{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T01:30:39Z","timestamp":1792200639956,"version":"4.4.0"},"reference-count":34,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:00:00Z","timestamp":1751846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background: Accurate upfront risk stratification in suspected clinically significant prostate cancer (csPCa) may reduce unnecessary prostate biopsies. Integrating clinical and Magnetic Resonance Imaging (MRI) variables using deep learning could improve prediction. Methods: We retrospectively analysed 538 men who underwent MRI and biopsy between April 2019-September 2024. A fully connected neural network was trained using 5-fold cross-validation. Model 1 included clinical features (age, prostate-specific antigen [PSA], PSA density, digital rectal examination, family history, prior negative biopsy, and ongoing therapy). Model 2 used MRI-derived Prostate Imaging Reporting and Data System (PI-RADS) categories. Model 3 used all previous variables as well as lesion size, location, and prostate volume as determined on MRI. Results: Model 3 achieved the highest area under the receiver operating characteristic curve (AUC = 0.822), followed by Model 2 (AUC = 0.778) and Model 1 (AUC = 0.716). Sensitivities for detecting clinically significant prostate cancer (csPCa) were 87.4%, 91.6%, and 86.8% for Models 1, 2, and 3, respectively. Although Model 3 had slightly lower sensitivity than Model 2, it showed higher specificity, reducing false positives and avoiding 43.4% and 21.2% more biopsies compared to Models 1 and 2. Decision curve analysis showed M2 had the highest net benefit at risk thresholds \u2264 20%, while M3 was superior above 20%. Conclusions: Model 3 improved csPCa risk stratification, particularly in biopsy-averse settings, while Model 2 was more effective in cancer-averse scenarios. These models support personalized, context-sensitive biopsy decisions.<\/jats:p>","DOI":"10.3390\/cancers17132257","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T04:43:37Z","timestamp":1751863417000},"page":"2257","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["A Deep Learning Model Integrating Clinical and MRI Features Improves Risk Stratification and Reduces Unnecessary Biopsies in Men with Suspected Prostate Cancer"],"prefix":"10.3390","volume":"17","author":[{"given":"Emiliano","family":"Bacchetti","sequence":"first","affiliation":[{"name":"Institute of Radiology, Department of Medicine (DMED), University of Udine, and University Hospital \u201cSanta Maria della Misericordia\u201d, ASU FC, P.le S. M. Della Misericordia 15, 33100 Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0762-708X","authenticated-orcid":false,"given":"Axel","family":"De Nardin","sequence":"additional","affiliation":[{"name":"Artificial Vision and Machine Learning Laboratory (AVML Lab), Department of Mathematics, Computer Science and Physics (DMIF), University of Udine, Via delle Scienze 206, 33100 Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6995-246X","authenticated-orcid":false,"given":"Gianluca","family":"Giannarini","sequence":"additional","affiliation":[{"name":"Urology Unit, University Hospital \u201cSanta Maria della Misericordia\u201d, ASU FC, P.le S. M. Della Misericordia 15, 33100 Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Cereser","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Department of Medicine (DMED), University of Udine, and University Hospital \u201cSanta Maria della Misericordia\u201d, ASU FC, P.le S. M. Della Misericordia 15, 33100 Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chiara","family":"Zuiani","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Department of Medicine (DMED), University of Udine, and University Hospital \u201cSanta Maria della Misericordia\u201d, ASU FC, P.le S. M. Della Misericordia 15, 33100 Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Crestani","sequence":"additional","affiliation":[{"name":"Urology Unit, Department of Medicine (DMED), University of Udine, and University Hospital \u201cSanta Maria della Misericordia\u201d, ASU FC, P.le S. M. Della Misericordia 15, 33100 Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rossano","family":"Girometti","sequence":"additional","affiliation":[{"name":"Institute of Radiology, Department of Medicine (DMED), University of Udine, and University Hospital \u201cSanta Maria della Misericordia\u201d, ASU FC, P.le S. M. Della Misericordia 15, 33100 Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8425-6892","authenticated-orcid":false,"given":"Gian Luca","family":"Foresti","sequence":"additional","affiliation":[{"name":"Artificial Vision and Real-Time Systems Laboratory (AViReS Lab), Department of Mathematics, Computer Science and Physics (DMIF), University of Udine, Via Delle Scienze 206, 33100 Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.eururo.2024.03.027","article-title":"EAU-EANM-ESTRO-ESUR-ISUP-SIOG guidelines on prostate cancer\u20142024 update. Part I: Screening, diagnosis, and local treatment with curative intent","volume":"86","author":"Cornford","year":"2024","journal-title":"Eur. Urol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1016\/j.eururo.2020.03.048","article-title":"Negative