{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T08:05:47Z","timestamp":1789113947591,"version":"build-2803163510"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203296"],"award-info":[{"award-number":["62203296"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["2021SHZDZX"],"award-info":[{"award-number":["2021SHZDZX"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.media.2026.104279","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T15:34:11Z","timestamp":1787585651000},"page":"104279","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Surgical instrument-tissue characterization via multi-task self-supervised instrument segmentation and motion estimation"],"prefix":"10.1016","volume":"114","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2431-2653","authenticated-orcid":false,"given":"Yuxuan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9131-7738","authenticated-orcid":false,"given":"Xinyao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6050-4106","authenticated-orcid":false,"given":"Yating","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9810-6272","authenticated-orcid":false,"given":"Yunfei","family":"Luan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9799-7608","authenticated-orcid":false,"given":"Musen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8041-1245","authenticated-orcid":false,"given":"Yao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4060-4020","authenticated-orcid":false,"given":"Guang-Zhong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.media.2026.104279_b1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10462-024-10979-w","article-title":"Deep learning for surgical instrument recognition and segmentation in robotic-assisted surgeries: a systematic review","volume":"58","author":"Ahmed","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.media.2026.104279_b2","series-title":"2018 Robotic scene segmentation challenge","author":"Allan","year":"2020"},{"key":"10.1016\/j.media.2026.104279_b3","series-title":"2017 Robotic instrument segmentation challenge","author":"Allan","year":"2019"},{"key":"10.1016\/j.media.2026.104279_b4","article-title":"Multi-task feature learning","volume":"19","author":"Argyriou","year":"2006","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104279_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103726","article-title":"Pixel-wise recognition for holistic surgical scene understanding","author":"Ayobi","year":"2025","journal-title":"Med. Image Anal."},{"issue":"10","key":"10.1016\/j.media.2026.104279_b6","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1109\/TMI.2023.3268774","article-title":"Motion decoupling network for intra-operative motion estimation under occlusion","volume":"42","author":"Bian","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104279_b7","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-025-02227-4","article-title":"Artificial intelligence for surgical scene understanding: a systematic review and reporting quality meta-analysis","author":"Carstens","year":"2025","journal-title":"Npj Digit. Med."},{"key":"10.1016\/j.media.2026.104279_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102569","article-title":"Real-time instance segmentation of surgical instruments using attention and multi-scale feature fusion","volume":"81","author":"Cer\u00f3n","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104279_b9","series-title":"2017 IEEE Visual Communications and Image Processing","first-page":"1","article-title":"Linknet: Exploiting encoder representations for efficient semantic segmentation","author":"Chaurasia","year":"2017"},{"key":"10.1016\/j.media.2026.104279_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.107121","article-title":"FRSR: Framework for real-time scene reconstruction in robot-assisted minimally invasive surgery","volume":"163","author":"Chen","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.104279_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102994","article-title":"A temporal learning approach to inpainting endoscopic specularities and its effect on image correspondence","volume":"90","author":"Daher","year":"2023","journal-title":"Med. Image Anal."},{"issue":"60","key":"10.1016\/j.media.2026.104279_b12","doi-asserted-by":"crossref","first-page":"eabi8017","DOI":"10.1126\/scirobotics.abi8017","article-title":"A decade retrospective of medical robotics research from 2010 to 2020","volume":"6","author":"Dupont","year":"2021","journal-title":"Sci. Robot."},{"issue":"4","key":"10.1016\/j.media.2026.104279_b13","article-title":"Learning multiple tasks with kernel methods.","volume":"6","author":"Evgeniou","year":"2005","journal-title":"J. Mach. Learn. Res."},{"issue":"12","key":"10.1016\/j.media.2026.104279_b14","doi-asserted-by":"crossref","first-page":"4356","DOI":"10.1109\/TMI.2024.3439701","article-title":"Self-supervised cyclic diffeomorphic mapping for soft tissue deformation recovery in robotic surgery scenes","volume":"43","author":"Gong","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"10.1016\/j.media.2026.104279_b15","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1146\/annurev-control-061521-070251","article-title":"Medical robotics: opportunities in China","volume":"5","author":"Guo","year":"2022","journal-title":"Annu. Rev. Control. Robot. Auton. Syst."