation":[{"name":"Department of Radiology &amp; Medical Imaging, Stritch School of Medicine Loyola University Chicago  Maywood Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ari","family":"Goldberg","sequence":"additional","affiliation":[{"name":"Department of Radiology &amp; Medical Imaging, Stritch School of Medicine Loyola University Chicago  Maywood Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cara","family":"Joyce","sequence":"additional","affiliation":[{"name":"Clinical Research Office, Stritch School of Medicine Loyola University Chicago  Maywood Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gopal","family":"Gupta","sequence":"additional","affiliation":[{"name":"Departments of Urology and Urologic Oncology, Stritch School of Medicine Loyola University Chicago  Maywood Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Grimm","sequence":"additional","affiliation":[{"name":"Research &amp; Clinical Translation, Magnetic Resonance Siemens Healthineers AG  Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heinrich","family":"von Busch","sequence":"additional","affiliation":[{"name":"Strategy &amp; Innovation, Digital &amp; Automation Siemens Healthineers AG  Forchheim Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Lou","sequence":"additional","affiliation":[{"name":"Digital Technology and Innovation Division Siemens Healthineers  Princeton New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Kamen","sequence":"additional","affiliation":[{"name":"Digital Technology and Innovation Division Siemens Healthineers  Princeton New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2100852"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1801993"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2019.05.029"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470\u20102045(18)30569\u20102"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2018.0219"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.euo.2018.03.008"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140\u20106736(16)32401\u20101"},{"key":"e_1_2_8_9_1","unstructured":"RosenkrantzAB ChuS ChoykePL et\u00a0al.ACR Prostate MRI Model Policy.2019.https:\/\/web.archive.org\/web\/20240609143050\/https:\/\/www.acr.org\/\u2010\/media\/ACR\/Files\/Advocacy\/AIA\/Prostate\u2010MRI\u2010Model\u2010Policy72219.pdf"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21654"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.5.4.044501"},{"key":"e_1_2_8_12_1","doi-asserted-by":"crossref","unstructured":"SeahJCY TangJSN KitchenA.Detection of prostate cancer on multiparametric MRI.Proceedings of SPIE \u2010 The International Society for Optical Engineering.ArmatoSG PetrickNA eds2017;10134:1013429. doi:10.1117\/12.2277122","DOI":"10.1117\/12.2277122"},{"key":"e_1_2_8_13_1","doi-asserted-by":"crossref","unstructured":"MehrtashA SedghiA GhafoorianM et\u00a0al.Classification of Clinical Significance of MRI Prostate Findings Using 3D Convolutional Neural Networks.ArmatoSG PetrickNA eds.Proceedings of SPIE \u2010 The International Society for Optical Engineering.2017;10134:101342A. doi:10.1117\/12.2277123","DOI":"10.1117\/12.2277123"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2277121"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2277120"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26047"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2018.08.006"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.5.4.044507"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2789181"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548\u2010019\u201001967\u20105"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13367"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2901928"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00261\u2010018\u20101824\u20105"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010019\u201055972\u20104"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/S10278\u2010018\u20100160\u20101"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019190938"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11571\u2010020\u201009587\u20105"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010019\u201006417\u2010z"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010020\u201007030\u20101"},{"key":"e_1_2_8_30_1","doi-asserted-by":"crossref","unstructured":"SanfordT HarmonSA TurkbeyEB et\u00a0al.Deep\u2010learning\u2010based artificial intelligence for PI\u2010RADS classification to assist multiparametric prostate MRI interpretation: a development study.J Magn Reson Imaging.2020:jmri.27204 doi:10.1002\/jmri.27204","DOI":"10.1002\/jmri.27204"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10110951"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010020\u201007008\u2010z"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2020.2993528"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27595"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010020\u201007086\u2010z"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14855"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000780"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27599"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010021\u201008320\u2010y"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.222276"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470\u20102045(24)00220\u20101"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1002\/pros.24528"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15091141"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232788"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers17050815"},{"key":"e_1_2_8_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010022\u201008978\u2010y"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00261\u2010022\u201003419\u20102"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019192515"},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2015.08.052"},{"key":"e_1_2_8_50_1","first-page":"1355","volume-title":"Proc\u2014Int Symp Biomed Imaging","author":"Yu X","year":"2020"},{"key":"e_1_2_8_51_1","doi-asserted-by":"publisher","DOI":"10.3389\/FNINF.2014.00013"},{"key":"e_1_2_8_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2025.02.008"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70614","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70614","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T13:44:19Z","timestamp":1788270259000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70614"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":51,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1002\/mp.70614"],"URL":"https:\/\/doi.org\/10.1002\/mp.70614","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"2025-08-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70614"}}