{"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":1778080166876,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"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_22","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:02:20Z","timestamp":1727884940000},"page":"230-240","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["Endora: Video Generation Models as\u00a0Endoscopy Simulators"],"prefix":"10.1007","author":[{"given":"Chenxin","family":"Li","sequence":"first","affiliation":[]},{"given":"Hengyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Brandon Y.","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Wuyang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xinyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Shao","sequence":"additional","affiliation":[]},{"given":"Yixuan","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"22_CR1","unstructured":"https:\/\/github.com\/google-research\/fixmatch"},{"key":"22_CR2","unstructured":"https:\/\/github.com\/colmap\/colmap"},{"key":"22_CR3","unstructured":"Amir, S., Gandelsman, Y., Bagon, S., Dekel, T.: Deep vit features as dense visual descriptors. arXiv preprint arXiv:2112.058142(3), \u00a04 (2021)"},{"key":"22_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2019.101684","volume":"79","author":"K Armanious","year":"2020","unstructured":"Armanious, K., Jiang, C., Fischer, M., K\u00fcstner, T., Hepp, T., Nikolaou, K., Gatidis, S., Yang, B.: Medgan: Medical image translation using gans. Computerized medical imaging and graphics 79, 101684 (2020)","journal-title":"Computerized medical imaging and graphics"},{"key":"22_CR5","unstructured":"Ben\u00a0Abacha, A., Hasan, S.A., Datla, V.V., Demner-Fushman, D., M\u00fcller, H.: Vqa-med: Overview of the medical visual question answering task. In: Proceedings of CLEF 2019 Working Notes. 9-12 September 2019 (2019)"},{"issue":"1","key":"22_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-020-00622-y","volume":"7","author":"H Borgli","year":"2020","unstructured":"Borgli, H., Thambawita, V., Smedsrud, P.H., Hicks, S., Jha, D., Eskeland, S.L., Randel, K.R., Pogorelov, K., Lux, M., Nguyen, D.T.D., et\u00a0al.: Hyperkvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Scientific data 7(1), 1\u201314 (2020)","journal-title":"Scientific data"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: ICCV. pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Ding, Z., Dong, Q., Xu, H., Li, C., Ding, X., Huang, Y.: Unsupervised anomaly segmentation for brain lesions using dual semantic-manifold reconstruction. In: ICONIP. pp. 133\u2013144. Springer (2022)","DOI":"10.1007\/978-3-031-30111-7_12"},{"key":"22_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR (2021)"},{"key":"22_CR10","unstructured":"He, Y., Yang, T., Zhang, Y., Shan, Y., Chen, Q.: Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221 (2023)"},{"key":"22_CR11","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. In: NeurIPS (2022)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Kazerouni, A., Aghdam, E.K., Heidari, M., Azad, R., Fayyaz, M., Hacihaliloglu, I., Merhof, D.: Diffusion models for medical image analysis: A comprehensive survey. arXiv preprint arXiv:2211.07804 (2022)","DOI":"10.1016\/j.media.2023.102846"},{"key":"22_CR13","first-page":"21696","volume":"34","author":"D Kingma","year":"2021","unstructured":"Kingma, D., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. NeurIPS 34, 21696\u201321707 (2021)","journal-title":"Variational diffusion models. NeurIPS"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Li, C., Feng, B.Y., Fan, Z., Pan, P., Wang, Z.: Steganerf: Embedding invisible information within neural radiance fields. In: CVPR. pp. 441\u2013453 (2023)","DOI":"10.1109\/ICCV51070.2023.00047"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Li, C., Feng, B.Y., Liu, Y., Liu, H., Wang, C., Yu, W., Yuan, Y.: Endosparse: Real-time