{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:10:42Z","timestamp":1767337842184,"version":"3.40.3"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031164484"},{"type":"electronic","value":"9783031164491"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16449-1_37","type":"book-chapter","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T08:04:54Z","timestamp":1663315494000},"page":"387-398","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["CaRTS: Causality-Driven Robot Tool Segmentation from\u00a0Vision and\u00a0Kinematics Data"],"prefix":"10.1007","author":[{"given":"Hao","family":"Ding","sequence":"first","affiliation":[]},{"given":"Jintan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Kazanzides","sequence":"additional","affiliation":[]},{"given":"Jie Ying","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Mathias","family":"Unberath","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,17]]},"reference":[{"key":"37_CR1","unstructured":"Ouyang, C., et al.: Causality-inspired single-source domain generalization for medical image segmentation. arxiv:2111.12525 (2021)"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Gao, C., et al.: Generalizing spatial transformers to projective geometry with applications to 2D\/3D registration. arxiv:2003.10987 (2020)","DOI":"10.1007\/978-3-030-59716-0_32"},{"key":"37_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/978-3-030-59710-8_31","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"D Lenis","year":"2020","unstructured":"Lenis, D., Major, D., Wimmer, M., Berg, A., Sluiter, G., B\u00fchler, Katja: Domain aware medical image classifier interpretation by counterfactual impact analysis. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12261, pp. 315\u2013325. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59710-8_31"},{"key":"37_CR4","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. TPAMI (2019)"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: Hybrid task cascade for instance segmentation. In: Proceedings of Computer Vision and Pattern Recognition Conference, CVPR (2019)","DOI":"10.1109\/CVPR.2019.00511"},{"key":"37_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with Atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"37_CR7","unstructured":"Peraza-Herrera, L.C.G., et al.: ToolNet: Holistically-nested real-time segmentation of robotic surgical tools. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5717\u20135722 (2017)"},{"key":"37_CR8","unstructured":"Ravi, N., et al.: Accelerating 3D deep learning with pyTorch3D. arXiv:2007.08501 (2020)"},{"key":"37_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/978-3-030-87202-1_40","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Y Long","year":"2021","unstructured":"Long, Y., et al.: E-DSSR: efficient dynamic surgical scene reconstruction with\u00a0transformer-based stereoscopic depth perception. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12904, pp. 415\u2013425. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87202-1_40"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6177\u20136186 (2021)","DOI":"10.1109\/ICCV48922.2021.00614"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: One to many: adaptive instrument segmentation via meta learning and dynamic online adaptation in robotic surgical video. In: International Conference on Robotics and Automation, ICRA (2021)","DOI":"10.1109\/ICRA48506.2021.9561690"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Allan, M., Ourselin, S., Hawkes, D.J., Kelly, J.D., Stoyanov, D.: 3-D pose estimation of articulated instruments in robotic minimally invasive surgery. IEEE Trans. Med. Imaging 37(5), 1204\u20131213 (2018)","DOI":"10.1109\/TMI.2018.2794439"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Castro, D.C., Walker, I., Glocker, B.: Causality matters in medical imaging. Nat. Commun. 11(1), 3673 (2020)","DOI":"10.1038\/s41467-020-17478-w"},{"key":"37_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1007\/978-3-030-59716-0_67","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"E Colleoni","year":"2020","unstructured":"Colleoni, E., Edwards, P., Stoyanov, D.: Synthetic and real inputs for tool segmentation in robotic surgery. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 700\u2013710. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_67"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"da Costa Rocha, C., Padoy, N., Rosa, B.: Self-supervised surgical tool segmentation using kinematic information. In: 2019 International Conference on Robotics and Automation, ICRA (2019)","DOI":"10.1109\/ICRA.2019.8794334"},{"key":"37_CR16","unstructured":"Couprie, C.: Indoor semantic segmentation using depth information. In: First International Conference on Learning Representations (ICLR), pp. 1\u20138 (2013)"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Ding, H., Qiao, S., Yuille, A.L., Shen, W.: Deeply shape-guided cascade for instance segmentation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00818"},{"key":"37_CR18","unstructured":"Drenkow, N., Sani, N., Shpitser, I., Unberath, M.: Robustness in deep learning for computer vision: mind the gap? arxiv:2112.00639 (2021)"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Fontanelli, G.A., Ficuciello, F., Villani, L., Siciliano, B.: Modelling and identification of the da Vinci research kit robotic arms. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1464-1469 (2017)","DOI":"10.1109\/IROS.2017.8205948"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O.M., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Guo, X., Yang, K., Yang, W., Wang, X., Li, H.: Group-wise correlation stereo network. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR (2019)","DOI":"10.1109\/CVPR.2019.00339"},{"key":"37_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-319-54181-5_14","volume-title":"Computer Vision \u2013 ACCV 2016","author":"C Hazirbas","year":"2017","unstructured":"Hazirbas, C., Ma, L., Domokos, C., Cremers, D.: FuseNet: Incorporating depth into semantic segmentation via fusion-based CNN architecture. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10111, pp. 213\u2013228. