{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T13:30:06Z","timestamp":1793626206940,"version":"4.5.1"},"reference-count":61,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001665","name":"French National Research Agency","doi-asserted-by":"publisher","award":["ANR-20-CHIA-0029-01"],"award-info":[{"award-number":["ANR-20-CHIA-0029-01"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"French National Research Agency","doi-asserted-by":"publisher","award":["ANR-10-IAHU-02"],"award-info":[{"award-number":["ANR-10-IAHU-02"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","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":[[2027,1]]},"DOI":"10.1016\/j.media.2026.104325","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:58:27Z","timestamp":1789721907000},"page":"104325","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["State-change learning for prediction of future events in endoscopic videos"],"prefix":"10.1016","volume":"115","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6021-6132","authenticated-orcid":false,"given":"Saurav","family":"Sharma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chinedu Innocent","family":"Nwoye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Didier","family":"Mutter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5010-4137","authenticated-orcid":false,"given":"Nicolas","family":"Padoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.media.2026.104325_b1","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2300088","article-title":"Artificial intelligence identifies factors associated with blood loss and surgical experience in cholecystectomy","volume":"1","author":"Aklilu","year":"2024","journal-title":"NEJM AI"},{"key":"10.1016\/j.media.2026.104325_b2","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"586","article-title":"Deep neural networks predict remaining surgery duration from cholecystectomy videos","author":"Aksamentov","year":"2017"},{"key":"10.1016\/j.media.2026.104325_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103726","article-title":"Pixel-wise recognition for holistic surgical scene understanding","author":"Ayobi","year":"2025","journal-title":"Med. Image Anal."},{"issue":"6","key":"10.1016\/j.media.2026.104325_b4","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":"Bati\u0107","year":"2024","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.104325_b5","series-title":"The saras endoscopic surgeon action detection (esad) dataset: Challenges and methods","author":"Bawa","year":"2021"},{"issue":"5","key":"10.1016\/j.media.2026.104325_b6","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1007\/s11548-008-0239-0","article-title":"Workflow mining for visualization and analysis of surgeries","volume":"3","author":"Blum","year":"2008","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.104325_b7","series-title":"Supra: Surgical phase recognition and anticipation for intra-operative planning","author":"Boels","year":"2024"},{"key":"10.1016\/j.media.2026.104325_b8","first-page":"1","article-title":"SWAG: Long-term surgical workflow prediction with generative-based anticipation","author":"Boels","year":"2025","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.104325_b9","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"178","article-title":"Feature mixing approach for detecting intraoperative adverse events in laparoscopic roux-en-y gastric bypass surgery","author":"Bose","year":"2025"},{"key":"10.1016\/j.media.2026.104325_b10","series-title":"How attentive are graph attention networks?","author":"Brody","year":"2021"},{"key":"10.1016\/j.media.2026.104325_b11","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume":"26","author":"Cuturi","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104325_b12","series-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2020 - 23rd International Conference, Lima, Peru, October 4-8, 2020, Proceedings, Part III","first-page":"343","article-title":"TeCNO: Surgical phase recognition with multi-stage temporal convolutional networks","volume":"vol. 12263","author":"Czempiel","year":"2020"},{"issue":"11","key":"10.1016\/j.media.2026.104325_b13","doi-asserted-by":"crossref","first-page":"4125","DOI":"10.1109\/TPAMI.2020.2991965","article-title":"The EPIC-KITCHENS dataset: Collection, challenges and baselines","volume":"43","author":"Damen","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"issue":"6","key":"10.1016\/j.media.2026.104325_b14","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1007\/s11548-016-1371-x","article-title":"Automatic data-driven real-time segmentation and recognition of surgical workflow","volume":"11","author":"Dergachyova","year":"2016","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.104325_b15","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.media.2026.104325_b16","unstructured":"Feydy, J., S\u00e9journ\u00e9, T., Vialard, F.X., Amari, S.i., Trouve, A., Peyr\u00e9, G., 2019. Interpolating between Optimal Transport and MMD using Sinkhorn Divergences. In: The 22nd International Conference on Artificial Intelligence and Statistics. pp. 2681\u20132690."