{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T13:30:56Z","timestamp":1793626256632,"version":"4.5.1"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.media.2026.104318","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T20:00:32Z","timestamp":1789502432000},"page":"104318","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SurgTPGS++: Text-promptable Gaussian Splatting with dense features aggregation for semantic 4D surgical scene understanding"],"prefix":"10.1016","volume":"115","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":"78","reference":[{"key":"10.1016\/j.media.2026.104318_b1","series-title":"2018 Robotic scene segmentation challenge","author":"Allan","year":"2020"},{"key":"10.1016\/j.media.2026.104318_b2","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"6859","article-title":"Surgical-VQLA: Transformer with gated vision-language embedding for visual question localized-answering in robotic surgery","author":"Bai","year":"2023"},{"key":"10.1016\/j.media.2026.104318_b3","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V., 2018. COCO-Stuff: Thing and Stuff Classes in Context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"10.1016\/j.media.2026.104318_b4","doi-asserted-by":"crossref","unstructured":"Cho, S., Shin, H., Hong, S., Arnab, A., Seo, P.H., Kim, S., 2024. 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.","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"10.1016\/j.media.2026.104318_b5","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"208","article-title":"Endodac: Efficient adapting foundation model for self-supervised depth estimation from any endoscopic camera","author":"Cui","year":"2024"},{"issue":"1","key":"10.1016\/j.media.2026.104318_b6","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","article-title":"The pascal visual object classes challenge: A retrospective","volume":"111","author":"Everingham","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.media.2026.104318_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102053","article-title":"CaDIS: Cataract dataset for surgical RGB-image segmentation","volume":"71","author":"Grammatikopoulou","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104318_b8","series-title":"Cholecseg8k: A semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80","author":"Hong","year":"2020"},{"key":"10.1016\/j.media.2026.104318_b9","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"584","article-title":"SurgTPGS: Semantic 3D surgical scene understanding with text promptable Gaussian splatting","author":"Huang","year":"2025"},{"key":"10.1016\/j.media.2026.104318_b10","series-title":"2025 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"4084","article-title":"Advancing dense endoscopic reconstruction with gaussian splatting-driven surface normal-aware tracking and mapping","author":"Huang","year":"2025"},{"key":"10.1016\/j.media.2026.104318_b11","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"197","article-title":"Endo-4dgs: Endoscopic monocular scene reconstruction with 4d gaussian splatting","author":"Huang","year":"2024"},{"issue":"11","key":"10.1016\/j.media.2026.104318_b12","doi-asserted-by":"crossref","first-page":"2991","DOI":"10.1109\/TMI.2022.3177077","article-title":"Exploring intra-and inter-video relation for surgical semantic scene segmentation","volume":"41","author":"Jin","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104318_b13","doi-asserted-by":"crossref","unstructured":"Karaev, N., Makarov, Y., Wang, J., Neverova, N., Vedaldi, A., Rupprecht, C., 2025. CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 6013\u20136022.","DOI":"10.1109\/ICCV51701.2025.00568"},{"issue":"4","key":"10.1016\/j.media.2026.104318_b14","doi-asserted-by":"crossref","DOI":"10.1145\/3592433","article-title":"3D Gaussian splatting for real-time radiance field rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.media.2026.104318_b15","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M., 2023. Lerf: Language embedded radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 19729\u201319739.","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"10.1016\/j.media.2026.104318_b16","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.-Y., et al., 2023. Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.media.2026.104318_b17","series-title":"European Conference on Computer Vision","first-page":"361","article-title":"DGD: Dynamic 3D Gaussians distillation","author":"Labe","year":"2024"},{"key":"10.1016\/j.media.2026.104318_b18","series-title":"LLaVA-surg: Towards multimodal surgical assistant via structured surgical video learning","author":"Li","year":"2024"},{"key":"10.1016\/j.media.2026.104318_b19","series-title":"Language-driven semantic segmentation","author":"Li","year":"2022"},{"issue":"3","key":"10.1016\/j.media.2026.104318_b20","article-title":"Variable stiffness methods of flexible robots for minimally invasive surgery: A review","volume":"4","author":"Lin","year":"2024","journal-title":"Biomim. Intell. Robot."