{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:35:31Z","timestamp":1780572931440,"version":"3.54.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727436","type":"print"},{"value":"9783031727443","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:00:00Z","timestamp":1728432000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:00:00Z","timestamp":1728432000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72744-3_11","type":"book-chapter","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T14:02:40Z","timestamp":1728396160000},"page":"109-118","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Interactive Generation of\u00a0Laparoscopic Videos with\u00a0Diffusion Models"],"prefix":"10.1007","author":[{"given":"Ivan","family":"Iliash","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simeon","family":"Allmendinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Meissen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niklas","family":"K\u00fchl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"R\u00fcckert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,9]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Allmendinger, S., Hemmer, P., Queisner, M., Sauer, I., M\u00fcller, L., Jakubik, J., V\u00f6ssing, M., K\u00fchl, N.: Navigating the synthetic realm: Harnessing diffusion-based models for laparoscopic text-to-image generation. arXiv preprint arXiv:2312.03043 (2023)","DOI":"10.1007\/978-3-031-63592-2_4"},{"key":"11_CR2","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying mmd gans (2021)"},{"key":"11_CR3","unstructured":"Chambon, P., Bluethgen, C., Delbrouck, J.B., Van\u00a0der Sluijs, R., Po\u0142acin, M., Chaves, J.M.Z., Abraham, T.M., Purohit, S., Langlotz, C.P., Chaudhari, A.: Roentgen: vision-language foundation model for chest x-ray generation. arXiv preprint arXiv:2211.12737 (2022)"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Frisch, Y., Fuchs, M., Sanner, A., Ucar, F.A., Frenzel, M., Wasielica-Poslednik, J., Gericke, A., Wagner, F.M., Dratsch, T., Mukhopadhyay, A.: Synthesising rare cataract surgery samples with guided diffusion models (2023)","DOI":"10.1007\/978-3-031-43996-4_34"},{"key":"11_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101994","volume":"70","author":"MK Hasan","year":"2021","unstructured":"Hasan, M.K., Calvet, L., Rabbani, N., Bartoli, A.: Detection, segmentation, and 3d pose estimation of surgical tools using convolutional neural networks and algebraic geometry. Medical Image Analysis 70, 101994 (2021)","journal-title":"Medical Image Analysis"},{"key":"11_CR6","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol.\u00a030. Curran Associates, Inc. (2017)"},{"key":"11_CR7","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems. vol.\u00a033, pp. 6840\u20136851. Curran Associates, Inc. (2020)"},{"key":"11_CR8","unstructured":"Hong, W., Kao, C., Kuo, Y., Wang, J., Chang, W., Shih, C.: Cholecseg8k: A semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80. CoRR abs\/2012.12453 (2020)"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Jayasumana, S., Ramalingam, S., Veit, A., Glasner, D., Chakrabarti, A., Kumar, S.: Rethinking fid: Towards a better evaluation metric for image generation. arXiv preprint arXiv:2401.09603 (2023)","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"11_CR10","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics YOLO (Jan 2023), version 8.0.0. Available at https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Kaleta, J., Dall\u2019Alba, D., P\u0142otka, S., Korzeniowski, P.: Minimal data requirement for realistic endoscopic image generation with stable diffusion. International Journal of Computer Assisted Radiology and Surgery pp.\u00a01\u20139 (2023)","DOI":"10.1007\/s11548-023-03030-w"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Kim, B., Ye, J.C.: Diffusion deformable model for 4d temporal medical image generation (2022)","DOI":"10.1007\/978-3-031-16431-6_51"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., Yu, T., Gonzalez, C., Seeliger, B., Mascagni, P., Mutter, D., Marescaux, J., Padoy, N.: Rendezvous: Attention mechanisms for the recognition of surgical action triplets in endoscopic videos. CoRR abs\/2109.03223 (2021)","DOI":"10.1016\/j.media.2022.102433"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., Yu, T., Gonzalez, C., Seeliger, B., Mascagni, P., Mutter, D., Marescaux, J., Padoy, N.: Rendezvous: Attention mechanisms for the recognition of surgical action triplets in endoscopic videos. CoRR abs\/2109.03223 (2021)","DOI":"10.1016\/j.media.2022.102433"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Parmar, G., Zhang, R., Zhu, J.: On buggy resizing libraries and surprising subtleties in FID calculation. CoRR abs\/2104.11222 (2021)","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Pfeiffer, M., Funke, I., Robu, M.R., Bodenstedt, S., Strenger, L., Engelhardt, S., Ro\u00df, T., Clarkson, M.J., Gurusamy, K., Davidson, B.R., Maier-Hein, L., Riediger, C., Welsch, T., Weitz, J., Speidel, S.: Generating large labeled data sets for laparoscopic image processing tasks using unpaired image-to-image translation. CoRR abs\/1907.02882 (2019)","DOI":"10.1007\/978-3-030-32254-0_14"},{"key":"11_CR17","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision (2021)"},{"key":"11_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102943","volume":"90","author":"J Ramalhinho","year":"2023","unstructured":"Ramalhinho, J., Yoo, S., Dowrick, T., Koo, B., Somasundaram, M., Gurusamy, K., Hawkes, D.J., Davidson, B., Blandford, A., Clarkson, M.J.: The value of augmented reality in surgery-a usability study on laparoscopic liver surgery. Medical Image Analysis 90, 102943 (2023)","journal-title":"Medical Image Analysis"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Reynaud, H., Qiao, M., Dombrowski, M., Day, T., Razavi, R., Gomez, A., Leeson, P., Kainz, B.: Feature-conditioned cascaded video diffusion models for precise echocardiogram synthesis. arXiv:2303.12644 (2023)","DOI":"10.1007\/978-3-031-43999-5_14"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. CoRR abs\/2112.10752 (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. CoRR abs\/1505.04597 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11_CR22","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 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"11_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.suronc.2021.101637","volume":"38","author":"C Schneider","year":"2021","unstructured":"Schneider, C., Allam, M., Stoyanov, D., Hawkes, D., Gurusamy, K., Davidson, B.: Performance of image guided navigation in laparoscopic liver surgery\u2013a systematic review. Surgical Oncology 38, 101637 (2021)","journal-title":"Surgical Oncology"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Sutherland, L.M., Middleton, P.F., Anthony, A., Hamdorf, J., Cregan, P., Scott, D., &\u00a0Maddern, G.J.: Surgical simulation: a systematic review. Annals of surgery (2006)","DOI":"10.1097\/01.sla.0000200839.93965.26"},{"key":"11_CR25","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., de\u00a0Mathelin, M., Padoy, N.: Endonet: A deep architecture for recognition tasks on laparoscopic videos. CoRR abs\/1602.03012 (2016)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"11_CR27","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: Controlvideo: Training-free controllable text-to-video generation. arXiv preprint arXiv:2305.13077 (2023)"}],"container-title":["Lecture Notes in Computer Science","Deep Generative Models"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72744-3_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T14:04:14Z","timestamp":1728396254000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72744-3_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,9]]},"ISBN":["9783031727436","9783031727443"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72744-3_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,9]]},"assertion":[{"value":"9 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DGM4MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"MICCAI Workshop on Deep Generative Models","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":"9 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dgm4miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dgm4miccai.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}