{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T02:43:04Z","timestamp":1792809784129,"version":"4.5.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01|S23067"],"award-info":[{"award-number":["01|S23067"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Foundation models, trained on multitudes of public datasets, often require additional fine-tuning or re-prompting mechanisms to be applied to visually distinct target domains such as surgical videos. Further, without domain knowledge, they cannot model the specific semantics of the target domain. Hence, when applied to surgical video segmentation, they fail to generalise to sections where previously tracked objects leave the scene or new objects enter.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We propose\n                      <jats:italic>SASVi<\/jats:italic>\n                      , a novel re-prompting mechanism based on a frame-wise object detection\n                      <jats:italic>Overseer<\/jats:italic>\n                      model, which is trained on a minimal amount of scarcely available annotations for the target domain. This model automatically re-prompts the foundation model\n                      <jats:italic>SAM2<\/jats:italic>\n                      when the scene constellation changes, allowing for temporally smooth and complete segmentation of full surgical videos.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Re-prompting based on our\n                      <jats:italic>Overseer<\/jats:italic>\n                      model significantly improves the temporal consistency of surgical video segmentation compared to similar prompting techniques and especially frame-wise segmentation, which neglects temporal information, by at least 2.4%. Our proposed approach allows us to successfully deploy\n                      <jats:italic>SAM2<\/jats:italic>\n                      to surgical videos, which we quantitatively and qualitatively demonstrate for three different cholecystectomy and cataract surgery datasets.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      <jats:italic>SASVi<\/jats:italic>\n                      can serve as a new baseline for smooth and temporally consistent segmentation of surgical videos with scarcely available annotation data. Our method allows us to leverage scarce annotations and obtain complete annotations for full videos of the large-scale counterpart datasets. We make those annotations publicly available, providing extensive annotation data for the future development of surgical data science models.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-025-03408-y","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T11:22:27Z","timestamp":1747740147000},"page":"1409-1419","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["SASVi: segment any surgical video"],"prefix":"10.1007","volume":"20","author":[{"given":"Ssharvien Kumar","family":"Sivakumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8097-0158","authenticated-orcid":false,"given":"Yannik","family":"Frisch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amin","family":"Ranem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anirban","family":"Mukhopadhyay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,20]]},"reference":[{"key":"3408_CR1","first-page":"1","volume-title":"International conference on pattern recognition","author":"AP Sanner","year":"2024","unstructured":"Sanner AP, Grauhan NF, Meyer M, Leukert L, Brockmann MA, Othman AE, Mukhopadhyay A (2024) Detection of intracranial hemorrhage for trauma patients. International conference on pattern recognition. Springer, Berlin, pp 1\u201314"},{"key":"3408_CR2","first-page":"24","volume":"52","author":"H Al Hajj","year":"2019","unstructured":"Al Hajj H, Lamard M, Conze P-H, Roychowdhury S, Hu X, Mar\u0161alkait\u0117 G, Zisimopoulos O, Dedmari MA, Zhao F, Prellberg J (2019) Cataracts: challenge on automatic tool annotation for cataract surgery. Media 52:24\u201341","journal-title":"Media"},{"issue":"1","key":"3408_CR3","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"},{"issue":"1","key":"3408_CR4","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma J, He Y, Li F, Han L, You C, Wang B (2024) Segment anything in medical images. Nat Commun 15(1):654","journal-title":"Nat Commun"},{"key":"3408_CR5","unstructured":"Yu J, Wang A, Dong W, Xu M, Islam M, Wang J, Bai L, Ren H (2024) Sam 2 in robotic surgery: an empirical evaluation for robustness and generalization in surgical video segmentation. arXiv preprint arXiv:2408.04593"},{"key":"3408_CR6","doi-asserted-by":"crossref","unstructured":"Chen T, Lu A, Zhu L, Ding C, Yu C, Ji D, Li Z, Sun L, Mao P, Zang Y (2024) Sam2-adapter: evaluating & adapting segment anything 2 in downstream tasks: Camouflage, shadow, medical image segmentation, and more. arXiv preprint arXiv:2408.04579","DOI":"10.21203\/rs.3.rs-4876632\/v1"},{"key":"3408_CR7","unstructured":"Kamtam DN, Shrager JB, Malla SD, Wang X, Lin N, Cardona JJ, Yeung-Levy S, Hu C (2025) Surgisam2: fine-tuning a foundational model for surgical video anatomy segmentation and detection. arXiv preprint arXiv:2503.03942"},{"key":"3408_CR8","doi-asserted-by":"crossref","unstructured":"Sheng Y, Bano S, Clarkson MJ, Islam M (2024) Surgical-desam: decoupling sam for instrument segmentation in robotic surgery. IJCARS, pp 1\u20135","DOI":"10.1007\/s11548-024-03163-6"},{"key":"3408_CR9","doi-asserted-by":"publisher","first-page":"6890","DOI":"10.1609\/aaai.v38i7.28514","volume":"38","author":"W Yue","year":"2024","unstructured":"Yue W, Zhang J, Hu K, Xia Y, Luo J, Wang Z (2024) Surgicalsam: efficient class