{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:27:02Z","timestamp":1787009222187,"version":"build-2736575974"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:00:00Z","timestamp":1780617600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":74,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Project of Taizhou Science and Technology Bureau in Zhejiang Province","award":["25ywa29"],"award-info":[{"award-number":["25ywa29"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    To address the diagnostic challenge of indeterminate PI-RADS 3 prostate lesions, we developed a non-invasive deep learning radiomics model using multiparametric MRI. This dual-center retrospective study included 382 patients. Lesions on T2WI, DWI, and ADC were segmented and standardized. Deep learning features were extracted via ResNet101, and radiomics features were selected using minimum Redundancy Maximum Relevance (mRMR) and Least Absolute Shrinkage and Selection Operator (LASSO). We built and compared three models: clinical, deep-learning radiomics signature (DLRS), and a combined model. The combined model achieved the highest AUCs (0.951, 0.964, 0.925), significantly outperforming the clinical model (\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.05). The DLRS model also showed high performance (AUCs: 0.946, 0.932, 0.918). The nomogram was well-calibrated, and DCA indicated clinical utility. This mpMRI-based deep learning model accurately differentiates malignant from benign PI-RADS 3 lesions, offering a valuable non-invasive tool to aid clinical decisions and reduce unnecessary biopsies.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-56643-x","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T18:40:41Z","timestamp":1780684841000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning based on multiparametric MRI for differentiating benign from malignant PI-RADS 3 prostate lesions: a dual-center study"],"prefix":"10.1038","volume":"16","author":[{"given":"He","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongfei","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"WeiQun","family":"Ao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingfeng","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binghui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"GuoHua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danjiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,5]]},"reference":[{"key":"56643_CR1","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3322\/caac.21871","volume":"75","author":"RL Siegel","year":"2025","unstructured":"Siegel, R. L., Kratzer, T. B., Giaquinto, A. N., Sung, H. & Jemal, A. Cancer statistics, 2025. CA Cancer J. Clin. 75, 10\u201345. https:\/\/doi.org\/10.3322\/caac.21871 (2025).","journal-title":"CA Cancer J. Clin."},{"key":"56643_CR2","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/j.ejca.2021.07.039","volume":"157","author":"T Dyba","year":"2021","unstructured":"Dyba, T. et al. The European cancer burden in 2020: incidence and mortality estimates for 40 countries and 25 major cancers. Eur. J. Cancer. 157, 308\u2013347. https:\/\/doi.org\/10.1016\/j.ejca.2021.07.039 (2021).","journal-title":"Eur. J. Cancer"},{"key":"56643_CR3","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1038\/s41572-020-00243-0","volume":"7","author":"RJ Rebello","year":"2021","unstructured":"Rebello, R. J. et al. Prostate cancer. Nat. Rev. Dis. Primers. 7, 9. https:\/\/doi.org\/10.1038\/s41572-020-00243-0 (2021).","journal-title":"Nat. Rev. Dis. Primers"},{"key":"56643_CR4","doi-asserted-by":"publisher","first-page":"e929913","DOI":"10.12659\/MSM.929913","volume":"27","author":"M Chen","year":"2021","unstructured":"Chen, M. et al. Diagnosis of Prostate Cancer in Patients with Prostate-Specific Antigen (PSA) in the Gray Area: Construction of 2 Predictive Models. Med. Sci. Monit. 27, e929913. https:\/\/doi.org\/10.12659\/MSM.929913 (2021).","journal-title":"Med. Sci. Monit."