{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T23:59:37Z","timestamp":1793404777347,"version":"4.5.0"},"reference-count":77,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100023452","name":"Hanarth Fund Foundation","doi-asserted-by":"publisher","award":["2022-13"],"award-info":[{"award-number":["2022-13"]}],"id":[{"id":"10.13039\/501100023452","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":[[2026,2]]},"DOI":"10.1016\/j.media.2025.103873","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T10:10:21Z","timestamp":1763374221000},"page":"103873","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":20,"special_numbering":"C","title":["Scaling up self-supervised learning for improved surgical foundation models"],"prefix":"10.1016","volume":"108","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8306-5058","authenticated-orcid":false,"given":"Tim J.M.","family":"Jaspers","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7806-4340","authenticated-orcid":false,"given":"Ronald L.P.D.","family":"de Jong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0239-3682","authenticated-orcid":false,"given":"Yiping","family":"Li","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\/0000-0001-7852-9332","authenticated-orcid":false,"given":"Franciscus H.A.","family":"Bakker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0025-9261","authenticated-orcid":false,"given":"Romy C.","family":"van Jaarsveld","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4013-7824","authenticated-orcid":false,"given":"Gino M.","family":"Kuiper","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7134-261X","authenticated-orcid":false,"given":"Richard","family":"van Hillegersberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6584-1677","authenticated-orcid":false,"given":"Jelle P.","family":"Ruurda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7883-0213","authenticated-orcid":false,"given":"Willem M.","family":"Brinkman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7327-9178","authenticated-orcid":false,"given":"Josien P.W.","family":"Pluim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7639-7716","authenticated-orcid":false,"given":"Peter H.N.","family":"de With","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1822-8970","authenticated-orcid":false,"given":"Marcel","family":"Breeuwer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6839-3507","authenticated-orcid":false,"given":"Yasmina","family":"Al Khalil","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.2025.103873_bib0001","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024","first-page":"328","article-title":"Jumpstarting surgical computer vision","author":"Alapatt","year":"2024"},{"key":"10.1016\/j.media.2025.103873_bib0002","unstructured":"Azad, B., Azad, R., Eskandari, S., Bozorgpour, A., Kazerouni, A., Rekik, I., Merhof, D., 2023. Foundational models in medical imaging: a comprehensive survey and future vision. arXiv preprint arXiv:2310.18689."},{"key":"10.1016\/j.media.2025.103873_bib0003","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"3458","article-title":"Big self-supervised models advance medical image classification","author":"Azizi","year":"2021"},{"key":"10.1016\/j.media.2025.103873_bib0004","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","first-page":"541","article-title":"Self-supervised learning for cardiac MR image segmentation by anatomical position prediction","author":"Bai","year":"2019"},{"issue":"7","key":"10.1016\/j.media.2025.103873_bib0005","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1089\/end.2023.0697","article-title":"Estimating surgical urethral length on intraoperative robot-assisted prostatectomy images using artificial intelligence anatomy recognition","volume":"38","author":"Bakker","year":"2024","journal-title":"J. Endourol."},{"key":"10.1016\/j.media.2025.103873_bib0006","series-title":"2021 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"14531","article-title":"Aggregating long-term context for learning laparoscopic and robot-assisted surgical workflows","author":"Ban","year":"2021"},{"key":"10.1016\/j.media.2025.103873_bib0007","unstructured":"Bardes, A., Garrido, Q., Ponce, J., Chen, X., Rabbat, M., LeCun, Y., Assran, M., Ballas, N., 2024. Revisiting feature prediction for learning visual representations from video. arXiv preprint arXiv:2404.08471."