{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T23:07:18Z","timestamp":1787785638244,"version":"build-2784847793"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Urol."],"abstract":"<jats:sec>\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>The diagnosis of prostate cancer and prostatitis becomes challenging when using biparametric Magnetic Resonance (MR) images. This research investigates deep learning models to assess their capability for improving diagnostic accuracy and assisting radiologists.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study analyzed 153 patients who received histopathological diagnoses of prostate cancer or prostatitis between January 2017 and December 2023. Patients were categorized according to PI-RADS scores, and both T2A and ADC-DWI (Apparent Diffusion Coefficient\u2013Diffusion-Weighted Imaging) sequences were examined. Expert radiologists labeled the images prior to lesion detection with the Faster R-CNN (Faster Region-based Convolutional Neural Network) model. Nine different classification models were trained using normal and augmented datasets to evaluate their performance. Model reliability was further assessed through cross-validation and statistical significance testing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The Faster R-CNN model achieved 96% accuracy (95% CI: 93.2\u201398.8%) for P5 and 99% accuracy (95% CI: 96.7\u2013100%) for prostatitis in T2A sequences, and 90% accuracy (95% CI: 85.4\u201394.6%) for P5 and 97% accuracy (95% CI: 93.8\u2013100%) for prostatitis in ADC-DWI sequences. However, the model failed to effectively detect P4 lesions (0% sensitivity in T2A and 30% in ADC-DWI). The model demonstrated comparable performance to expert radiologists, with no significant difference in overall P5 detection (p &amp;gt; 0.05), and Cohen\u2019s kappa indicated substantial agreement (\u03ba = 0.86). The classification models achieved up to 97% accuracy with InceptionV3 in T2A sequences and up to 99% accuracy with DenseNet201 in ADC-DWI sequences. To further evaluate discriminative performance, AUROC values were calculated for all classification models. In T2A sequences, AUROC scores were DenseNet201 (0.98), EfficientNetV2L (0.99), InceptionV3 (0.99), MobileNetV2 (0.92), NASNetLarge (0.83), ResNet50 (0.76), VGG16 (0.98), VGG19 (0.97), and Xception (0.96). In ADC-DWI sequences, AUROC values were DenseNet201 (0.99), EfficientNetV2L (0.96), InceptionV3 (0.99), MobileNetV2 (0.82), NASNetLarge (0.90), ResNet50 (0.64), VGG16 (0.96), VGG19 (0.86), and Xception (0.97), reinforcing the superior discriminative ability of DenseNet201 and InceptionV3 across modalities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The deep learning models demonstrated promising diagnostic capabilities, comparable to radiologists, in distinguishing prostatitis and P5 prostate cancer lesions. Overall, the findings suggest that AI-based diagnostic tools hold potential as clinical decision support systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fruro.2025.1726795","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T05:27:54Z","timestamp":1768800474000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Lesion detection using artificial intelligence models in MR images of prostate cancer and prostatitis patients and comparison of model performance"],"prefix":"10.3389","volume":"5","author":[{"given":"Muhammed","family":"Kaya","sequence":"first","affiliation":[{"name":"Faculty of Medicine, Recep Tayyip Erdo\u011fan University","place":["Rize, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osman","family":"Durdag","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Ataturk University","place":["Erzurum, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Merve","family":"Solak","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Recep Tayyip Erdo\u011fan University","place":["Rize, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmet","family":"Coskuncay","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Ataturk University","place":["Erzurum, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gulen","family":"Burakgazi","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Recep Tayyip Erdo\u011fan University","place":["Rize, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1473\u20131480","DOI":"10.15585\/mmwr.mm6941a1","article-title":"Prostate cancer incidence and survival, by stage and race\/ethnicity \u2014 United states, 2001\u20132017","volume":"69","author":"Siegel","year":"2020","journal-title":"Morbidity Mortality Weekly Rep"},{"key":"B2","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.juro.2016.05.026","article-title":"Re: molecular imaging of prostate cancer","volume":"196","author":"Siegel","year":"2016","journal-title":"J Urol"},{"key":"B3","article-title":"Detection of prostatic carcinoma: the role of TRUS, TRUS guided biopsy, digital rectal examination, PSA and PSA density","volume":"20","author":"Men","year":"2001","journal-title":"J\u00a0Exp Clin Cancer Research: CR"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.18231\/j.ijcbr.2024.037","article-title":"Comparing the effectiveness of digital rectal examination, prostate specific antigen, and TRUS guided prostate biopsy, in the detection of prostate cancer","volume":"11","author":"Krishna","year":"2025","journal-title":"Int J Clin Biochem Res"},{"key":"B5","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/s41972-021-00128-8","article-title":"Der transrektale ultraschall (TRUS) in