{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T23:41:42Z","timestamp":1793317302426,"version":"4.5.0"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009734","name":"Olympus Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009734","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003246","name":"Dutch Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1016\/j.media.2024.103298","type":"journal-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T23:58:37Z","timestamp":1723507117000},"page":"103298","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":53,"special_numbering":"C","title":["Foundation models in gastrointestinal endoscopic AI: Impact of architecture, pre-training approach and data efficiency"],"prefix":"10.1016","volume":"98","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1944-8908","authenticated-orcid":false,"given":"Tim G.W.","family":"Boers","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiki N.","family":"Fockens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0915-9048","authenticated-orcid":false,"given":"Joost A.","family":"van der Putten","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8306-5058","authenticated-orcid":false,"given":"Tim J.M.","family":"Jaspers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3114-3888","authenticated-orcid":false,"given":"Carolus H.J.","family":"Kusters","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4536-8349","authenticated-orcid":false,"given":"Jelmer B.","family":"Jukema","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8593-3875","authenticated-orcid":false,"given":"Martijn R.","family":"Jong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maarten R.","family":"Struyvenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeroen","family":"de Groof","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacques J.","family":"Bergman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter H.N.","family":"de With","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3593-2356","authenticated-orcid":false,"given":"Fons","family":"van der Sommen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2024.103298_b1","doi-asserted-by":"crossref","unstructured":"Azizi, S., Mustafa, B., Ryan, F., Beaver, Z., Freyberg, J., Deaton, J., Loh, A., Karthikesalingam, A., Kornblith, S., Chen, T., et al., 2021. Big self-supervised models advance medical image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3478\u20133488.","DOI":"10.1109\/ICCV48922.2021.00346"},{"key":"10.1016\/j.media.2024.103298_b2","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A., 2021. Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9650\u20139660.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"10.1016\/j.media.2024.103298_b3","series-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"10.1016\/j.media.2024.103298_b4","series-title":"International Conference on Machine Learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.media.2024.103298_b5","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume":"vol. 33","author":"Chen","year":"2020"},{"key":"10.1016\/j.media.2024.103298_b6","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K., An empirical study of training self-supervised vision transformers. In 2021 IEEE. In: CVF International Conference on Computer Vision. ICCV, pp. 9620\u20139629.","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"10.1016\/j.media.2024.103298_b7","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.cobme.2018.12.005","article-title":"Cats or CAT scans: Transfer learning from natural or medical image source data sets?","volume":"9","author":"Cheplygina","year":"2019","journal-title":"Curr. Opin. Biomed. Eng."},{"key":"10.1016\/j.media.2024.103298_b8","series-title":"2022 International Joint Conference on Neural Networks","first-page":"1","article-title":"Effect of pre-training scale on intra-and inter-domain, full and few-shot transfer learning for natural and X-ray chest images","author":"Cherti","year":"2022"},{"key":"10.1016\/j.media.2024.103298_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.104578","article-title":"Convolutional neural networks for the evaluation of cancer in Barrett\u2019s esophagus: Explainable AI to lighten up the black-box","volume":"135","author":"de Souza","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2024.103298_b10","series-title":"Gastrointestinal image analysis challenge","author":"EndoVis-Challenge","year":"2018"},{"issue":"12","key":"10.1016\/j.media.2024.103298_b11","doi-asserted-by":"crossref","first-page":"e905","DOI":"10.1016\/S2589-7500(23)00199-1","article-title":"A deep learning system for detection of early Barrett\u2019s neoplasia: A model development and validation study","volume":"5","author":"Fockens","year":"2023","journal-title":"Lancet Digit. Health"},{"issue":"6","key":"10.1016\/j.media.2024.103298_b12","doi-asserted-by":"crossref","first-page":"AB237","DOI":"10.1016\/j.gie.2022.04.598","article-title":"A robust and compact deep learning system for primary detection of early barrett\u2019s neoplasia outperforms general endoscopists","volume":"95","author":"Fockens","year":"2022","journal-title":"Gastrointest. Endosc."