},{"key":"56643_CR5","doi-asserted-by":"publisher","first-page":"117955492312011","DOI":"10.1177\/11795549231201122","volume":"17","author":"YH Qian","year":"2023","unstructured":"Qian, Y. H. et al. Evaluating the Role of Morphological Parameters in the Prostate Transition Zone in PHI-Based Predictive Models for Detecting Gray Zone Prostate Cancer. Clin. Med. Insights Oncol. 17, 11795549231201122. https:\/\/doi.org\/10.1177\/11795549231201122 (2023).","journal-title":"Clin. Med. Insights Oncol."},{"key":"56643_CR6","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1056\/NEJMoa1801993","volume":"378","author":"V Kasivisvanathan","year":"2018","unstructured":"Kasivisvanathan, V. et al. MRI-Targeted or Standard Biopsy for Prostate-Cancer Diagnosis. N Engl. J. Med. 378, 1767\u20131777. https:\/\/doi.org\/10.1056\/NEJMoa1801993 (2018).","journal-title":"N Engl. J. Med."},{"key":"56643_CR7","doi-asserted-by":"publisher","first-page":"141","DOI":"10.2214\/AJR.20.24199","volume":"217","author":"R Bhayana","year":"2021","unstructured":"Bhayana, R. et al. PI-RADS Versions 2 and 2.1: Interobserver Agreement and Diagnostic Performance in Peripheral and Transition Zone Lesions Among Six Radiologists. AJR Am. J. Roentgenol. 217, 141\u2013151. https:\/\/doi.org\/10.2214\/AJR.20.24199 (2021).","journal-title":"AJR Am. J. Roentgenol."},{"key":"56643_CR8","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.2214\/AJR.20.23883","volume":"216","author":"CG Wei","year":"2021","unstructured":"Wei, C. G. et al. Diagnostic Accuracy and Interobserver Agreement of PI-RADS Version 2 and Version 2.1 for the Detection of Transition Zone Prostate Cancers. AJR Am. J. Roentgenol. 216, 1247\u20131256. https:\/\/doi.org\/10.2214\/AJR.20.23883 (2021).","journal-title":"AJR Am. J. Roentgenol."},{"key":"56643_CR9","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/s00330-011-2377-y","volume":"22","author":"JO Barentsz","year":"2012","unstructured":"Barentsz, J. O. et al. ESUR prostate MR guidelines 2012. Eur. Radiol. 22, 746\u2013757. https:\/\/doi.org\/10.1007\/s00330-011-2377-y (2012).","journal-title":"Eur. Radiol."},{"key":"56643_CR10","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1111\/1754-9485.12678","volume":"62","author":"M Bastian-Jordan","year":"2018","unstructured":"Bastian-Jordan, M. Magnetic resonance imaging of the prostate and targeted biopsy, Comparison of PIRADS and Gleason grading. J. Med. Imaging Radiat. Oncol. 62, 183\u2013187. https:\/\/doi.org\/10.1111\/1754-9485.12678 (2018).","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"56643_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-07877-y","author":"H Bae","year":"2021","unstructured":"Bae, H. et al. Radiomics analysis of contrast-enhanced CT for classification of hepatic focal lesions in colorectal cancer patients: its limitations compared to radiologists. Eur. Radiol. https:\/\/doi.org\/10.1007\/s00330-021-07877-y (2021).","journal-title":"Eur. Radiol."},{"key":"56643_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-021-05371-7","author":"M Kirienko","year":"2021","unstructured":"Kirienko, M. et al. Radiomics and gene expression profile to characterise the disease and predict outcome in patients with lung cancer. Eur. J. Nucl. Med. Mol. Imaging. https:\/\/doi.org\/10.1007\/s00259-021-05371-7 (2021).","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"56643_CR13","doi-asserted-by":"publisher","first-page":"3519","DOI":"10.1038\/s41598-017-02425-5","volume":"7","author":"SF Yip","year":"2017","unstructured":"Yip, S. F. et al. Associations between radiologist-defined semantic and automatically computed radiomic features in non-small cell lung cancer. Sci. Rep. 7, 3519. https:\/\/doi.org\/10.1038\/s41598-017-02425-5 (2017).","journal-title":"Sci. Rep."},{"key":"56643_CR14","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1016\/j.ejmp.2017.05.071","volume":"38","author":"M Avanzo","year":"2017","unstructured":"Avanzo, M., Stancanello, J. & El Naqa, I. Beyond imaging: The promise of radiomics. Phys. Med. 38, 122\u2013139. https:\/\/doi.org\/10.1016\/j.ejmp.2017.05.071 (2017).","journal-title":"Phys. Med."