{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:16:31Z","timestamp":1783696591685,"version":"3.55.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2239077"],"award-info":[{"award-number":["2239077"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"DOI":"10.1007\/s11548-026-03644-w","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T05:24:19Z","timestamp":1776317059000},"page":"969-977","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TwinOR: photorealistic digital twins of dynamic operating rooms for embodied AI research"],"prefix":"10.1007","volume":"21","author":[{"given":"Han","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roger D.","family":"Soberanis-Mukul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankita","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lalithkumar","family":"Seenivasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jose L.","family":"Porras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhekai","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenjia","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lonny","family":"Yarmus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angela Christine","family":"Argento","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masaru","family":"Ishii","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":[[2026,4,16]]},"reference":[{"key":"3644_CR1","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1007\/978-3-031-72089-5_43","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024","author":"E \u00d6zsoy","year":"2024","unstructured":"\u00d6zsoy E, Pellegrini C, Keicher M, Navab N (2024) ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling. In: Linguraru MG, Dou Q, Feragen A, Giannarou S, Glocker B, Lekadir K, Schnabel JA (eds) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. Springer, Cham, pp 455\u2013465"},{"key":"3644_CR2","doi-asserted-by":"publisher","unstructured":"Killeen BD, Wang LJ, I\u00f1\u00edgo B, Zhang H, Armand M, Taylor RH, Osgood G, Unberath M (2026) FluoroSAM: A Language-Promptable Foundation Model for Flexible X-Ray Image Segmentation. In: Gee, J.C., Alexander, D.C., Hong, J., Iglesias, J.E., Sudre, C.H., Venkataraman, A., Golland, P., Kim, J.H., Park, J. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025, pp. 248\u2013258. Springer, Cham . https:\/\/doi.org\/10.1007\/978-3-032-04981-0_24","DOI":"10.1007\/978-3-032-04981-0_24"},{"issue":"6","key":"3644_CR3","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1049\/htl2.12103","volume":"11","author":"H Zhang","year":"2024","unstructured":"Zhang H, Killeen BD, Ku Y-C, Seenivasan L, Zhao Y, Liu M, Yang Y, Gu S, Martin-Gomez A, Taylor Osgood G, Unberath M (2024) StraightTrack: towards mixed reality navigation system for percutaneous K-wire insertion. Healthc Technol Lett 11(6):355\u2013364. https:\/\/doi.org\/10.1049\/htl2.12103","journal-title":"Healthc Technol Lett"},{"key":"3644_CR4","doi-asserted-by":"publisher","unstructured":"Zhang H, Seenivasan L, Porras JL, Soberanis-Mukul RD, Ding H, Shu H, Killeen BD, Ghosh A, Yarmus L, Ishii M, Argento AC, Unberath M (2025) Did you just see that? Arbitrary view synthesis for egocentric replay of operating room workflows from ambient sensors. arXiv. arXiv:2510.04802 [cs] . https:\/\/doi.org\/10.48550\/arXiv.2510.04802","DOI":"10.48550\/arXiv.2510.04802"},{"key":"3644_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2025.100943","volume":"48","author":"C Liu","year":"2025","unstructured":"Liu C, Tang D, Zhu H, Zhang Z, Wang L, Zhang Y (2025) Vision language model-enhanced embodied intelligence for digital twin-assisted human-robot collaborative assembly. J Ind Inf Integr 48:100943. https:\/\/doi.org\/10.1016\/j.jii.2025.100943","journal-title":"J Ind Inf Integr"},{"key":"3644_CR6","doi-asserted-by":"publisher","unstructured":"Kumar SN, Joy J, James AJ, Dixen A (2024) Health