{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T21:06:00Z","timestamp":1778101560774,"version":"3.51.4"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T00:00:00Z","timestamp":1671580800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T00:00:00Z","timestamp":1671580800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"DOI":"10.1007\/s11548-022-02811-z","type":"journal-article","created":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T06:03:58Z","timestamp":1671602638000},"page":"785-794","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Surgical workflow recognition with temporal convolution and transformer for action segmentation"],"prefix":"10.1007","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1906-2116","authenticated-orcid":false,"given":"Bokai","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bharti","family":"Goel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad Hasan","family":"Sarhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Varun Kejriwal","family":"Goel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rami","family":"Abukhalil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bindu","family":"Kalesan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Natalie","family":"Stottler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Svetlana","family":"Petculescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,21]]},"reference":[{"issue":"8","key":"2811_CR1","doi-asserted-by":"publisher","first-page":"3285","DOI":"10.1007\/s00464-020-07628-y","volume":"34","author":"LS Feldman","year":"2020","unstructured":"Feldman LS, Pryor AD, Gardner AK, Dunkin BJ, Schultz L, Awad MM, Ritter EM (2020) Sages video-based assessment (VBA) program: a vision for life-long learning for surgeons. Surg Endosc 34(8):3285\u20133288","journal-title":"Surg Endosc"},{"issue":"1","key":"2811_CR2","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda AP, Shehata S, Mutter D, Marescaux J, De Mathelin M, Padoy N (2016) Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans Med Imaging 36(1):86\u201397","journal-title":"IEEE Trans Med Imaging"},{"key":"2811_CR3","doi-asserted-by":"crossref","unstructured":"Zia A, Hung A, Essa I, Jarc A (2018) Surgical activity recognition in robot-assisted radical prostatectomy using deep learning. In: International conference on medical image computing and computer-assisted intervention, pp. 273\u2013280 . Springer","DOI":"10.1007\/978-3-030-00937-3_32"},{"issue":"5","key":"2811_CR4","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1109\/TMI.2017.2787657","volume":"37","author":"Y Jin","year":"2017","unstructured":"Jin Y, Dou Q, Chen H, Yu L, Qin J, Fu C-W, Heng P-A (2017) SV-RCnet: workflow recognition from surgical videos using recurrent convolutional network. IEEE Trans Med Imaging 37(5):1114\u20131126","journal-title":"IEEE Trans Med Imaging"},{"key":"2811_CR5","doi-asserted-by":"crossref","unstructured":"Zisimopoulos O, Flouty E, Luengo I, Giataganas P, Nehme J, Chow A, Stoyanov D (2018) Deepphase: surgical phase recognition in cataracts videos. In: International conference on medical image computing and computer-assisted intervention, pp. 265\u2013272 . Springer","DOI":"10.1007\/978-3-030-00937-3_31"},{"issue":"3","key":"2811_CR6","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1097\/SLA.0000000000003460","volume":"270","author":"DA Hashimoto","year":"2019","unstructured":"Hashimoto DA, Rosman G, Witkowski ER, Stafford C, Navarrete-Welton AJ, Rattner DW, Lillemoe KD, Rus DL, Meireles OR (2019) Computer vision analysis of intraoperative video: automated recognition of operative steps in laparoscopic sleeve gastrectomy. Ann Surg 270(3):414","journal-title":"Ann Surg"},{"issue":"4","key":"2811_CR7","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1007\/s11548-018-1882-8","volume":"14","author":"H Nakawala","year":"2019","unstructured":"Nakawala H, Bianchi R, Pescatori LE, De Cobelli O, Ferrigno G, De Momi E (2019) \u201cDeep-Onto\u2019\u2019 network for surgical workflow and context recognition. Int J Comput Assist Radiol Surg 14(4):685\u2013696","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"2811_CR8","doi-asserted-by":"publisher","first-page":"101572","DOI":"10.1016\/j.media.2019.101572","volume":"59","author":"Y Jin","year":"2020","unstructured":"Jin Y, Li H, Dou Q, Chen H, Qin J, Fu C-W, Heng P-A (2020) Multi-task recurrent convolutional network with correlation loss for surgical video analysis. Med Image Anal 59:101572","journal-title":"Med Image Anal"},{"key":"2811_CR9","doi-asserted-by":"crossref","unstructured":"Farha YA, Gall J (2019) Ms-tcn: Multi-stage temporal convolutional network for action segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 3575\u20133584","DOI":"10.1109\/CVPR.2019.00369"},{"issue":"7","key":"2811_CR10","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1007\/s11548-021-02388-z","volume":"16","author":"S Ramesh","year":"2021","unstructured":"Ramesh S, Dall\u2019Alba D, Gonzalez C, Yu T, Mascagni P, Mutter D, Marescaux J, Fiorini P, Padoy N (2021) Multi-task temporal convolutional networks for joint recognition of surgical phases and steps in gastric bypass procedures. Int J Comput Assist Radiol Surg 16(7):1111\u20131119","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"2811_CR11","unstructured":"Zhang B, Ghanem A, Simes A, Choi H, Yoo A, Min A (2021) Swnet: surgical workflow recognition with deep convolutional network. In: Medical imaging with deep learning, pp. 855\u2013869. PMLR"},{"issue":"5","key":"2811_CR12","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1007\/s11548-022-02616-0","volume":"17","author":"R Sanchez-Matilla","year":"2022","unstructured":"Sanchez-Matilla R, Robu M, Grammatikopoulou M, Luengo I, Stoyanov D (2022) Data-centric multi-task surgical phase estimation with sparse scene segmentation. Int J Comput Assist Radiol Surg 17(5):953\u2013960","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"2811_CR13","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Guyon I, Von Luxburg U, Bengio S, Wallach HM, Fergus R, Vishwanathan SVN, Garnett R (eds) Advances in neural information processing systems 30: annual conference on neural information processing systems 2017, December 4-9, 2017. Long Beach, CA, USA, pp 5998\u20136008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845"},{"key":"2811_CR14","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. In: International conference on learning representations"},{"key":"2811_CR15","doi-asserted-by":"crossref","unstructured":"Arnab A, Dehghani M, Heigold G, Sun C, Lu\u010di\u0107 M, Schmid C (2021) Vivit: A video vision transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 6836\u20136846","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"2811_CR16","doi-asserted-by":"crossref","unstructured":"Valderrama N, Ruiz\u00a0Puentes P, Hern\u00e1ndez I, Ayobi N, Verlyck M, Santander J, Caicedo J, Fern\u00e1ndez N, Arbel\u00e1ez P (2022) Towards holistic surgical scene understanding. In: International conference on medical image computing and computer-assisted intervention, pp. 442\u2013452. Springer","DOI":"10.1007\/978-3-031-16449-1_42"},{"key":"2811_CR17","doi-asserted-by":"crossref","unstructured":"Czempiel T, Paschali M, Keicher M, Simson W, Feussner H, Kim ST, Navab N (2020) Tecno: Surgical phase recognition with multi-stage temporal convolutional networks. In: International conference on medical image computing and computer-assisted intervention, pp. 343\u2013352 . Springer","DOI":"10.1007\/978-3-030-59716-0_33"},{"issue":"7","key":"2811_CR18","doi-asserted-by":"publisher","first-page":"1911","DOI":"10.1109\/TMI.2021.3069471","volume":"40","author":"Y Jin","year":"2021","unstructured":"Jin Y, Long Y, Chen C, Zhao Z, Dou Q, Heng P-A (2021) Temporal memory relation network for workflow recognition from surgical video. IEEE Trans Med Imaging 40(7):1911\u20131923","journal-title":"IEEE Trans Med Imaging"},{"issue":"11","key":"2811_CR19","doi-asserted-by":"publisher","first-page":"2029","DOI":"10.1007\/s11548-021-02473-3","volume":"16","author":"B Zhang","year":"2021","unstructured":"Zhang B, Ghanem A, Simes A, Choi H, Yoo A (2021) Surgical workflow recognition with 3dcnn for sleeve gastrectomy. Int J Comput Assist Radiol Surg 16(11):2029\u20132036","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"2811_CR20","unstructured":"Neimark D, Bar O, Zohar M, Hager GD, Asselmann D (2021) \u201cTrain one, classify one, teach one\u201d-cross-surgery transfer learning for surgical step recognition. In: Medical imaging with deep learning, pp. 532\u2013544. PMLR"},{"key":"2811_CR21","doi-asserted-by":"crossref","unstructured":"Wang Z, Ding X, Zhao W, Li X (2022) Less is more: Surgical phase