{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T12:49:25Z","timestamp":1792414165163,"version":"4.4.0"},"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100016275","name":"Seoul National University Bundang Hospital","doi-asserted-by":"publisher","award":["18-2018-0023"],"award-info":[{"award-number":["18-2018-0023"]}],"id":[{"id":"10.13039\/100016275","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016275","name":"Seoul National University Bundang Hospital","doi-asserted-by":"publisher","award":["18-2025-0005"],"award-info":[{"award-number":["18-2025-0005"]}],"id":[{"id":"10.13039\/100016275","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Microsatellite instability, a genetic indication of DNA mismatch impairment, provides promising treatment options. Our study aimed to detect the mutation with whole-slide image (WSI) and discover the most effective pre-trained deep-learning model to sort diagnostic slides between high microsatellite instability (MSI-H) and microsatellite stable (MSS). WSI data retrieved from public dataset were processed for training and evaluating MSI categorization model. We detected MSI in slide levels for colorectal cancer (CRC), stomach adenocarcinoma (STAD), uterine corpus, and endometrial adenocarcinoma (UCEC). Models trained with a single tissue type were evaluated with the test dataset of corresponding tissue and subsequently with the test dataset of other types of tissue (cross-tissue evaluation). Finally, another model trained with multi-tissue types was built to predict the test dataset of individual tissue. Our models achieved AUC values of 0.93, 0.84, and 0.79 in TCGA-CRC, TCGA-STAD and TCGA-UCEC, respectively. We observed that a model trained on a corresponding tumor tissue demonstrates higher accuracy, particularly compared to those trained on other tumor tissues. In the combined model trained on multi-tissue, we observed diverse outcomes regarding which model was prioritized depending on the cancer type. These results demonstrate that models trained on multiple tissues have the potential to discern features that are generalizable across different types of cancer.<\/jats:p>","DOI":"10.1371\/journal.pone.0332034","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:31:11Z","timestamp":1757957471000},"page":"e0332034","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-cancer analysis of histopathologic MSI screening based on digital histology image"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3151-9679","authenticated-orcid":true,"given":"Jin-Ok","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang Yeon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6108-6341","authenticated-orcid":true,"given":"Sejoon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin-Haeng","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,9,15]]},"reference":[{"key":"pone.0332034.ref001","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1186\/s12935-019-1091-8","article-title":"Microsatellite instability: a review of what the oncologist should know","volume":"20","author":"K Li","year":"2020","journal-title":"Cancer Cell Int"},{"issue":"1","key":"pone.0332034.ref002","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/s40425-018-0342-x","article-title":"Significance and implications of FDA approval of pembrolizumab for biomarker-defined disease","volume":"6","author":"MM Boyiadzis","year":"2018","journal-title":"J Immunother Cancer"},{"key":"pone.0332034.ref003","doi-asserted-by":"crossref","first-page":"15180","DOI":"10.1038\/ncomms15180","article-title":"A molecular portrait of microsatellite instability across multiple cancers","volume":"8","author":"I Cortes-Ciriano","year":"2017","journal-title":"Nat Commun"},{"issue":"1","key":"pone.0332034.ref004","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1186\/s13045-019-0738-1","article-title":"Mismatch repair deficiency\/microsatellite instability-high as a predictor for anti-PD-1\/PD-L1 immunotherapy efficacy","volume":"12","author":"P Zhao","year":"2019","journal-title":"J Hematol Oncol"},{"key":"pone.0332034.ref005","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/978-1-4939-9773-2_5","article-title":"Detection of Microsatellite Instability Biomarkers via Next-Generation Sequencing","volume":"2055","author":"R Bonneville","year":"2020","journal-title":"Methods Mol Biol"},{"key":"pone.0332034.ref006","article-title":"Landscape of Microsatellite Instability Across 39 Cancer Types","volume":"2017","author":"R Bonneville","year":"2017","journal-title":"JCO Precis Oncol"},{"key":"pone.0332034.ref007","doi-asserted-by":"crossref","first-page":"101817","DOI":"10.1016\/j.cpsurg.2025.101817","article-title":"Analysis of the clinical tumor stage and survival prognosis of rectal cancer patients on the basis of deep learning and imaging characteristics: An observational