},{"issue":"6","key":"10.1016\/j.media.2025.103873_bib0008","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1007\/s11548-024-03091-5","article-title":"EndoViT: pretraining vision transformers on a large collection of endoscopic images","volume":"19","author":"Batic","year":"2024","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2025.103873_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103298","article-title":"Foundation models in gastrointestinal endoscopic AI: impact of architecture, pre-training approach and data efficiency","volume":"98","author":"Boers","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2025.103873_bib0010","unstructured":"Bawa, V. S., Singh, G., KapingA, F., Skarga-Bandurova, I., Oleari, E., Leporini, A., Landolfo, C., Zhao, P., Xiang, X., Luo, G., Wang, K., Li, L., Wang, B., Zhao, S., Li, L., Stabile, A., Setti, F., Muradore, R., Cuzzolin, F., 2021. The SARAS endoscopic surgeon action detection (ESAD) dataset: Challenges and methods. arXiv preprint arXiv:2104.03178."},{"key":"10.1016\/j.media.2025.103873_bib0011","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"9630","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"issue":"1","key":"10.1016\/j.media.2025.103873_bib0012","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1038\/s41597-022-01719-2","article-title":"The dresden surgical anatomy dataset for abdominal organ segmentation in surgical data science","volume":"10","author":"Carstens","year":"2023","journal-title":"Sci. Data"},{"issue":"4","key":"10.1016\/j.media.2025.103873_bib0013","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1109\/TMI.2023.3341948","article-title":"SurgNet: self-supervised pretraining with semantic consistency for vessel and instrument segmentation in surgical images","volume":"43","author":"Chen","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"3","key":"10.1016\/j.media.2025.103873_bib0014","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat. Med."},{"key":"10.1016\/j.media.2025.103873_bib0015","series-title":"Proceedings of the 37th International Conference on Machine Learning","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.media.2025.103873_bib0016","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"3008","article-title":"RandAugment: practical automated data augmentation with a reduced search space","author":"Cubuk","year":"2020"},{"key":"10.1016\/j.media.2025.103873_bib0017","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III 23","first-page":"343","article-title":"TeCNO: surgical phase recognition with multi-stage temporal convolutional networks","author":"Czempiel","year":"2020"},{"key":"10.1016\/j.media.2025.103873_bib0018","doi-asserted-by":"crossref","unstructured":"de Jong, R.L.P. D., Khalil, Y. a., Jaspers, T.J. M., van Jaarsveld, R. C., Kuiper, G. M., Li, Y., van Hillegersberg, R., Ruurda, J. P., Breeuwer, M., van der Sommen, F., 2024. Benchmarking pretrained attention-based models for real-time recognition in robot-assisted esophagectomy. arXiv preprint arXiv:2412.03401.","DOI":"10.1117\/12.3045187"},{"issue":"7","key":"10.1016\/j.media.2025.103873_bib0019","doi-asserted-by":"crossref","first-page":"5164","DOI":"10.1007\/s00464-023-09990-z","article-title":"Deep learning-based recognition of key anatomical structures during robot-assisted minimally invasive esophagectomy","volume":"37","author":"den Boer","year":"2023","journal-title":"Surg. Endosc."},{"issue":"12","key":"10.1016\/j.media.2025.103873_bib0020","doi-asserted-by":"crossref","first-page":"8737","DOI":"10.1007\/s00464-022-09421-5","article-title":"Computer-aided anatomy recognition in intrathoracic and -abdominal surgery: a systematic review","volume":"36","author":"den Boer","year":"2022","journal-title":"Surg Endosc"},{"key":"10.1016\/j.media.2025.103873_bib0021","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N., 2021. An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929."