{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T08:40:45Z","timestamp":1791362445067,"version":"4.3.1"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004191","name":"Novo Nordisk","doi-asserted-by":"publisher","award":["NNFSA210073688"],"award-info":[{"award-number":["NNFSA210073688"]}],"id":[{"id":"10.13039\/501100004191","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Vet. Sci."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Use of Machine learning (ML) is rapidly expanding in histopathology, offering the potential to reduce interobserver variability and improve quantitative assessment. However, large datasets and computational resources commonly used in toxicology and human medicine are often unavailable to the veterinary pathologist. This study aimed to evaluate the feasibility and limitations of applying supervised ML on histopathological samples with limited training data, exemplified by training an ML model to segment the intestinal wall into its histological layers.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and methods<\/jats:title><jats:p>The study included 145 piglets from five age groups (4, 14, 25, 49, and 67\u202fdays). Full-wall samples from duodenum, jejunum and ileum were collected post-mortem, stained with H&amp;amp;E and digitized. A three-step ML model was trained on 8\u201315 images: Step 1 identified tissue, Step 2 segmented mucosa from submucosal layers, and Step 3 separated lamina propria from epithelium. Model performance was assessed by comparing AI-generated areas to manual annotations, calculating relative deviation, categorized agreement levels, Intersection over Union, and Pearson correlation coefficients. Qualitative error analyses were used as directions for future training options.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>A three-step separation model was successfully developed, but showed a significant amount of age-related performance variation, depicted as larger inaccuracies in samples from the younger age-groups, reflecting additional tissue heterogeneity from immature morphology. Classification errors could be categorized into intrinsic limitations (e.g., thresholding issues in tissue identification) and training deficits (e.g., misclassification of goblet cells and crypt abscesses), of which only the latter category could be corrected by adding additional training data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>This study demonstrates the feasibility of ML-based histopathology with limited sample sizes, providing a viable option for veterinary pathologists. Models trained on small datasets require careful supervision, with special emphasis on age-diverse tissue heterogeneity and overfitting. In these cases, ML should be seen as a tool to augment, not replace, expert oversight, ensuring reliable and reproducible quantitative histopathological measures.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fvets.2025.1620338","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T08:23:38Z","timestamp":1759739018000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Machine-learning for quantitative histopathology of piglet intestinal tissues: challenges with limited training data"],"prefix":"10.3389","volume":"12","author":[{"given":"Cecilie Brandt","family":"Becker","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mette Sif","family":"Hansen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S\u00f8ren Saxmose","family":"Nielsen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henrik Elvang","family":"Jensen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,6]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1080\/01652176.1992.9694322","article-title":"The pathogenesis of the post-weaning syndrome in weaned piglets: a review","volume":"14","author":"van Beers-Schreurs","year":"1992","journal-title":"Vet Q"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1016\/B978-0-323-35775-3.00007-2","article-title":"Alimentary system and the peritoneum, omentum, mesentery, and peritoneal cavity","volume-title":"Pathologic basis of veterinary disease","author":"Gelberg","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40813-017-0063-4","article-title":"Swine enteric colibacillosis: diagnosis, therapy and antimicrobial resistance","volume":"3","author":"Luppi","year":"2017","journal-title":"Porc Health Manag"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13028-017-0299-7","article-title":"Post weaning diarrhea in pigs: risk factors and non-colistin-based control strategies","volume":"59","author":"Rhouma","year":"2017","journal-title":"Acta Vet Scand"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40813-021-00232-z","article-title":"Post-weaning diarrhea in pigs weaned without medicinal zinc: risk factors, pathogen dynamics, and association to growth rate","volume":"7","author":"Eriksen","year":"2021","journal-title":"Porc Health Manag"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13028-023-00693-y","article-title":"Gastro-intestinal lesions are not relatable to diarrhoea or specific pathogens in post-weaning diarrhoea (PWD) in pigs","volume":"65","author":"Blirup-Plum","year":"2023","journal-title":"Acta Vet Scand"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40813-023-00319-9","article-title":"Lesions and pathogens found in pigs that died during the nursery period in five Danish farms","volume":"9","author":"Barington","year":"2023","journal-title":"Porc Health Manag"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1002\/path.1700930221","article-title":"Autolysis and post-mortem bacteriological changes in the alimentary tract of the pig","volume":"93","author":"Thorpe","year":"1967","journal-title":"J Pathol Bacteriol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.2460\/javma.2002.220.1177","article-title":"Interobserver variation among histopathologic evaluations of intestinal tissues from dogs and cats","volume":"220","author":"Willard","year":"2002","journal-title":"J Am Vet Med