{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:58:17Z","timestamp":1788998297755,"version":"build-2803163510"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T00:00:00Z","timestamp":1750636800000},"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><jats:title>Background<\/jats:title><jats:p>Microsatellite instability (MSI) is a crucial molecular phenotype in colorectal cancer (CRC), which aids in determining treatment strategies and predicting prognosis. However, existing prediction methods have limitations and are not universally applicable to all patient populations. Consequently, we proposed a hybrid prediction model that integrates pathological and clinical features to predict MSI.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and methods<\/jats:title><jats:p>This study encompassed two patient cohorts: The Cancer Genome Atlas cohort (TCGA set, n = 559), which was divided into training and internal validation subsets at a ratio of 7:3, and the Dongyang CRC cohort (Dongyang set, n = 123), serving as an external testing cohort. Two deep learning approaches\u2014semi-supervised and fully-supervised\u2014were employed to extract features from pathological images. Subsequently, the pathomic signatures derived from these approaches were integrated with clinical features to develop a hybrid model. The hybrid model was assessed using an external validation cohort to determine the area under the curve (AUC). Furthermore, to investigate genes associated with MSI, we performed enrichment analysis and constructed a protein-protein interaction (PPI) network using mRNA sequencing data obtained from the TCGA database.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The fully-supervised pathological model demonstrated promising performance, achieving an AUC of 0.928 in the internal validation cohort, compared to the semi-supervised pathological model\u2019s AUC of 0.786. In the external testing cohort, the model attained an AUC of 0.811. Subsequently, a hybrid model was established, which achieved an AUC of 0.949 in the validation cohort and a robust AUC of 0.862 in the test cohort. Additionally, a nomogram was developed to enhance its clinical applicability. Gene Ontology (GO) analysis identified differentially expressed genes (DEGs) related to MSI status, which were enriched in humoral immune response, among other pathways. Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Set Enrichment Analysis (GSEA) revealed enrichment in pathways such as rheumatoid arthritis. A PPI network identified key hub genes, including IFNG and CD8A.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The fully-supervised model consistently outperformed the semi-supervised model in predicting MSI. Furthermore, the hybrid model, which combines pathological and clinical features, demonstrated strong predictive ability.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2025.1580195","type":"journal-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T04:10:36Z","timestamp":1750651836000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Hybrid model for predicting microsatellite instability in colorectal cancer using hematoxylin &amp; eosin-stained images and clinical features"],"prefix":"10.3389","volume":"15","author":[{"given":"Hangping","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofang","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"101174","DOI":"10.1016\/j.tranon.2021.101174","article-title":"Global colorectal cancer burden in 2020 and projections to 2040","volume":"14","author":"Xi","year":"2021","journal-title":"Transl Oncol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/S2468-1253(21)00426-X","article-title":"The rising tide of early-onset colorectal cancer: a comprehensive review of epidemiology, clinical features, biology, risk factors, prevention, and early detection","volume":"7","author":"Patel","year":"2022","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2022-327736","article-title":"Global burden of colorectal cancer in 2020 and 2040: incidence and mortality estimates from GLOBOCAN","volume":"72","author":"Morgan","year":"2023","journal-title":"Gut"},{"key":"B4","first-page":"97","article-title":"Microsatellite instability in colorectal cancer","volume":"89","author":"De' Angelis","year":"2018","journal-title":"Acta BioMed"},{"key":"B5","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3889\/oamjms.2017.003","article-title":"Mismatch repair proteins and microsatellite instability in colorectal carcinoma (MLH1, MSH2, MSH6 and PMS2): histopathological and immunohistochemical study","volume":"5","author":"Ismael","year":"2017","journal-title":"Open Access Maced J Med Sci"},{"key":"B6","doi-asserted-by":"publisher","first-page":"197","DOI":"10.3390\/ijms18010197","article-title":"Colorectal carcinoma: A general overview and future perspectives in colorectal cancer","volume":"18","author":"Marmol","year":"2017","journal-title":"Int J Mol Sci"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2796","DOI":"10.3390\/cancers16162796","article-title":"Exploring predictive and prognostic biomarkers in colorectal cancer: A comprehensive review","volume":"16","author":"Ashouri","year":"2024","journal-title":"Cancers (Basel)"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1038\/nrclinonc.2009.237","article-title":"Microsatellite instability in colorectal cancer-the stable evidence","volume":"7","author":"Vilar","year":"2010","journal-title":"Nat Rev Clin Oncol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.7150\/thno.49864","article-title":"Development and interpretation of a pathomics-based model for the prediction of microsatellite instability in Colorectal Cancer","volume":"10","author":"Cao","year":"2020","journal-title":"Theranostics"},{"key":"B10","doi-asserted-by":"publisher","first-page":"6695","DOI":"10.1038\/s41467-023-42453-6","article-title":"Validation of MSIntuit as an AI-based pre-screening tool for MSI detection from colorectal cancer histology slides","volume":"14","author":"Saillard","year":"2023","journal-title":"Nat Commun"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1093\/annonc\/mdz116","article-title":"ESMO recommendations on microsatellite instability testing for immunotherapy in cancer, and its relationship with PD-1\/PD-L1 expression and tumour mutational burden: a systematic review-based