},{"issue":"6","key":"10.1016\/j.media.2025.103873_bib0022","doi-asserted-by":"crossref","DOI":"10.1117\/1.JMI.9.6.064503","article-title":"Contrastive self-supervised learning from 100 million medical images with optional supervision","volume":"9","author":"Ghesu","year":"2022","journal-title":"J. Med. Imaging"},{"issue":"2","key":"10.1016\/j.media.2025.103873_bib0023","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1007\/s11548-023-02971-6","article-title":"A spatio-temporal network for video semantic segmentation in surgical videos","volume":"19","author":"Grammatikopoulou","year":"2024","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"issue":"4, Supplement 1","key":"10.1016\/j.media.2025.103873_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.jamcollsurg.2017.07.387","article-title":"Artificial intelligence for intraoperative video analysis: machine learning\u2019s role in surgical education","volume":"225","author":"Hashimoto","year":"2017","journal-title":"J. Am. Coll. Surg."},{"key":"10.1016\/j.media.2025.103873_bib0025","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"15979","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.media.2025.103873_bib0026","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9726","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.media.2025.103873_bib0027","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023","first-page":"569","article-title":"Self-supervised learning for endoscopic video analysis","author":"Hirsch","year":"2023"},{"key":"10.1016\/j.media.2025.103873_bib0028","unstructured":"Hong, W.-Y., Kao, C.-L., Kuo, Y.-H., Wang, J.-R., Chang, W.-L., Shih, C. S., 2020. Cholecseg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80. arXiv preprint arXiv:2012.12453."},{"key":"10.1016\/j.media.2025.103873_bib0029","series-title":"Data Engineering in Medical Imaging","first-page":"43","article-title":"Exploring the effect of dataset diversity in self-supervised learning for surgical computer vision","author":"Jaspers","year":"2025"},{"issue":"5","key":"10.1016\/j.media.2025.103873_bib0030","doi-asserted-by":"crossref","first-page":"1114","DOI":"10.1109\/TMI.2017.2787657","article-title":"SV-RCNet: workflow recognition from surgical videos using recurrent convolutional network","volume":"37","author":"Jin","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2025.103873_bib0031","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6392","article-title":"Panoptic feature pyramid networks","author":"Kirillov","year":"2019"},{"key":"10.1016\/j.media.2025.103873_bib0032","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., Dollar, P., Girshick, R., 2023. Segment anything. arXiv preprint arXiv:2304.02643.","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"11","key":"10.1016\/j.media.2025.103873_bib0033","doi-asserted-by":"crossref","first-page":"2249","DOI":"10.1007\/s11548-024-03166-3","article-title":"Challenges in multi-centric generalization: phase and step recognition in Roux-en-Y gastric bypass surgery","volume":"19","author":"Lavanchy","year":"2024","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2025.103873_bib0034","series-title":"MultiMedia Modeling","first-page":"439","article-title":"GLENDA: gynecologic laparoscopy endometriosis dataset","author":"Leibetseder","year":"2020"},{"key":"10.1016\/j.media.2025.103873_bib0035","series-title":"Proceedings of the 9th ACM Multimedia Systems Conference","first-page":"357","article-title":"LapGyn4: a dataset for 4 automatic content analysis problems in the domain of laparoscopic gynecology","author":"Leibetseder","year":"2018"},{"key":"10.1016\/j.media.2025.103873_bib0036","doi-asserted-by":"crossref","unstructured":"Li, Y., van Jaarsveld, R., de Jong, R., Bongers, J., Kuiper, G., van Hillegersberg, R., Ruurda, J., Breeuwer, M., Khalil, Y. A., 2024. Benchmarking and enhancing surgical phase recognition models for robotic-assisted esophagectomy. arXiv preprint arXiv:2412.04039.","DOI":"10.1117\/12.3040084"},{"key":"10.1016\/j.media.2025.103873_bib0037","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"14420","article-title":"EfficientViT: memory efficient vision transformer with cascaded group attention","author":"Liu","year":"2023"},{"key":"10.1016\/j.media.2025.103873_bib0038","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11966","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"issue":"1","key":"10.1016\/j.media.2025.103873_bib0039","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.media.2025.103873_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102306","article-title":"Surgical data science from concepts toward clinical translation","volume":"76","author":"Maier-Hein","year":"2022","journal-title":"Med. Image Anal."