{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T03:13:34Z","timestamp":1788923614178,"version":"build-2803163510"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T00:00:00Z","timestamp":1779494400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":83,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Data"],"DOI":"10.1038\/s41597-026-07464-0","type":"journal-article","created":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T02:33:52Z","timestamp":1779503632000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis"],"prefix":"10.1038","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2177-9936","authenticated-orcid":false,"given":"Mohammad Javad","family":"Ahmadi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iman","family":"Gandomi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parisa","family":"Abdi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seyed-Farzad","family":"Mohammadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amirhossein","family":"Taslimi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehdi","family":"Khodaparast","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hassan","family":"Hashemi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahdi","family":"Tavakoli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid","family":"D. Taghirad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,23]]},"reference":[{"key":"7464_CR1","doi-asserted-by":"publisher","first-page":"1918","DOI":"10.1097\/MS9.0000000000003128","volume":"87","author":"E Yaqoob","year":"2025","unstructured":"Yaqoob, E. et al. Public health meets global surgery: a synergistic approach to better outcomes. Annals of Medicine and Surgery (Lond.) 87, 1918\u20131923, https:\/\/doi.org\/10.1097\/MS9.0000000000003128 (2025).","journal-title":"Annals of Medicine and Surgery (Lond.)"},{"key":"7464_CR2","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/s44186-025-00355-9","volume":"4","author":"E Cruz","year":"2025","unstructured":"Cruz, E. et al. A scalable solution: effective AI implementation in laparoscopic simulation training assessments. Global Surgical Education 4, 355, https:\/\/doi.org\/10.1007\/s44186-025-00355-9 (2025).","journal-title":"Global Surgical Education"},{"key":"7464_CR3","doi-asserted-by":"publisher","first-page":"1037048","DOI":"10.3389\/fbioe.2022.1037048","volume":"10","author":"JZ Moolenaar","year":"2022","unstructured":"Moolenaar, J. Z., T\u00fcmer, N. & Checa, S. Computer-assisted preoperative planning of bone fracture fixation surgery: a state-of-the-art review. Frontiers in Bioengineering and Biotechnology 10, 1037048, https:\/\/doi.org\/10.3389\/fbioe.2022.1037048 (2022).","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"key":"7464_CR4","doi-asserted-by":"publisher","first-page":"89963","DOI":"10.60118\/001c.89963","volume":"5","author":"DAL Schoenmakers","year":"2024","unstructured":"Schoenmakers, D. A. L. et al. Computer-based pre- and intra-operative planning modalities for Total Knee Arthroplasty: a comprehensive review. Journal of Orthopaedic Experience & Innovation 5, 89963, https:\/\/doi.org\/10.60118\/001c.89963 (2024).","journal-title":"Journal of Orthopaedic Experience & Innovation"},{"key":"7464_CR5","doi-asserted-by":"publisher","unstructured":"Ahmadi, M. J. et al. ARAS-Farabi experimental framework for skill assessment in capsulorhexis surgery. 2021 9th RSI International Conference on Robotics and Mechatronics (ICRoM), 385\u2013390, https:\/\/doi.org\/10.1109\/ICRoM54204.2021.9663494 (2021).","DOI":"10.1109\/ICRoM54204.2021.9663494"},{"key":"7464_CR6","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00707-5","volume":"5","author":"P Mascagni","year":"2022","unstructured":"Mascagni, P. et al. Computer vision in surgery: from potential to clinical value. NPJ Digital Medicine 5, 163, https:\/\/doi.org\/10.1038\/s41746-022-00707-5 (2022).","journal-title":"NPJ Digital Medicine"},{"key":"7464_CR7","doi-asserted-by":"publisher","first-page":"7108","DOI":"10.3390\/jcm13237108","volume":"13","author":"N Kenig","year":"2024","unstructured":"Kenig, N., Monton Echeverria, J. & Muntaner Vives, A. Artificial intelligence in surgery: a systematic review of use and validation. Journal of Clinical Medicine 13, 7108, https:\/\/doi.org\/10.3390\/jcm13237108 (2024).","journal-title":"Journal