},{"issue":"7","key":"10.1016\/j.media.2026.104279_b16","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1007\/s11548-023-02919-w","article-title":"Learning how to robustly estimate camera pose in endoscopic videos","volume":"18","author":"Hayoz","year":"2023","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.104279_b17","doi-asserted-by":"crossref","unstructured":"Jiang, S., Campbell, D., Lu, Y., Li, H., Hartley, R., 2021. Learning to estimate hidden motions with global motion aggregation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9772\u20139781.","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"10.1016\/j.media.2026.104279_b18","doi-asserted-by":"crossref","unstructured":"Jiang, H., Sun, D., Jampani, V., Lv, Z., Learned-Miller, E., Kautz, J., 2019. Sense: A shared encoder network for scene-flow estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3195\u20133204.","DOI":"10.1109\/ICCV.2019.00329"},{"key":"10.1016\/j.media.2026.104279_b19","series-title":"Surgical scene understanding in the era of foundation ai models: A comprehensive review","author":"Khan","year":"2025"},{"key":"10.1016\/j.media.2026.104279_b20","doi-asserted-by":"crossref","unstructured":"Kokkinos, I., 2017. Ubernet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6129\u20136138.","DOI":"10.1109\/CVPR.2017.579"},{"key":"10.1016\/j.media.2026.104279_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103765","article-title":"Collaborative surgical instrument segmentation for monocular depth estimation in minimally invasive surgery","author":"Li","year":"2025","journal-title":"Med. Image Anal."},{"issue":"8","key":"10.1016\/j.media.2026.104279_b22","doi-asserted-by":"crossref","first-page":"2803","DOI":"10.1109\/TMI.2024.3381209","article-title":"Instrument-tissue interaction detection framework for surgical video understanding","volume":"43","author":"Lin","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104279_b23","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"399","article-title":"Instrument-tissue interaction quintuple detection in surgery videos","author":"Lin","year":"2022"},{"key":"10.1016\/j.media.2026.104279_b24","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"435","article-title":"Resurgsam2: Referring segment anything in surgical video via credible long-term tracking","author":"Liu","year":"2025"},{"key":"10.1016\/j.media.2026.104279_b25","series-title":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"7726","article-title":"Towards accurate brain electrode implantation via cross-modality fusion of white-light and photoacoustic microscopy","author":"Liu","year":"2025"},{"key":"10.1016\/j.media.2026.104279_b26","series-title":"IJCAI","first-page":"876","article-title":"Unsupervised learning of scene flow estimation fusing with local rigidity.","author":"Liu","year":"2019"},{"key":"10.1016\/j.media.2026.104279_b27","article-title":"FPM-R2Net: Fused photoacoustic and operating microscopic imaging with cross-modality representation and registration network","author":"Liu","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104279_b28","article-title":"Simultaneous surgical stereo depth and motion estimation via brightness-aware self-supervised learning","author":"Liu","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.media.2026.104279_b29","article-title":"PLDKD-Net: Pixel-level discriminative knowledge distillation for surgical scene segmentation with graph-based visual parsing","author":"Lu","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.media.2026.104279_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103303","article-title":"A lightweight hierarchical feature fusion network for surgical instrument segmentation in internet of medical things","author":"Mahmood","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.media.2026.104279_b31","doi-asserted-by":"crossref","DOI":"10.1109\/TMI.2025.3590457","article-title":"Instrument-tissue-guided surgical action triplet detection via textual-temporal trail exploration","author":"Pei","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"11","key":"10.1016\/j.media.2026.104279_b32","doi-asserted-by":"crossref","first-page":"3218","DOI":"10.1109\/TMI.2022.3181229","article-title":"MSDESIS: Multitask stereo disparity estimation and surgical instrument segmentation","volume":"41","author":"Psychogyios","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104279_b33","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1007\/s11548-020-02160-9","article-title":"Learned optical flow for intra-operative tracking of the retinal fundus","volume":"15","author":"Ravasio","year":"2020","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.104279_b34","series-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"10.1016\/j.media.2026.104279_b35","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.media.2026.104279_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.107929","article-title":"Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art","volume":"169","author":"Rueckert","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.104279_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102751","article-title":"Fun-sis: A fully unsupervised approach for surgical instrument segmentation","volume":"85","author":"Sestini","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104279_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102338","article-title":"Self-supervised monocular depth and ego-motion estimation in endoscopy: Appearance flow to the rescue","volume":"77","author":"Shao","year":"2022","journal-title":"Med. Image Anal."