approach","volume":"30","author":"Luchini","year":"2019","journal-title":"Ann Oncol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1038\/s41571-019-0252-y","article-title":"Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology","volume":"16","author":"Bera","year":"2019","journal-title":"Nat Rev Clin Oncol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"051802","DOI":"10.1117\/1.JMI.10.5.051802","article-title":"Artificial intelligence and digital pathology: clinical promise and deployment considerations","volume":"10","author":"Zarella","year":"2023","journal-title":"J Med Imaging (Bellingham)"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e1796","DOI":"10.1002\/cnr2.1796","article-title":"Artificial intelligence and digital biomarker in precision pathology guiding immune therapy selection and precision oncology","volume":"6","author":"Huss","year":"2023","journal-title":"Cancer Rep (Hoboken)"},{"key":"B15","doi-asserted-by":"publisher","first-page":"698","DOI":"10.3348\/kjr.2022.0765","article-title":"Developing and evaluating deep learning algorithms for object detection: key points for achieving superior model performance","volume":"24","author":"Oh","year":"2023","journal-title":"Korean J Radiol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"2197","DOI":"10.3390\/mi13122197","article-title":"Application of deep learning in histopathology images of breast cancer: A review","volume":"13","author":"Zhao","year":"2022","journal-title":"Micromachines (Basel)"},{"key":"B17","doi-asserted-by":"publisher","first-page":"100914","DOI":"10.1016\/j.xcrm.2022.100914","article-title":"Predicting colorectal cancer microsatellite instability with a self-attention-enabled convolutional neural network","volume":"4","author":"Chang","year":"2023","journal-title":"Cell Rep Med"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1038\/nature11252","article-title":"Comprehensive molecular characterization of human colon and rectal cancer","volume":"487","year":"2012","journal-title":"Nature"},{"key":"B19","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1016\/j.ccell.2018.03.010","article-title":"Comparative molecular analysis of gastrointestinal adenocarcinomas","volume":"33","author":"Liu","year":"2018","journal-title":"Cancer Cell"},{"key":"B20","first-page":"2009","article-title":"A method for normalizing histology slides for quantitative analysis","author":"Macenko","year":"2009"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-21-1935","article-title":"Immunotherapy of MSI cancer: facts and hopes","volume":"30","author":"Wilbur","year":"2024","journal-title":"Clin Cancer Res"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.trecan.2023.07.002","article-title":"Tumor-agnostic drug development in dMMR\/MSI-H solid tumors","volume":"9","author":"Bhamidipati","year":"2023","journal-title":"Trends Cancer"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2017699","article-title":"Pembrolizumab in microsatellite-Instability-High advanced colorectal cancer","volume":"383","author":"Andre","year":"2020","journal-title":"N Engl J Med"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2023.02.016","article-title":"Pembrolizumab for previously treated, microsatellite instability-high\/mismatch repair-deficient advanced colorectal cancer: final analysis of KEYNOTE-164","volume":"186","author":"Le","year":"2023","journal-title":"Eur J Cancer"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-023-14103-0","article-title":"Heterogeneity and adjuvant therapeutic approaches in MSI-H\/dMMR resectable gastric cancer: emerging trends in immunotherapy","volume":"30","author":"Wu","year":"2023","journal-title":"Ann Surg Oncol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1080\/14737140.2024.2367472","article-title":"Immunotherapy in MMR-d\/MSI-H recurrent\/metastatic endometrial cancer","volume":"24","author":"Pacholczak-Madej","year":"2024","journal-title":"Expert Rev Anticancer Ther"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/s12029-023-01003-5","article-title":"Management of microsatellite instability high (MSI-H) gastroesophageal adenocarcinoma","volume":"55","author":"Zhou","year":"2024","journal-title":"J Gastrointest Cancer"},{"key":"B28","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1002\/path.v256.1","article-title":"Weakly supervised annotation-free cancer detection and prediction of genotype in routine histopathology","volume":"256","author":"Schrammen","year":"2022","journal-title":"J Pathol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.ctrv.2016.10.005","article-title":"The evolving role of microsatellite instability in colorectal cancer: A review","volume":"51","author":"Gelsomino","year":"2016","journal-title":"Cancer Treat Rev"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1007\/s10147-021-01968-y","article-title":"Clinicopathological features of sporadic MSI colorectal cancer and Lynch syndrome: a single-center retrospective cohort study","volume":"26","author":"Nakayama","year":"2021","journal-title":"Int J Clin Oncol"},{"key":"B31","doi-asserted-by":"publisher","first-page":"3428945","DOI":"10.1155\/2020\/3428945","article-title":"PD-1 inhibitor therapy in a patient with preexisting P-ANCA vasculitis: A case report and review of the literature","volume":"2020","author":"Ramos","year":"2020","journal-title":"Case Rep Oncol Med"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.4143\/crt.2024.317","article-title":"Effector function characteristics of exhausted CD8+ T-cell in microsatellite stable and unstable gastric cancer","volume":"56","author":"Han","year":"2024","journal-title":"Cancer Res Treat"},{"key":"B33","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1186\/s12967-024-04973-7","article-title":"Comparing anti-tumor and anti-self immunity in a patient with melanoma receiving immune checkpoint blockade","volume":"22","author":"Chen","year":"2024","journal-title":"J Transl Med"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1580195\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T04:10:37Z","timestamp":1750651837000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1580195\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":33,"alternative-id":["10.3389\/fonc.2025.1580195"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1580195","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,23]]},"article-number":"1580195"}}