sparse view synthesis of endoscopic scenes using gaussian splatting. arXiv preprint arXiv:2407.01029 (2024)","DOI":"10.1007\/978-3-031-72089-5_24"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Li, C., Lin, M., Ding, Z., Lin, N., Zhuang, Y., Huang, Y., Ding, X., Cao, L.: Knowledge condensation distillation. In: ECCV, pages=19\u201335, year=2022, organization=Springer","DOI":"10.1007\/978-3-031-20083-0_2"},{"key":"22_CR17","volume":"141","author":"C Li","year":"2022","unstructured":"Li, C., Lin, X., Mao, Y., Lin, W., Qi, Q., Ding, X., Huang, Y., Liang, D., Yu, Y.: Domain generalization on medical imaging classification using episodic training with task augmentation. CBM 141, 105144 (2022)","journal-title":"CBM"},{"key":"22_CR18","unstructured":"Li, C., Liu, H., Fan, Z., Li, W., Liu, Y., Pan, P., Yuan, Y.: Gaussianstego: A generalizable stenography pipeline for generative 3d gaussians splatting. arXiv preprint arXiv:2407.01301 (2024)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Li, C., Liu, H., Liu, Y., Feng, B.Y., Li, W., Liu, X., Chen, Z., Shao, J., Yuan, Y.: Endora: Video generation models as endoscopy simulators. arXiv preprint arXiv:2403.11050 (2024)","DOI":"10.1007\/978-3-031-72089-5_22"},{"key":"22_CR20","unstructured":"Li, C., Liu, X., Li, W., Wang, C., Liu, H., Yuan, Y.: U-kan makes strong backbone for medical image segmentation and generation. arXiv:2406.02918 (2024)"},{"key":"22_CR21","unstructured":"Li, C., Ma, W., Sun, L., Ding, X., Huang, Y., Wang, G., Yu, Y.: Hierarchical deep network with uncertainty-aware semi-supervised learning for vessel segmentation. Neural Computing and Applications pp. 1\u201314 (2022)"},{"key":"22_CR22","unstructured":"Li, C., Zhang, Y., Li, J., Huang, Y., Ding, X.: Unsupervised anomaly segmentation using image-semantic cycle translation. arXiv preprint arXiv:2103.09094 (2021)"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Li, C., Zhang, Y., Liang, Z., Ma, W., Huang, Y., Ding, X.: Consistent posterior distributions under vessel-mixing: a regularization for cross-domain retinal artery\/vein classification. In: ICIP. pp. 61\u201365. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506148"},{"key":"22_CR24","unstructured":"Li, X., Zhou, D., Zhang, C., Wei, S., Hou, Q., Cheng, M.M.: Sora generates videos with stunning geometrical consistency. arXiv preprint arXiv:2402.17403 (2024)"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Liang, Z., Rong, Y., Li, C., Zhang, Y., Huang, Y., Xu, T., Ding, X., Huang, J.: Unsupervised large-scale social network alignment via cross network embedding. In: CIKM. pp. 1008\u20131017 (2021)","DOI":"10.1145\/3459637.3482310"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Liu, H., Liu, Y., Li, C., Li, W., Yuan, Y.: Lgs: A light-weight 4d gaussian splatting for efficient surgical scene reconstruction. arXiv:2406.16073 (2024)","DOI":"10.1007\/978-3-031-72384-1_62"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, C., Yang, C., Yuan, Y.: Endogaussian: Gaussian splatting for deformable surgical scene reconstruction. arXiv:2401.12561 (2024)","DOI":"10.1007\/978-3-031-72384-1_62"},{"key":"22_CR28","unstructured":"Ma, X., Wang, Y., Jia, G., Chen, X., Liu, Z., Li, Y.F., Chen, C., Qiao, Y.: Latte: Latent diffusion transformer for video generation. arXiv:2401.03048 (2024)"},{"issue":"9","key":"22_CR29","first-page":"2051","volume":"35","author":"P Mesejo","year":"2016","unstructured":"Mesejo, P., Pizarro, D., Abergel, A., Rouquette, O., Beorchia, S., Poincloux, L., Bartoli, A.: Computer-aided classification of gastrointestinal lesions in regular colonoscopy. IEEE TMI 35(9), 2051\u20132063 (2016)","journal-title":"IEEE TMI"},{"key":"22_CR30","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/j.jbi.2014.06.009","volume":"52","author":"R Mishra","year":"2014","unstructured":"Mishra, R., Bian, J., Fiszman, M., Weir, C.R., Jonnalagadda, S., Mostafa, J., Del\u00a0Fiol, G.: Text summarization in the biomedical domain: a systematic review of recent research. Journal of biomedical informatics 52, 457\u2013467 (2014)","journal-title":"Journal of biomedical informatics"},{"key":"22_CR31","volume":"78","author":"CI Nwoye","year":"2022","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. MedIA 78, 102433 (2022)","journal-title":"MedIA"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Pan, P., Fan, Z., Feng, B.Y., Wang, P., Li, C., Wang, Z.: Learning to estimate 6dof pose from limited data: A few-shot, generalizable approach using rgb images. arXiv preprint arXiv:2306.07598 (2023)","DOI":"10.1109\/3DV62453.2024.00078"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Shen, X., Li, X., Elhoseiny, M.: Mostgan-v: Video generation with temporal motion styles. In: Computer Vision and Pattern Recognition. pp. 5652\u20135661 (2023)","DOI":"10.1109\/CVPR52729.2023.00547"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Tulyakov, S., Elhoseiny, M.: Stylegan-v: A continuous video generator with the price, image quality and perks of stylegan2. In: Computer Vision and Pattern Recognition. pp. 3626\u20133636 (2022)","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"22_CR35","volume":"140","author":"L Sun","year":"2022","unstructured":"Sun, L., Li, C., Ding, X., Huang, Y., Chen, Z., Wang, G., Yu, Y., Paisley, J.: Few-shot medical image segmentation using a global correlation network with discriminative embedding. CBM 140, 105067 (2022)","journal-title":"CBM"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Tian, Y., Pang, G., Liu, F., Liu, Y., Wang, C., Chen, Y., Verjans, J., Carneiro, G.: Contrastive transformer-based multiple instance learning for weakly supervised polyp frame detection. In: MICCAI. pp. 88\u201398. Springer (2022)","DOI":"10.1007\/978-3-031-16437-8_9"},{"key":"22_CR37","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.neucom.2015.08.104","volume":"184","author":"Y Wang","year":"2016","unstructured":"Wang, Y., Yao, H., Zhao, S.: Auto-encoder based dimensionality reduction. Neurocomputing 184, 232\u2013242 (2016)","journal-title":"Neurocomputing"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Xu, H., Li, C., Zhang, L., Ding, Z., Lu, T., Hu, H.: Immunotherapy efficacy prediction through a feature re-calibrated 2.5 d neural network. Computer Methods and Programs in Biomedicine 249, 108135 (2024)","DOI":"10.1016\/j.cmpb.2024.108135"},{"key":"22_CR39","unstructured":"Xu, H., Zhang, Y., Sun, L., Li, C., Huang, Y., Ding, X.: Afsc: Adaptive fourier space compression for anomaly detection. arXiv:2204.07963 (2022)"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, C., Lin, X., Sun, L., Zhuang, Y., Huang, Y., Ding, X., Liu, X., Yu, Y.: Generator versus segmentor: Pseudo-healthy synthesis. In: MICCAI. pp. 150\u2013160. Springer (2021)","DOI":"10.1007\/978-3-030-87231-1_15"},{"key":"22_CR41","unstructured":"Zhu, L., Wang, Z., Jin, Z., Lin, G., Yu, L.: Deformable endoscopic tissues reconstruction with gaussian splatting. arXiv preprint arXiv:2401.11535 (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_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:42:16Z","timestamp":1732840936000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72089-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720888","9783031720895"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72089-5_22","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":"Conceptualization: C. Li. Methodology: C. Li, Y. Liu, B. Feng. Implementation: C. Li, H. Liu, Y. Liu. Writing: C. Li, B. Feng. Experiment Design: C. Li, B. Feng, W. Li. Visualization: C. Li, H. Liu, B. Feng, W. Li. Supervision: X. Liu, Z. Chen, J. Shao, Y. Yuan.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Author Contributions"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":2,"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"}}]}}