{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Research Square"}],"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T04:45:25Z","timestamp":1773117925383,"version":"3.50.1"},"posted":{"date-parts":[[2025,10,27]]},"group-title":"In Review","reference-count":0,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,4,8]]},"abstract":"<title>Abstract<\/title>\n                <p>We propose Cut Instance Mixing (CIM), a domain-specific data augmentation method for improving deep learning (DL) models in detecting gastrointestinal lesions during endoscopy. CIM overcomes the limitations of state-of-the-art techniques like MixUp and CutMix by adapting them to the unique challenges of endoscopy, including localized, irregular lesions such as intestinal metaplasia (IM), dysplasia, and polyps. CIM promotes biologically relevant augmentations by identifying regions of interest and blending lesion features seamlessly using Poisson image editing and gradient mixing.\nOur experiments utilized ResNet50, trained on datasets for IM, dysplasia, and polyps, with extensive evaluation of internal and external test sets. Results demonstrate that CIM with optimized blending (\u03b1=0.8) significantly outperforms MixUp and CutMix across key metrics, achieving the highest AUC (0.879) and accuracy (0.823) for IM detection and near-perfect AUC (0.997) for dysplasia classification. Additionally, CIM exhibits superior generalization capabilities, maintaining robust performance on external polyp datasets under diverse conditions.\nCIM enhances model sensitivity and precision by producing realistic, lesion-focused training samples, as confirmed by Grad-CAM heatmap analyses. These results highlight its potential in improving DL-based endoscopic diagnosis or other specific domain contexts, particularly for underrepresented lesion classes. Our findings underscore the importance of domain-specific augmentations, especially in limited and unbalanced datasets.<\/p>","DOI":"10.21203\/rs.3.rs-6401606\/v1","type":"posted-content","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T12:36:27Z","timestamp":1761568587000},"source":"Crossref","is-referenced-by-count":0,"title":["Cut Instance Mixing: a domain-specific data augmentation method applied to gastrointestinal lesion detection"],"prefix":"10.21203","author":[{"given":"Alexandre","family":"Neto","sequence":"first","affiliation":[{"name":"INESC TEC \u2013 Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ci\u00eancia, 3200-465 Porto, Portugal"}]},{"given":"Eduarda","family":"Almeida","sequence":"additional","affiliation":[{"name":"INESC TEC \u2013 Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ci\u00eancia, 3200-465 Porto, Portugal"}]},{"given":"Diogo","family":"Lib\u00e2nio","sequence":"additional","affiliation":[{"name":"Faculdade de Medicina, Universidade do Porto, 4200-319 Porto, Portugal"}]},{"given":"M\u00e1rio","family":"Dinis-Ribeiro","sequence":"additional","affiliation":[{"name":"Faculdade de Medicina, Universidade do Porto, 4200-319 Porto, Portugal"}]},{"given":"Miguel","family":"Coimbra","sequence":"additional","affiliation":[{"name":"INESC TEC \u2013 Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ci\u00eancia, 3200-465 Porto, Portugal"}]},{"given":"Ant\u00f3nio","family":"Cunha","sequence":"additional","affiliation":[{"name":"Escola de Ci\u00eancias e Tecnologia, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5001-801 Vila Real, Portugal"}]}],"member":"297","container-title":[],"original-title":[],"link":[{"URL":"https:\/\/www.researchsquare.com\/article\/rs-6401606\/v1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.researchsquare.com\/article\/rs-6401606\/v1.html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T16:11:45Z","timestamp":1773072705000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchsquare.com\/article\/rs-6401606\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":0,"URL":"https:\/\/doi.org\/10.21203\/rs.3.rs-6401606\/v1","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1038\/s41598-026-42138-2","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2025,10,27]]},"subtype":"preprint"}}