{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:15:31Z","timestamp":1790640931897,"version":"4.1.0"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"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>Deep learning systems are increasingly used for colorectal cancer detection in digital histopathology, but studies often report heterogeneous endpoints, patch-level metrics, or non-thresholded area under the curve (AUC) values. We estimated the diagnostic accuracy of clinically interpretable slide-level or patient-level models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We searched PubMed, Embase, Scopus, Web of Science Core Collection, and IEEE Xplore for deep learning studies of human colorectal histopathology or whole-slide images. Eligible studies provided extractable or reconstructable slide-level or patient-level true-positive (TP), false-positive (FP), false-negative (FN), and true-negative (TN) values for colorectal cancer, colorectal adenocarcinoma, or closely aligned malignant colorectal histopathology detection. Risk of bias was assessed using QUADAS-2 with AI-pathology-specific considerations. The strict primary synthesis excluded endpoint-caveat cohorts. Summary sensitivity and specificity were estimated using a bivariate random-effects Reitsma model. A second reviewer verified eligibility, 2 x 2 tables, and QUADAS-2 judgments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The search identified 4,687 records; 2,307 unique records were screened. Three source studies contributing 14 validation cohorts met the inclusion criteria for the strict primary synthesis; five additional endpoint-caveat studies contributing seven cohorts were retained only for expanded and sensitivity analyses. Primary cohorts included 5,402 TP, 439 FP, 68 FN, and 3,596 TN. The exploratory bivariate model, which treated cohorts as independent observations, estimated a sensitivity of 0.982 (95% CI, 0.976\u20130.986), a specificity of 0.959 (95% CI, 0.922\u20130.979), and an AUC of 0.979. Wang (2021) contributed 12 of 14 cohorts; within-study correlation could therefore make these confidence intervals overly precise. Sensitivity was stable across scenarios, whereas crude specificity varied with endpoint definition, analysis unit, and large true-negative denominators.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Available cohort-level evidence suggests high sensitivity and strong overall discrimination for colorectal cancer detection on histopathological whole-slide images. However, the exploratory estimates are dominated by one development program and should not be interpreted as a mature, independently replicated, multisource evidence base. Specificity remains vulnerable to endpoint heterogeneity and slide-level calling rules. Current evidence supports the use of deep learning as an adjunct for prescreening, triage, or quality control, rather than as a standalone diagnostic replacement.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1885546","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T13:46:24Z","timestamp":1786974384000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Diagnostic accuracy of deep learning models for colorectal cancer detection in histopathological whole-slide images: a systematic review and diagnostic test accuracy meta-analysis"],"prefix":"10.3389","volume":"16","author":[{"given":"Xiang","family":"Yong","sequence":"first","affiliation":[{"name":"Department of Pathology, Wanbei Coal-Electricity Group General Hospital","place":["Suzhou, Anhui, China"]},{"name":"Suzhou City Key Laboratory of Tumor Pathology","place":["Suzhou, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Pathology, The Affiliated Changsha Hospital of Xiangya School of Medicine, Central South University\/The First Hospital of Changsha","place":["Changsha, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Pathology, The Second Affiliated Hospital of Anhui Medical University","place":["Hefei, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaiyuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Pathology, Wanbei Coal-Electricity Group General Hospital","place":["Suzhou, Anhui, China"]},{"name":"Suzhou City Key Laboratory of Tumor Pathology","place":["Suzhou, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"B2","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":"B3","doi-asserted-by":"publisher","DOI":"10.1038\/s41416-020-01122-x","article-title":"Deep learning in cancer pathology: a new generation of clinical biomarkers","volume":"124","author":"Echle","year":"2021","journal-title":"Br J Cancer"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0462-y","article-title":"Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer","volume":"25","author":"Kather","year":"2019","journal-title":"Nat Med"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/cancers12071884","article-title":"Current trends of artificial intelligence for colorectal cancer pathology image analysis: a systematic review","volume":"12","author":"Thakur","year":"2020","journal-title":"Cancers (Basel)"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2005.02.022","article-title":"Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews","volume":"58","author":"Reitsma","year":"2005","journal-title":"J Clin Epidemiol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxl004","article-title":"A unification of models for meta-analysis of diagnostic accuracy studies","volume":"8","author":"Harbord","year":"2007","journal-title":"Biostatistics"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n71","article-title":"The