predictive value of multiparametric magnetic resonance imaging in the detection of clinically significant prostate cancer in the prostate imaging reporting and data system era: A systematic review and meta-analysis","volume":"78","author":"Sathianathen","year":"2020","journal-title":"Eur. Urol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1001\/jamaoncol.2024.5497","article-title":"Oncological safety of MRI-informed biopsy decision-making in men with suspected prostate cancer","volume":"11","author":"Hamm","year":"2025","journal-title":"JAMA Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1016\/j.eururo.2024.08.022","article-title":"VISION: An individual patient data meta-analysis of randomised trials comparing magnetic resonance imaging targeted biopsy with standard transrectal ultrasound guided biopsy in the detection of prostate cancer","volume":"87","author":"Kasivisvanathan","year":"2025","journal-title":"Eur. Urol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1016\/j.euo.2020.12.004","article-title":"Positive predictive value of prostate imaging reporting and data system version 2 for the detection of clinically significant prostate cancer: A systematic review and meta-analysis","volume":"4","author":"Mazzone","year":"2021","journal-title":"Eur. Urol. Oncol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1002\/jmri.26220","article-title":"Interreader agreement of PI-RADS v. 2 in assessing prostate cancer with multiparametric MRI: A study using whole-mount histology as the standard of reference","volume":"49","author":"Girometti","year":"2019","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1604","DOI":"10.1002\/jmri.26743","article-title":"Head-to-head comparison between multiparametric MRI, the partin tables, memorial sloan kettering cancer center nomogram, and CAPRA score in predicting extraprostatic cancer in patients undergoing radical prostatectomy","volume":"50","author":"Zanelli","year":"2019","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Osses, D.F., Roobol, M.J., and Schoots, I.G. (2019). Prediction medicine: Biomarkers, risk calculators and magnetic resonance imaging as risk stratification tools in prostate cancer diagnosis. Int. J. Mol. Sci., 20.","DOI":"10.3390\/ijms20071637"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.euo.2018.02.010","article-title":"Prostate cancer risk assessment in biopsy-na\u00efve patients: The Rotterdam prostate cancer risk calculator in multiparametric magnetic resonance imaging-transrectal ultrasound (TRUS) fusion biopsy and systematic TRUS biopsy","volume":"1","author":"Mannaerts","year":"2018","journal-title":"Eur. Urol. Oncol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1097\/JU.0000000000000622","article-title":"External validation and comparison of prostate cancer risk calculators incorporating multiparametric magnetic resonance imaging for prediction of clinically significant prostate cancer","volume":"203","author":"Saba","year":"2020","journal-title":"J. Urol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e001411","DOI":"10.1136\/bmjophth-2023-001411","article-title":"Explainable artificial intelligence model for the detection of geographic atrophy using colour retinal photographs","volume":"8","author":"Sarao","year":"2023","journal-title":"BMJ Open Ophthalmol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Madni, H.A., Shujat, H., De Nardin, A., Zottin, S., and Foresti, G.L. (Int. J. Neural Syst., 2025). Unsupervised Brain MRI Anomaly Detection via Inter-Realization Channels, Int. J. Neural Syst., online ahead of print.","DOI":"10.1142\/S0129065725500479"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.euros.2022.04.017","article-title":"The Mount Sinai prebiopsy risk calculator for predicting any prostate cancer and clinically significant prostate cancer: Development of a risk predictive tool and validation with advanced neural networking, prostate magnetic resonance imaging outcome database, and European randomized study of screening for prostate cancer risk calculator","volume":"41","author":"Parekh","year":"2022","journal-title":"Eur. Urol. Open Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1002\/ijc.10370","article-title":"An artificial neural network considerably improves the diagnostic power of percent free prostate-specific antigen in prostate cancer diagnosis: Results of a 5-year investigation","volume":"99","author":"Stephan","year":"2002","journal-title":"Int. J. Cancer"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1016\/S0090-4295(00)00830-X","article-title":"Performance of a neural network in detecting prostate cancer in the prostate-specific antigen reflex range of 2.5 to 4.0 ng\/mL","volume":"56","author":"Babaian","year":"2000","journal-title":"Urology"},{"key":"ref_16","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","year":"2019","journal-title":"Eur. Urol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1097\/PAS.0000000000000530","article-title":"The 2014 International Society of Urological Pathology (ISUP) consensus conference on Gleason grading of prostatic carcinoma: Definition of grading patterns and proposal for a new grading system","volume":"40","author":"Epstein","year":"2016","journal-title":"Am. J. Surg. Pathol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"5404","DOI":"10.1007\/s00330-020-06929-z","article-title":"ESUR\/ESUI consensus statements on multi-parametric MRI for the detection of clinically significant prostate cancer: Quality requirements for image acquisition, interpretation and radiologists\u2019 training","volume":"30","author":"Tummers","year":"2020","journal-title":"Eur. Radiol."