},{"key":"56643_CR15","doi-asserted-by":"publisher","first-page":"3608","DOI":"10.3390\/cancers15143608","volume":"15","author":"X Jiang","year":"2023","unstructured":"Jiang, X., Hu, Z., Wang, S. & Zhang, Y. Deep Learning for Medical Image-Based Cancer Diagnosis. Cancers 15, 3608. https:\/\/doi.org\/10.3390\/cancers15143608 (2023).","journal-title":"Cancers"},{"key":"56643_CR16","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1148\/radiol.2018180547","volume":"290","author":"S Soffer","year":"2019","unstructured":"Soffer, S. et al. Convolutional Neural Networks for Radiologic Images: A Radiologist\u2019s Guide. Radiology 290, 590\u2013606. https:\/\/doi.org\/10.1148\/radiol.2018180547 (2019).","journal-title":"Radiology"},{"key":"56643_CR17","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.3390\/diagnostics12071565","volume":"12","author":"M Gravina","year":"2022","unstructured":"Gravina, M. et al. Machine Learning and Clinical-Radiological Characteristics for the Classification of Prostate Cancer in PI-RADS 3 Lesions. Diagnostics 12, 1565. https:\/\/doi.org\/10.3390\/diagnostics12071565 (2022).","journal-title":"Diagnostics"},{"key":"56643_CR18","doi-asserted-by":"publisher","first-page":"6304","DOI":"10.3390\/jcm11216304","volume":"11","author":"A Corsi","year":"2022","unstructured":"Corsi, A. et al. Radiomics in PI-RADS 3 Multiparametric MRI for Prostate Cancer Identification: Literature Models Re-Implementation and Proposal of a Clinical-Radiological Model. J. Clin. Med. 11, 6304. https:\/\/doi.org\/10.3390\/jcm11216304 (2022).","journal-title":"J. Clin. Med."},{"key":"56643_CR19","doi-asserted-by":"publisher","first-page":"1466","DOI":"10.1002\/jmri.27692","volume":"54","author":"SJ Hectors","year":"2021","unstructured":"Hectors, S. J. et al. Magnetic Resonance Imaging Radiomics-Based Machine Learning Prediction of Clinically Significant Prostate Cancer in Equivocal PI-RADS 3 Lesions. J. Magn. Reson. Imaging. 54, 1466\u20131473. https:\/\/doi.org\/10.1002\/jmri.27692 (2021).","journal-title":"J. Magn. Reson. Imaging"},{"key":"56643_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2019.02.033","author":"B Turkbey","year":"2019","unstructured":"Turkbey, B. et al. 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. (2019)."},{"key":"56643_CR21","doi-asserted-by":"publisher","first-page":"889","DOI":"10.56434\/j.arch.esp.urol.20247708.125","volume":"77","author":"W Wang","year":"2024","unstructured":"Wang, W. et al. Diagnostic Value Analysis of PI-RADS v2.1 Combined with ADC Values in the Risk Stratification of Prostate Cancer Gleason Scores: A Retrospective Study. Arch. Esp. Urol. 77, 889\u2013896. https:\/\/doi.org\/10.56434\/j.arch.esp.urol.20247708.125 (2024).","journal-title":"Arch. Esp. Urol."},{"key":"56643_CR22","doi-asserted-by":"publisher","first-page":"3600","DOI":"10.1007\/s00330-017-4775-2","volume":"27","author":"Y Iyama","year":"2017","unstructured":"Iyama, Y. et al. Development and validation of a logistic regression model to distinguish transition zone cancers from benign prostatic hyperplasia on multi-parametric prostate MRI. Eur. Radiol. 27, 3600\u20133608. https:\/\/doi.org\/10.1007\/s00330-017-4775-2 (2017).","journal-title":"Eur. Radiol."},{"key":"56643_CR23","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/s00330-024-10890-6","volume":"35","author":"G Agrotis","year":"2025","unstructured":"Agrotis, G. et al. Diagnostic performance of ADC and ADCratio in MRI-based prostate cancer assessment: A systematic review and meta-analysis. Eur. Radiol. 35, 404\u2013416. https:\/\/doi.org\/10.1007\/s00330-024-10890-6 (2025).","journal-title":"Eur. Radiol."},{"key":"56643_CR24","doi-asserted-by":"publisher","first-page":"2351","DOI":"10.1007\/s00330-021-08332-8","volume":"32","author":"M Boschheidgen","year":"2022","unstructured":"Boschheidgen, M. et al. MRI grading for the prediction of prostate cancer aggressiveness. Eur. Radiol. 