Assoc"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1080\/00365520600670349","article-title":"Interobserver variability in gastrointestinal pathology","volume":"41","author":"Vainer","year":"2006","journal-title":"Scand J Gastroenterol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"534","DOI":"10.5858\/arpa.2021-0598-OA","article-title":"Interobserver variability in assessment of depth of submucosal invasion for colonic endoscopic resections among subspecialized gastrointestinal pathologists","volume":"147","author":"Karamchandani","year":"2023","journal-title":"Arch Pathol Lab Med"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"946","DOI":"10.1177\/0300985813511123","article-title":"Design of a simplified histopathologic model for gastrointestinal inflammation in dogs","volume":"51","author":"Jergens","year":"2014","journal-title":"Vet Pathol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1016\/j.cgh.2023.11.044","article-title":"The evolving role of artificial intelligence in gastrointestinal histopathology: an update","volume":"22","author":"Codipilly","year":"2024","journal-title":"Clin Gastroenterol Hepatol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"137","DOI":"10.54097\/Be1ExjZa","article-title":"Development of machine learning and artificial intelligence in toxic pathology","volume":"6","author":"Song","year":"2024","journal-title":"Front Comp Intellig Syst"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1002\/gcc.23177","article-title":"Machine learning in computational histopathology: challenges and opportunities","volume":"62","author":"Cooper","year":"2023","journal-title":"Genes Chromosom Cancer"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2545","DOI":"10.3748\/wjg.v27.i20.2545","article-title":"State of machine and deep learning in histopathological applications in digestive diseases","volume":"27","author":"Kobayashi","year":"2021","journal-title":"World J Gastroenterol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1002\/ueg2.12562","article-title":"An artificial intelligence-driven scoring system to measure histological disease activity in ulcerative colitis","volume":"12","author":"Peyrin-Biroulet","year":"2024","journal-title":"United European Gastroenterol J"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1177\/03009858211040484","article-title":"Whole-slide imaging, tissue image analysis, and artificial intelligence in veterinary pathology: an updated introduction and review","volume":"59","author":"Zuraw","year":"2022","journal-title":"Vet Pathol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1016\/j.carj.2019.06.002","article-title":"Sample-size determination methodologies for machine learning in medical imaging research: a systematic review","volume":"70","author":"Balki","year":"2019","journal-title":"Can Assoc Radiol J"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.3390\/cancers14051199","article-title":"Recent advances of deep learning for computational histopathology: principles and applications","volume":"14","author":"Wu","year":"2022","journal-title":"Cancer"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-17204-5","article-title":"QuPath: open source software for digital pathology image analysis","volume":"7","author":"Bankhead","year":"2017","journal-title":"Sci Rep"},{"key":"ref22","author":"Bankhead","year":"2024"},{"key":"ref23","first-page":"109","article-title":"Correlation","volume-title":"Biostatistics manual for health research - a practical guide to data analysis","author":"Pearson","year":"2023"},{"key":"ref24","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-023-50183-4","article-title":"Rapid artefact removal and H & E-stained tissue segmentation","volume":"14","author":"Schreiber","year":"2024","journal-title":"Sci Rep"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","article-title":"Cascade R-CNN: high quality object detection and instance segmentation","volume":"43","author":"Cai","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1186\/BF03548261","article-title":"Histomorphological studies of the perinatal pig: comparison of five mortality groups with unaffected pigs","volume":"28","author":"Bj\u00f6rklund","year":"1987","journal-title":"Acta Vet Scand"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/030098587200900102","article-title":"Vacuolated villous epithelium of the small intestine of young pigs","volume":"9","author":"Moon","year":"1972","journal-title":"Vet Pathol"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1177\/0300985820954551","article-title":"Neonatal and juvenile ocular development in G\u00f6ttingen minipigs and domestic pigs: a histomorphological and immunohistochemical study","volume":"57","author":"Vrolyk","year":"2020","journal-title":"Vet Pathol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.3389\/fimmu.2020.01153","article-title":"The immature gut barrier and its importance in establishing immunity in newborn mammals","volume":"11","author":"Westr\u00f6m","year":"2020","journal-title":"Front Immunol"},{"key":"ref31","first-page":"87","article-title":"Gradual disappearance of vacuolated enterocytes in the small intestine of neonatal piglets","volume":"58","author":"Skrzypek","year":"2007","journal-title":"J Physiol Pharmacol"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1016\/j.jcmgh.2016.09.003","article-title":"Large animal models: the key to translational discovery in digestive disease research","volume":"2","author":"Ziegler","year":"2016","journal-title":"CMGH"}],"container-title":["Frontiers in Veterinary Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fvets.2025.1620338\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T08:23:39Z","timestamp":1759739019000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fvets.2025.1620338\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":32,"alternative-id":["10.3389\/fvets.2025.1620338"],"URL":"https:\/\/doi.org\/10.3389\/fvets.2025.1620338","relation":{},"ISSN":["2297-1769"],"issn-type":[{"value":"2297-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,6]]},"article-number":"1620338"}}