{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T21:41:23Z","timestamp":1781473283601,"version":"3.54.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051134","type":"print"},{"value":"9783032051141","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"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\/978-3-032-05114-1_56","type":"book-chapter","created":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:19Z","timestamp":1758377419000},"page":"584-594","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SurgTPGS: Semantic 3D Surgical Scene Understanding with\u00a0Text Promptable Gaussian Splatting"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9754-8608","authenticated-orcid":false,"given":"Yiming","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9762-6821","authenticated-orcid":false,"given":"Long","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7900-8032","authenticated-orcid":false,"given":"Beilei","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6030-8862","authenticated-orcid":false,"given":"Kun","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2440-4950","authenticated-orcid":false,"given":"Guankun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7162-2822","authenticated-orcid":false,"given":"Mobarak I.","family":"Hoque","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5010-4137","authenticated-orcid":false,"given":"Nicolas","family":"Padoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6032-5611","authenticated-orcid":false,"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6488-1551","authenticated-orcid":false,"given":"Hongliang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,21]]},"reference":[{"key":"56_CR1","unstructured":"Allan, M., et\u00a0al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)"},{"key":"56_CR2","doi-asserted-by":"crossref","unstructured":"Bai, L., Islam, M., Seenivasan, L., Ren, H.: Surgical-vqla: Transformer with gated vision-language embedding for visual question localized-answering in robotic surgery. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 6859\u20136865. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160403"},{"key":"56_CR3","doi-asserted-by":"crossref","unstructured":"Cho, S., Shin, H., Hong, S., Arnab, A., Seo, P.H., Kim, S.: Cat-seg: cost aggregation for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4113\u20134123 (2024)","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"56_CR4","doi-asserted-by":"publisher","unstructured":"Cui, B., Islam, M., Bai, L., Wang, A., Ren, H.: Endodac: efficient adapting foundation model for self-supervised depth estimation from any endoscopic camera. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 208\u2013218. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-72089-5_20","DOI":"10.1007\/978-3-031-72089-5_20"},{"key":"56_CR5","unstructured":"Hong, W.Y., Kao, C.L., Kuo, Y.H., Wang, J.R., Chang, W.L., Shih, C.S.: Cholecseg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80. arXiv preprint arXiv:2012.12453 (2020)"},{"key":"56_CR6","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Advancing dense endoscopic reconstruction with gaussian splatting-driven surface normal-aware tracking and mapping. arXiv preprint arXiv:2501.19319 (2025)","DOI":"10.1109\/ICRA55743.2025.11128637"},{"key":"56_CR7","doi-asserted-by":"publisher","unstructured":"Huang, Y., et al.: Endo-4dgs: endoscopic monocular scene reconstruction with 4d gaussian splatting. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 197\u2013207. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-72089-5_19","DOI":"10.1007\/978-3-031-72089-5_19"},{"issue":"11","key":"56_CR8","doi-asserted-by":"publisher","first-page":"2991","DOI":"10.1109\/TMI.2022.3177077","volume":"41","author":"Y Jin","year":"2022","unstructured":"Jin, Y., Yu, Y., Chen, C., Zhao, Z., Heng, P.A., Stoyanov, D.: Exploring intra-and inter-video relation for surgical semantic scene segmentation. IEEE Trans. Med. Imaging 41(11), 2991\u20133002 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"56_CR9","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023)","DOI":"10.1145\/3592433"},{"key":"56_CR10","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M.: Lerf: language embedded radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19729\u201319739 (2023)","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"56_CR11","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"56_CR12","doi-asserted-by":"publisher","unstructured":"Labe, I., Issachar, N., Lang, I., Benaim, S.: DGD: Dynamic 3D gaussians distillation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15126. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73113-6_21","DOI":"10.1007\/978-3-031-73113-6_21"},{"key":"56_CR13","unstructured":"Li, J., Skinner, G., Yang, G., Quaranto, B.R., Schwaitzberg, S.D., Kim, P.C., Xiong, J.: Llava-surg: towards multimodal surgical assistant via structured surgical video learning. arXiv preprint arXiv:2408.07981 (2024)"},{"issue":"4","key":"56_CR14","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1109\/TMI.2023.3335406","volume":"43","author":"M Liu","year":"2023","unstructured":"Liu, M., Han, Y., Wang, J., Wang, C., Wang, Y., Meijering, E.: Lskanet: long strip kernel attention network for robotic surgical scene segmentation. IEEE Trans. Med. Imaging 43(4), 1308\u20131322 (2023)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"56_CR15","unstructured":"Liu, Y., Li, C., Yang, C., Yuan, Y.: Endogaussian: Gaussian splatting for deformable surgical scene reconstruction. arXiv preprint arXiv:2401.12561 (2024)"},{"issue":"9800","key":"56_CR16","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1016\/S0140-6736(11)61597-3","volume":"378","author":"G McLachlan","year":"2011","unstructured":"McLachlan, G.: From 2d to 3d: the future of surgery? The Lancet 378(9800), 1368 (2011)","journal-title":"The Lancet"},{"issue":"1","key":"56_CR17","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"56_CR18","doi-asserted-by":"crossref","unstructured":"Qin, M., Li, W., Zhou, J., Wang, H., Pfister, H.: Langsplat: 3d language gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20051\u201320060 (2024)","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"56_CR19","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"56_CR20","doi-asserted-by":"publisher","unstructured":"Seenivasan, L., Islam, M., Krishna, A.K., Ren, H.: Surgical-VQA: visual question answering in surgical scenes using transformer. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022. MICCAI 2022. LNCS, vol. 13437. Springer, Cham (2022).https:\/\/doi.org\/10.1007\/978-3-031-16449-1_4","DOI":"10.1007\/978-3-031-16449-1_4"},{"issue":"1","key":"56_CR21","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., Mathelin, M., Padoy, N.: Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"56_CR22","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Video-instrument synergistic network for referring video instrument segmentation in robotic surgery. IEEE Trans. Med. Imaging (2024)","DOI":"10.1109\/TMI.2024.3426953"},{"key":"56_CR23","doi-asserted-by":"publisher","unstructured":"Wang, Y., Long, Y., Fan, S.H., Dou, Q.: Neural rendering for stereo 3d reconstruction of deformable tissues in robotic surgery. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 431\u2013441. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-16449-1_41","DOI":"10.1007\/978-3-031-16449-1_41"},{"key":"56_CR24","unstructured":"Wu, Y., et\u00a0al.: Opengaussian: Towards point-level 3d gaussian-based open vocabulary understanding. arXiv preprint arXiv:2406.02058 (2024)"},{"key":"56_CR25","doi-asserted-by":"publisher","unstructured":"Yang, S., Li, Q., Shen, D., Gong, B., Dou, Q., Jin, Y.: Deform3DGS: flexible deformation for fast surgical scene reconstruction with gaussian splatting. In: Linguraru, M.G., et al. Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. MICCAI 2024. LNCS, vol. 15006. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72089-5_13","DOI":"10.1007\/978-3-031-72089-5_13"},{"key":"56_CR26","doi-asserted-by":"publisher","unstructured":"Yoon, J. et al.: Surgical scene segmentation using semantic image synthesis with a virtual surgery environment. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022. MICCAI 2022. LNCS, vol. 13437. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16449-1_53","DOI":"10.1007\/978-3-031-16449-1_53"},{"key":"56_CR27","unstructured":"Yuan, K., Srivastav, V., Yu, T., Lavanchy, J., Mascagni, P., Navab, N., Padoy, N.: Learning multi-modal representations by watching hundreds of surgical video lectures (2023)"},{"key":"56_CR28","doi-asserted-by":"publisher","unstructured":"Zha, R., Cheng, X., Li, H., Harandi, M., Ge, Z.: EndoSurf: neural surface reconstruction of deformable tissues with stereo endoscope videos. In: Greenspan, H., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023. MICCAI 2023. LNCS, vol. 14228. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43996-4_2","DOI":"10.1007\/978-3-031-43996-4_2"},{"key":"56_CR29","first-page":"28611","volume":"36","author":"Z Zhou","year":"2023","unstructured":"Zhou, Z., Alabi, O., Wei, M., Vercauteren, T., Shi, M.: Text promptable surgical instrument segmentation with vision-language models. Adv. Neural. Inf. Process. Syst. 36, 28611\u201328623 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"56_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, Z., Jin, Z., Lin, G., Yu, L.: Deformable endoscopic tissues reconstruction with gaussian splatting. arXiv preprint arXiv:2401.11535 (2024)","DOI":"10.1007\/978-3-031-77610-6_13"},{"key":"56_CR31","doi-asserted-by":"crossref","unstructured":"Zwicker, M., Pfister, H., Van\u00a0Baar, J., Gross, M.: Surface splatting. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, pp. 371\u2013378 (2001)","DOI":"10.1145\/383259.383300"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05114-1_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:25Z","timestamp":1758377425000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05114-1_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"ISBN":["9783032051134","9783032051141"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05114-1_56","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,21]]},"assertion":[{"value":"21 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are 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":"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":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}