{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:52:58Z","timestamp":1769748778830,"version":"3.49.0"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"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. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background and objective<\/jats:title>\n                    <jats:p>Accurate prostate cancer risk stratification benefits from the fusion of T2-weighted (T2WI) and Apparent Diffusion Coefficient (ADC) MRI. However, patient motion and imaging distortions frequently cause spatial misalignments between these sequences. While radiologists compensate for this via subjective cognitive fusion, the process introduces inter-reader variability and can be particularly challenging in equivocal cases. Conventional fusion models are even more vulnerable, as they require perfect image registration, making them brittle in real-world clinical scenarios. We aimed to develop and validate a deep learning framework that overcomes these limitations by robustly fusing unregistered mpMRI data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed a cohort of 300 consecutive men (mean age, 71.5 \u00b1 7.6 years) who underwent pre-biopsy prostate mpMRI at our institution between January 2021 and May 2023. All included patients had pathologically confirmed prostate cancer, with high-risk prostate cancer, as defined by NCCN guidelines, present in 184 of 300 cases (61.3%). The dataset was partitioned chronologically into a development cohort (n=250) for 5-fold cross-validation and a temporal test cohort (n=50) for independent evaluation. We developed Cross-Modal Optimal Transport Fusion (CMOT-Fusion), a deep learning framework that learns to identify and match diagnostically relevant regions between misaligned T2WI and ADC images. This approach enables robust multimodal fusion without requiring an explicit image registration step.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>For discriminating NCCN high-risk versus low\/intermediate-risk disease among pathologically confirmed prostate cancer cases, CMOT-Fusion achieved a mean Area Under the Curve (AUC) of 0.849 \u00b1 0.034 in 5-fold cross-validation, outperforming single-modality baselines and conventional fusion methods. On an independent test set, the model\u2019s performance remained robust, with an ensemble AUC of 0.824 (95% CI: 0.694\u20130.930; ensemble probability computed as the mean of the five fold-specific model probabilities per patient). As a cohort-specific clinical reference based on routine radiology suspicion scoring, PI-RADS v2.1 achieved an AUC of 0.839 (95% CI: 0.726\u20130.930) on the same test cohort.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our results demonstrate that learning a direct correspondence between unregistered mpMRI sequences significantly improves prostate cancer risk stratification. The proposed CMOT-Fusion framework offers a robust solution to the common clinical problem of inter-sequence misalignment, potentially enhancing diagnostic reliability and streamlining clinical workflows by removing the need for a separate image registration step. Given the single-center retrospective design and the small independent test cohort, these findings should be considered exploratory and warrant multi-center prospective validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2025.1700447","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T15:27:01Z","timestamp":1769700421000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust prostate cancer risk stratification from unregistered mpMRI via learned cross-modal correspondence"],"prefix":"10.3389","volume":"15","author":[{"given":"Hanying","family":"Gong","sequence":"first","affiliation":[{"name":"Department of Radiology, The First Hospital of Jiaxing, The Affiliated Hospital of Jiaxing University","place":["Jiaxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Health Care, Jinling Hospital, Medical School of Nanjing University","place":["Nanjing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shufan","family":"Mao","sequence":"additional","affiliation":[{"name":"Perception Vision Medical Technologies Co Ltd","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanchen","family":"Gong","sequence":"additional","affiliation":[{"name":"Jiaxing University Master Degree Cultivation Base, Zhejiang Chinese Medical University","place":["Jiaxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First Hospital of Jiaxing, The Affiliated Hospital of Jiaxing University","place":["Jiaxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First Hospital of Jiaxing, The Affiliated Hospital of Jiaxing University","place":["Jiaxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First Hospital of Jiaxing, The Affiliated Hospital of Jiaxing University","place":["Jiaxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"B1","volume-title":"Prostate cancer: diagnosis and clinical management","author":"Tewari","year":"2013"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.7248","article-title":"The diagnosis and treatment of prostate cancer: a review","volume":"317","author":"Litwin","year":"2017","journal-title":"Jama"},{"key":"B3","doi-asserted-by":"publisher","first-page":"63","DOI":"10.14740\/wjon1191","article-title":"Epidemiology of prostate cancer","volume":"10","author":"Rawla","year":"2019","journal-title":"World J Oncol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.6004\/jnccn.2024.0019","article-title":"Nccn guidelines\u00ae insights: prostate cancer, version 3.2024: featured updates to the nccn guidelines","volume":"22","author":"Schaeffer","year":"2024","journal-title":"J Natl Compr Cancer Network"},{"key":"B5","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41585-019-0212-4","article-title":"Multiparametric mri for prostate cancer diagnosis: current status and future directions","volume":"17","author":"Stabile","year":"2020","journal-title":"Nat Rev Urol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.eururo.2015.08.052","article-title":"Pi-rads prostate imaging\u2013reporting and data system: 2015, version 2","volume":"69","author":"Weinreb","year":"2016","journal-title":"Eur Urol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2019.10.024","article-title":"Multiparametric magnetic resonance imaging for the detection of clinically significant prostate cancer: what urologists need to know. part 2: interpretation","volume":"77","author":"Isra\u00ebl","year":"2020","journal-title":"Eur Urol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2019.09.021","article-title":"Multiparametric magnetic resonance imaging for the detection of clinically significant prostate cancer: what urologists need to know. part 1: acquisition","volume":"77","author":"Engels","year":"2020","journal-title":"Eur Urol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"19805","DOI":"10.1038\/s41598-023-46747-z","article-title":"Addressing image misalignments in multi-parametric prostate mri for enhanced computer-aided diagnosis of prostate cancer","volume":"13","author":"Kovacs","year":"2023","journal-title":"Sci Rep"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2019.10.009","article-title":"Multiparametric