},{"key":"10.1016\/j.media.2024.103298_b13","doi-asserted-by":"crossref","DOI":"10.1155\/2020\/8374317","article-title":"Application of deep learning for early screening of colorectal precancerous lesions under white light endoscopy","volume":"2020","author":"Gao","year":"2020","journal-title":"Comput. Math. Methods Med."},{"key":"10.1016\/j.media.2024.103298_b14","series-title":"Self-supervised learning from 100 million medical images","author":"Ghesu","year":"2022"},{"issue":"1","key":"10.1016\/j.media.2024.103298_b15","first-page":"1","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2021","journal-title":"ACM Trans. Comput. Healthc. (HEALTH)"},{"key":"10.1016\/j.media.2024.103298_b16","doi-asserted-by":"crossref","unstructured":"He, K., Girshick, R., Doll\u00e1r, P., 2019. Rethinking imagenet pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 4918\u20134927.","DOI":"10.1109\/ICCV.2019.00502"},{"key":"10.1016\/j.media.2024.103298_b17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"10.1016\/j.media.2024.103298_b18","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0269728","article-title":"Automated evaluation of colon capsule endoscopic severity of ulcerative colitis using ResNet50","volume":"17","author":"Higuchi","year":"2022","journal-title":"PLoS One"},{"key":"10.1016\/j.media.2024.103298_b19","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"569","article-title":"Self-supervised learning for endoscopic video analysis","author":"Hirsch","year":"2023"},{"key":"10.1016\/j.media.2024.103298_b20","series-title":"2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference","first-page":"0280","article-title":"Gastrointestinal disorder detection with a transformer based approach","author":"Hosain","year":"2022"},{"key":"10.1016\/j.media.2024.103298_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103157","article-title":"Robustness evaluation of deep neural networks for endoscopic image analysis: Insights and strategies","volume":"94","author":"Jaspers","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2024.103298_b22","series-title":"International Conference on Multimedia Modeling","first-page":"451","article-title":"Kvasir-seg: A segmented polyp dataset","author":"Jha","year":"2020"},{"key":"10.1016\/j.media.2024.103298_b23","series-title":"Ultralytics YOLOv8","author":"Jocher","year":"2023"},{"key":"10.1016\/j.media.2024.103298_b24","doi-asserted-by":"crossref","unstructured":"Kang, M., Song, H., Park, S., Yoo, D., Pereira, S., 2023. Benchmarking Self-Supervised Learning on Diverse Pathology Datasets. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3344\u20133354.","DOI":"10.1109\/CVPR52729.2023.00326"},{"key":"10.1016\/j.media.2024.103298_b25","series-title":"Efficient self-supervised vision transformers for representation learning","author":"Li","year":"2021"},{"key":"10.1016\/j.media.2024.103298_b26","series-title":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics","first-page":"1","article-title":"Classification of video capsule endoscopy images using visual transformers","author":"Lima","year":"2022"},{"issue":"12","key":"10.1016\/j.media.2024.103298_b27","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1016\/S1470-2045(19)30637-0","article-title":"Real-time artificial intelligence for detection of upper gastrointestinal cancer by endoscopy: A multicentre, case-control, diagnostic study","volume":"20","author":"Luo","year":"2019","journal-title":"Lancet Oncol."},{"key":"10.1016\/j.media.2024.103298_b28","series-title":"Artificial Intelligence in Data and Big Data Processing: Proceedings of ICABDE 2021","first-page":"381","article-title":"Improving gastroesophageal reflux diseases classification diagnosis from endoscopic images using stylegan2-ada","author":"Nguyen","year":"2022"},{"key":"10.1016\/j.media.2024.103298_b29","doi-asserted-by":"crossref","DOI":"10.1109\/JBHI.2023.3276778","article-title":"Multi-scale hybrid vision transformer for learning gastric histology: AI-based decision support system for gastric cancer treatment","author":"Oh","year":"2023","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"10.1016\/j.media.2024.103298_b30","series-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"10.1016\/j.media.2024.103298_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2020.101914","article-title":"Multi-stage domain-specific pretraining for improved detection and localization of barrett\u2019s neoplasia: A comprehensive clinically validated study","volume":"107","author":"Van der Putten","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.media.2024.103298_b32","series-title":"MICCAI Workshop on Data Engineering in Medical Imaging","first-page":"102","article-title":"Vision