},{"issue":"5","key":"10.1016\/j.media.2025.103873_bib0041","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1097\/SLA.0000000000004351","article-title":"Artificial intelligence for surgical safety: automatic assessment of the critical view of safety in laparoscopic cholecystectomy using deep learning","volume":"275","author":"Mascagni","year":"2022","journal-title":"Ann. Surg."},{"key":"10.1016\/j.media.2025.103873_bib0042","unstructured":"Murali, A., Alapatt, D., Mascagni, P., Vardazaryan, A., Garcia, A., Okamoto, N., Costamagna, G., Mutter, D., Marescaux, J., Dallemagne, B., Padoy, N., 2024a. The endoscapes dataset for surgical scene segmentation, object detection, and critical view of safety assessment: Official splits and benchmark. arXiv preprint arXiv:2312.12429."},{"issue":"3","key":"10.1016\/j.media.2025.103873_bib0043","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1109\/TMI.2023.3333034","article-title":"Latent graph representations for critical view of safety assessment","volume":"43","author":"Murali","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2025.103873_bib0044","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","first-page":"364","article-title":"Recognition of instrument-tissue interactions in endoscopic videos via action triplets","author":"Nwoye","year":"2020"},{"key":"10.1016\/j.media.2025.103873_bib0045","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., Assran, M., Ballas, N., Galuba, W., Howes, R., Huang, P.-Y., Li, S.-W., Misra, I., Rabbat, M., Sharma, V., Synnaeve, G., Xu, H., Jegou, H., Mairal, J., Labatut, P., Joulin, A., Bojanowski, P., 2024. DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193."},{"issue":"3","key":"10.1016\/j.media.2025.103873_bib0046","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1016\/j.media.2010.10.001","article-title":"Statistical modeling and recognition of surgical workflow","volume":"16","author":"Padoy","year":"2012","journal-title":"Med. Image Anal."},{"issue":"3","key":"10.1016\/j.media.2025.103873_bib0047","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/s42256-024-00807-9","article-title":"Foundation model for cancer imaging biomarkers","volume":"6","author":"Pai","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.media.2025.103873_bib0048","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.2025.103873_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103126","article-title":"On the pitfalls of batch normalization for end-to-end video learning: a study on surgical workflow analysis","volume":"94","author":"Rivoir","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2025.103873_bib0050","unstructured":"Schmidgall, S., Kim, J. W., Jopling, J., Krieger, A., 2024. General surgery vision transformer: a video pre-trained foundation model for general surgery. arXiv preprint arXiv:2403.05949."},{"key":"10.1016\/j.media.2025.103873_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102338","article-title":"Self-supervised monocular depth and ego-motion estimation in endoscopy: appearance flow to the rescue","volume":"77","author":"Shao","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2025.103873_bib0052","unstructured":"Sowrirajan, H., Yang, J., Ng, A. Y., Rajpurkar, P., 2021. MoCo-CXR: MoCo pretraining improves representation and transferability of chest x-ray models. arXiv preprint arXiv:2010.05352."