{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:14:00Z","timestamp":1793319240265,"version":"4.5.0"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"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<\/jats:title>\n                    <jats:p>Nodal involvement (N stage) is a key prognostic factor in prostate cancer (PCa). Conventional imaging and histopathology often have limited sensitivity and inter-observer variability. AI-based computational pathology, using multi-instance learning (MIL) and foundation models, offers a promising approach for accurate and interpretable N stage prediction from H&amp;amp;E-stained whole slide images (WSIs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this multicenter retrospective study, we developed a weakly supervised deep learning framework integrating MIL with domain-adapted foundation model encoders (UNI-v2, CONCH, ResNet-50) to predict N stage. WSIs from 280 RHWU patients were used for training and 306 TCGA patients for external validation. Attention heatmaps enabled interpretability, while transcriptomic analyses explored molecular correlates via differential expression and bioinformation analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The UNI-v2-based model achieved the highest performance (AUC 0.879 in RHWU, 0.850 in TCGA), surpassing CONCH and ResNet-50. Attention heatmaps highlighted tumor-stromal interfaces and poorly differentiated tumor clusters. Transcriptomic analysis identified 94 differentially expressed genes; upregulated genes were enriched in cell cycle, and immune pathways, while downregulated genes involved ion transport and metabolism.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This AI-MIL framework accurately predicts nodal involvement in PCa and provides biologically interpretable insights, supporting its potential as a precision oncology tool for risk stratification and treatment planning.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1775750","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T05:42:28Z","timestamp":1772602948000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A foundation model-based multi-instance learning framework for accurate prediction of lymph node metastasis in prostate cancer from whole slide images"],"prefix":"10.3389","volume":"16","author":[{"given":"Guang","family":"Zeng","sequence":"first","affiliation":[{"name":"Division of Urology, The Central Hospital of Enshi Tujia and Miao Autonomous Prefecture","place":["Enshi, Hubei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"Li","sequence":"additional","affiliation":[{"name":"Division of Nephrology, The Central Hospital of Enshi Tujia and Miao Autonomous Prefecture","place":["Enshi, Hubei, China"]},{"name":"Hubei Selenium and Human Health Institute, The Central Hospital of Enshi Tujia and Miao Autonomous Prefecture","place":["Enshi, China"]},{"name":"Hubei Provincial Key Lab of Selenium Resources and Bioapplications","place":["Enshi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Mei","sequence":"additional","affiliation":[{"name":"The First Clinical College, Wuhan University","place":["Wuhan, Hubei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Du","sequence":"additional","affiliation":[{"name":"Division of Nephrology, The Central Hospital of Enshi Tujia and Miao Autonomous Prefecture","place":["Enshi, Hubei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3390\/molecules27175730","article-title":"Prostate cancer review: genetics, diagnosis, treatment options, and alternative approaches","volume":"27","author":"Sekhoacha","year":"2022","journal-title":"Molecules"},{"key":"B2","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3322\/caac.21871","article-title":"Cancer statistics, 2025","volume":"75","author":"Siegel","year":"2025","journal-title":"CA: A Cancer J Clin"},{"key":"B3","doi-asserted-by":"publisher","first-page":"100904","DOI":"10.1016\/j.modpat.2025.100904","article-title":"AI-driven screening of equivocal prostate IHC cases: development and validation of a screening and cancer detection framework","author":"Nateghi","year":"2025","journal-title":"Mod Pathol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2024.03.027","article-title":"EAU-EANM-ESTRO-ESUR-ISUP-SIOG guidelines on prostate cancer-2024 update. Part I: screening, diagnosis, and local treatment with curative intent","volume":"86","author":"Cornford","year":"2024","journal-title":"Eur Urol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-5347(05)65177-4","article-title":"Extended pelvic lymphadenectomy in patients undergoing radical prostatectomy: high incidence of lymph node metastasis","volume":"167","author":"Heidenreich","year":"2002","journal-title":"J Urol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.21037\/tau-20-1031","article-title":"Narrative review of management strategies and outcomes in node-positive prostate cancer","volume":"10","author":"D\u2019Rummo","year":"2021","journal-title":"Transl Androl Urol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/s00261-025-05073-w","article-title":"Diagnostic performance of conventional MRI using T1W and T2W for primary lymph node staging in intermediate- and high-risk prostate cancer patients prior to pelvic lymph node dissection","volume":"51","author":"Daouacher","year":"2025","journal-title":"Abdom Radiol (NY)"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2021.3771","article-title":"Diagnostic accuracy of 68Ga-PSMA-11 PET for pelvic nodal metastasis detection prior to radical prostatectomy and pelvic lymph node dissection: A multicenter prospective phase 3 