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54181-5_14"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980-2988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Islam, M.: Real-time instrument segmentation in robotic surgery using auxiliary supervised deep adversarial learning. In: IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 2188-2195 (2019)","DOI":"10.1109\/LRA.2019.2900854"},{"key":"37_CR25","doi-asserted-by":"crossref","unstructured":"Jin, Y., Cheng, K., Dou, Q., Heng, P.: Incorporating temporal prior from motion flow for instrument segmentation in minimally invasive surgery video. In: Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019, 22nd International Conference, pp.440-448 (2019)","DOI":"10.1007\/978-3-030-32254-0_49"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Kato, H., Ushiku, Y., Harada, T.: Neural 3D mesh renderer. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR (2018)","DOI":"10.1109\/CVPR.2018.00411"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Kazanzides, P., Chen, Z., Deguet, A., Fischer, G.S., Taylor, R.H., DiMaio, S.P.: An open-source research kit for the da Vinci surgical system. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 6434-6439 (2014)","DOI":"10.1109\/ICRA.2014.6907809"},{"key":"37_CR28","doi-asserted-by":"publisher","unstructured":"Lecca, P.: Machine learning for causal inference in biological networks: perspectives of this challenge. Front. Bioinform. 1 (2021). https:\/\/doi.org\/10.3389\/fbinf.2021.746712","DOI":"10.3389\/fbinf.2021.746712"},{"key":"37_CR29","unstructured":"Li, Z.: Temporally consistent online depth estimation in dynamic scenes (2021). https:\/\/arxiv.org\/abs\/2111.09337"},{"key":"37_CR30","unstructured":"Liu, C.: Learning causal semantic representation for out-of-distribution prediction. In: Advances in Neural Information Processing Systems 34, NeurIPS (2021)"},{"key":"37_CR31","doi-asserted-by":"crossref","unstructured":"Liu, S., Chen, W., Li, T., Li, H.: Soft rasterizer: a differentiable renderer for image-based 3D reasoning. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7707-7716 (2019)","DOI":"10.1109\/ICCV.2019.00780"},{"key":"37_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision, ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"37_CR33","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"37_CR34","unstructured":"Mitrovic, J., McWilliams, B., Walker, J.C., Buesing, L.H., Blundell, C.: Representation learning via invariant causal mechanisms. In: International Conference on Learning Representations, ICLR (2021)"},{"key":"37_CR35","doi-asserted-by":"crossref","unstructured":"Munawar, A., Wang, Y., Gondokaryono, R., Fischer, G.S.: A real-time dynamic simulator and an associated front-end representation format for simulating complex robots and environments. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS (2019)","DOI":"10.1109\/IROS40897.2019.8968568"},{"key":"37_CR36","doi-asserted-by":"crossref","unstructured":"Pakhomov, D., Premachandran, V., Allan, M., Azizian, M., Navab, N.: Deep residual learning for instrument segmentation in robotic surgery. In: Machine Learning in Medical Imaging, MLMI (2019)","DOI":"10.1007\/978-3-030-32692-0_65"},{"key":"37_CR37","unstructured":"Pawlowski, N., de Castro, D.C., Glocker, B.: Deep structural causal models for tractable counterfactual inference. In: Advances in Neural Information Processing Systems, NIPS (2020)"},{"key":"37_CR38","doi-asserted-by":"crossref","unstructured":"Qin, F.: Surgical instrument segmentation for endoscopic vision with data fusion of CNN prediction and kinematic pose. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 9821-9827 (2019)","DOI":"10.1109\/ICRA.2019.8794122"},{"key":"37_CR39","doi-asserted-by":"crossref","unstructured":"Quionero-Candela, J., Sugiyama, M., Schwaighofer, A., Lawrence, N.D.: Dataset Shift in Machine Learning. The MIT Press (2009)","DOI":"10.7551\/mitpress\/9780262170055.001.0001"},{"key":"37_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1007\/978-3-030-87240-3_75","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"JC Reinhold","year":"2021","unstructured":"Reinhold, J.C., Carass, A., Prince, J.L.: A structural causal model for MR images of multiple sclerosis. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 782\u2013792. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_75"},{"key":"37_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"37_CR42","doi-asserted-by":"crossref","unstructured":"Shvets, A.A., Rakhlin, A., Kalinin, A.A., Iglovikov, V.I.: Automatic instrument segmentation in robot-assisted surgery using deep learning. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 624-628 (2018)","DOI":"10.1109\/ICMLA.2018.00100"},{"key":"37_CR43","doi-asserted-by":"crossref","unstructured":"Su, Y.H., Huang, K., Hannaford, B.: Real-time vision-based surgical tool segmentation with robot kinematics prior. In: 2018 International Symposium on Medical Robotics (ISMR), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/ISMR.2018.8333305"},{"key":"37_CR44","doi-asserted-by":"crossref","unstructured":"Wang, J., Lan, C., Liu, C., Ouyang, Y., Qin, T.: Generalizing to unseen domains: A survey on domain generalization. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI (2021)","DOI":"10.24963\/ijcai.2021\/628"},{"key":"37_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1007\/978-3-319-46720-7_45","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2016","author":"M Ye","year":"2016","unstructured":"Ye, M., Zhang, L., Giannarou, S., Yang, G.-Z.: Real-time 3D tracking of articulated tools for robotic surgery. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9900, pp. 386\u2013394. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46720-7_45"},{"key":"37_CR46","unstructured":"Zhang, C., Zhang, K., Li, Y.: A causal view on robustness of neural networks. In: Advances in Neural Information Processing Systems 33, NeurIPS (2020)"},{"key":"37_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, X., Cui, P., Xu, R., Zhou, L., He, Y., Shen, Z.: Deep stable learning for out-of-distribution generalization. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00533"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16449-1_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:56:56Z","timestamp":1709830616000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16449-1_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164484","9783031164491"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16449-1_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft Conference","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1831","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"574","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}