{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T13:11:11Z","timestamp":1778764271749,"version":"3.51.4"},"reference-count":70,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62471293"],"award-info":[{"award-number":["62471293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20199"],"award-info":[{"award-number":["U20A20199"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computerized Medical Imaging and Graphics"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.compmedimag.2026.102770","type":"journal-article","created":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T06:33:25Z","timestamp":1776494005000},"page":"102770","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TPDPM: Text promptable diffusion probabilistic model for referring surgical instrument segmentation"],"prefix":"10.1016","volume":"131","author":[{"given":"Jiale","family":"Guan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simeng","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4173-0379","authenticated-orcid":false,"given":"Guoyan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.compmedimag.2026.102770_b1","series-title":"2018 Robotic scene segmentation challenge","author":"Allan","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102770_b2","series-title":"2017 Robotic instrument segmentation challenge","author":"Allan","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102770_b3","series-title":"2023 IEEE 20th International Symposium on Biomedical Imaging","first-page":"1","article-title":"Matis: Masked-attention transformers for surgical instrument segmentation","author":"Ayobi","year":"2023"},{"issue":"3","key":"10.1016\/j.compmedimag.2026.102770_b4","first-page":"3","article-title":"Generative or discriminative? getting the best of both worlds","volume":"8","author":"Bernardo","year":"2007","journal-title":"Bayesian Stat."},{"issue":"12","key":"10.1016\/j.compmedimag.2026.102770_b5","doi-asserted-by":"crossref","first-page":"2603","DOI":"10.1109\/TMI.2015.2450831","article-title":"Detecting surgical tools by modelling local appearance and global shape","volume":"34","author":"Bouget","year":"2015","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compmedimag.2026.102770_b6","doi-asserted-by":"crossref","unstructured":"Chen, J., Lu, J., Zhu, X., Zhang, L., 2023. Generative semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7111\u20137120.","DOI":"10.1109\/CVPR52729.2023.00687"},{"key":"10.1016\/j.compmedimag.2026.102770_b7","article-title":"HiDiff: hybrid diffusion framework for medical image segmentation","author":"Chen","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compmedimag.2026.102770_b8","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"491","article-title":"Berdiff: Conditional bernoulli diffusion model for medical image segmentation","author":"Chen","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102770_b9","series-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"2164","article-title":"Conditional gan for enhancing diffusion models in efficient and authentic global gesture generation from audios","author":"Cheng","year":"2025"},{"key":"10.1016\/j.compmedimag.2026.102770_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102608","article-title":"Taming large vision model for medical image segmentation via dual visual prompt tuning","author":"Cui","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102770_b11","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K., 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"issue":"5","key":"10.1016\/j.compmedimag.2026.102770_b12","doi-asserted-by":"crossref","first-page":"1450","DOI":"10.1109\/TMI.2021.3057884","article-title":"Image compositing for segmentation of surgical tools without manual annotations","volume":"40","author":"Garcia-Peraza-Herrera","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compmedimag.2026.102770_b13","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"595","article-title":"Isinet: an instance-based approach for surgical instrument segmentation","author":"Gonz\u00e1lez","year":"2020"},{"issue":"3","key":"10.1016\/j.compmedimag.2026.102770_b14","first-page":"299","article-title":"Surgical instrument grounding for robot-assisted interventions","volume":"10","author":"Gonz\u00e1lez","year":"2022","journal-title":"Comput. Methods Biomech. Biomed. Eng.: Imaging & Vis."},{"key":"10.1016\/j.compmedimag.2026.102770_b15","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1298","article-title":"Vision-based surgical tool pose estimation for the da vinci\u00ae robotic surgical system","author":"Hao","year":"2018"},{"key":"10.1016\/j.compmedimag.2026.102770_b16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compmedimag.2026.102770_b17","doi-asserted-by":"crossref","unstructured":"Hu, Z., Feng, G., Sun, J., Zhang, L., Lu, H., 2020. Bi-directional relationship inferring network for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4424\u20134433.","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"10.1016\/j.compmedimag.2026.102770_b18","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11\u201314, 2016, Proceedings, Part I 14","first-page":"108","article-title":"Segmentation from natural language expressions","author":"Hu","year":"2016"},{"key":"10.1016\/j.compmedimag.2026.102770_b19","series-title":"Clinicalbert: Modeling clinical notes and predicting hospital readmission","author":"Huang","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102770_b20","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part V 22","first-page":"440","article-title":"Incorporating temporal prior from motion flow for instrument segmentation in minimally invasive surgery video","author":"Jin","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102770_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2023.102248","article-title":"Automatic summarization of endoscopic skull base surgical videos through object detection and hidden Markov