of Clinical Medicine"},{"key":"7464_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-05093-7","volume":"12","author":"Z Ye","year":"2025","unstructured":"Ye, Z. et al. A comprehensive video dataset for surgical laparoscopic action analysis. Scientific Data 12, 5093, https:\/\/doi.org\/10.1038\/s41597-025-05093-7 (2025).","journal-title":"Scientific Data"},{"key":"7464_CR9","doi-asserted-by":"publisher","first-page":"e1221","DOI":"10.1016\/S2214-109X(17)30393-5","volume":"5","author":"SR Flaxman","year":"2017","unstructured":"Flaxman, S. R. et al. Global causes of blindness and distance vision impairment 1990\u20132020: a systematic review and meta-analysis. Lancet Global Health 5, e1221\u2013e1234, https:\/\/doi.org\/10.1016\/S2214-109X(17)30393-5 (2017).","journal-title":"Lancet Global Health"},{"key":"7464_CR10","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1097\/ICU.0000000000001092","volume":"36","author":"H Hashemi","year":"2025","unstructured":"Hashemi, H., Fayaz, F., Hashemi, A. & Khabazkhoob, M. Global prevalence of cataract surgery. Current Opinion in Ophthalmology 36, 10\u201317, https:\/\/doi.org\/10.1097\/ICU.0000000000001092 (2025).","journal-title":"Current Opinion in Ophthalmology"},{"key":"7464_CR11","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1167\/tvst.13.4.20","volume":"13","author":"S M\u00fcller","year":"2024","unstructured":"M\u00fcller, S. et al. Artificial intelligence in cataract surgery: a systematic review. Translational Vision Science & Technology 13, 20, https:\/\/doi.org\/10.1167\/tvst.13.4.20 (2024).","journal-title":"Translational Vision Science & Technology"},{"key":"7464_CR12","doi-asserted-by":"publisher","first-page":"100164","DOI":"10.1016\/j.xops.2022.100164","volume":"2","author":"DJ Lindegger","year":"2022","unstructured":"Lindegger, D. J., Wawrzynski, J. & Saleh, G. M. Evolution and applications of artificial intelligence to cataract surgery. Ophthalmology Science 2, 100164, https:\/\/doi.org\/10.1016\/j.xops.2022.100164 (2022).","journal-title":"Ophthalmology Science"},{"key":"7464_CR13","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.media.2018.11.008","volume":"52","author":"H Al Hajj","year":"2019","unstructured":"Al Hajj, H. et al. CATARACTS: Challenge on automatic tool annotation for cataRACT surgery. Medical Image Analysis 52, 24\u201341, https:\/\/doi.org\/10.1016\/j.media.2018.11.008 (2019).","journal-title":"Medical Image Analysis"},{"key":"7464_CR14","doi-asserted-by":"publisher","first-page":"102053","DOI":"10.1016\/j.media.2021.102053","volume":"71","author":"M Grammatikopoulou","year":"2021","unstructured":"Grammatikopoulou, M. et al. CaDIS: Cataract dataset for surgical RGB-image segmentation. Medical Image Analysis 71, 102053, https:\/\/doi.org\/10.1016\/j.media.2021.102053 (2021).","journal-title":"Medical Image Analysis"},{"key":"7464_CR15","doi-asserted-by":"publisher","unstructured":"Ghamsarian, N. et al. Relevance-Based Compression of Cataract Surgery Videos Using Convolutional Neural Networks. MM \u201920: The 28th ACM International Conference on Multimedia, 3577\u20133585, https:\/\/doi.org\/10.1145\/3394171.3413658 (2020).","DOI":"10.1145\/3394171.3413658"},{"key":"7464_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-00303-z","volume":"15","author":"S Mueller","year":"2025","unstructured":"Mueller, S., Sachdeva, B. & Prasad, S. N. et al. Phase recognition in manual Small-Incision cataract surgery with MS-TCN++ on the novel SICS-105 dataset. Scientific Reports 15, 16886, https:\/\/doi.org\/10.1038\/s41598-025-00303-z (2025).","journal-title":"Scientific Reports"},{"key":"7464_CR17","doi-asserted-by":"publisher","unstructured":"Sachdeva, B. et al. Phase-Informed Tool Segmentation for Manual Small-Incision Cataract Surgery. Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025 15968, https:\/\/doi.org\/10.1007\/978-3-032-05114-1_43 (2026).","DOI":"10.1007\/978-3-032-05114-1_43"},{"key":"7464_CR18","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03193-4","volume":"11","author":"N Ghamsarian","year":"2024","unstructured":"Ghamsarian, N. et al. Cataract-1K dataset for deep-learning-assisted analysis of cataract surgery videos. Scientific Data 11, 373, https:\/\/doi.org\/10.1038\/s41597-024-03193-4 (2024).","journal-title":"Scientific Data"},{"key":"7464_CR19","doi-asserted-by":"crossref","unstructured":"Hatam, S. M. et al. AI-Powered Framework for Cataract Surgery Video Optimization. 