study","volume":"69","author":"L Zhang","year":"2025","journal-title":"Curr Probl Surg"},{"issue":"7","key":"pone.0332034.ref008","doi-asserted-by":"crossref","first-page":"78","DOI":"10.3390\/tomography11070078","article-title":"Deep Learning Approaches for Automated Prediction of Treatment Response in Non-Small-Cell Lung Cancer Patients Based on CT and PET Imaging","volume":"11","author":"R Guzm\u00e1n G\u00f3mez","year":"2025","journal-title":"Tomography"},{"issue":"1","key":"pone.0332034.ref009","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1038\/s41698-024-00770-z","article-title":"A universal immunohistochemistry analyzer for generalizing AI-driven assessment of immunohistochemistry across immunostains and cancer types","volume":"8","author":"B Brattoli","year":"2024","journal-title":"NPJ Precis Oncol"},{"issue":"8","key":"pone.0332034.ref010","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1038\/s43018-020-0085-8","article-title":"Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis","volume":"1","author":"Y Fu","year":"2020","journal-title":"Nat Cancer"},{"issue":"1","key":"pone.0332034.ref011","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1097\/PAS.0b013e31817ec2b1","article-title":"Pathologic predictors of microsatellite instability in colorectal cancer","volume":"33","author":"JK Greenson","year":"2009","journal-title":"Am J Surg Pathol"},{"issue":"4","key":"pone.0332034.ref012","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1038\/modpathol.2016.198","article-title":"Morphological characterization of colorectal cancers in The Cancer Genome Atlas reveals distinct morphology-molecular associations: clinical and biological implications","volume":"30","author":"J Shia","year":"2017","journal-title":"Mod Pathol"},{"issue":"7","key":"pone.0332034.ref013","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.1038\/s41591-019-0462-y","article-title":"Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer","volume":"25","author":"JN Kather","year":"2019","journal-title":"Nat Med"},{"issue":"4","key":"pone.0332034.ref014","doi-asserted-by":"crossref","DOI":"10.1053\/j.gastro.2020.06.021","article-title":"Clinical-Grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning","volume":"159","author":"A Echle","year":"2020","journal-title":"Gastroenterology"},{"issue":"1","key":"pone.0332034.ref015","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/S1470-2045(20)30535-0","article-title":"Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study","volume":"22","author":"R Yamashita","year":"2021","journal-title":"Lancet Oncol"},{"issue":"3","key":"pone.0332034.ref016","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1002\/ijc.33599","article-title":"Feasibility of deep learning-based fully automated classification of microsatellite instability in tissue slides of colorectal cancer","volume":"149","author":"SH Lee","year":"2021","journal-title":"Int J Cancer"},{"issue":"5","key":"pone.0332034.ref017","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1002\/path.5028","article-title":"PanCancer insights from The Cancer Genome Atlas: the pathologist\u2019s perspective","volume":"244","author":"LA Cooper","year":"2018","journal-title":"J Pathol"},{"issue":"1","key":"pone.0332034.ref018","doi-asserted-by":"crossref","first-page":"5002","DOI":"10.1038\/s41598-022-08351-5","article-title":"Automated quality assessment of large digitised histology cohorts by artificial intelligence","volume":"12","author":"M Haghighat","year":"2022","journal-title":"Sci Rep"},{"key":"pone.0332034.ref019","first-page":"1107","article-title":"A method for normalizing histology slides for quantitative analysis","author":"M Macenko","year":"2009","journal-title":"2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro"},{"issue":"1","key":"pone.0332034.ref020","doi-asserted-by":"crossref","first-page":"12218","DOI":"10.1038\/s41598-022-16283-3","article-title":"Comparative analysis of high- and low-level deep learning approaches in microsatellite instability prediction","volume":"12","author":"J Park","year":"2022","journal-title":"Sci Rep"},{"issue":"2","key":"pone.0332034.ref021","doi-asserted-by":"crossref","first-page":"100400","DOI":"10.1016\/j.esmoop.2022.100400","article-title":"Artificial intelligence for detection of microsatellite instability in colorectal cancer-a multicentric analysis of a pre-screening tool for clinical application","volume":"7","author":"A Echle","year":"2022","journal-title":"ESMO Open"},{"key":"pone.0332034.ref022","article-title":"A ConvNet for the 2020s","author":"Z Liu","year":"2022","journal-title":"arXiv"},{"key":"pone.0332034.ref023","article-title":"Neighborhood Attention Transformer","author":"A Hassani","year":"2023","journal-title":"arXiv"},{"issue":"1","key":"pone.0332034.ref024","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1097\/PAI.0000000000000264","article-title":"Clinicopathologic