promptable surgical instrument segmentation. AAAI 38:6890\u20136898","journal-title":"AAAI"},{"key":"3408_CR10","doi-asserted-by":"crossref","unstructured":"Wu Z, Schmidt A, Kazanzides P, Salcudean SE (2024) Real-time surgical instrument segmentation in video using point tracking and segment anything. arXiv preprint arXiv:2403.08003","DOI":"10.22541\/au.173089470.05750142\/v1"},{"key":"3408_CR11","unstructured":"Liu H, Zhang E, Wu J, Hong M, Jin Y (2024) Surgical sam 2: real-time segment anything in surgical video by efficient frame pruning. arXiv preprint arXiv:2408.07931"},{"key":"3408_CR12","doi-asserted-by":"crossref","unstructured":"Lou A, Li Y, Zhang Y, Labadie RF, Noble J (2024) Zero-shot surgical tool segmentation in monocular video using segment anything model 2. arXiv preprint arXiv:2408.01648","DOI":"10.1117\/12.3047479"},{"key":"3408_CR13","unstructured":"Ravi N, Gabeur V, Hu Y-T, Hu R, Ryali C, Ma T, Khedr H, R\u00e4dle R, Rolland C, Gustafson L, et\u00a0al (2024) Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714"},{"key":"3408_CR14","first-page":"234","volume-title":"MICCAI","author":"A Wang","year":"2023","unstructured":"Wang A, Islam M, Xu M, Zhang Y, Ren H (2023) Sam meets robotic surgery: an empirical study on generalization, robustness and adaptation. MICCAI. Springer, Berlin, pp 234\u2013244"},{"key":"3408_CR15","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: ICCV","DOI":"10.1109\/ICCV.2017.322"},{"key":"3408_CR16","first-page":"213","volume-title":"ECCV","author":"N Carion","year":"2020","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. ECCV. Springer, Berlin, pp 213\u2013229"},{"key":"3408_CR17","doi-asserted-by":"crossref","unstructured":"Cheng B, Misra I, Schwing AG, Kirillov A, Girdhar R (2022) Masked-attention mask transformer for universal image segmentation. In: CVPR, pp 1290\u20131299","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"3408_CR18","first-page":"341","volume-title":"MICCAI","author":"J Wang","year":"2021","unstructured":"Wang J, Jin Y, Wang L, Cai S, Heng P-A, Qin J (2021) Efficient global-local memory for real-time instrument segmentation of robotic surgical video. MICCAI. Springer, Berlin, pp 341\u2013351"},{"key":"3408_CR19","volume":"74","author":"Z Zhao","year":"2021","unstructured":"Zhao Z, Jin Y, Chen J, Lu B, Ng C-F, Liu Y-H, Dou Q, Heng P-A (2021) Anchor-guided online meta adaptation for fast one-shot instrument segmentation from robotic surgical videos. Media 74:102240","journal-title":"Media"},{"key":"3408_CR20","doi-asserted-by":"crossref","unstructured":"Wu F, Marquez-Neila P, Zheng M, Rafii-Tari H, Sznitman R (2024) Correlation-aware active learning for surgery video segmentation. In: WACV, pp 2010\u20132020","DOI":"10.1109\/WACV57701.2024.00201"},{"key":"3408_CR21","doi-asserted-by":"crossref","unstructured":"Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, Xiao T, Whitehead S, Berg AC, Lo W-Y (2023) Segment anything. In: ICCV, pp 4015\u20134026","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"3408_CR22","unstructured":"Ranem A, Aflal MAM, Fuchs M, Mukhopadhyay A (2024) Uncle sam: Unleashing sam\u2019s potential for continual prostate mri segmentation. In: MIDL"},{"key":"3408_CR23","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":"3408_CR24","volume":"71","author":"M Grammatikopoulou","year":"2021","unstructured":"Grammatikopoulou M, Flouty E, Kadkhodamohammadi A, Quellec G, Chow A, Nehme J, Luengo I, Stoyanov D (2021) Cadis: cataract dataset for surgical RGB-image segmentation. Media 71:102053","journal-title":"Media"},{"key":"3408_CR25","unstructured":"Ghamsarian N, El-Shabrawi Y, Nasirihaghighi S, Putzgruber-Adamitsch D, Zinkernagel M, Wolf S, Schoeffmann K, Sznitman R (2023) Cataract-1k: cataract surgery dataset for scene segmentation, phase recognition, and irregularity detection. arXiv preprint arXiv:2312.06295"},{"key":"3408_CR26","unstructured":"Loshchilov I (2017) Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101"},{"key":"3408_CR27","doi-asserted-by":"crossref","unstructured":"Rivoir D, Pfeiffer M, Docea R, Kolbinger F, Riediger C, Weitz J, Speidel S (2021) Long-term temporally consistent unpaired video translation from simulated surgical 3d data. In: ICCV, pp 3343\u20133353","DOI":"10.1109\/ICCV48922.2021.00333"},{"issue":"7","key":"3408_CR28","first-page":"1217","volume":"18","author":"Y Frisch","year":"2023","unstructured":"Frisch Y, Fuchs M, Mukhopadhyay A (2023) Temporally consistent sequence-to-sequence translation of cataract surgeries. IJCARS 18(7):1217\u20131224","journal-title":"IJCARS"},{"issue":"2","key":"3408_CR29","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein KH (2021) nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18(2):203\u2013211","journal-title":"Nat Methods"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03408-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-025-03408-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03408-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T15:09:38Z","timestamp":1757171378000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-025-03408-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,20]]},"references-count":29,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["3408"],"URL":"https:\/\/doi.org\/10.1007\/s11548-025-03408-y","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,20]]},"assertion":[{"value":"14 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 August 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Horizontal lines have been updated correctly in Tables 1 & 2","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}