},{"issue":"1","key":"10.1016\/j.media.2025.103873_bib0053","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","article-title":"EndoNet: a deep architecture for recognition tasks on laparoscopic videos","volume":"36","author":"Twinanda","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"4","key":"10.1016\/j.media.2025.103873_bib0054","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1109\/TMI.2018.2878055","article-title":"RSDNet: learning to predict remaining surgery duration from laparoscopic videos without manual annotations","volume":"38","author":"Twinanda","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2025.103873_bib0055","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022","first-page":"442","article-title":"Towards holistic surgical scene understanding","author":"Valderrama","year":"2022"},{"issue":"1","key":"10.1016\/j.media.2025.103873_bib0056","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s41746-022-00592-y","article-title":"Machine learning for medical imaging: methodological failures and recommendations for the future","volume":"5","author":"Varoquaux","year":"2022","journal-title":"npj Digit. Med."},{"key":"10.1016\/j.media.2025.103873_bib0057","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1038\/s41591-024-03141-0","article-title":"A foundation model for clinical-grade computational pathology and rare cancers detection","volume":"30","author":"Vorontsov","year":"2024","journal-title":"Nat. Med."},{"key":"10.1016\/j.media.2025.103873_bib0058","unstructured":"Wagner, M., Muller-Stich, B.-P., Kisilenko, A., Tran, D., Heger, P., Mundermann, L., Lubotsky, D. M., Muller, B., Davitashvili, T., Capek, M., Reinke, A., Yu, T., Vardazaryan, A., Nwoye, C. I., Padoy, N., Liu, X., Lee, E.-J., Disch, C., Meine, H., Xia, T., Jia, F., Kondo, S., Reiter, W., Jin, Y., Long, Y., Jiang, M., Dou, Q., Heng, P. A., Twick, I., Kirtac, K., Hosgor, E., Bolmgren, J. L., Stenzel, M., von Siemens, B., Kenngott, H. G., Nickel, F., von Frankenberg, M., Mathis-Ullrich, F., Maier-Hein, L., Speidel, S., Bodenstedt, S., 2021. Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the heichole benchmark. arXiv preprint arXiv:2109.14956."},{"key":"10.1016\/j.media.2025.103873_bib0059","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"19738","article-title":"Tracking everything everywhere all at once","author":"Wang","year":"2023"},{"key":"10.1016\/j.media.2025.103873_bib0060","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"548","article-title":"Pyramid vision transformer: a versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.media.2025.103873_bib0061","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.2025.103873_bib0062","doi-asserted-by":"crossref","unstructured":"Wang, Z., Lu, B., Long, Y., Zhong, F., Cheung, T.-H., Dou, Q., Liu, Y., 2022. Autolaparo: a new dataset of integrated multi-tasks for image-guided surgical automation in laparoscopic hysterectomy. arXiv preprint arXiv:2208.02049.","DOI":"10.1007\/978-3-031-16449-1_46"},{"issue":"7","key":"10.1016\/j.media.2025.103873_bib0063","doi-asserted-by":"crossref","first-page":"4008","DOI":"10.1007\/s00464-020-07833-9","article-title":"Automated operative phase identification in peroral endoscopic myotomy","volume":"35","author":"Ward","year":"2021","journal-title":"Surg. Endosc."},{"issue":"1","key":"10.1016\/j.media.2025.103873_bib0064","doi-asserted-by":"crossref","first-page":"2369","DOI":"10.1038\/s41598-021-82017-6","article-title":"Methods and open-source toolkit for analyzing and visualizing challenge results","volume":"11","author":"Wiesenfarth","year":"2021","journal-title":"Sci. Rep."},{"key":"10.1016\/j.media.2025.103873_bib0065","unstructured":"Wu, J., Ji, W., Liu, Y., Fu, H., Xu, M., Xu, Y., Jin, Y., 2023. Medical SAM adapter: adapting segment anything model for medical image segmentation. arXiv preprint arXiv:2304.12620."