der urologischen praxis","volume":"28","author":"Enzmann","year":"2021","journal-title":"J f\u00fcr Urologie und Urogyn\u00e4kologie\/\u00d6sterreich"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/S0302-2838(03)00320-8","article-title":"Multiple vesico-urethral biopsies following radical prostatectomy: the predictive rroles of TRUS, DRE, PSA and the pathological stage","volume":"44","author":"Scattoni","year":"2003","journal-title":"Eur Urol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"14","DOI":"10.36648\/2254-6081.8.4.14","article-title":"High levels of the PSA (Prostate specific antigen) in patients with benign prostatic hyperplasia and prostate cancer","volume":"8","author":"Bansal","year":"2021","journal-title":"Arch Cancer Res"},{"key":"B8","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1111\/J.1464-410X.1995.TB07830.X","article-title":"Prostate-specific antigen density: correlation with histological diagnosis of prostate cancer, benign prostatic hyperplasia and prostatitis","volume":"76","author":"Van Iersel","year":"1995","journal-title":"Br J Urol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1158\/1055-9965.EPI-22-0443","article-title":"Association of prostate-specific antigen levels with prostate cancer risk in a multiethnic population: stability over time and comparison with polygenic risk score","volume":"31","author":"Chou","year":"2022","journal-title":"Cancer Epidemiology Biomarkers Prevention: A Publ Am Assoc Cancer Research Cosponsored by Am Soc Prev Oncol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.clgc.2024.102162","article-title":"PSA levels and mortality in prostate cancer patients","volume":"22","author":"Jehle","year":"2024","journal-title":"Clin Genitourin Cancer"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1109\/58.503779","article-title":"Typing of prostate tissue by ultrasonic spectrum analysis","volume":"43","author":"Feleppa","year":"1996","journal-title":"IEEE Trans Ultrasonics Ferroelectrics Frequency Control"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2015.33.7_SUPPL.51","article-title":"How reliable is a negative MRI\/TRUS fusion biopsy? The predictive value of targeted biopsy for prostate cancer","volume":"33","author":"Fascelli","year":"2015","journal-title":"J Clin Oncol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2014.06.026","article-title":"Negative predictive value of multiparametric MRI for prostate cancer detection: outcome of 5-year follow-up in men with negative findings on initial MRI studies","volume":"83","author":"Itatani","year":"2014","journal-title":"Eur J Radiol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25391","article-title":"Quantitative diffusion-weighted imaging and dynamic contrast-enhanced characterization of the index lesion with multiparametric MRI in prostate cancer patients","volume":"45","author":"Yuan","year":"2017","journal-title":"J Magnetic Resonance Imaging"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.22514\/jomh.2023.138","article-title":"Value of dynamic contrast-enhanced MRI and DWI in diagnosis of prostate cancer and its pathological comparison","volume":"19","author":"Shen","year":"2023","journal-title":"J Men's Health"},{"key":"B16","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.crad.2016.09.011","article-title":"Dynamic contrast-enhanced imaging has limited added value over T2-weighted imaging and diffusion-weighted imaging when using PI-radsv2 for diagnosis of clinically significant prostate cancer in patients with elevated PSA","volume":"72","author":"De Visschere","year":"2017","journal-title":"Clin Radiol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2020.01.031","article-title":"Quality of prostate MRI: is the PI-RADS standard sufficient","volume":"28","author":"Sackett","year":"2020","journal-title":"Acad Radiol"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.euf.2018.10.008","article-title":"Accuracy and variability of prostate multiparametric magnetic resonance imaging interpretation using the prostate imaging reporting and data system: A blinded comparison of radiologists","volume":"6","author":"Pickersgill","year":"2020","journal-title":"Eur Urol Focus"},{"key":"B19","doi-asserted-by":"publisher","first-page":"2370\u20132378","DOI":"10.1007\/s00261-023-03917-x","article-title":"Prostate imaging-reporting and data system version 2 has improved biopsy tumor grade accuracy: A single, tertiary institutional experience","volume":"48","author":"Park","year":"2023","journal-title":"Abdominal Radiol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1097\/CM9.0000000000003689","article-title":"Artificial intelligence in prostate cancer","volume":"138","author":"Li","year":"2025","journal-title":"Chin Med J"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1093\/ajcp\/aqad182","article-title":"Artificial intelligence-based algorithms for the diagnosis of prostate cancer: A systematic review","volume":"161","author":"Marletta","year":"2024","journal-title":"Am J Clin Pathol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"5595","DOI":"10.3390\/cancers14225595","article-title":"Artificial intelligence for clinical diagnosis and treatment of prostate cancer","volume":"14","author":"Rabaan","year":"2022","journal-title":"Cancers"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-09433-2","article-title":"The added value of AI-based computer-aided diagnosis in classification of cancer at prostate MRI","volume":"33","author":"Liu","year":"2023","journal-title":"Eur