{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T02:38:59Z","timestamp":1792550339268,"version":"4.5.0"},"reference-count":33,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T00:00:00Z","timestamp":1792454400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T00:00:00Z","timestamp":1792454400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R37CA260346"],"award-info":[{"award-number":["R37CA260346"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["OT2OD038017"],"award-info":[{"award-number":["OT2OD038017"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["OT2OD038065"],"award-info":[{"award-number":["OT2OD038065"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA308887"],"award-info":[{"award-number":["R01CA308887"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bjui-journals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["BJU International"],"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop the magnetic resonance imaging (MRI)\u2010UltraSound UNet (MRUSuNet), a model that uses both MRI and transrectal ultrasonography (TRUS) as input to detect and localise the three\u2010dimensional spatial volume of clinically significant prostate cancer on TRUS images to allow better visualisation of cancer in the TRUS space.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Patients and Methods<\/jats:title>\n                    <jats:p>Pre\u2010biopsy MRI is increasingly used to target suspicious prostate lesions. The lesions identified by radiologists are mapped onto TRUS images to enable real\u2010time targeting during the biopsy. Yet, the misalignment of MRI and TRUS results in sampling errors, and in some cases even missing the clinically significant cancers. This study included two MRI\u2010TRUS fusion biopsy cohorts (3000 patients) for model development, and one radical prostatectomy cohort (110 patients) used for independent validation and for the comparison with radiologist interpretation. A total of 1700 independent cases were reserved to compare the MRUSuNet with single\u2010modality MRI\u2010only and TRUS\u2010only models. Sensitivity and lesion\u2010level Dice similarity scores were computed using targeted biopsy pathology as the reference standard in the biopsy cohorts and whole\u2010mount prostatectomy pathology in the radical prostatectomy cohort.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Result<\/jats:title>\n                    <jats:p>\n                      The MRUSuNet achieved significantly superior sensitivity (0.80) and lesion Dice score (0.42) across all test cohorts compared to the MRI\u2010only model (sensitivity: 0.73,\n                      <jats:italic>P<\/jats:italic>\n                      \u2009=\u20090.033; Dice score: 0.30,\n                      <jats:italic>P<\/jats:italic>\n                      \u2009&lt;\u20090.001) and the TRUS\u2010only model (sensitivity: 0.49,\n                      <jats:italic>P<\/jats:italic>\n                      \u2009&lt;\u20090.001; Dice score: 0.27,\n                      <jats:italic>P<\/jats:italic>\n                      \u2009&lt;\u20090.001). Compared to radiologists in the prostatectomy cohort, the MRUSuNet showed significantly higher specificity (0.88 vs 0.78;\n                      <jats:italic>P<\/jats:italic>\n                      \u2009=\u20090.004) and lesion Dice score (0.32 vs 0.27;\n                      <jats:italic>P<\/jats:italic>\n                      \u2009=\u20090.048), with no observed statistical difference in sensitivity (0.79;\n                      <jats:italic>P<\/jats:italic>\n                      \u2009=\u20091.000).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our findings demonstrate the potential of combining MRI and TRUS in a multimodal artificial intelligence (AI) model to improve localisation of clinically significant prostate cancer on TRUS images relative to single\u2010modality models. These findings support further study of such multimodal AI models as an adjunct to MRI\u2010TRUS fusion workflows.