recognition from timestamp supervision. arXiv preprint arXiv:2202.08199","DOI":"10.1109\/TMI.2023.3242980"},{"key":"2811_CR22","doi-asserted-by":"crossref","unstructured":"Schmidt A, Sharghi A, Haugerud H, Oh D, Mohareri O (2021) Multi-view surgical video action detection via mixed global view attention. In: International conference on medical image computing and computer-assisted intervention, pp. 626\u2013635. Springer","DOI":"10.1007\/978-3-030-87202-1_60"},{"issue":"5","key":"2811_CR23","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1007\/s11548-022-02600-8","volume":"17","author":"A Kadkhodamohammadi","year":"2022","unstructured":"Kadkhodamohammadi A, Luengo I, Stoyanov D (2022) PATG: position-aware temporal graph networks for surgical phase recognition on laparoscopic videos. Int J Comput Assist Radiol Surg 17(5):849\u2013856","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"2811_CR24","doi-asserted-by":"crossref","unstructured":"Czempiel T, Paschali M, Ostler D, Kim ST, Busam B, Navab N (2021) Opera: Attention-regularized transformers for surgical phase recognition. In: International conference on medical image computing and computer-assisted intervention, pp. 604\u2013614. Springer","DOI":"10.1007\/978-3-030-87202-1_58"},{"key":"2811_CR25","doi-asserted-by":"crossref","unstructured":"Zhang B, Abbing J, Ghanem A, Fer D, Barker J, Abukhalil R, Goel VK, Milletar\u00ec F (2022) Towards accurate surgical workflow recognition with convolutional networks and transformers. Comput Methods Biomech Biomed Eng Imaging Vis 10(4):349\u2013356. https:\/\/doi.org\/10.1080\/21681163.2021.2002191","DOI":"10.1080\/21681163.2021.2002191"},{"key":"2811_CR26","doi-asserted-by":"crossref","unstructured":"Gao X, Jin Y, Long Y, Dou Q, Heng P-A (2021) Trans-svnet: accurate phase recognition from surgical videos via hybrid embedding aggregation transformer. In: international conference on medical image computing and computer-assisted intervention, pp. 593\u2013603. Springer","DOI":"10.1007\/978-3-030-87202-1_57"},{"key":"2811_CR27","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (2018) A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6450\u20136459","DOI":"10.1109\/CVPR.2018.00675"},{"key":"2811_CR28","doi-asserted-by":"crossref","unstructured":"Ghadiyaram D, Tran D, Mahajan D (2019) Large-scale weakly-supervised pre-training for video action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 12046\u201312055","DOI":"10.1109\/CVPR.2019.01232"},{"key":"2811_CR29","unstructured":"Yi F, Wen H, Jiang T (2021) Asformer: Transformer for action segmentation. arXiv preprint arXiv:2110.08568"},{"issue":"1","key":"2811_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-79173-6","volume":"10","author":"O Bar","year":"2020","unstructured":"Bar O, Neimark D, Zohar M, Hager GD, Girshick R, Fried GM, Wolf T, Asselmann D (2020) Impact of data on generalization of AI for surgical intelligence applications. Sci Rep 10(1):1\u201312","journal-title":"Sci Rep"},{"key":"2811_CR31","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"2811_CR32","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":"1","key":"2811_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.asjsur.2012.06.002","volume":"36","author":"S-H Chuang","year":"2013","unstructured":"Chuang S-H (2013) From multi-incision to single-incision laparoscopic cholecystectomy step-by-step: one surgeon\u2019s self-taught experience and retrospective analysis. Asian J Surg 36(1):1\u20136","journal-title":"Asian J Surg"},{"issue":"6","key":"2811_CR34","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1016\/j.jsurg.2014.04.009","volume":"71","author":"MS Bethlehem","year":"2014","unstructured":"Bethlehem MS, Kramp KH, van Det MJ, Henk O, Veeger NJ, Pierie JPE (2014) Development of a standardized training course for laparoscopic procedures using Delphi methodology. J Surg Educ 71(6):810\u2013816","journal-title":"J Surg Educ"},{"issue":"2","key":"2811_CR35","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.jamcollsurg.2016.05.006","volume":"223","author":"S Dissanaike","year":"2016","unstructured":"Dissanaike S (2016) A step-by-step guide to laparoscopic subtotal fenestrating cholecystectomy: a damage control approach to the difficult gallbladder. J Am Coll Surg 223(2):15\u201318","journal-title":"J Am Coll