Characteristics of Microsatellite Instable Gastric Carcinomas Revisited: Urgent Need for Standardization","volume":"25","author":"M Mathiak","year":"2017","journal-title":"Appl Immunohistochem Mol Morphol"},{"issue":"12","key":"pone.0332034.ref025","article-title":"Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study","volume":"3","author":"M Bilal","year":"2021","journal-title":"Lancet Digit Health"},{"issue":"3","key":"pone.0332034.ref026","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1002\/cjp2.312","article-title":"Predicting microsatellite instability and key biomarkers in colorectal cancer from H&E-stained images: achieving state-of-the-art predictive performance with fewer data using Swin Transformer","volume":"9","author":"B Guo","year":"2023","journal-title":"J Pathol Clin Res"},{"issue":"4","key":"pone.0332034.ref027","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1016\/j.cell.2013.10.015","article-title":"The landscape of microsatellite instability in colorectal and endometrial cancer genomes","volume":"155","author":"T-M Kim","year":"2013","journal-title":"Cell"},{"issue":"5","key":"pone.0332034.ref028","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2024.01.027","article-title":"Pan-cancer proteogenomics characterization of tumor immunity","volume":"187","author":"F Petralia","year":"2024","journal-title":"Cell"},{"issue":"7407","key":"pone.0332034.ref029","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1038\/nature11252","article-title":"Comprehensive molecular characterization of human colon and rectal cancer","volume":"487","author":"Network Cancer Genome Atlas","year":"2012","journal-title":"Nature"},{"issue":"7517","key":"pone.0332034.ref030","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1038\/nature13480","article-title":"Comprehensive molecular characterization of gastric adenocarcinoma","volume":"513","author":"Network Cancer Genome Atlas Research","year":"2014","journal-title":"Nature"},{"issue":"7447","key":"pone.0332034.ref031","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/nature12113","article-title":"Integrated genomic characterization of endometrial carcinoma","volume":"497","author":"Network Cancer Genome Atlas Research","year":"2013","journal-title":"Nature"},{"issue":"4","key":"pone.0332034.ref032","article-title":"Comparative Molecular Analysis of Gastrointestinal Adenocarcinomas","volume":"33","author":"Y Liu","year":"2018","journal-title":"Cancer Cell"},{"issue":"4","key":"pone.0332034.ref033","doi-asserted-by":"crossref","DOI":"10.1016\/j.immuni.2018.03.023","article-title":"The Immune Landscape of Cancer","volume":"48","author":"V Thorsson","year":"2018","journal-title":"Immunity"},{"issue":"1","key":"pone.0332034.ref034","doi-asserted-by":"crossref","DOI":"10.1016\/j.celrep.2018.03.086","article-title":"Spatial Organization and Molecular Correlation of Tumor-Infiltrating Lymphocytes Using Deep Learning on Pathology Images","volume":"23","author":"J Saltz","year":"2018","journal-title":"Cell Rep"},{"key":"pone.0332034.ref035","doi-asserted-by":"crossref","first-page":"100004","DOI":"10.1016\/j.mbplus.2019.04.001","article-title":"Pan-Cancer analysis of the expression and regulation of matrisome genes across 32 tumor types","volume":"1","author":"V Izzi","year":"2019","journal-title":"Matrix Biol Plus"},{"issue":"1","key":"pone.0332034.ref036","doi-asserted-by":"crossref","first-page":"4423","DOI":"10.1038\/s41467-021-24698-1","article-title":"The impact of site-specific digital histology signatures on deep learning model accuracy and bias","volume":"12","author":"FM Howard","year":"2021","journal-title":"Nat Commun"},{"issue":"3","key":"pone.0332034.ref037","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1109\/TBME.2021.3117407","article-title":"Domain Adaptation for Medical Image Analysis: A Survey","volume":"69","author":"H Guan","year":"2022","journal-title":"IEEE Trans Biomed Eng"},{"key":"pone.0332034.ref038","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K Simonyan","year":"2015","journal-title":"arXiv"},{"key":"pone.0332034.ref039","article-title":"Deep Residual Learning for Image Recognition","author":"K He","year":"2015","journal-title":"arXiv"},{"key":"pone.0332034.ref040","article-title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","author":"M Tan","year":"2020","journal-title":"arXiv"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0332034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:31:20Z","timestamp":1757957480000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0332034"}},"subtitle":[],"editor":[{"given":"Hao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"references-count":40,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0332034","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,15]]}}}