{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T23:35:35Z","timestamp":1767310535943,"version":"3.48.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032097835","type":"print"},{"value":"9783032097842","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-09784-2_4","type":"book-chapter","created":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T23:32:21Z","timestamp":1767310341000},"page":"32-41","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Scene Editing for\u00a0Cholecystectomy Surgery"],"prefix":"10.1007","author":[{"given":"\u00c7a\u011fhan","family":"K\u00f6ksal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yousef","family":"Yeganeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Azade","family":"Farshad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"4_CR1","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":"4_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1007\/978-3-030-59716-0_35","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"CI Nwoye","year":"2020","unstructured":"Nwoye, C.I., et al.: Recognition of instrument-tissue interactions in endoscopic videos via action triplets. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 364\u2013374. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_35"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., et al.: Rendezvous: attention mechanisms for the recognition of surgical action triplets in endoscopic videos. Med. Image Anal. 78 (2022)","DOI":"10.1016\/j.media.2022.102433"},{"key":"4_CR4","unstructured":"Mostafa, M.L., et al.: Surgical flow masked autoencoder for event recognition. Med. Imaging Deep Learn. (2025)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"\u00d6zsoy, E., \u00d6rnek, E.P., Eck, U., Czempiel, T., Tombari, F., Navab, N.: 4D-or: semantic scene graphs for or domain modeling. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp.\u00a0475\u2013485. Springer (2022)","DOI":"10.1007\/978-3-031-16449-1_45"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Holm, F., Ghazaei, G., Czempiel, T., \u00d6zsoy, E., Saur, S., Navab, N.: Dynamic scene graph representation for surgical video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp.\u00a081\u201387 (2023)","DOI":"10.1109\/ICCVW60793.2023.00015"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"K\u00f6ksal, \u00c7., Ghazaei, G., Holm, F., Farshad, A., Navab, N.: SANGRIA: surgical video scene graph optimization for surgical workflow prediction. arXiv preprint arXiv:2407.20214 (2024)","DOI":"10.1007\/978-3-031-83243-7_10"},{"issue":"8","key":"4_CR8","doi-asserted-by":"publisher","first-page":"1615","DOI":"10.1007\/s11548-024-03213-z","volume":"19","author":"DG Saragih","year":"2024","unstructured":"Saragih, D.G., Hibi, A., Tyrrell, P.N.: Using diffusion models to generate synthetic labeled data for medical image segmentation. Int. J. Comput. Assist. Radiol. Surg. 19(8), 1615\u20131625 (2024)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Endora: video generation models as endoscopy simulators. In: Linguraru, M.G., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024, pp.\u00a0230\u2013240, Springer, Heidelberg (2024)","DOI":"10.1007\/978-3-031-72089-5_22"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I.: Surgical text-to-image generation. Pattern Recogn. Lett. (2025)","DOI":"10.1016\/j.patrec.2025.02.002"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Frisch, Y., et al.: SurGrID: controllable surgical simulation via scene graph to image diffusion. arXiv preprint arXiv:2502.07945 (2025)","DOI":"10.1007\/s11548-025-03397-y"},{"key":"4_CR12","doi-asserted-by":"publisher","unstructured":"Yeganeh, Y., et al.: VISAGE: video synthesis using action graphs for surgery. In: Celebi, M.E., Reyes, M., Chen, Z., Li, X. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024 Workshops, pp.\u00a0146\u2013156, Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-77610-6_14","DOI":"10.1007\/978-3-031-77610-6_14"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Biagini, D., Navab, N., Farshad, A.: HieraSurg: hierarchy-aware diffusion model for surgical video generation. arXiv preprint arXiv:2506.21287 (2025)","DOI":"10.1007\/978-3-032-05114-1_30"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.\u00a010684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models, pp.\u00a03836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Gao, S., Lin, Z., Xie, X., Zhou, P., Cheng, M.-M., Yan, S.: EditAnything: empowering unparalleled flexibility in image editing and generation. In: Proceedings of the 31st ACM International Conference on Multimedia, pp.\u00a09414\u20139416 (2023)","DOI":"10.1145\/3581783.3612680"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhong, K., Wang, F., Wang, H., Zhao, X.: Surgical workflow image generation based on generative adversarial networks. In: 2018 International Conference on Artificial Intelligence and Big Data (ICAIBD), pp.\u00a082\u201386. IEEE (2018)","DOI":"10.1109\/ICAIBD.2018.8396171"},{"key":"4_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105834","volume":"200","author":"A Marzullo","year":"2021","unstructured":"Marzullo, A., Moccia, S., Catellani, M., Calimeri, F., De Momi, E.: Towards realistic laparoscopic image generation using image-domain translation. Comput. Methods Programs Biomed. 200, 105834 (2021)","journal-title":"Comput. Methods Programs Biomed."},{"key":"4_CR19","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"L\u00fcpke, S., Yeganeh, Y., Adeli, E., Navab, N., Farshad, A.: Physics-informed latent diffusion for multimodal brain MRI synthesis. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp.\u00a0198\u2013207. Springer (2024)","DOI":"10.1007\/978-3-031-84525-3_17"},{"key":"4_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103263","volume":"97","author":"E Colleoni","year":"2024","unstructured":"Colleoni, E., Matilla, R.S., Luengo, I., Stoyanov, D.: Guided image generation for improved surgical image segmentation. Med. Image Anal. 97, 103263 (2024)","journal-title":"Med. Image Anal."},{"key":"4_CR22","first-page":"21143","volume":"38","author":"S Hong","year":"2024","unstructured":"Hong, S., Lee, J., Woo, S.S.: All but one: surgical concept erasing with model preservation in text-to-image diffusion models. Proc. AAAI Conf. Artif. Intell. 38, 21143\u201321151 (2024)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"4_CR23","first-page":"20734","volume":"39","author":"W Sun","year":"2025","unstructured":"Sun, W., Dong, X.-M., Cui, B., Tang, J.: Attentive eraser: unleashing diffusion model\u2019s object removal potential via self-attention redirection guidance. Proc. AAAI Conf. Artif. Intell. 39, 20734\u201320742 (2025)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"4_CR24","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp.\u00a08748\u20138763. PMLR (2021)"},{"key":"4_CR25","unstructured":"Yuan, K., et al.: Learning multi-modal representations by watching hundreds of surgical video lectures. arXiv preprint arXiv:2307.15220 (2023)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, volume 1 (Long and Short Papers), pp.\u00a04171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Xie, S., Zhang, Z., Lin, Z., Hinz, T., Zhang, K.: SmartBrush: text and shape guided object inpainting with diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.\u00a022428\u201322437 (2023)","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Alabi, O., et al.: CholecinstanceSeg: a tool instance segmentation dataset for laparoscopic surgery. arXiv preprint arXiv:2406.16039 (2024)","DOI":"10.1038\/s41597-025-05163-w"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of CVPR, pp.\u00a022500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"}],"container-title":["Lecture Notes in Computer Science","Collaborative Intelligence and Autonomy in Image-Guided Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09784-2_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T23:32:23Z","timestamp":1767310343000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09784-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032097835","9783032097842"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09784-2_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"COLAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Collaborative Intelligence and Autonomy in Image-Guided Surgery","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":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"colas2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/sites.google.com\/view\/miccai-2025-colas\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}