},{"key":"ref_19","unstructured":"Mao, A., Mohri, M., and Zhong, Y. (2023, January 23\u201329). Cross-entropy loss functions: Theoretical analysis and applications. Proceedings of the 40th International Conference on Machine Learning, PMLR, Honolulu, HI, USA."},{"key":"ref_20","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference for Learning Representations, ICLR, San Diego, CA, USA. Poster."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1644","DOI":"10.1007\/s11547-024-01886-9","article-title":"Conceptual Review of Outcome Metrics and Measures Used in Clinical Evaluation of Artificial Intelligence in Radiology","volume":"129","author":"Park","year":"2024","journal-title":"Radiol. Med."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"364","DOI":"10.2214\/ajr.184.2.01840364","article-title":"Fundamentals of Clinical Research for Radiologists: ROC Analysis","volume":"184","author":"Obuchowski","year":"2005","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: A novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med. Decis. Mak."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"9567","DOI":"10.1007\/s00330-021-08021-6","article-title":"ESUR\/ESUI position paper: Developing artificial intelligence for precision diagnosis of prostate cancer using magnetic resonance imaging","volume":"31","author":"Penzkofer","year":"2021","journal-title":"Eur. Radiol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2326","DOI":"10.1007\/s00330-021-08535-z","article-title":"Balancing the benefits and harms of MRI-directed biopsy pathways","volume":"32","author":"Padhani","year":"2022","journal-title":"Eur. Radiol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1111\/bju.16163","article-title":"Performance of magnetic resonance imaging-based prostate cancer risk calculators and decision strategies in two large European medical centres","volume":"133","author":"Davik","year":"2024","journal-title":"BJU Int."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1016\/j.euf.2020.05.002","article-title":"Head-to-head comparison of conventional, and image-and biomarker-based prostate cancer risk calculators","volume":"7","author":"Mortezavi","year":"2021","journal-title":"Eur. Urol. Focus"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.eururo.2018.07.031","article-title":"Prediction of high-grade prostate cancer following multiparametric magnetic resonance imaging: Improving the Rotterdam European randomized study of screening for prostate cancer risk calculators","volume":"75","author":"Alberts","year":"2019","journal-title":"Eur. Urol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4767","DOI":"10.1007\/s00330-017-4858-0","article-title":"MRI findings in men on active surveillance for prostate cancer: Does dutasteride make MRI visible lesions less conspicuous? Results from a placebo-controlled, randomised clinical trial","volume":"27","author":"Giganti","year":"2017","journal-title":"Eur. Radiol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1139","DOI":"10.1097\/JU.0000000000001932","article-title":"Influence of 5-alpha reductase inhibitors on prostate cancer detection with magnetic resonance imaging: A matched cohort study","volume":"206","author":"Purysko","year":"2021","journal-title":"J. Urol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/j.urology.2013.10.007","article-title":"Dutasteride on benign prostatic hyperplasia: A meta-analysis on randomized clinical trials in 6460 patients","volume":"83","author":"Wu","year":"2014","journal-title":"Urology"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"908","DOI":"10.1056\/NEJMoa2100852","article-title":"MRI-Targeted or Standard Biopsy in Prostate Cancer Screening","volume":"385","author":"Eklund","year":"2021","journal-title":"N. Engl. J. Med."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1001\/jama.2024.3841","article-title":"Prostate Cancer Screening with PSA, Kallikrein Panel, and MRI: The ProScreen Randomized Trial","volume":"331","author":"Auvinen","year":"2024","journal-title":"JAMA"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"560857","DOI":"10.1155\/2013\/560857","article-title":"Global patterns of prostate cancer incidence, aggressiveness, and mortality in men of African descent","volume":"2013","author":"Rebbeck","year":"2013","journal-title":"Prostate Cancer"}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/13\/2257\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:05:38Z","timestamp":1760033138000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/13\/2257"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,7]]},"references-count":34,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["cancers17132257"],"URL":"https:\/\/doi.org\/10.3390\/cancers17132257","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,7]]}}}