{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:20:59Z","timestamp":1780420859321,"version":"3.54.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051134","type":"print"},{"value":"9783032051141","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-05114-1_45","type":"book-chapter","created":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:29Z","timestamp":1758377429000},"page":"467-477","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Recognizing Surgical Phases Anywhere: Few-Shot Test-Time Adaptation and\u00a0Task-Graph Guided Refinement"],"prefix":"10.1007","author":[{"given":"Kun","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingxuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jo\u00ebl L.","family":"Lavanchy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Heiliger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ege","family":"\u00d6zsoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vinkle","family":"Srivastav","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongliang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Padoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,21]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Alapatt, D., Murali, A., Srivastav, V., Consortium, A., Mascagni, P., Padoy, N.: Jumpstarting surgical computer vision. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 328\u2013338. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_31"},{"key":"45_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/978-3-030-59716-0_33","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"T Czempiel","year":"2020","unstructured":"Czempiel, T., et al.: TeCNO: surgical phase recognition with multi-stage temporal convolutional networks. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 343\u2013352. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_33"},{"issue":"4","key":"45_CR3","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1097\/SLA.0000000000004425","volume":"273","author":"CR Garrow","year":"2021","unstructured":"Garrow, C.R., et al.: Machine learning for surgical phase recognition: a systematic review. Ann. Surg. 273(4), 684\u2013693 (2021)","journal-title":"Ann. Surg."},{"key":"45_CR4","unstructured":"Honarmand, M., Jamal, M.A., Mohareri, O.: Vidlpro: a video-language pre-training framework for robotic and laparoscopic surgery. In: Advancements In Medical Foundation Models: Explainability, Robustness, Security, and Beyond (2024)"},{"key":"45_CR5","unstructured":"Hu, M., et\u00a0al.: Ophclip: hierarchical retrieval-augmented learning for ophthalmic surgical video-language pretraining. arXiv preprint arXiv:2411.15421 (2024)"},{"issue":"9","key":"45_CR6","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","volume":"29","author":"Z Huang","year":"2023","unstructured":"Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T.J., Zou, J.: A visual-language foundation model for pathology image analysis using medical twitter. Nat. Med. 29(9), 2307\u20132316 (2023)","journal-title":"Nat. Med."},{"key":"45_CR7","unstructured":"Ikezogwo, W., et al.: Quilt-1M: one million image-text pairs for histopathology. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"45_CR8","unstructured":"Jaspers, T.J., et\u00a0al.: Scaling up self-supervised learning for improved surgical foundation models. arXiv preprint arXiv:2501.09436 (2025)"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Lavanchy, J.L., et al.: Challenges in multi-centric generalization: phase and step recognition in Roux-en-Y gastric bypass surgery. Int. J. Comput. Assis. Radiol. Sur. 19, 1\u20139 (2024)","DOI":"10.1007\/s11548-024-03166-3"},{"key":"45_CR10","unstructured":"Ma, C., et al.: Eye-gaze guided multi-modal alignment for medical representation learning. In: Advances in Neural Information Processing Systems, vol. 37, pp. 6126\u20136153 (2025)"},{"issue":"9","key":"45_CR11","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1038\/s41551-017-0132-7","volume":"1","author":"L Maier-Hein","year":"2017","unstructured":"Maier-Hein, L., et al.: Surgical data science for next-generation interventions. Nature Biomed. Eng. 1(9), 691\u2013696 (2017)","journal-title":"Nature Biomed. Eng."},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Mascagni, P., et\u00a0al.: Computer vision in surgery: from potential to clinical value. NPJ Digital Med. 5(1), 163 (2022)","DOI":"10.1038\/s41746-022-00707-5"},{"key":"45_CR13","unstructured":"Murali, A., et al..: Latent graph representations for critical view of safety assessment. arXiv preprint arXiv:2212.04155 (2022)"},{"key":"45_CR14","doi-asserted-by":"crossref","unstructured":"\u00d6zsoy, E., Pellegrini, C., Keicher, M., Navab, N.: Oracle: large vision-language models for knowledge-guided holistic or domain modeling. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 455\u2013465. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_43"},{"key":"45_CR15","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"45_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102844","volume":"88","author":"S Ramesh","year":"2023","unstructured":"Ramesh, S., et al.: Dissecting self-supervised learning methods for surgical computer vision. Med. Image Anal. 88, 102844 (2023)","journal-title":"Med. Image Anal."},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Shakeri, F., et al.: Few-shot adaptation of medical vision-language models. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 553\u2013563. Springer (2024)","DOI":"10.1007\/978-3-031-72390-2_52"},{"key":"45_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103357","volume":"99","author":"J Silva-Rodriguez","year":"2025","unstructured":"Silva-Rodriguez, J., Chakor, H., Kobbi, R., Dolz, J., Ayed, I.B.: A foundation language-image model of the retina (flair): encoding expert knowledge in text supervision. Med. Image Anal. 99, 103357 (2025)","journal-title":"Med. Image Anal."},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Silva-Rodriguez, J., Hajimiri, S., Ben\u00a0Ayed, I., Dolz, J.: A closer look at the few-shot adaptation of large vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23681\u201323690 (2024)","DOI":"10.1109\/CVPR52733.2024.02235"},{"issue":"1","key":"45_CR20","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., Mathelin, M., Padoy, N.: EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"45_CR21","doi-asserted-by":"publisher","first-page":"4457","DOI":"10.1109\/TMI.2024.3426953","volume":"43","author":"H Wang","year":"2024","unstructured":"Wang, H., et al.: Video-instrument synergistic network for referring video instrument segmentation in robotic surgery. IEEE Trans. Med. Imaging 43, 4457\u20134469 (2024)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"45_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: Medclip: contrastive learning from unpaired medical images and text. arXiv preprint arXiv:2210.10163 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"45_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Autolaparo: a new dataset of integrated multi-tasks for image-guided surgical automation in laparoscopic hysterectomy. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 486\u2013496. Springer (2022)","DOI":"10.1007\/978-3-031-16449-1_46"},{"key":"45_CR24","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Medklip: medical knowledge enhanced language-image pre-training for x-ray diagnosis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21372\u201321383 (2023)","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"45_CR25","doi-asserted-by":"crossref","unstructured":"Yuan, K., Srivastav, V., Navab, N., Padoy, N.: HecVL: hierarchical video-language pretraining for zero-shot surgical phase recognition. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 306\u2013316. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_29"},{"key":"45_CR26","unstructured":"Yuan, K., Srivastav, V., Navab, N., Padoy, N., et\u00a0al.: Procedure-aware surgical video-language pretraining with hierarchical knowledge augmentation. arXiv preprint arXiv:2410.002632 (2024)"},{"key":"45_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103644","volume":"105","author":"K Yuan","year":"2025","unstructured":"Yuan, K., et al.: Learning multi-modal representations by watching hundreds of surgical video lectures. Med. Image Anal. 105, 103644 (2025)","journal-title":"Med. Image Anal."},{"key":"45_CR28","unstructured":"Zhang, R., et al.: Tip-adapter: training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930 (2021)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05114-1_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:36Z","timestamp":1758377436000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05114-1_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"ISBN":["9783032051134","9783032051141"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05114-1_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,21]]},"assertion":[{"value":"21 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}