magnetic resonance imaging for the detection of clinically significant prostate cancer: what urologists need to know. part 3: targeted biopsy","volume":"77","author":"Venderink","year":"2020","journal-title":"Eur Urol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD012663.pub2","article-title":"Prostate mri, with or without mri-targeted biopsy, and systematic biopsy for detecting prostate cancer","volume":"4","author":"Drost","year":"2019","journal-title":"Cochrane Database Systematic Rev"},{"key":"B12","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1148\/radiol.2020190646","article-title":"Variability of the positive predictive value of pi-rads for prostate mri across 26 centers: experience of the society of abdominal radiology prostate cancer disease-focused panel","volume":"296","author":"Westphalen","year":"2020","journal-title":"Radiology"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2017.12.020","article-title":"Gas-induced susceptibility artefacts on diffusion-weighted mri of the rectum at 1.5 t\u2013effect of applying a micro-enema to improve image quality","volume":"99","author":"van Griethuysen","year":"2018","journal-title":"Eur J Radiol"},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-73480-9_12","article-title":"Deformable mri sequence registration for ai-based prostate cancer diagnosis","volume-title":"International workshop on biomedical image registration","author":"Hering","year":"2024"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13244-021-00990-y","article-title":"Standardisation of prostate multiparametric mri across a hospital network: a london experience","volume":"12","author":"Papoutsaki","year":"2021","journal-title":"Insights into Imaging"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000023817","article-title":"Diagnostic accuracy of different computer-aided diagnostic systems for prostate cancer based on magnetic resonance imaging: A systematic review with diagnostic meta-analysis","volume":"100","author":"Xing","year":"2021","journal-title":"Medicine"},{"key":"B17","doi-asserted-by":"publisher","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":"B18","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-074819","article-title":"Evaluation of clinical prediction models (part 1): from development to external validation","volume":"384","author":"Collins","year":"2024","journal-title":"Bmj"},{"key":"B19","unstructured":"Pv-icurve intelligent radiotherapy contouring system"},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"B21","first-page":"1","article-title":"Introducing transfer learning to 3d resnet-18 for alzheimer\u2019s disease detection on mri images","author":"Ebrahimi","year":"2020"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition. In","author":"He","year":"2016","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit"},{"key":"B23","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"B24","first-page":"06450","article-title":"Layer normalization","volume":"1607","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"B25","doi-asserted-by":"publisher","first-page":"124432","DOI":"10.1016\/j.jmaa.2020.124432","article-title":"Entropic regularization of continuous optimal transport problems","volume":"494","author":"Clason","year":"2021","journal-title":"J Math Anal Appl"},{"key":"B26","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural","volume":"26","author":"Cuturi","year":"2013","journal-title":"Inf Process Syst"},{"key":"B27","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1561\/2200000073","article-title":"Computational optimal transport: With applications to data science","volume":"11","author":"Peyr\u00e9","year":"2019","journal-title":"Foundations Trends\u00ae Mach Learn"},{"key":"B28","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.18.20536","article-title":"Interreader variability of prostate imaging reporting and data system version 2 in detecting and assessing prostate cancer lesions at prostate mri","volume":"212","author":"Greer","year":"2019","journal-title":"Am J Roentgenology"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2017.05.071","article-title":"Beyond imaging: the promise of radiomics","volume":"38","author":"Avanzo","year":"2017","journal-title":"Physica Med"},{"key":"B31","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":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2021.08.019","article-title":"A cascaded deep learning\u2013based artificial intelligence algorithm for automated lesion detection and classification on biparametric prostate magnetic resonance imaging","volume":"29","author":"Mehralivand","year":"2022","journal-title":"Acad Radiol"},{"key":"B33","article-title":"Attention-guided prostate lesion localization and grade group classification with multiple instance learning","author":"Redekop","year":"2022"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)32401-1","article-title":"Diagnostic accuracy of multi-parametric mri and trus biopsy in prostate cancer (promis): a paired validating confirmatory study","volume":"389","author":"Ahmed","year":"2017","journal-title":"Lancet"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1801993","article-title":"Mri-targeted or standard biopsy for prostate-cancer diagnosis","volume":"378","author":"Kasivisvanathan","year":"2018","journal-title":"New Engl J Med"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210064","article-title":"External validation of deep learning algorithms for radiologic diagnosis: a systematic review","volume":"4","author":"Yu","year":"2022","journal-title":"Radiology: Artif Intell"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2010.09.025","article-title":"A reproducible evaluation of ANTs similarity metric performance in brain image registration","volume":"54","author":"Avants","year":"2011","journal-title":"Neuroimage"},{"key":"B39","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/TMI.2009.2035616","article-title":"elastix: A toolbox for intensity-based medical image registration","volume":"29","author":"Klein","year":"2009","journal-title":"IEEE Trans Med Imaging"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30219-3","article-title":"Guidelines for clinical trial protocols for interventions involving artificial intelligence: the spirit-ai extension","volume":"2","author":"Rivera","year":"2020","journal-title":"Lancet Digital Health"},{"key":"B41","doi-asserted-by":"publisher","first-page":"102470","DOI":"10.1016\/j.media.2022.102470","article-title":"Explainable artificial intelligence (xai) in deep learning-based medical image analysis","volume":"79","author":"Van der Velden","year":"2022","journal-title":"Med Image Anal"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1700447\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T15:27:04Z","timestamp":1769700424000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1700447\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,29]]},"references-count":41,"alternative-id":["10.3389\/fonc.2025.1700447"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1700447","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,29]]},"article-number":"1700447"}}