{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:09:26Z","timestamp":1778080166882,"version":"3.51.4"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031720888","type":"print"},{"value":"9783031720895","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72089-5_52","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:02:20Z","timestamp":1727884940000},"page":"553-563","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["See, Predict, Plan: Diffusion for\u00a0Procedure Planning in\u00a0Robotic Surgical Videos"],"prefix":"10.1007","author":[{"given":"Ziyuan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fen","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xulei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianli","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cuntai","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. Kevin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"52_CR1","doi-asserted-by":"crossref","unstructured":"Bi, J., Luo, J., Xu, C.: Procedure planning in instructional videos via contextual modeling and model-based policy learning. In: IEEE CVPR. pp. 15611\u201315620 (2021)","DOI":"10.1109\/ICCV48922.2021.01532"},{"issue":"1","key":"52_CR2","doi-asserted-by":"publisher","first-page":"6676","DOI":"10.1038\/s41467-023-42451-8","volume":"14","author":"J Cao","year":"2023","unstructured":"Cao, J., Yip, H.C., Chen, Y., Scheppach, M., Luo, X., Yang, H., Cheng, M.K., Long, Y., Jin, Y., Chiu, P.W.Y., et\u00a0al.: Intelligent surgical workflow recognition for endoscopic submucosal dissection with real-time animal study. Nature Communications 14(1), \u00a06676 (2023)","journal-title":"Nature Communications"},{"key":"52_CR3","doi-asserted-by":"crossref","unstructured":"Chang, C.Y., Huang, D.A., Xu, D., Adeli, E., Fei-Fei, L., Niebles, J.C.: Procedure planning in instructional videos. In: European Conference on Computer Vision. pp. 334\u2013350. Springer (2020)","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"52_CR4","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34, 8780\u20138794 (2021)","journal-title":"Advances in neural information processing systems"},{"key":"52_CR5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"52_CR6","doi-asserted-by":"crossref","unstructured":"Ehsani, K., Han, W., Herrasti, A., VanderBilt, E., Weihs, L., Kolve, E., Kembhavi, A., Mottaghi, R.: Manipulathor: A framework for visual object manipulation. In: IEEE CVPR. pp. 4497\u20134506 (2021)","DOI":"10.1109\/CVPR46437.2021.00447"},{"key":"52_CR7","doi-asserted-by":"crossref","unstructured":"Funke, I., Bodenstedt, S., Oehme, F., von Bechtolsheim, F., Weitz, J., Speidel, S.: Using 3d convolutional neural networks to learn spatiotemporal features for automatic surgical gesture recognition in video. In: MICCAI. pp. 467\u2013475. Springer (2019)","DOI":"10.1007\/978-3-030-32254-0_52"},{"key":"52_CR8","doi-asserted-by":"crossref","unstructured":"Gao, X., Jin, Y., Dou, Q., Fu, C.W., Heng, P.A.: Accurate grid keypoint learning for efficient video prediction. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 5908\u20135915. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636874"},{"key":"52_CR9","doi-asserted-by":"crossref","unstructured":"Gao, X., Jin, Y., Zhao, Z., Dou, Q., Heng, P.A.: Future frame prediction for robot-assisted surgery. In: International Conference on Information Processing in Medical Imaging. pp. 533\u2013544. Springer (2021)","DOI":"10.1007\/978-3-030-78191-0_41"},{"key":"52_CR10","doi-asserted-by":"crossref","unstructured":"Gubert, L.C., da\u00a0Costa, C.A., Righi, R.d.R.: Context awareness in healthcare: a systematic literature review. Universal Access in the Information Society 19, 245\u2013259 (2020)","DOI":"10.1007\/s10209-019-00664-z"},{"key":"52_CR11","unstructured":"Hashimoto, D.A., Rosman, G., Meireles, O.R.: Artificial intelligence in surgery: understanding the role of AI in surgical practice. McGraw Hill Professional (2021)"},{"key":"52_CR12","unstructured":"Ho, J., Chan, W., Saharia, C., Whang, J., Gao, R., Gritsenko, A., Kingma, D.P., Poole, B., Norouzi, M., Fleet, D.J., et\u00a0al.: Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"52_CR13","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Advances in neural information processing systems 33, 6840\u20136851 (2020)","journal-title":"Advances in neural information processing systems"},{"key":"52_CR14","doi-asserted-by":"crossref","unstructured":"Jin, Y., Cheng, K., Dou, Q., Heng, P.A.: Incorporating temporal prior from motion flow for instrument segmentation in minimally invasive surgery video. In: MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part V 22. pp. 440\u2013448. Springer (2019)","DOI":"10.1007\/978-3-030-32254-0_49"},{"issue":"7","key":"52_CR15","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.: Temporal memory relation network for workflow recognition from surgical video. IEEE Transactions on Medical Imaging 40(7), 1911\u20131923 (2021)","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"52_CR16","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neucom.2022.01.029","volume":"479","author":"H Li","year":"2022","unstructured":"Li, H., Yang, Y., Chang, M., Chen, S., Feng, H., Xu, Z., Li, Q., Chen, Y.: Srdiff: Single image super-resolution with diffusion probabilistic models. Neurocomputing 479, 47\u201359 (2022)","journal-title":"Neurocomputing"},{"issue":"9","key":"52_CR17","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., Vedula, S.S., Speidel, S., Navab, N., Kikinis, R., Park, A., Eisenmann, M., Feussner, H., Forestier, G., Giannarou, S., et\u00a0al.: Surgical data science for next-generation interventions. Nature Biomedical Engineering 1(9), 691\u2013696 (2017)","journal-title":"Nature Biomedical Engineering"},{"key":"52_CR18","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: Howto100m: Learning a text-video embedding by watching hundred million narrated video clips. In: IEEE CVPR. pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"52_CR19","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning. pp. 8162\u20138171. PMLR (2021)"},{"issue":"2","key":"52_CR20","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1080\/13645706.2019.1584116","volume":"28","author":"N Padoy","year":"2019","unstructured":"Padoy, N.: Machine and deep learning for workflow recognition during surgery. Minimally Invasive Therapy & Allied Technologies 28(2), 82\u201390 (2019)","journal-title":"Minimally Invasive Therapy & Allied Technologies"},{"key":"52_CR21","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: International conference on machine learning. pp. 2778\u20132787. PMLR (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"52_CR22","doi-asserted-by":"crossref","unstructured":"Peng, W., Adeli, E., Bosschieter, T., Park, S.H., Zhao, Q., Pohl, K.M.: Generating realistic brain mris via a conditional diffusion probabilistic model. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 14\u201324. Springer (2023)","DOI":"10.1007\/978-3-031-43993-3_2"},{"key":"52_CR23","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"52_CR24","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International conference on machine learning. pp. 2256\u20132265. PMLR (2015)"},{"key":"52_CR25","unstructured":"Srinivas, A., Jabri, A., Abbeel, P., Levine, S., Finn, C.: Universal planning networks: Learning generalizable representations for visuomotor control. In: International Conference on Machine Learning. pp. 4732\u20134741. PMLR (2018)"},{"issue":"2","key":"52_CR26","doi-asserted-by":"publisher","first-page":"4924","DOI":"10.1109\/LRA.2022.3150855","volume":"7","author":"J Sun","year":"2022","unstructured":"Sun, J., Huang, D.A., Lu, B., Liu, Y.H., Zhou, B., Garg, A.: Plate: Visually-grounded planning with transformers in procedural tasks. IEEE Robotics and Automation Letters 7(2), 4924\u20134930 (2022)","journal-title":"IEEE Robotics and Automation Letters"},{"key":"52_CR27","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.: Towards holistic surgical scene understanding. In: MICCAI. pp. 442\u2013452. Springer (2022)","DOI":"10.1007\/978-3-031-16449-1_42"},{"key":"52_CR28","doi-asserted-by":"crossref","unstructured":"Wang, H., Wu, Y., Guo, S., Wang, L.: Pdpp: Projected diffusion for procedure planning in instructional videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14836\u201314845 (2023)","DOI":"10.1109\/CVPR52729.2023.01425"},{"key":"52_CR29","doi-asserted-by":"crossref","unstructured":"Wang, P.: The applications of generative adversarial network in surgical videos. In: Third International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI 2022). vol. 12509, pp. 300\u2013305. SPIE (2023)","DOI":"10.1117\/12.2656026"},{"issue":"3","key":"52_CR30","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/TG.2018.2877047","volume":"11","author":"M Wydmuch","year":"2018","unstructured":"Wydmuch, M., Kempka, M., Ja\u015bkowski, W.: Vizdoom competitions: Playing doom from pixels. IEEE Transactions on Games 11(3), 248\u2013259 (2018)","journal-title":"IEEE Transactions on Games"},{"key":"52_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, H., Hadji, I., Dvornik, N., Derpanis, K.G., Wildes, R.P., Jepson, A.D.: P3iv: Probabilistic procedure planning from instructional videos with weak supervision. In: IEEE CVPR. pp. 2938\u20132948 (2022)","DOI":"10.1109\/CVPR52688.2022.00295"},{"key":"52_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102240","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.: Anchor-guided online meta adaptation for fast one-shot instrument segmentation from robotic surgical videos. Medical Image Analysis 74, 102240 (2021)","journal-title":"Medical Image Analysis"},{"key":"52_CR33","unstructured":"Zhou, Z., Alabi, O., Wei, M., Vercauteren, T., Shi, M.: Text promptable surgical instrument segmentation with vision-language models. Advances in Neural Information Processing Systems 36 (2024)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72089-5_52","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:08:16Z","timestamp":1727885296000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72089-5_52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720888","9783031720895"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72089-5_52","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are 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":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}