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/bju.70491","type":"journal-article","created":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T01:56:26Z","timestamp":1792547786000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An artificial intelligence model combining\n                    <scp>MRI<\/scp>\n                    and ultrasound images\u00a0(MRUSuNet) for prostate cancer detection outperforms radiologist\n                    <scp>MRI<\/scp>\n                    interpretation"],"prefix":"10.1111","author":[{"given":"Hassan","family":"Jahanandish","sequence":"first","affiliation":[{"name":"Department of Urology Stanford University  Stanford CA USA"},{"name":"Department of Radiology Stanford University  Stanford CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengtian","family":"Sang","sequence":"additional","affiliation":[{"name":"Department of Radiology Stanford University  Stanford CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cynthia Xinran","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computational and Mathematical Engineering Stanford University  Stanford CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sulaiman","family":"Vesal","sequence":"additional","affiliation":[{"name":"Department of Urology Stanford University  Stanford CA USA"},{"name":"Department of Radiology Stanford University  Stanford CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1557-6961","authenticated-orcid":false,"given":"Indrani","family":"Bhattacharya","sequence":"additional","affiliation":[{"name":"Department of Urology Stanford University  Stanford CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1789-8270","authenticated-orcid":false,"given":"Jeong Hoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Radiology Stanford University  Stanford CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajesh","family":"Venkataraman","sequence":"additional","affiliation":[{"name":"Eigen Health Services LLC  Grass Valley CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard E.","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Urology Stanford University  Stanford CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0850-1956","authenticated-orcid":false,"given":"Geoffrey A.","family":"Sonn","sequence":"additional","affiliation":[{"name":"Department of Urology Stanford University  Stanford CA USA"},{"name":"Department of Radiology Stanford University  Stanford CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0372-0367","authenticated-orcid":false,"given":"Mirabela","family":"Rusu","sequence":"additional","affiliation":[{"name":"Department of Urology Stanford University  Stanford CA USA"},{"name":"Department of Radiology Stanford University  Stanford CA USA"},{"name":"Department of Biomedical Data Science Stanford University  Stanford CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,20]]},"reference":[{"key":"e_1_2_12_2_1","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray F","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"e_1_2_12_3_1","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1016\/S0140-6736(16)32401-1","article-title":"Diagnostic accuracy of multi\u2010parametric MRI and TRUS biopsy in prostate cancer (PROMIS): a paired validating confirmatory study","volume":"389","author":"Ahmed HU","year":"2017","journal-title":"Lancet"},{"key":"e_1_2_12_4_1","first-page":"1","article-title":"Trends in pre\u2010biopsy MRI usage for prostate cancer detection, 2007\u20132022","volume":"45","author":"Soerensen SJC","year":"2024","journal-title":"Prostate Cancer Prostatic Dis"},{"key":"e_1_2_12_5_1","doi-asserted-by":"crossref","first-page":"3","DOI":"10.21037\/tau.2017.03.77","article-title":"A critical comparison of techniques for MRI\u2010targeted biopsy of the prostate","volume":"6","author":"Giganti F","year":"2017","journal-title":"Transl Androl Urol"},{"key":"e_1_2_12_6_1","first-page":"1","article-title":"Prostate cancer detection and complications of MRI\u2010targeted prostate biopsy using cognitive registration, software\u2010assisted image fusion or in\u2010bore guidance: a systematic review and meta\u2010analysis of comparative studies","volume":"2","author":"Falagario UG","year":"2024","journal-title":"Prostate Cancer Prostatic Dis"},{"key":"e_1_2_12_7_1","doi-asserted-by":"crossref","first-page":"188","DOI":"10.2214\/AJR.21.26917","article-title":"Artificial intelligence for automated cancer detection on prostate MRI: opportunities and ongoing challenges, from the AJR special series on AI applications","volume":"219","author":"Turkbey B","year":"2022","journal-title":"AJR Am J