2024 12th RSI International Conference on Robotics and Mechatronics (ICRoM), 419\u2013425 (2024).","DOI":"10.1109\/ICRoM64545.2024.10903624"},{"key":"7464_CR20","doi-asserted-by":"publisher","first-page":"2456","DOI":"10.1016\/j.ophtha.2013.05.003","volume":"120","author":"CA McCannel","year":"2013","unstructured":"McCannel, C. A., Reed, D. C. & Goldman, D. R. Ophthalmic surgery simulator training improves resident performance of capsulorhexis in the operating room. Ophthalmology 120, 2456\u20132461, https:\/\/doi.org\/10.1016\/j.ophtha.2013.05.003 (2013).","journal-title":"Ophthalmology"},{"key":"7464_CR21","doi-asserted-by":"publisher","unstructured":"Aharon, N. et al. BoT-SORT: Robust Associations Multi-Pedestrian Tracking. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2206.14651 (2022).","DOI":"10.48550\/arXiv.2206.14651"},{"key":"7464_CR22","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1016\/j.ophtha.2005.05.010","volume":"112","author":"SL Cremers","year":"2005","unstructured":"Cremers, S. L., Lora, A. N. & Ferrufino-Ponce, Z. K. Global Rating Assessment of Skills in Intraocular Surgery (GRASIS). Ophthalmology 112, 1655\u20131660, https:\/\/doi.org\/10.1016\/j.ophtha.2005.05.010 (2005).","journal-title":"Ophthalmology"},{"key":"7464_CR23","first-page":"427\u2013427.e5","volume":"118","author":"KC Golnik","year":"2011","unstructured":"Golnik, K. C., Beaver, H., Gauba, V., Lee, A. G., Mayorga, E., Palis, G. & Saleh, G. M. Cataract Surgical Skill Assessment. Ophthalmology 118, 427\u2013427.e5 (2011).","journal-title":"Ophthalmology"},{"key":"7464_CR24","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Computation 9, 1735\u20131780, https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735 (1997).","journal-title":"Neural Computation"},{"key":"7464_CR25","doi-asserted-by":"publisher","unstructured":"Cho, K. et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1724\u20131734, https:\/\/doi.org\/10.3115\/v1\/D14-1179 (2014).","DOI":"10.3115\/v1\/D14-1179"},{"key":"7464_CR26","doi-asserted-by":"publisher","unstructured":"Feichtenhofer, C., Fan, H., Malik, J. & He, K. SlowFast networks for video recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision, 6202\u20136211, https:\/\/doi.org\/10.1109\/ICCV.2019.00630 (2019).","DOI":"10.1109\/ICCV.2019.00630"},{"key":"7464_CR27","doi-asserted-by":"publisher","unstructured":"Feichtenhofer, C. X3D: Expanding architectures for efficient video recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 200\u2013210, https:\/\/doi.org\/10.1109\/CVPR42600.2020.00028 (2020).","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"7464_CR28","doi-asserted-by":"publisher","unstructured":"Tran, D. et al. A closer look at spatiotemporal convolutions for action recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6450\u20136459, https:\/\/doi.org\/10.1109\/CVPR.2018.00675 (2018).","DOI":"10.1109\/CVPR.2018.00675"},{"key":"7464_CR29","doi-asserted-by":"publisher","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L. & Paluri, M. Learning spatiotemporal features with 3D convolutional networks. Proceedings of the IEEE International Conference on Computer Vision, 4489\u20134497, https:\/\/doi.org\/10.1109\/ICCV.2015.510 (2015).","DOI":"10.1109\/ICCV.2015.510"},{"key":"7464_CR30","doi-asserted-by":"publisher","unstructured":"Fan, H. et al. Multiscale vision transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision, 6804\u20136815, https:\/\/doi.org\/10.1109\/ICCV48922.2021.00675 (2021).","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"7464_CR31","doi-asserted-by":"publisher","unstructured":"Liu, Z. et al. Video Swin Transformer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3192\u20133201, https:\/\/doi.org\/10.1109\/CVPR52688.2022.00320 (2022).","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"7464_CR32","doi-asserted-by":"publisher","unstructured":"Czempiel, T. et al. TeCNO: Surgical Phase Recognition with Multi-stage Temporal Convolutional Networks. In Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020 (eds. Martel, A. L.et al.) 343\u2013352 https:\/\/doi.org\/10.1007\/978-3-030-59716-0_33 (Springer, 