Surg"},{"issue":"2","key":"2811_CR36","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1016\/j.amjsurg.2018.11.011","volume":"217","author":"DA Hashimoto","year":"2019","unstructured":"Hashimoto DA, Axelsson CG, Jones CB, Phitayakorn R, Petrusa E, McKinley SK, Gee D, Pugh C (2019) Surgical procedural map scoring for decision-making in laparoscopic cholecystectomy. Am J Surg 217(2):356\u2013361","journal-title":"Am J Surg"},{"key":"2811_CR37","doi-asserted-by":"crossref","unstructured":"Zhang Y, Bano S, Page A-S, Deprest J, Stoyanov D, Vasconcelos F (2022) Retrieval of surgical phase transitions using reinforcement learning. In: International conference on medical image computing and computer-assisted intervention, pp. 497\u2013506. Springer","DOI":"10.1007\/978-3-031-16449-1_47"},{"key":"2811_CR38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021756","author":"S-J Li","year":"2020","unstructured":"Li S-J, AbuFarha Y, Liu Y, Cheng M-M, Gall J (2020) Ms-tcn++: multi-stage temporal convolutional network for action segmentation. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2020.3021756","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"2811_CR39","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1002\/ima.22571","volume":"31","author":"W Zhang","year":"2021","unstructured":"Zhang W, Yang G, Huang H, Yang W, Xu X, Liu Y, Lai X (2021) Me-net: multi-encoder net framework for brain tumor segmentation. Int J Imaging Syst Technol 31(4):1834\u20131848","journal-title":"Int J Imaging Syst Technol"},{"key":"2811_CR40","doi-asserted-by":"crossref","unstructured":"Shi D, Liu R, Tao L, He Z, Huo L (2021) Multi-encoder parse-decoder network for sequential medical image segmentation. In: 2021 IEEE international conference on image processing (ICIP), pp. 31\u201335 . IEEE","DOI":"10.1109\/ICIP42928.2021.9506463"},{"key":"2811_CR41","doi-asserted-by":"crossref","unstructured":"Rahman A, Tasnim S (2014) Ensemble classifiers and their applications: a review. arXiv preprint arXiv:1404.4088","DOI":"10.14445\/22312803\/IJCTT-V10P107"},{"key":"2811_CR42","doi-asserted-by":"crossref","unstructured":"Yang P, Hwa\u00a0Yang Y, B\u00a0Zhou B, Y\u00a0Zomaya A (2010) A review of ensemble methods in bioinformatics. Curr Bioinform 5(4):296\u2013308","DOI":"10.2174\/157489310794072508"},{"issue":"2","key":"2811_CR43","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1093\/bib\/bbab569","volume":"23","author":"SR Stahlschmidt","year":"2022","unstructured":"Stahlschmidt SR, Ulfenborg B, Synnergren J (2022) Multimodal deep learning for biomedical data fusion: a review. Brief Bioinform 23(2):569","journal-title":"Brief Bioinform"},{"key":"2811_CR44","doi-asserted-by":"crossref","unstructured":"Lea C, Vidal R, Hager GD (2016) Learning convolutional action primitives for fine-grained action recognition. In: 2016 IEEE international conference on robotics and automation (ICRA), pp. 1642\u20131649. IEEE","DOI":"10.1109\/ICRA.2016.7487305"},{"key":"2811_CR45","doi-asserted-by":"crossref","unstructured":"Lea C, Flynn MD, Vidal R, Reiter A, Hager GD (2017) Temporal convolutional networks for action segmentation and detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 156\u2013165","DOI":"10.1109\/CVPR.2017.113"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-022-02811-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-022-02811-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-022-02811-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,25]],"date-time":"2023-03-25T11:18:43Z","timestamp":1679743123000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-022-02811-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,21]]},"references-count":45,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["2811"],"URL":"https:\/\/doi.org\/10.1007\/s11548-022-02811-z","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,21]]},"assertion":[{"value":"8 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Bokai Zhang, Bharti Goel, Mohammad Hasan Sarhan, Varun Kejriwal Goel, Rami Abukhalil, Bindu Kalesan, Natalie Stottler, and Svetlana Petculescu declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"For this type of study, formal consent is not required.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"This article contains statistical data from an internal dataset which is approved to use for research purposes.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}