Roentgenol"},{"key":"e_1_2_12_8_1","doi-asserted-by":"crossref","DOI":"10.1177\/17562872221128791","article-title":"A review of artificial intelligence in prostate cancer detection on imaging","volume":"14","author":"Bhattacharya I","year":"2022","journal-title":"Ther Adv Urol"},{"key":"e_1_2_12_9_1","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1016\/S1470-2045(24)00220-1","article-title":"Artificial intelligence and radiologists in prostate cancer detection on MRI (PI\u2010CAI): an international, paired, non\u2010inferiority, confirmatory study","volume":"25","author":"Saha A","year":"2024","journal-title":"Lancet Oncol"},{"key":"e_1_2_12_10_1","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1109\/TMI.2014.2303821","article-title":"Computer\u2010aided detection of prostate cancer in MRI","volume":"33","author":"Litjens G","year":"2014","journal-title":"IEEE Trans Med Imaging"},{"key":"e_1_2_12_11_1","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/s12880-019-0308-6","article-title":"Comparing radiomic classifiers and classifier ensembles for detection of peripheral zone prostate tumors\u00a0on T2\u2010weighted MRI: a multi\u2010site study","volume":"19","author":"Viswanath SE","year":"2019","journal-title":"BMC Med Imaging"},{"key":"e_1_2_12_12_1","doi-asserted-by":"crossref","first-page":"2960","DOI":"10.1002\/mp.14855","article-title":"Automated detection of aggressive and indolent prostate cancer on magnetic resonance imaging","volume":"48","author":"Seetharaman A","year":"2021","journal-title":"Med Phys"},{"key":"e_1_2_12_13_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102155","article-title":"End\u2010to\u2010end prostate cancer detection in bpMRI via 3D CNNs: effects of attention mechanisms, clinical priori and decoupled false positive reduction","volume":"73","author":"Saha A","year":"2021","journal-title":"Med Image Anal"},{"key":"e_1_2_12_14_1","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.230031","article-title":"Semisupervised learning with report\u2010guided pseudo labels for deep learning\u2010based prostate cancer detection using Biparametric MRI","volume":"5","author":"Bosma JS","year":"2023","journal-title":"Radiol Artif Intell"},{"key":"e_1_2_12_15_1","doi-asserted-by":"crossref","first-page":"103486","DOI":"10.1016\/j.media.2025.103486","article-title":"ProstAtlasDiff: prostate cancer detection on MRI using diffusion probabilistic models guided by population spatial cancer atlases","volume":"101","author":"Li CX","year":"2025","journal-title":"Med Image Anal"},{"key":"e_1_2_12_16_1","doi-asserted-by":"crossref","first-page":"e87","DOI":"10.1097\/PAS.0000000000001497","article-title":"The 2019 International Society of Urological Pathology (ISUP) consensus conference on grading of prostatic carcinoma","volume":"44","author":"Leenders GJLH","year":"2020","journal-title":"Am J Surg Pathol"},{"key":"e_1_2_12_17_1","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.rcl.2017.10.013","article-title":"Future perspectives and challenges of prostate MRI","volume":"56","author":"Turkbey B","year":"2018","journal-title":"Radiol Clin North Am"},{"key":"e_1_2_12_18_1","doi-asserted-by":"crossref","first-page":"37","DOI":"10.11152\/mu-1705","article-title":"MRI\u2010TRUS fusion guided prostate biopsy \u2013 initial experience and assessment of the role of contralateral lobe systematic biopsy","volume":"21","author":"Andras I","year":"2019","journal-title":"Med Ultrason"},{"key":"e_1_2_12_19_1","doi-asserted-by":"crossref","first-page":"2510","DOI":"10.21037\/tau-20-1001","article-title":"Systematic sampling during MRI\u2010US fusion prostate biopsy can overcome errors of targeting\u2014prospective single center experience after 300 cases in first biopsy setting","volume":"9","author":"Cata E","year":"2020","journal-title":"Transl Androl Urol"},{"key":"e_1_2_12_20_1","doi-asserted-by":"crossref","DOI":"10.1259\/bjr.20210633","article-title":"Multiparametric ultrasound and micro\u2010ultrasound in prostate cancer: a comprehensive review","volume":"95","author":"Dias AB","year":"2022","journal-title":"Br J Radiol"},{"key":"e_1_2_12_21_1","unstructured":"VesalS BhattacharyaI JahanandishHet\u00a0al.ProsDectNet: Bridging the Gap in Prostate Cancer Detection via Transrectal B\u2010mode Ultrasound Imaging.2023. Available