modeling","volume":"108","author":"King","year":"2023","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102770_b22","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"},{"issue":"9","key":"10.1016\/j.compmedimag.2026.102770_b23","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1007\/s11548-021-02438-6","article-title":"Accurate instance segmentation of surgical instruments in robotic surgery: model refinement and cross-dataset evaluation","volume":"16","author":"Kong","year":"2021","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102770_b24","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.surg.2021.01.051","article-title":"Validity and effectiveness of augmented reality in surgical education: a systematic review","volume":"170","author":"Kovoor","year":"2021","journal-title":"Surgery"},{"key":"10.1016\/j.compmedimag.2026.102770_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102660","article-title":"Efficient frequency-decomposed transformer via large vision model guidance for surgical image desmoking","author":"Li","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102770_b26","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"717","article-title":"Multi-target domain adaptation with prompt learning for medical image segmentation","author":"Lin","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102770_b27","series-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102770_b28","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III 23","first-page":"657","article-title":"Unsupervised surgical instrument segmentation via anchor generation and semantic diffusion","author":"Liu","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102770_b29","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhang, Y., Chen, J.N., Xiao, J., Lu, Y., A Landman, B., Yuan, Y., Yuille, A., Tang, Y., Zhou, Z., 2023. Clip-driven universal model for organ segmentation and tumor detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 21152\u201321164.","DOI":"10.1109\/ICCV51070.2023.01934"},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102770_b30","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.compmedimag.2026.102770_b31","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3520386","article-title":"Samsurg: Surgical instrument segmentation in robotic surgeries using vision foundation model","author":"Matasyoh","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.compmedimag.2026.102770_b32","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102770_b33","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s41746-021-00455-y","article-title":"Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction","volume":"4","author":"Rasmy","year":"2021","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.compmedimag.2026.102770_b34","article-title":"Secure and privacy-preserving surgical instrument segmentation in minimally invasive surgeries using federated differential privacy approach","author":"Savarimuthu","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102770_b35","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.compmedimag.2026.102770_b36","article-title":"Next-generation virtual and augmented reality in surgical education: a narrative review","volume":"33","author":"Sheik-Ali","year":"2019","journal-title":"Surg. Technol. Int."},{"key":"10.1016\/j.compmedimag.2026.102770_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102501","article-title":"ProtoSAM-3D: Interactive semantic segmentation in volumetric medical imaging via a Segment Anything Model and mask-level prototypes","volume":"121","author":"Shen","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"issue":"7","key":"10.1016\/j.compmedimag.2026.102770_b38","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.compmedimag.2026.102770_b39","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.compmedimag.2026.102770_b40","series-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"issue":"7","key":"10.1016\/j.compmedimag.2026.102770_b41","first-page":"3779","article-title":"See-through vision with unsupervised scene occlusion reconstruction","volume":"44","author":"Tukra","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102770_b42","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","article-title":"Endonet: a deep architecture for recognition tasks on laparoscopic videos","volume":"36","author":"Twinanda","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compmedimag.2026.102770_b43","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compmedimag.2026.102770_b44","doi-asserted-by":"crossref","unstructured":"Wang, Z., Lu, Y., Li, Q., Tao, X., Guo, Y., Gong, M., Liu, T., 2022a. Cris: Clip-driven referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11686\u201311695.","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"10.1016\/j.compmedimag.2026.102770_b45","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"486","article-title":"Autolaparo: A new dataset of integrated multi-tasks for image-guided surgical automation in laparoscopic hysterectomy","author":"Wang","year":"2022"},{"key":"10.1016\/j.compmedimag.2026.102770_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102650","article-title":"Collect vascular specimens in one cabinet: A hierarchical prompt-guided universal model for 3D vascular segmentation","author":"Wang","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102770_b47","series-title":"International Workshop on Efficient Medical Artificial Intelligence","first-page":"320","article-title":"DetSAM: A joint detection-and-segmentation learning framework for multi-class surgical instrument segmentation","author":"Wang","year":"2025"},{"issue":"6","key":"10.1016\/j.compmedimag.2026.102770_b48","doi-asserted-by":"crossref","DOI":"10.1002\/rcs.2441","article-title":"Real-time trajectory prediction of laparoscopic instrument tip based on long short-term memory neural network in laparoscopic surgery training","volume":"18","author":"Wang","year":"2022","journal-title":"Int. J. Med. Robot. Comput. Assist. Surg."},{"key":"10.1016\/j.compmedimag.2026.102770_b49","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.compmedimag.2026.102770_b50","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2024.102406","article-title":"PFMNet: Prototype-based feature mapping network for few-shot domain adaptation in medical image segmentation","volume":"116","author":"Wang","year":"2024","journal-title":"Comput. Med. Imaging Graph."