},{"key":"10.1016\/j.media.2026.104325_b17","first-page":"85","article-title":"Temporal coherence-based self-supervised learning for laparoscopic workflow analysis","volume":"vol. 11041","author":"Funke","year":"2018"},{"issue":"11","key":"10.1016\/j.media.2026.104325_b18","doi-asserted-by":"crossref","first-page":"4021","DOI":"10.1109\/TPAMI.2020.2992889","article-title":"Rolling-unrolling lstms for action anticipation from first-person video","volume":"43","author":"Furnari","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.104325_b19","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Grauman, K., 2021. Anticipative video transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 13505\u201313515.","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"10.1016\/j.media.2026.104325_b20","first-page":"3220","article-title":"Surgical workflow recognition and blocking effectiveness detection in laparoscopic liver resection with pringle maneuver","volume":"vol. 39","author":"Guo","year":"2025"},{"key":"10.1016\/j.media.2026.104325_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2021.106452","article-title":"Micro-surgical anastomose workflow recognition challenge report","volume":"212","author":"Huaulm\u00e9","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.media.2026.104325_b22","article-title":"Scaling up self-supervised learning for improved surgical foundation models","author":"Jaspers","year":"2025","journal-title":"Med. Image Anal."},{"issue":"5","key":"10.1016\/j.media.2026.104325_b23","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":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104325_b24","series-title":"2018 IEEE Winter Conference on Applications of Computer Vision","first-page":"691","article-title":"Tool detection and operative skill assessment in surgical videos using region-based convolutional neural networks","author":"Jin","year":"2018"},{"issue":"3","key":"10.1016\/j.media.2026.104325_b25","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1109\/TMI.2019.2931158","article-title":"Future-state predicting LSTM for early surgery type recognition","volume":"39","author":"Kannan","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104325_b26","series-title":"Information Processing in Computer-Assisted Interventions - 5th International Conference, IPCAI 2014, Fukuoka, Japan, June 28, 2014. Proceedings","first-page":"158","article-title":"Knowledge-driven formalization of laparoscopic surgeries for rule-based intraoperative context-aware assistance","volume":"vol. 8498","author":"Katic","year":"2014"},{"key":"10.1016\/j.media.2026.104325_b27","doi-asserted-by":"crossref","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","author":"Lavanchy","year":"2024","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"issue":"7","key":"10.1016\/j.media.2026.104325_b28","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1007\/s11548-024-03147-6","article-title":"Parameter-efficient framework for surgical action triplet recognition","volume":"19","author":"Li","year":"2024","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.104325_b29","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"399","article-title":"Instrument-tissue interaction quintuple detection in surgery videos","author":"Lin","year":"2022"},{"issue":"2","key":"10.1016\/j.media.2026.104325_b30","doi-asserted-by":"crossref","DOI":"10.1002\/rcs.2632","article-title":"Prediction of remaining surgery duration in laparoscopic videos based on visual saliency and the transformer network","volume":"20","author":"Loukas","year":"2024","journal-title":"Int. J. Med. Robot. Comput. Assist. Surg."},{"key":"10.1016\/j.media.2026.104325_b31","doi-asserted-by":"crossref","DOI":"10.1038\/s41551-017-0132-7","article-title":"Surgical data science for next-generation interventions","volume":"1","author":"Maier-Hein","year":"2017","journal-title":"Nat. Biomed. Eng."},{"key":"10.1016\/j.media.2026.104325_b32","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"426","article-title":"Catanet: Predicting remaining cataract surgery duration","author":"Marafioti","year":"2021"},{"key":"10.1016\/j.media.2026.104325_b33","article-title":"Artificial intelligence for surgical safety: Automatic assessment of the critical view of safety in laparoscopic cholecystectomy using deep learning","author":"Mascagni","year":"2021","journal-title":"Ann. Surg."},{"key":"10.1016\/j.media.2026.104325_b34","series-title":"OpenMMLab\u2019s next generation video understanding toolbox and benchmark","author":"MMAction2 Contributors","year":"2020"},{"key":"10.1016\/j.media.2026.104325_b35","first-page":"1","article-title":"Latent graph representations for critical view of safety assessment","author":"Murali","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"10.1016\/j.media.2026.104325_b36","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1197\/jamia.M2748","article-title":"Validation of knowledge acquisition for surgical process models","volume":"16","author":"Neumuth","year":"2009","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.media.2026.104325_b37","unstructured":"Nwoye, C.I., Elgohary, K., Srinivas, A., Zaid, F., Lavanchy, J.L., Padoy, N., CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR."},{"key":"10.1016\/j.media.2026.104325_b38","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","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.2026.104325_b39","series-title":"Data splits and metrics for benchmarking methods on surgical action triplet datasets","author":"Nwoye","year":"2022"},{"key":"10.1016\/j.media.2026.104325_b40","doi-asserted-by":"crossref","first-page":"102433","DOI":"10.1016\/j.media.2022.102433","article-title":"Rendezvous: Attention mechanisms for the recognition of surgical action triplets in endoscopic videos","volume":"78","author":"Nwoye","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104325_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102888","article-title":"CholecTriplet2022: Show me a tool and tell me the triplet \u2014 An endoscopic vision challenge for surgical action triplet detection","volume":"89","author":"Nwoye","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104325_b42","doi-asserted-by":"crossref","unstructured":"Osman, N., Camporese, G., Coscia, P., Ballan, L., 2021. Slowfast rolling-unrolling lstms for action anticipation in egocentric videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3437\u20133445.","DOI":"10.1109\/ICCVW54120.2021.00383"},{"issue":"3","key":"10.1016\/j.media.2026.104325_b43","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."