Care Industry Use Cases of Embodied AI. In: Raj, P., Rocha, A., Singh, S.P., Dutta, P.K., Sundaravadivazhagan, B. (eds.) Building Embodied AI Systems: The Agents, the Architecture Principles, Challenges, and Application Domains, pp. 223\u2013239. Springer, Cham . https:\/\/doi.org\/10.1007\/978-3-031-68256-8_10","DOI":"10.1007\/978-3-031-68256-8_10"},{"key":"3644_CR7","doi-asserted-by":"publisher","unstructured":"Tagliabue E, Pore A, Dall\u2019Alba D, Magnabosco E, Piccinelli M, Fiorini P (2020) Soft Tissue Simulation Environment to Learn Manipulation Tasks in Autonomous Robotic Surgery. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3261\u20133266. IEEE, Las Vegas, NV, USA . https:\/\/doi.org\/10.1109\/IROS45743.2020.9341710","DOI":"10.1109\/IROS45743.2020.9341710"},{"issue":"12","key":"3644_CR8","doi-asserted-by":"publisher","first-page":"13145","DOI":"10.1109\/LRA.2025.3627088","volume":"10","author":"Y-J Ho","year":"2025","unstructured":"Ho Y-J, Chiu Z-Y, Zhi Y, Yip MC (2025) Surgirl: toward life-long learning for surgical automation by incremental reinforcement learning. IEEE Robot Autom Lett 10(12):13145\u201313152. https:\/\/doi.org\/10.1109\/LRA.2025.3627088","journal-title":"IEEE Robot Autom Lett"},{"issue":"3","key":"3644_CR9","doi-asserted-by":"publisher","first-page":"109","DOI":"10.20517\/ais.2024.16","volume":"4","author":"H Ding","year":"2024","unstructured":"Ding H, Seenivasan L, Killeen BD, Cho SM, Unberath M (2024) Digital twins as a unifying framework for surgical data science: the enabling role of geometric scene understanding. Artif Intell Surg 4(3):109\u2013138. https:\/\/doi.org\/10.20517\/ais.2024.16","journal-title":"Artif Intell Surg"},{"key":"3644_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2024.100764","volume":"44","author":"KH Oo","year":"2025","unstructured":"Oo KH, Koomsap P, Ayutthaya DHN (2025) Digital twin-enabled multi-robot system for collaborative assembly of unorganized parts. J Ind Inf Integr 44:100764. https:\/\/doi.org\/10.1016\/j.jii.2024.100764","journal-title":"J Ind Inf Integr"},{"key":"3644_CR11","doi-asserted-by":"publisher","unstructured":"Liu Y, Ku Y-C, Zhang J, Ding H, Kazanzides P, Armand M (2025) dart vinci: Egocentric data collection for surgical robot learning at scale. In: 2025 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp. 3978\u20133985 . https:\/\/doi.org\/10.1109\/IROS60139.2025.11247229","DOI":"10.1109\/IROS60139.2025.11247229"},{"issue":"3","key":"3644_CR12","doi-asserted-by":"publisher","DOI":"10.1088\/2516-1091\/acd28b","volume":"5","author":"BD Killeen","year":"2023","unstructured":"Killeen BD, Cho SM, Armand M, Taylor RH, Unberath M (2023) In silico simulation: a key enabling technology for next-generation intelligent surgical systems. Prog Biomed Eng 5(3):032001. https:\/\/doi.org\/10.1088\/2516-1091\/acd28b","journal-title":"Prog Biomed Eng"},{"issue":"4","key":"3644_CR13","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1080\/21681163.2021.1999331","volume":"10","author":"A Munawar","year":"2022","unstructured":"Munawar A, Li Z, Kunjam P, Nagururu N, Ding AS, Kazanzides P, Looi T, Creighton FX, Taylor RH, Unberath M (2022) Virtual reality for synergistic surgical training and data generation. Computer Methods Biomech Biomed Eng Imag Visual 10(4):366\u2013374. https:\/\/doi.org\/10.1080\/21681163.2021.1999331","journal-title":"Computer Methods Biomech Biomed Eng Imag Visual"},{"issue":"6","key":"3644_CR14","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.1007\/s11548-024-03138-7","volume":"19","author":"BD Killeen","year":"2024","unstructured":"Killeen BD, Zhang H, Wang LJ, Liu Z, Kleinbeck C, Rosen M, Taylor RH, Osgood G, Unberath M (2024) Stand in surgeon\u2019s shoes: virtual reality cross-training to enhance teamwork in surgery. Int J Comput Assist Radiol Surg 