},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102770_b51","doi-asserted-by":"crossref","first-page":"14042","DOI":"10.1038\/s41598-025-94568-z","article-title":"SegMatch: semi-supervised surgical instrument segmentation","volume":"15","author":"Wei","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.compmedimag.2026.102770_b52","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"533","article-title":"Prompting segment anything model with domain-adaptive prototype for generalizable medical image segmentation","author":"Wei","year":"2024"},{"key":"10.1016\/j.compmedimag.2026.102770_b53","series-title":"International Conference on Medical Imaging with Deep Learning","first-page":"1336","article-title":"Diffusion models for implicit image segmentation ensembles","author":"Wolleb","year":"2022"},{"key":"10.1016\/j.compmedimag.2026.102770_b54","series-title":"Medical Imaging with Deep Learning","first-page":"1623","article-title":"Medsegdiff: Medical image segmentation with diffusion probabilistic model","author":"Wu","year":"2024"},{"key":"10.1016\/j.compmedimag.2026.102770_b55","first-page":"6030","article-title":"Medsegdiff-v2: Diffusion-based medical image segmentation with transformer","volume":"vol. 38","author":"Wu","year":"2024"},{"key":"10.1016\/j.compmedimag.2026.102770_b56","doi-asserted-by":"crossref","first-page":"1782","DOI":"10.1109\/TIP.2024.3371348","article-title":"Toward robust referring image segmentation","volume":"33","author":"Wu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.compmedimag.2026.102770_b57","doi-asserted-by":"crossref","unstructured":"Wu, J., Xu, M., 2024. One-prompt to segment all medical images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11302\u201311312.","DOI":"10.1109\/CVPR52733.2024.01074"},{"key":"10.1016\/j.compmedimag.2026.102770_b58","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2023.102314","article-title":"Nonlinear regression of remaining surgery duration from videos via Bayesian LSTM-based deep negative correlation learning","volume":"110","author":"Wu","year":"2023","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102770_b59","series-title":"Tackling the generative learning trilemma with denoising diffusion GANs","author":"Xiao","year":"2021"},{"key":"10.1016\/j.compmedimag.2026.102770_b60","series-title":"Diff-unet: A diffusion embedded network for volumetric segmentation","author":"Xing","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102770_b61","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhao, Y., Xiao, Z., Hou, T., 2024. Ufogen: You forward once large scale text-to-image generation via diffusion gans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8196\u20138206.","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"10.1016\/j.compmedimag.2026.102770_b62","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112350","article-title":"Cold SegDiffusion: A novel diffusion model for medical image segmentation","volume":"301","author":"Yan","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.compmedimag.2026.102770_b63","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H., 2022. Lavt: Language-aware vision transformer for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18155\u201318165.","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"10.1016\/j.compmedimag.2026.102770_b64","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"508","article-title":"Uniseg: A prompt-driven universal segmentation model as well as a strong representation learner","author":"Ye","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102770_b65","first-page":"6890","article-title":"Surgicalsam: Efficient class promptable surgical instrument segmentation","volume":"vol. 38","author":"Yue","year":"2024"},{"key":"10.1016\/j.compmedimag.2026.102770_b66","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III 23","first-page":"679","article-title":"Learning motion flows for semi-supervised instrument segmentation from robotic surgical video","author":"Zhao","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102770_b67","series-title":"2022 International Conference on Robotics and Automation","first-page":"11186","article-title":"Trasetr: track-to-segment transformer with contrastive query for instance-level instrument segmentation in robotic surgery","author":"Zhao","year":"2022"},{"key":"10.1016\/j.compmedimag.2026.102770_b68","first-page":"28611","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.compmedimag.2026.102770_b69","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102604","article-title":"Capturing action triplet correlations for accurate surgical activity recognition","author":"Zou","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102770_b70","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102622","article-title":"SSIFNet: Spatial\u2013temporal stereo information fusion network for self-supervised surgical video inpainting","author":"Zou","year":"2025","journal-title":"Comput. Med. Imaging Graph."}],"container-title":["Computerized Medical Imaging and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089561112600073X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089561112600073X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:41:45Z","timestamp":1778762505000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089561112600073X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":70,"alternative-id":["S089561112600073X"],"URL":"https:\/\/doi.org\/10.1016\/j.compmedimag.2026.102770","relation":{},"ISSN":["0895-6111"],"issn-type":[{"value":"0895-6111","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TPDPM: Text promptable diffusion probabilistic model for referring surgical instrument segmentation","name":"articletitle","label":"Article Title"},{"value":"Computerized Medical Imaging and Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compmedimag.2026.102770","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102770"}}