Radiol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1038\/s41585-019-0193-3","article-title":"A new era: artificial intelligence and machine learning in prostate cancer","volume":"16","author":"Goldenberg","year":"2019","journal-title":"Nat Rev Urol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-med-053117-123215","article-title":"Prostate magnetic resonance imaging: lesion detection and local staging","volume":"70","author":"Turkbey","year":"2019","journal-title":"Annu Rev Med"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e0217702","DOI":"10.1371\/journal.pone.0217702","article-title":"Radiomics and machine learning of multisequence multiparametric prostate MRI: towards improved non-invasive prostate cancer characterization","volume":"14","author":"Toivonen","year":"2019","journal-title":"PloS One"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2020.03.002","article-title":"Additional value of dynamic contrast-enhanced sequences in multiparametric prostate magnetic resonance imaging: data from the PROMIS study","volume":"78","author":"Bosaily","year":"2020","journal-title":"Eur Urology"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105866","article-title":"Lung nodule detection based on faster R-CNN framework","volume":"200","author":"Su","year":"2021","journal-title":"Comput Methods Programs Biomedicine"},{"key":"B29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICASET.2019.8714263","article-title":"Brain tumor classification and segmentation using faster R-CNN","volume-title":"2019 Advances in Science and Engineering Technology International Conferences (ASET)","author":"Kaldera","year":"2019"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3128942","article-title":"Pulmonary nodule detection based on faster R-CNN with adaptive anchor box","volume":"9","author":"Nguyen","year":"2021","journal-title":"IEEE Access"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JSEN.2020.3036005","article-title":"A new approach to polyp detection by pre-processing of images and enhanced faster R-CNN","volume":"11","author":"Qian","year":"2020","journal-title":"IEEE Sensors J"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06417-z","article-title":"Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network","volume":"30","author":"Aldoj","year":"2020","journal-title":"Eur Radiol"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019190938","article-title":"Classification of cancer at prostate MRI: deep learning versus clinical PI-RADS assessment","volume":"293","author":"Schelb","year":"2019","journal-title":"Radiology"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.11.7634","article-title":"The clinical value of diffusion-weighted imaging in combination with T2-weighted imaging in diagnosing prostate carcinoma: A systematic review and meta-analysis","volume":"199","author":"Wu","year":"2012","journal-title":"Am J Roentgenology"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/5497120","article-title":"Light weighted healthcare CNN model to detect prostate cancer on multiparametric MRI","volume":"2022","author":"Soni","year":"2022","journal-title":"Comput Intell Neurosci"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13040806","article-title":"Diagnostic performance evaluation of multiparametric magnetic resonance imaging in the detection of prostate cancer with supervised machine learning methods","volume":"13","author":"Nematollahi","year":"2023","journal-title":"Diagnostics"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16557","article-title":"Prostate cancer detection and segmentation on MRI using non-local mask R-CNN with histopathological ground truth","volume":"50","author":"Dai","year":"2023","journal-title":"Med Physics"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102155","article-title":"End-to-End Prostate Cancer Detection in bpMRI via 3D CNNs: Effects of Attention Mechanisms, Clinical Priori and Decoupled False Positive Reduction","volume":"73","author":"Saha","year":"2021","journal-title":"Med Image Analysis"},{"key":"B39","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1186\/s12911-024-02419-0","article-title":"Improved prostate cancer diagnosis using a modified resNet50-based deep learning architecture","volume":"24","author":"Talaat","year":"2024","journal-title":"BMC Med Inf Decision Making"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.5152\/dir.2019.19125","article-title":"Artificial intelligence at the intersection of pathology and radiology in prostate cancer","volume":"25","author":"Harmon","year":"2019","journal-title":"Diagn Interv Radiol"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14010012","article-title":"Classification of clinically significant prostate cancer on multi-parametric MRI: A validation study comparing deep learning and radiomics","volume":"14","author":"Castillo","year":"2022","journal-title":"Cancers"}],"container-title":["Frontiers in Urology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fruro.2025.1726795\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T05:27:55Z","timestamp":1768800475000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fruro.2025.1726795\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":41,"alternative-id":["10.3389\/fruro.2025.1726795"],"URL":"https:\/\/doi.org\/10.3389\/fruro.2025.1726795","relation":{},"ISSN":["2673-9828"],"issn-type":[{"value":"2673-9828","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,19]]},"article-number":"1726795"}}