PRISMA 2020 statement: an updated guideline for reporting systematic reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.19163","article-title":"Preferred reporting items for a systematic review and meta-analysis of diagnostic test accuracy studies: the PRISMA-DTA statement","volume":"319","author":"McInnes","year":"2018","journal-title":"JAMA"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-155-8-201110180-00009","article-title":"QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies","volume":"155","author":"Whiting","year":"2011","journal-title":"Ann Intern Med"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.h5527","article-title":"STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies","volume":"351","author":"Bossuyt","year":"2015","journal-title":"BMJ"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03953-8","article-title":"The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence","volume":"31","author":"Sounderajah","year":"2025","journal-title":"Nat Med"},{"key":"B13","doi-asserted-by":"crossref","DOI":"10.32614\/CRAN.package.mada","article-title":"mada: meta-analysis of diagnostic accuracy","volume-title":"R Package","author":"Doebler","year":""},{"key":"B14","volume-title":"R: A Language and Environment for Statistical Computing","year":"2026"},{"key":"B15","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1186\/s12916-021-01942-5","article-title":"Accurate diagnosis of colorectal cancer based on histopathology images using artificial intelligence","volume":"19","author":"Wang","year":"2021","journal-title":"BMC Med"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajpath.2022.12.003","article-title":"Detection of colorectal adenocarcinoma and grading dysplasia on histopathologic slides using deep learning","volume":"193","author":"Kim","year":"2023","journal-title":"Am J Pathol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1365364","article-title":"Development and external validation of a transfer learning-based system for the pathological diagnosis of colorectal cancer: a large emulated prospective study","volume":"14","author":"Yuan","year":"2024","journal-title":"Front Oncol"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0278542","article-title":"Improving quality control in the routine practice for histopathological interpretation of gastrointestinal endoscopic biopsies using artificial intelligence","volume":"17","author":"Ko","year":"2022","journal-title":"PloS One"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.modpat.2023.100327","article-title":"Artificial intelligence-based tool for tumor detection and quantitative tissue analysis in colorectal specimens","volume":"36","author":"Griem","year":"2023","journal-title":"Mod Pathol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1111\/his.15331","article-title":"A deep learning approach to case prioritization of colorectal biopsies","volume":"86","author":"White","year":"2025","journal-title":"Histopathology"},{"key":"B21","doi-asserted-by":"publisher","first-page":"8398","DOI":"10.1038\/s41598-023-35491-z","article-title":"Deep learning for multi-class semantic segmentation enables colorectal cancer detection and classification in digital pathology images","volume":"13","author":"Bokhorst","year":"2023","journal-title":"Sci Rep"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14102489","article-title":"iMIL4PATH: a semi-supervised interpretable approach for colorectal whole-slide images","volume":"14","author":"Neto","year":"2022","journal-title":"Cancers (Basel)"},{"key":"B23","doi-asserted-by":"publisher","first-page":"6311","DOI":"10.1038\/s41467-021-26643-8","article-title":"Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images","volume":"12","author":"Yu","year":"2021","journal-title":"Nat Commun"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1038\/s41598-022-06264-x","article-title":"A promising deep learning-assistive algorithm for histopathological screening of colorectal cancer","volume":"12","author":"Ho","year":"2022","journal-title":"Sci Rep"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(23)00148-6","article-title":"Development and validation of artificial intelligence-based prescreening of large-bowel biopsies taken in the UK and Portugal: a retrospective cohort study","volume":"5","author":"Bilal","year":"2023","journal-title":"Lancet Digit Health"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1101\/2022.02.28.22271565","article-title":"AI based pre-screening of large bowel cancer via weakly supervised learning of colorectal biopsy histology images","author":"Bilal","year":"2022","journal-title":"medRxiv"},{"key":"B27","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1002\/path.5800","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":"B28","doi-asserted-by":"publisher","DOI":"10.1136\/jclinpath-2021-208042","article-title":"Dual resolution deep learning network with self-attention mechanism for classification and localisation of colorectal cancer in histopathological images","volume":"76","author":"Xu","year":"2023","journal-title":"J Clin Pathol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1885546\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T13:46:25Z","timestamp":1786974385000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1885546\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":28,"alternative-id":["10.3389\/fonc.2026.1885546"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1885546","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,17]]},"article-number":"1885546"}}