2020).","DOI":"10.1007\/978-3-030-59716-0_33"},{"key":"7464_CR33","doi-asserted-by":"crossref","unstructured":"Yi, F. et al. ASFormer: Transformer for Action Segmentation. The British Machine Vision Conference (BMVC) (2021).","DOI":"10.5244\/C.35.49"},{"key":"7464_CR34","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y. et al. Microsoft COCO: Common Objects in Context. In Computer Vision \u2013 ECCV 2014 (eds. Fleet, D., Pajdla, T., Schiele, B. & Tuytelaars, T.) 740\u2013755 https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48 (Springer, 2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"7464_CR35","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P. & Girshick, R. Mask R-CNN. IEEE Transactions on Pattern Analysis and Machine Intelligence 42, 386\u2013397, https:\/\/doi.org\/10.1109\/TPAMI.2018.2844175 (2020).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"7464_CR36","unstructured":"Jocher, G., Qiu, J. & Chaurasia, A. Ultralytics YOLO, version 8.0.0. GitHub https:\/\/github.com\/ultralytics\/ultralytics (2023)."},{"key":"7464_CR37","doi-asserted-by":"publisher","unstructured":"Kirillov, A. et al. Segment Anything. Proceedings of the IEEE\/CVF International Conference on Computer Vision, 3992\u20134003, https:\/\/doi.org\/10.1109\/ICCV51070.2023.00371 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"7464_CR38","doi-asserted-by":"publisher","unstructured":"Ravi, N. et al. SAM 2: Segment Anything in Images and Videos. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2408.00714 (2024).","DOI":"10.48550\/arXiv.2408.00714"},{"key":"7464_CR39","unstructured":"Bertasius, G., Wang, H. & Torresani, L. Is space-time attention all you need for video understanding? 38th International Conference on Machine Learning, 813\u2013824, https:\/\/proceedings.mlr.press\/v139\/bertasius21a.html (2021)."},{"key":"7464_CR40","doi-asserted-by":"publisher","first-page":"101014","DOI":"10.1016\/j.xops.2025.101014","volume":"6","author":"D Mikhail","year":"2026","unstructured":"Mikhail, D. et al. Quantitative Analysis of Instrument Motion Paths in Cataract Surgery across a Resident\u2019s Training. Ophthalmology Science 6, 101014, https:\/\/doi.org\/10.1016\/j.xops.2025.101014 (2026).","journal-title":"Ophthalmology Science"},{"key":"7464_CR41","doi-asserted-by":"publisher","unstructured":"Ahmadi, M. J. et al. Cataract-LMM. Hugging Face https:\/\/doi.org\/10.57967\/hf\/8673 (2026).","DOI":"10.57967\/hf\/8673"},{"key":"7464_CR42","doi-asserted-by":"crossref","unstructured":"Gandomi, I. et al. A Deep Dive Into Capsulorhexis Segmentation: From Dataset Creation to SAM Fine-tuning. 2023 11th RSI International Conference on Robotics and Mechatronics (ICRoM), 675\u2013681 (2023).","DOI":"10.1109\/ICRoM60803.2023.10412370"},{"key":"7464_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Y. et al. ByteTrack: Multi-Object Tracking by Associating Every Detection Box. Proceedings of the European Conference on Computer Vision (ECCV) (2022).","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"7464_CR44","doi-asserted-by":"publisher","unstructured":"Sapkota, R. et al. YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2509.25164 (2026).","DOI":"10.48550\/arXiv.2509.25164"},{"key":"7464_CR45","doi-asserted-by":"crossref","unstructured":"Zeng, F. et al. MOTR: End-to-End Multiple-Object Tracking with TRansformer. European Conference on Computer Vision (ECCV) (2022).","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"7464_CR46","doi-asserted-by":"crossref","unstructured":"Lafouti, M. et al. Surgical Instrument Tracking for Capsulorhexis Eye Surgery Based on Siamese Networks. 2022 10th RSI International Conference on Robotics and Mechatronics (ICRoM), 196\u2013201 (2022).","DOI":"10.1109\/ICRoM57054.2022.10025355"},{"key":"7464_CR47","doi-asserted-by":"crossref","unstructured":"Cheng, B. et al. Masked-attention Mask Transformer for Universal Image Segmentation. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022).","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"7464_CR48","doi-asserted-by":"publisher","unstructured":"Ayobi, N. et al. MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation. 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI) 1\u20135, https:\/\/doi.org\/10.1109\/ISBI53787.2023.10230819 (2023).","DOI":"10.1109\/ISBI53787.2023.10230819"},{"key":"7464_CR49","doi-asserted-by":"publisher","unstructured":"Yang, J. et al. Track Anything: Segment Anything Meets Videos. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2304.11968 (2023).","DOI":"10.48550\/arXiv.2304.11968"},{"key":"7464_CR50","doi-asserted-by":"crossref","unstructured":"Karaev, N. et al. CoTracker: It is Better to Track Together. Proceedings of ECCV (2024).","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"7464_CR51","doi-asserted-by":"publisher","unstructured":"Hira, S. et al. Video-based assessment of intraoperative surgical skill. International Journal of Computer Assisted Radiology and Surgery17, 1801\u20131811, https:\/\/doi.org\/10.1007\/s11548-022-02681-5 (2022).","DOI":"10.1007\/s11548-022-02681-5"},{"key":"7464_CR52","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1007\/s11548-019-01995-1","volume":"14","author":"I Funke","year":"2019","unstructured":"Funke, I. et al. Video-based surgical skill assessment using 3D convolutional neural networks. International Journal of Computer Assisted Radiology and Surgery 14, 1217\u20131225, https:\/\/doi.org\/10.1007\/s11548-019-01995-1 (2019).","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"7464_CR53","doi-asserted-by":"crossref","unstructured":"Li, Z. et al. Surgical Skill Assessment via Video Semantic Aggregation. Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022 410\u2013420 (2022).","DOI":"10.1007\/978-3-031-16449-1_39"},{"key":"7464_CR54","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1167\/tvst.12.3.23","volume":"12","author":"HH Yeh","year":"2023","unstructured":"Yeh, H. H. et al. PhacoTrainer: Deep Learning for Cataract Surgical Videos to Track Surgical Tools. Translational Vision Science & Technology 12, 23, https:\/\/doi.org\/10.1167\/tvst.12.3.23 (2023).","journal-title":"Translational Vision Science & Technology"},{"key":"7464_CR55","doi-asserted-by":"publisher","unstructured":"Chen, X., Fan, H., Girshick, R. & He, K. Improved baselines with momentum contrastive learning. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2003.04297 (2020).","DOI":"10.48550\/arXiv.2003.04297"},{"key":"7464_CR56","doi-asserted-by":"publisher","unstructured":"Ramesh, S. et al. Dissecting self-supervised learning methods for surgical computer vision. Medical Image Analysis 88, 102844, https:\/\/doi.org\/10.1016\/j.media.2023.102844 (2023).","DOI":"10.1016\/j.media.2023.102844"},{"key":"7464_CR57","doi-asserted-by":"publisher","unstructured":"Yang, S. et al. Large-scale self-supervised video foundation model for intelligent surgery. npj Digital Medicine, https:\/\/doi.org\/10.1038\/s41746-026-02403-0 (2026).","DOI":"10.1038\/s41746-026-02403-0"},{"key":"7464_CR58","doi-asserted-by":"crossref","unstructured":"Hu, M. et al. Ophclip: Hierarchical retrieval-augmented learning for ophthalmic surgical video-language pretraining. Proceedings of the IEEE\/CVF International Conference on Computer Vision 19838\u201319849 (2025).","DOI":"10.1109\/ICCV51701.2025.01845"},{"key":"7464_CR59","doi-asserted-by":"publisher","unstructured":"Luengo, I. et al. SurReal: enhancing Surgical simulation Realism using style transfer. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.1811.02946 (2018).","DOI":"10.48550\/arXiv.1811.02946"},{"key":"7464_CR60","doi-asserted-by":"publisher","unstructured":"Chen, T. et al. SurgSora: Object-Aware Diffusion Model for Controllable Surgical Video Generation. Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 202515969, https:\/\/doi.org\/10.1007\/978-3-032-05127-1_50 (2026).","DOI":"10.1007\/978-3-032-05127-1_50"}],"container-title":["Scientific Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07464-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07464-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07464-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T22:53:46Z","timestamp":1786661626000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07464-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,23]]},"references-count":60,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["7464"],"URL":"https:\/\/doi.org\/10.1038\/s41597-026-07464-0","relation":{},"ISSN":["2052-4463"],"issn-type":[{"value":"2052-4463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,23]]},"assertion":[{"value":"12 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"1189"}}