from:https:\/\/neurips.cc\/virtual\/2023\/82501"},{"key":"e_1_2_12_22_1","first-page":"121","volume-title":"International Workshop on Advances in Simplifying Medical Ultrasound","author":"Bhattacharya I","year":"2023"},{"key":"e_1_2_12_23_1","first-page":"168","volume-title":"Medical Imaging 2024: Ultrasonic Imaging and Tomography [Internet]","author":"Jahanandish H","year":"2024"},{"key":"e_1_2_12_24_1","first-page":"680","volume-title":"Medical Image\u00a0Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October\u00a01, 2021, Proceedings, Part VIII 24","author":"Javadi G","year":"2021"},{"key":"e_1_2_12_25_1","article-title":"ProCUSNet: prostate cancer detection on B\u2010mode transrectal ultrasound using artificial intelligence for targeting during prostate biopsies","volume":"45","author":"Rusu M","year":"2025","journal-title":"Eur Urol Oncol"},{"key":"e_1_2_12_26_1","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/j.future.2021.09.030","article-title":"Prostate cancer classification from ultrasound and MRI images using deep learning based explainable artificial intelligence","volume":"127","author":"Hassan MR","year":"2022","journal-title":"Future Gener Comput Syst"},{"key":"e_1_2_12_27_1","unstructured":"NatarajanS PresterA MargolisD HuangJ MarksLS.Prostate MRI and ultrasound with pathology and coordinates of tracked biopsy (Prostate\u2010MRI\u2010US\u2010Biopsy) [Data set].Cancer Imaging Arch.https:\/\/doi.org\/10.7937\/TCIA.2020.A61IOC1A"},{"key":"e_1_2_12_28_1","first-page":"39","volume-title":"Medical Imaging 2024: Ultrasonic Imaging and Tomography [Internet]","author":"Sang S","year":"2024"},{"key":"e_1_2_12_29_1","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU\u2010net: a self\u2010configuring method for deep learning\u2010based biomedical image segmentation","volume":"18","author":"Isensee F","year":"2021","journal-title":"Nat Methods"},{"key":"e_1_2_12_30_1","volume-title":"Medical Image Computing and Computer\u2010Assisted Intervention \u2013 MICCAI 2016 [Internet]","author":"\u00c7i\u00e7ek \u00d6","year":"2016"},{"key":"e_1_2_12_31_1","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.eururo.2015.08.052","article-title":"PI\u2010RADS prostate imaging\u00a0\u2013 reporting and data system: 2015, version 2","volume":"69","author":"Weinreb JC","year":"2016","journal-title":"Eur Urol"},{"key":"e_1_2_12_32_1","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1016\/j.eururo.2019.02.033","article-title":"Prostate imaging reporting and data system version 2.1: 2019 update of prostate imaging reporting and data system version 2","volume":"76","author":"Turkbey B","year":"2019","journal-title":"Eur Urol"},{"key":"e_1_2_12_33_1","first-page":"29","article-title":"Performance of cognitive vs. image\u2010guided fusion biopsy for detection of overall and clinically significant prostate cancer in a multiethnic population","volume":"42","author":"Ho K","year":"2024","journal-title":"Urol Oncol"},{"key":"e_1_2_12_34_1","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.urology.2023.11.039","article-title":"Prostate cancer detection rate of Transperineal prostate biopsy: cognitive vs software fusion, a multicenter analysis","volume":"186","author":"Hung M","year":"2024","journal-title":"Urology"}],"container-title":["BJU International"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/bjui-journals.onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/bju.70491","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/bjui-journals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/bju.70491","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/bjui-journals.onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/bju.70491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T01:56:31Z","timestamp":1792547791000},"score":1,"resource":{"primary":{"URL":"https:\/\/bjui-journals.onlinelibrary.wiley.com\/doi\/10.1111\/bju.70491"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,20]]},"references-count":33,"alternative-id":["10.1111\/bju.70491"],"URL":"https:\/\/doi.org\/10.1111\/bju.70491","archive":["Portico"],"relation":{},"ISSN":["1464-4096","1464-410X"],"issn-type":[{"value":"1464-4096","type":"print"},{"value":"1464-410X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,20]]},"assertion":[{"value":"2026-10-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"bju.70491"}}