32, 2351\u20132359. https:\/\/doi.org\/10.1007\/s00330-021-08332-8 (2022).","journal-title":"Eur. Radiol."},{"key":"56643_CR25","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1148\/radiol.15142394","volume":"276","author":"C An","year":"2015","unstructured":"An, C. et al. Single Hepatocellular Carcinoma: Preoperative MR Imaging to Predict Early Recurrence after Curative Resection. Radiology 276, 433\u2013443. https:\/\/doi.org\/10.1148\/radiol.15142394 (2015).","journal-title":"Radiology"},{"key":"56643_CR26","doi-asserted-by":"publisher","first-page":"W253","DOI":"10.2214\/AJR.13.10595","volume":"203","author":"CT Chou","year":"2014","unstructured":"Chou, C. T. et al. Prediction of microvascular invasion of hepatocellular carcinoma: preoperative CT and histopathologic correlation. AJR Am. J. Roentgenol. 203, W253\u2013259. https:\/\/doi.org\/10.2214\/AJR.13.10595 (2014).","journal-title":"AJR Am. J. Roentgenol."},{"key":"56643_CR27","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1002\/med.21846","volume":"42","author":"J Guiot","year":"2022","unstructured":"Guiot, J. et al. A review in radiomics: Making personalized medicine a reality via routine imaging. Med. Res. Rev. 42, 426\u2013440. https:\/\/doi.org\/10.1002\/med.21846 (2022).","journal-title":"Med. Res. Rev."},{"key":"56643_CR28","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.clgc.2018.02.015","volume":"16","author":"W Song","year":"2018","unstructured":"Song, W. et al. Role of PI-RADS Version 2 for Prediction of Upgrading in Biopsy-Proven Prostate Cancer With Gleason Score 6. Clin. Genitourin. Cancer. 16, 281\u2013287. https:\/\/doi.org\/10.1016\/j.clgc.2018.02.015 (2018).","journal-title":"Clin. Genitourin. Cancer"},{"key":"56643_CR29","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1111\/bju.13570","volume":"119","author":"SR Leyh-Bannurah","year":"2017","unstructured":"Leyh-Bannurah, S. R. et al. Primary Gleason pattern upgrading in contemporary patients with D\u2019Amico low-risk prostate cancer: implications for future biomarkers and imaging modalities. BJU Int. 119, 692\u2013699. https:\/\/doi.org\/10.1111\/bju.13570 (2017).","journal-title":"BJU Int."},{"key":"56643_CR30","doi-asserted-by":"publisher","first-page":"4223","DOI":"10.1007\/s00261-020-02678-1","volume":"45","author":"Y Hou","year":"2020","unstructured":"Hou, Y. et al. A radiomics machine learning-based redefining score robustly identifies clinically significant prostate cancer in equivocal PI-RADS score 3 lesions. Abdom. Radiol. 45, 4223\u20134234. https:\/\/doi.org\/10.1007\/s00261-020-02678-1 (2020).","journal-title":"Abdom. Radiol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56643-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56643-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56643-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:00:46Z","timestamp":1787007646000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56643-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,5]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["56643"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-56643-x","relation":{"references":[{"id-type":"doi","id":"10.1016\/j.eururo.2019.02.033","asserted-by":"subject"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,5]]},"assertion":[{"value":"9 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This retrospective study was reviewed and approved by the ethics committees of both participating institutions. The Medical Ethics Committee of Taizhou First People\u2019s Hospital (Approval No. 2024-KY006-01) and the Medical Ethics Committee of Putuo District People\u2019s Hospital, Shanghai (Approval No. 2022-07) approved the study and granted a waiver of informed consent given the retrospective nature of the study and the use of anonymized patient data.","order":2,"name":"Ethics","label":"Ethics statement","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"25757"}}