},{"key":"10.1016\/j.media.2026.104325_b44","first-page":"1","article-title":"Multi-task temporal convolutional networks for joint recognition of surgical phases and steps in gastric bypass procedures","author":"Ramesh","year":"2021","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.104325_b45","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."},{"issue":"1","key":"10.1016\/j.media.2026.104325_b46","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1038\/s41597-023-02073-7","article-title":"Cholec80-CVS: An open dataset with an evaluation of strasberg\u2019s critical view of safety for AI","volume":"10","author":"R\u00edos","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2026.104325_b47","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"752","article-title":"Rethinking anticipation tasks: Uncertainty-aware anticipation of sparse surgical instrument usage for context-aware assistance","author":"Rivoir","year":"2020"},{"key":"10.1016\/j.media.2026.104325_b48","first-page":"1","article-title":"Rendezvous in time: An attention-based temporal fusion approach for surgical triplet recognition","author":"Sharma","year":"2023","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.104325_b49","series-title":"Medical Image Computing and Computer Assisted Intervention","first-page":"505","article-title":"Surgical action triplet detection by mixed supervised learning of instrument-tissue interactions","author":"Sharma","year":"2023"},{"key":"10.1016\/j.media.2026.104325_b50","doi-asserted-by":"crossref","unstructured":"Sou\u010dek, T., Alayrac, J.B., Miech, A., Laptev, I., Sivic, J., 2022. Look for the change: Learning object states and state-modifying actions from untrimmed web videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13956\u201313966.","DOI":"10.1109\/CVPR52688.2022.01357"},{"key":"10.1016\/j.media.2026.104325_b51","doi-asserted-by":"crossref","unstructured":"Stegm\u00fcller, T., Lebailly, T., Bozorgtabar, B., Tuytelaars, T., Thiran, J.P., 2023. CrOC: Cross-view online clustering for dense visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7000\u20137009.","DOI":"10.1109\/CVPR52729.2023.00676"},{"issue":"1","key":"10.1016\/j.media.2026.104325_b52","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":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"4","key":"10.1016\/j.media.2026.104325_b53","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":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104325_b54","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"442","article-title":"Towards holistic surgical scene understanding","author":"Valderrama","year":"2022"},{"issue":"1","key":"10.1016\/j.media.2026.104325_b55","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/JPROC.2019.2946993","article-title":"CAI4CAI: The rise of contextual Artificial Intelligence in computer-assisted interventions","volume":"108","author":"Vercauteren","year":"2019","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.media.2026.104325_b56","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102770","article-title":"Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the HeiChole benchmark","volume":"86","author":"Wagner","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104325_b57","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, B., Zhao, Z., Tong, Z., He, Y., Wang, Y., Wang, Y., Qiao, Y., 2023. VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 14549\u201314560.","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"10.1016\/j.media.2026.104325_b58","series-title":"Machine Learning for Healthcare Conference","first-page":"283","article-title":"Intraoperative adverse event detection in laparoscopic surgery: Stabilized multi-stage temporal convolutional network with focal-uncertainty loss","author":"Wei","year":"2021"},{"key":"10.1016\/j.media.2026.104325_b59","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2023.102314","article-title":"Nonlinear regression of remaining surgery duration from videos via Bayesian LSTM-based deep negative correlation learning","volume":"110","author":"Wu","year":"2023","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.media.2026.104325_b60","series-title":"Hypergraph-transformer (HGT) for interactive event prediction in laparoscopic and robotic surgery","author":"Yin","year":"2024"},{"key":"10.1016\/j.media.2026.104325_b61","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102611","article-title":"Anticipation for surgical workflow through instrument interaction and recognized signals","volume":"82","author":"Yuan","year":"2022","journal-title":"Med. Image Anal."}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003944?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003944?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T12:54:35Z","timestamp":1793624075000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526003944"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":61,"alternative-id":["S1361841526003944"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104325","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"State-change learning for prediction of future events in endoscopic videos","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104325","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104325"}}