19(6):1213\u20131222. https:\/\/doi.org\/10.1007\/s11548-024-03138-7","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3644_CR15","doi-asserted-by":"publisher","unstructured":"Towards Robust Automation of Surgical Systems via Digital Twin-based Scene Representations from Foundation Models. In: Collaborative Intelligence and Autonomy in Image-Guided Surgery. COLAS 2025. https:\/\/doi.org\/10.1007\/978-3-032-09784-2_3","DOI":"10.1007\/978-3-032-09784-2_3"},{"key":"3644_CR16","doi-asserted-by":"publisher","unstructured":"Ding H, Zhang Y, Cheng W, Wang X, Lian X, Yu C, Shu H, Kim JW, Krieger A, Unberath M (2026) Towards robust algorithms for surgical phase recognition via digital twin representation. In: Digital Twin for Healthcare - 1st International Workshop, DT4H 2025. Lecture Notes in Computer Science, pp. 119\u2013129 . https:\/\/doi.org\/10.1007\/978-3-032-07694-6_12","DOI":"10.1007\/978-3-032-07694-6_12"},{"key":"3644_CR17","unstructured":"Perez A, Zhang H, Ku Y-C, Seenivasan L, Soberanis-Mukul RD, Porras JL, Day R, Jopling JK, Najjar P, Unberath M (2025) Privacy-preserving operating room workflow analysis using digital twins. In: Medical Imaging with Deep Learning - Short Papers . https:\/\/openreview.net\/forum?id=vVQlsfd3tr"},{"key":"3644_CR18","doi-asserted-by":"crossref","unstructured":"Shen Y, Liu B, Li C, Seenivasan L, Unberath M (2025) Online reasoning video segmentation with just-in-time digital twins. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 24698\u201324706","DOI":"10.1109\/ICCV51701.2025.02290"},{"key":"3644_CR19","doi-asserted-by":"crossref","unstructured":"Hein J, Giraud F, Calvet L, Schwarz A, Cavalcanti NA, Prokudin S, Farshad M, Tang S, Pollefeys M, Carrillo F, F\u00fcrnstahl P (2024) Creating a digital twin of spinal surgery: A proof of concept. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","DOI":"10.1109\/CVPRW63382.2024.00241"},{"issue":"7","key":"3644_CR20","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1007\/s11548-024-03143-w","volume":"19","author":"C Kleinbeck","year":"2024","unstructured":"Kleinbeck C, Zhang H, Killeen BD, Roth D, Unberath M (2024) Neural digital twins: reconstructing complex medical environments for spatial planning in virtual reality. Int J Comput Assist Radiol Surg 19(7):1301\u20131312. https:\/\/doi.org\/10.1007\/s11548-024-03143-w","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3644_CR21","doi-asserted-by":"publisher","unstructured":"Li Z, M\u00fcller T, Evans A, Taylor RH, Unberath M, Liu M-Y, Lin C-H (2023) Neuralangelo: High-fidelity neural surface reconstruction. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8456\u20138465. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00817","DOI":"10.1109\/CVPR52729.2023.00817"},{"key":"3644_CR22","doi-asserted-by":"crossref","unstructured":"Loper M, Mahmood N, Romero J, Pons-Moll G, Black MJ (2023) SMPL: A Skinned Multi-Person Linear Model. In: Seminal Graphics Papers: Pushing the Boundaries, Volume 2 vol. Volume 2, 1st edn., pp. 851\u2013866. Association for Computing Machinery, New York, NY, USA. https:\/\/dl.acm.org\/doi\/10.1145\/3596711.3596800","DOI":"10.1145\/3596711.3596800"},{"key":"3644_CR23","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.1109\/TPAMI.2023.3330016","volume":"46","author":"Y Xu","year":"2024","unstructured":"Xu Y, Zhang J, Zhang Q, Tao D (2024) Vitpose++: Vision transformer foundation model for generic body pose estimation. IEEE Trans Pattern Anal Mach Intell 46:1212\u20131230. https:\/\/doi.org\/10.1109\/TPAMI.2023.3330016","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3644_CR24","doi-asserted-by":"publisher","unstructured":"Zeng A, Yang L, Ju X, Li J, Wang J, Xu Q (2022) Smoothnet: A plug-and-play network for refining human poses in videos. In: European Conference on Computer Vision . https:\/\/doi.org\/10.1007\/978-3-031-20065-6_36 . Springer Nature Switzerland","DOI":"10.1007\/978-3-031-20065-6_36"},{"key":"3644_CR25","unstructured":"EasyMoCap - Make human motion capture easier. Github (2021). https:\/\/github.com\/zju3dv\/EasyMocap"},{"key":"3644_CR26","unstructured":"Ravi N, Gabeur V, Hu Y-T, Hu R, Ryali C, Ma T, Khedr H, R\u00e4dle R, Rolland C, Gustafson L, Mintun E, Pan J, Alwala KV, Carion N, Wu C-Y, Girshick R, Dollar P, Feichtenhofer C SAM 2: Segment anything in images and videos. