{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T18:26:17Z","timestamp":1794853577756,"version":"4.9.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032382320","type":"print"},{"value":"9783032382337","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-38233-7_2","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T20:55:26Z","timestamp":1790283326000},"page":"14-24","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["AffordTissue: Dense Affordance Prediction for\u00a0Tool-Action Specific Tissue Interaction"],"prefix":"10.1007","author":[{"given":"Aiza","family":"Maksutova","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lalithkumar","family":"Seenivasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiru","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenhao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyan","family":"Jing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathias","family":"Unberath","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"2_CR1","unstructured":"AI, M., et\u00a0al.: Sam 3: segment anything with concepts. In: International Conference on Learning Representations (ICLR) (2026). https:\/\/openreview.net\/forum?id=r35clVtGzw"},{"key":"2_CR2","unstructured":"Allan, M., et\u00a0al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2d human pose estimation: new benchmark and state of the art analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.471"},{"issue":"1","key":"2_CR4","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1146\/annurev-control-062420-090543","volume":"4","author":"A Attanasio","year":"2021","unstructured":"Attanasio, A., Scaglioni, B., De Momi, E., Fiorini, P., Valdastri, P.: Autonomy in surgical robotics. Ann. Rev. Control Rob. Auton. Syst. 4(1), 651\u2013679 (2021)","journal-title":"Ann. Rev. Control Rob. Auton. Syst."},{"key":"2_CR5","unstructured":"Black, K., et\u00a0al.: $$pi_0$$: a vision-language-action flow model for general robot control. arXiv preprint arXiv:2410.24164 (2024)"},{"issue":"10\u201311","key":"2_CR6","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1177\/02783649241273668","volume":"44","author":"C Chi","year":"2025","unstructured":"Chi, C., et al.: Diffusion policy: visuomotor policy learning via action diffusion. Int. J. Rob. Res. 44(10\u201311), 1684\u20131704 (2025)","journal-title":"Int. J. Rob. Res."},{"key":"2_CR7","unstructured":"Deitke, M., Schwenk, D., Salvador, J., VanderBilt, L., Aniol, K., et\u00a0al.: Molmo and pixmo: open weights and open data for state-of-the-art multimodal models. arXiv preprint arXiv:2409.17146 (2024)"},{"key":"2_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1007\/3-540-45468-3_62","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2001","author":"G Gerig","year":"2001","unstructured":"Gerig, G., Jomier, M., Chakos, M.: Valmet: a new validation tool for assessing and improving 3D object segmentation. In: Niessen, W.J., Viergever, M.A. (eds.) MICCAI 2001. LNCS, vol. 2208, pp. 516\u2013523. Springer, Heidelberg (2001). https:\/\/doi.org\/10.1007\/3-540-45468-3_62"},{"issue":"2","key":"2_CR9","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/TMRB.2019.2913282","volume":"1","author":"T Haidegger","year":"2019","unstructured":"Haidegger, T.: Autonomy for surgical robots: concepts and paradigms. IEEE Trans. Med. Rob. Bionics 1(2), 65\u201376 (2019)","journal-title":"IEEE Trans. Med. Rob. Bionics"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Kim, J.W., et\u00a0al.: Srt-h: a hierarchical framework for autonomous surgery via language-conditioned imitation learning. Sci. Rob. 10(104), eadt5254 (2025)","DOI":"10.1126\/scirobotics.adt5254"},{"key":"2_CR12","unstructured":"Kim, M.J., et al.: Openvla: an open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2_CR15","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Lu, D.V., Hershberger, D., Smart, W.D.: Layered costmaps for context-sensitive navigation. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 709\u2013715. IEEE (2014)","DOI":"10.1109\/IROS.2014.6942636"},{"key":"2_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102306","volume":"76","author":"L Maier-Hein","year":"2022","unstructured":"Maier-Hein, L., et al.: Surgical data science-from concepts toward clinical translation. Med. Image Anal. 76, 102306 (2022)","journal-title":"Med. Image Anal."},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV) (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Feichtenhofer, C., Grauman, K.: Grounded human-object interaction hotspots from video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8688\u20138697 (2019)","DOI":"10.1109\/ICCV.2019.00878"},{"key":"2_CR20","unstructured":"Oh, K.H., et al.: Expanded comprehensive robotic cholecystectomy dataset (crcd). arXiv preprint arXiv:2412.12238 (2024)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"2_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"issue":"2","key":"2_CR23","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1109\/LRA.2022.3227873","volume":"8","author":"PM Scheikl","year":"2022","unstructured":"Scheikl, P.M., et al.: Sim-to-real transfer for visual reinforcement learning of deformable object manipulation for robot-assisted surgery. IEEE Rob. Autom. Lett. 8(2), 560\u2013567 (2022)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"2_CR24","unstructured":"Team, O.M., et al.: Octo: an open-source generalist robot policy. arXiv preprint arXiv:2405.12213 (2024)"},{"key":"2_CR25","unstructured":"Tschannen, M., et al.: Siglip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"issue":"1","key":"2_CR26","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., De 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":"2_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. (2017)"},{"key":"2_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102770","volume":"86","author":"M Wagner","year":"2023","unstructured":"Wagner, M., et al.: Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the heichole benchmark. Med. Image Anal. 86, 102770 (2023)","journal-title":"Med. Image Anal."},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Xu, R., et\u00a0al.: A0: an affordance-aware hierarchical model for general robotic manipulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13491\u201313501 (2025)","DOI":"10.1109\/ICCV51701.2025.01253"},{"key":"2_CR30","unstructured":"Yang, A., Yang, B., Zhang, B., Hui, B., et\u00a0al.: Qwen2.5 technical report. arXiv preprint arXiv:2412.15115 (2024)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"2_CR32","unstructured":"Zia, A., et al.: Surgical visual understanding (surgvu) dataset. arXiv preprint arXiv:2501.09209 (2025)"},{"key":"2_CR33","unstructured":"Zitkovich, B., et\u00a0al.: Rt-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning, pp. 2165\u20132183. PMLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38233-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T20:55:32Z","timestamp":1790283332000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38233-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"ISBN":["9783032382320","9783032382337"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38233-7_2","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-032-38233-7","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"assertion":[{"value":"25 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"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":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2026\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}