imaging trial","volume":"7","author":"Hope","year":"2021","journal-title":"JAMA Oncol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.euo.2020.08.005","article-title":"Management of patients with node-positive prostate cancer at radical prostatectomy and pelvic lymph node dissection: A systematic review","volume":"3","author":"Marra","year":"2020","journal-title":"Eur Urol Oncol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra2214183","article-title":"Medical artificial intelligence and human values","volume":"390","author":"Yu","year":"2024","journal-title":"N Engl J Med"},{"key":"B11","doi-asserted-by":"publisher","first-page":"102337","DOI":"10.1016\/j.compmedimag.2024.102337","article-title":"Multiple instance learning for digital pathology: A review of the state-of-the-art, limitations & future potential","volume":"112","author":"Gadermayr","year":"2024","journal-title":"Computerized Med Imaging Graphics"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2017.2651164","article-title":"Multiple-instance learning for medical image and video analysis","volume":"10","author":"Quellec","year":"2017","journal-title":"IEEE Rev BioMed Eng"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15235671","article-title":"Integrated genomic analysis of primary prostate tumor foci and corresponding lymph node metastases identifies mutations and pathways associated with metastasis","volume":"15","author":"Moreno","year":"2023","journal-title":"Cancers (Basel)"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02856-4","article-title":"A visual-language foundation model for computational pathology","volume":"30","author":"Lu","year":"2024","journal-title":"Nat Med"},{"key":"B16","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images","volume":"5","author":"Lu","year":"2021","journal-title":"Nat BioMed Eng"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1117\/12.2253887","article-title":"Computer aided analysis of prostate histopathology images to support a refined Gleason grading system","volume":"10133","author":"Ren","year":"2017","journal-title":"Proc SPIE Int Soc Opt Eng"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2875868","article-title":"Path R-CNN for prostate cancer diagnosis and gleason grading of histological images","volume":"38","author":"Li","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"B20","doi-asserted-by":"publisher","first-page":"102076","DOI":"10.1016\/j.artmed.2021.102076","article-title":"A hybrid deep learning approach for gland segmentation in prostate histopathological images","volume":"115","author":"Salvi","year":"2021","journal-title":"Artif Intell Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"101846","DOI":"10.1016\/j.compmedimag.2020.101846","article-title":"WeGleNet: A weakly-supervised convolutional neural network for the semantic segmentation of Gleason grades in prostate histology images","volume":"88","author":"Silva-Rodr\u00edguez","year":"2021","journal-title":"Comput Med Imaging Graph"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30159-X","article-title":"An artificial intelligence algorithm for prostate cancer diagnosis in whole slide images of core needle biopsies: a blinded clinical validation and deployment study","volume":"2","author":"Pantanowitz","year":"2020","journal-title":"Lancet Digit Health"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(19)30739-9","article-title":"Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study","volume":"21","author":"Bulten","year":"2020","journal-title":"Lancet Oncol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(19)30738-7","article-title":"Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study","volume":"21","author":"Str\u00f6m","year":"2020","journal-title":"Lancet Oncol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0508-1","article-title":"Clinical-grade computational pathology using weakly supervised deep learning on whole slide images","volume":"25","author":"Campanella","year":"2019","journal-title":"Nat Med"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01409","article-title":"Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning","volume":"2021","author":"Li","year":"2021","journal-title":"Conf Comput Vis Pattern Recognit Workshops"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2106.00908","article-title":"Transmil: Transformer based correlated multiple instance learning for whole slide image classification","volume":"34","author":"Shao","year":"2021","journal-title":"Adv Neural Inf Process systems"},{"key":"B28","doi-asserted-by":"publisher","first-page":"106340","DOI":"10.1016\/j.compbiomed.2022.106340","article-title":"Automatic diagnosis and grading of Prostate Cancer with weakly supervised learning on whole slide images","volume":"152","author":"Xiang","year":"2023","journal-title":"Comput Biol Med"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1111\/bju.15386","article-title":"Deep learning approach to predict lymph node metastasis directly from primary tumour histology in prostate cancer","volume":"128","author":"Wessels","year":"2021","journal-title":"BJU Int"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1775750\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T05:42:30Z","timestamp":1772602950000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1775750\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"references-count":29,"alternative-id":["10.3389\/fonc.2026.1775750"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1775750","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]},"article-number":"1775750"}}