transformer-based self-supervised learning for ulcerative colitis grading in colonoscopy","author":"Pyatha","year":"2023"},{"key":"10.1016\/j.media.2024.103298_b33","article-title":"Transfusion: Understanding transfer learning for medical imaging","volume":"vol. 32","author":"Raghu","year":"2019"},{"key":"10.1016\/j.media.2024.103298_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102844","article-title":"Dissecting self-supervised learning methods for surgical computer vision","volume":"88","author":"Ramesh","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2024.103298_b35","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C., 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"issue":"S 01","key":"10.1016\/j.media.2024.103298_b36","first-page":"eP481","article-title":"Detection of celiac disease using a deep learning algorithm","volume":"53","author":"Scheppach","year":"2021","journal-title":"Endoscopy"},{"issue":"5","key":"10.1016\/j.media.2024.103298_b37","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","article-title":"Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning","volume":"35","author":"Shin","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2024.103298_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106723","article-title":"Transformer-based multi-task learning for classification and segmentation of gastrointestinal tract endoscopic images","volume":"157","author":"Tang","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2024.103298_b39","series-title":"Meta-polyp: a baseline for efficient polyp segmentation","author":"Trinh","year":"2023"},{"key":"10.1016\/j.media.2024.103298_b40","doi-asserted-by":"crossref","first-page":"23","DOI":"10.21037\/jmai.2019.11.03","article-title":"Gastroenterology needs its own ImageNet","volume":"2","author":"Van der Sommen","year":"2019","journal-title":"J. Med. Artif. Intell."},{"key":"10.1016\/j.media.2024.103298_b41","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"101","article-title":"Foundation model for endoscopy video analysis via large-scale self-supervised pre-train","author":"Wang","year":"2023"},{"key":"10.1016\/j.media.2024.103298_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2021.103145","article-title":"Rethinking pre-training on medical imaging","volume":"78","author":"Wen","year":"2021","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"1","key":"10.1016\/j.media.2024.103298_b43","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.gie.2021.06.033","article-title":"Deep learning system compared with expert endoscopists in predicting early gastric cancer and its invasion depth and differentiation status (with videos)","volume":"95","author":"Wu","year":"2022","journal-title":"Gastrointest. Endosc."},{"key":"10.1016\/j.media.2024.103298_b44","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., Savarese, S., 2018. Taskonomy: Disentangling task transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3712\u20133722.","DOI":"10.1109\/CVPR.2018.00391"},{"issue":"6","key":"10.1016\/j.media.2024.103298_b45","doi-asserted-by":"crossref","first-page":"AB250","DOI":"10.1016\/j.gie.2022.04.651","article-title":"Real-time classification of colorectal polyps using artificial intelligence\u2013A prospective pilot study comparing two computer-aided diagnosis systems and one expert endoscopist","volume":"95","author":"van der Zander","year":"2022","journal-title":"Gastrointest. Endosc."},{"key":"10.1016\/j.media.2024.103298_b46","series-title":"On the challenges and perspectives of foundation models for medical image analysis","author":"Zhang","year":"2023"},{"key":"10.1016\/j.media.2024.103298_b47","series-title":"Ibot: Image bert pre-training with online tokenizer","author":"Zhou","year":"2021"},{"key":"10.1016\/j.media.2024.103298_b48","series-title":"Mugs: A multi-granular self-supervised learning framework","author":"Zhou","year":"2022"},{"key":"10.1016\/j.media.2024.103298_b49","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2021.106539","article-title":"Domain-and task-specific transfer learning for medical segmentation tasks","volume":"214","author":"Zoetmulder","year":"2022","journal-title":"Comput. Methods Programs Biomed."}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841524002238?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841524002238?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T03:47:41Z","timestamp":1725767261000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841524002238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":49,"alternative-id":["S1361841524002238"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2024.103298","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Foundation models in gastrointestinal endoscopic AI: Impact of architecture, pre-training approach and data efficiency","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2024.103298","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103298"}}