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=Ha6RTeWMd0"},{"key":"3644_CR27","doi-asserted-by":"publisher","unstructured":"Rusu RB, Blodow N, Beetz M (2009) Fast Point Feature Histograms (FPFH) for 3D registration. In: 2009 IEEE International Conference on Robotics and Automation, pp. 3212\u20133217 .https:\/\/doi.org\/10.1109\/ROBOT.2009.5152473","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"3644_CR28","doi-asserted-by":"publisher","unstructured":"Park J, Zhou Q-Y, Koltun V (2017) Colored Point Cloud Registration Revisited. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 143\u2013152 . https:\/\/doi.org\/10.1109\/ICCV.2017.25","DOI":"10.1109\/ICCV.2017.25"},{"key":"3644_CR29","doi-asserted-by":"publisher","unstructured":"Schonberger JL, Frahm J-M (2016) Structure-from-Motion Revisited. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4104\u20134113. IEEE, Las Vegas, NV, USA . https:\/\/doi.org\/10.1109\/CVPR.2016.445","DOI":"10.1109\/CVPR.2016.445"},{"key":"3644_CR30","doi-asserted-by":"publisher","unstructured":"Schops T, Schonberger JL, Galliani S, Sattler T, Schindler K, Pollefeys M, Geiger A (2017) A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2538\u20132547. IEEE, Honolulu, HI . https:\/\/doi.org\/10.1109\/CVPR.2017.272","DOI":"10.1109\/CVPR.2017.272"},{"issue":"4","key":"3644_CR31","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/3072959.3073599","volume":"36","author":"A Knapitsch","year":"2017","unstructured":"Knapitsch A, Park J, Zhou Q-Y, Koltun V (2017) Tanks and temples: benchmarking large-scale scene reconstruction. ACM Trans Graph 36(4):78\u201317813. https:\/\/doi.org\/10.1145\/3072959.3073599","journal-title":"ACM Trans Graph"},{"key":"3644_CR32","doi-asserted-by":"crossref","unstructured":"Wen B, Trepte M, Aribido J, Kautz J, Gallo O, Birchfield S (2025) Foundationstereo: Zero-shot stereo matching. CVPR","DOI":"10.1109\/CVPR52734.2025.00495"},{"key":"3644_CR33","doi-asserted-by":"publisher","unstructured":"Campos C, Elvira R, Rodr\u00edguez JJG, Montiel M, JM, D Tard\u00f3s J, (2021) Orb-slam3: an accurate open-source library for visual, visual-inertial, and multimap slam. IEEE Trans Rob 37(6):1874\u20131890. https:\/\/doi.org\/10.1109\/TRO.2021.3075644","DOI":"10.1109\/TRO.2021.3075644"},{"key":"3644_CR34","doi-asserted-by":"publisher","unstructured":"Vedadi A, Yousefi-Koma A, Yazdankhah P, Mozayyan A (2023) Comparative Evaluation of RGB-D SLAM Methods for Humanoid Robot Localization and Mapping. In: 2023 11th RSI International Conference on Robotics and Mechatronics (ICRoM), pp. 807\u2013812 . https:\/\/doi.org\/10.1109\/ICRoM60803.2023.10412425","DOI":"10.1109\/ICRoM60803.2023.10412425"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03644-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-026-03644-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03644-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:54:52Z","timestamp":1783695292000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-026-03644-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,16]]},"references-count":34,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["3644"],"URL":"https:\/\/doi.org\/10.1007\/s11548-026-03644-w","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,16]]},"assertion":[{"value":"15 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Data collection procedures were approved under HIRB00016983 and IRB00421946.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}]}}