},{"key":"10.1016\/j.media.2025.103873_bib0066","series-title":"Machine Learning in Medical Imaging","first-page":"176","article-title":"Mammo-SAM: adapting foundation segment anything model for automatic breast mass segmentation in whole mammograms","author":"Xiong","year":"2024"},{"key":"10.1016\/j.media.2025.103873_bib0067","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10371","article-title":"Depth anything: unleashing the power of large-scale unlabeled data","author":"Yang","year":"2024"},{"key":"10.1016\/j.media.2025.103873_bib0068","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","first-page":"393","article-title":"HSDB-instrument: instrument localization database for laparoscopic and robotic surgeries","author":"Yoon","year":"2021"},{"issue":"2","key":"10.1016\/j.media.2025.103873_bib0069","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1109\/TPAMI.2023.3329173","article-title":"Metaformer baselines for vision","volume":"46","author":"Yu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2025.103873_bib0070","unstructured":"Yuan, K., Srivastav, V., Navab, N., Padoy, N., 2024a. Procedure-aware surgical video-language pretraining with hierarchical knowledge augmentation. arXiv preprint arXiv:2410.00263."},{"key":"10.1016\/j.media.2025.103873_bib0071","doi-asserted-by":"crossref","unstructured":"Yuan, K., Srivastav, V., Yu, T., Lavanchy, J. L., Mascagni, P., Navab, N., Padoy, N., 2024b. Learning multi-modal representations by watching hundreds of surgical video lectures. arXiv preprint arXiv:2307.15220.","DOI":"10.1016\/j.media.2025.103644"},{"issue":"2-3","key":"10.1016\/j.media.2025.103873_bib0072","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1049\/htl2.12069","article-title":"Towards better laparoscopic video segmentation: a class-wise contrastive learning approach with multi-scale feature extraction","volume":"11","author":"Zhang","year":"2024","journal-title":"Healthc. Technol. Lett."},{"key":"10.1016\/j.media.2025.103873_bib0073","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022","first-page":"497","article-title":"Retrieval of surgical phase transitions using reinforcement learning","author":"Zhang","year":"2022"},{"key":"10.1016\/j.media.2025.103873_bib0074","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","first-page":"398","article-title":"Comparing to learn: surpassing imagenet pretraining on radiographs by comparing image representations","author":"Zhou","year":"2020"},{"key":"10.1016\/j.media.2025.103873_bib0075","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","first-page":"420","article-title":"Self-supervised feature learning for 3d medical images by playing a rubik\u2019s cube","author":"Zhuang","year":"2019"},{"key":"10.1016\/j.media.2025.103873_bib0076","unstructured":"Zia, A., Bhattacharyya, K., Liu, X., Berniker, M., Wang, Z., Nespolo, R., Kondo, S., Kasai, S., Hirasawa, K., Liu, B., Austin, D., Wang, Y., Futrega, M., Puget, J.-F., Li, Z., Sato, Y., Fujii, R., Hachiuma, R., Masuda, M., Saito, H., Wang, A., Xu, M., Islam, M., Bai, L., Pang, W., Ren, H., Nwoye, C., Sestini, L., Padoy, N., Nielsen, M., Schuttler, S., Sentker, T., Husseini, H., Baltruschat, I., Schmitz, R., Werner, R., Matsun, A., Farooq, M., Saaed, N., Viera, J. R. R., Yaqub, M., Getty, N., Xia, F., Zhao, Z., Duan, X., Yao, X., Lou, A., Yang, H., Han, J., Noble, J., Wu, J. Y., Alshirbaji, T. A., Jalal, N. A., Arabian, H., Ding, N., Moeller, K., Chen, W., He, Q., Bilal, M., Akinosho, T., Qayyum, A., Caputo, M., Vohra, H., Loizou, M., Ajayi, A., Berrou, I., Niyi-Odumosu, F., Maier-Hein, L., Stoyanov, D., Speidel, S., Jarc, A., 2023. Surgical tool classification and localization: results and methods from the MICCAI 2022 surgtoolloc challenge. arXiv preprint arXiv:2305.07152."},{"key":"10.1016\/j.media.2025.103873_bib0077","unstructured":"Zou, X., Yang, J., Zhang, H., Li, F., Li, L., Wang, J., Wang, L., Gao, J., Lee, Y. J., 2023. Segment everything everywhere all at once. arXiv preprint arXiv:2304.06718."}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841525004190?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841525004190?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T13:02:51Z","timestamp":1769518971000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841525004190"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":77,"alternative-id":["S1361841525004190"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2025.103873","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Scaling up self-supervised learning for improved surgical foundation models","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2025.103873","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103873"}}