},{"issue":"4","key":"10.1016\/j.media.2026.104318_b21","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1109\/TMI.2023.3335406","article-title":"LSKANet: Long strip kernel attention network for robotic surgical scene segmentation","volume":"43","author":"Liu","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104318_b22","series-title":"Endogaussian: Gaussian splatting for deformable surgical scene reconstruction","author":"Liu","year":"2024"},{"issue":"9800","key":"10.1016\/j.media.2026.104318_b23","doi-asserted-by":"crossref","first-page":"1368","DOI":"10.1016\/S0140-6736(11)61597-3","article-title":"From 2D to 3D: The future of surgery?","volume":"378","author":"McLachlan","year":"2011","journal-title":"Lancet"},{"issue":"1","key":"10.1016\/j.media.2026.104318_b24","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3503250","article-title":"Nerf: Representing scenes as neural radiance fields for view synthesis","volume":"65","author":"Mildenhall","year":"2021","journal-title":"Commun. ACM"},{"issue":"3","key":"10.1016\/j.media.2026.104318_b25","article-title":"Image segmentation network for laparoscopic surgery","volume":"5","author":"Peng","year":"2025","journal-title":"Biomim. Intell. Robot."},{"key":"10.1016\/j.media.2026.104318_b26","doi-asserted-by":"crossref","unstructured":"Qin, M., Li, W., Zhou, J., Wang, H., Pfister, H., 2024. Langsplat: 3d language gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 20051\u201320060.","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"10.1016\/j.media.2026.104318_b27","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.media.2026.104318_b28","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"33","article-title":"Surgical-vqa: Visual question answering in surgical scenes using transformer","author":"Seenivasan","year":"2022"},{"key":"10.1016\/j.media.2026.104318_b29","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"431","article-title":"Neural rendering for stereo 3d reconstruction of deformable tissues in robotic surgery","author":"Wang","year":"2022"},{"key":"10.1016\/j.media.2026.104318_b30","article-title":"Video-instrument synergistic network for referring video instrument segmentation in robotic surgery","author":"Wang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104318_b31","doi-asserted-by":"crossref","first-page":"19114","DOI":"10.52202\/079017-0604","article-title":"Opengaussian: towards point-level 3d gaussian-based open vocabulary understanding","volume":"37","author":"Wu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104318_b32","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"132","article-title":"Deform3dgs: Flexible deformation for fast surgical scene reconstruction with gaussian splatting","author":"Yang","year":"2024"},{"key":"10.1016\/j.media.2026.104318_b33","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"551","article-title":"Surgical scene segmentation using semantic image synthesis with a virtual surgery environment","author":"Yoon","year":"2022"},{"key":"10.1016\/j.media.2026.104318_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103644","article-title":"Learning multi-modal representations by watching hundreds of surgical video lectures","volume":"105","author":"Yuan","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104318_b35","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"13","article-title":"Endosurf: Neural surface reconstruction of deformable tissues with stereo endoscope videos","author":"Zha","year":"2023"},{"key":"10.1016\/j.media.2026.104318_b36","doi-asserted-by":"crossref","first-page":"28611","DOI":"10.52202\/075280-1243","article-title":"Text promptable surgical instrument segmentation with vision-language models","volume":"36","author":"Zhou","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104318_b37","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A., 2017. Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 633\u2013641.","DOI":"10.1109\/CVPR.2017.544"},{"key":"10.1016\/j.media.2026.104318_b38","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"135","article-title":"Endogs: deformable endoscopic tissues reconstruction with gaussian splatting","author":"Zhu","year":"2024"},{"key":"10.1016\/j.media.2026.104318_b39","doi-asserted-by":"crossref","unstructured":"Zwicker, M., Pfister, H., Van Baar, J., Gross, M., 2001. Surface splatting. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques. pp. 371\u2013378.","DOI":"10.1145\/383259.383300"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003877?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003877?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T13:02:23Z","timestamp":1793624543000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526003877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":39,"alternative-id":["S1361841526003877"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104318","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SurgTPGS++: Text-promptable Gaussian Splatting with dense features aggregation for semantic 4D surgical scene understanding","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104318","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104318"}}