},{"issue":"11","key":"10.1016\/j.media.2026.104279_b39","doi-asserted-by":"crossref","first-page":"3408","DOI":"10.1109\/TMI.2023.3288127","article-title":"Branch aggregation attention network for robotic surgical instrument segmentation","volume":"42","author":"Shen","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"7","key":"10.1016\/j.media.2026.104279_b40","doi-asserted-by":"crossref","first-page":"1267","DOI":"10.1007\/s11548-024-03163-6","article-title":"Surgical-DeSAM: decoupling SAM for instrument segmentation in robotic surgery","volume":"19","author":"Sheng","year":"2024","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.media.2026.104279_b41","series-title":"2018 17th IEEE International Conference on Machine Learning and Applications","first-page":"624","article-title":"Automatic instrument segmentation in robot-assisted surgery using deep learning","author":"Shvets","year":"2018"},{"key":"10.1016\/j.media.2026.104279_b42","series-title":"2018 17th IEEE International Conference on Machine Learning and Applications","first-page":"624","article-title":"Automatic instrument segmentation in robot-assisted surgery using deep learning","author":"Shvets","year":"2018"},{"key":"10.1016\/j.media.2026.104279_b43","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16","first-page":"402","article-title":"Raft: Recurrent all-pairs field transforms for optical flow","author":"Teed","year":"2020"},{"key":"10.1016\/j.media.2026.104279_b44","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.2026.104279_b45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yang, Y., Yang, Z., Zhao, L., Wang, P., Xu, W., 2018. Occlusion aware unsupervised learning of optical flow. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4884\u20134893.","DOI":"10.1109\/CVPR.2018.00513"},{"key":"10.1016\/j.media.2026.104279_b46","article-title":"Video-instrument synergistic network for referring video instrument segmentation in robotic surgery","author":"Wang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"6","key":"10.1016\/j.media.2026.104279_b47","doi-asserted-by":"crossref","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","article-title":"Knowledge distillation and student-teacher learning for visual intelligence: A review and new outlooks","volume":"44","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.104279_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103387","article-title":"LACOSTE: Exploiting stereo and temporal contexts for surgical instrument segmentation","volume":"99","author":"Wang","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104279_b49","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"14","key":"10.1016\/j.media.2026.104279_b50","doi-asserted-by":"crossref","first-page":"eaar7650","DOI":"10.1126\/scirobotics.aar7650","article-title":"The grand challenges of science robotics","volume":"3","author":"Yang","year":"2018","journal-title":"Sci. Robot."},{"key":"10.1016\/j.media.2026.104279_b51","series-title":"Medical Image Understanding and Analysis: 25th Annual Conference, MIUA 2021, Oxford, United Kingdom, July 12\u201314, 2021, Proceedings 25","first-page":"337","article-title":"Dense depth estimation from stereo endoscopy videos using unsupervised optical flow methods","author":"Yang","year":"2021"},{"key":"10.1016\/j.media.2026.104279_b52","doi-asserted-by":"crossref","unstructured":"Yin, Z., Shi, J., 2018. Geonet: Unsupervised learning of dense depth, optical flow and camera pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1983\u20131992.","DOI":"10.1109\/CVPR.2018.00212"},{"key":"10.1016\/j.media.2026.104279_b53","doi-asserted-by":"crossref","unstructured":"Yogamani, S., Hughes, C., Horgan, J., Sistu, G., Varley, P., O\u2019Dea, D., Uric\u00e1r, M., Milz, S., Simon, M., Amende, K., 2019. Woodscape: A multi-task, multi-camera fisheye dataset for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9308\u20139318.","DOI":"10.1109\/ICCV.2019.00940"},{"key":"10.1016\/j.media.2026.104279_b54","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6890","article-title":"Surgicalsam: Efficient class promptable surgical instrument segmentation","volume":"vol. 38","author":"Yue","year":"2024"},{"issue":"9","key":"10.1016\/j.media.2026.104279_b55","doi-asserted-by":"crossref","first-page":"6547","DOI":"10.1109\/TVCG.2023.3347438","article-title":"A self-supervised network-based smoke removal and depth estimation for monocular endoscopic videos","volume":"30","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.media.2026.104279_b56","first-page":"28611","article-title":"Text promptable surgical instrument segmentation with vision-language models","volume":"36","author":"Zhou","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003488?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003488?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T07:06:27Z","timestamp":1789110387000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526003488"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":56,"alternative-id":["S1361841526003488"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104279","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Surgical instrument-tissue characterization via multi-task self-supervised instrument segmentation and motion estimation","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104279","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104279"}}