{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:28:00Z","timestamp":1742912880972,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819981441"},{"type":"electronic","value":"9789819981458"}],"license":[{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8145-8_32","type":"book-chapter","created":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T23:02:21Z","timestamp":1701039741000},"page":"413-426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid U-Net: Instrument Semantic Segmentation in\u00a0RMIS"],"prefix":"10.1007","author":[{"given":"Yue","family":"Wang","sequence":"first","affiliation":[]},{"given":"Huajian","family":"Song","sequence":"additional","affiliation":[]},{"given":"Guangyuan","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Qingguo","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Zhiyuan","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Ancai","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jianlong","family":"Qiu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,27]]},"reference":[{"key":"32_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/978-3-319-24553-9_41","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"M Allan","year":"2015","unstructured":"Allan, M., et al.: Image based surgical instrument pose estimation with multi-class labelling and optical flow. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 331\u2013338. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24553-9_41"},{"key":"32_CR2","unstructured":"Allan, M., et al.: 2017 robotic instrument segmentation challenge. arXiv preprint arXiv:1902.06426 (2019)"},{"issue":"12","key":"32_CR3","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR4","unstructured":"Chen, L.C., et al.: Searching for efficient multi-scale architectures for dense image prediction. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"32_CR5","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":"32_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"32_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3\u201311 (2018)","journal-title":"Neural Netw."},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Unet 3+: a full-scale connected unet for medical image segmentation. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1055\u20131059. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"key":"32_CR9","unstructured":"Iglovikov, V., Shvets, A.: Ternausnet: U-net with vgg11 encoder pre-trained on imagenet for image segmentation. arXiv e-prints, arXiv-1801 (2018)"},{"key":"32_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101837","volume":"67","author":"M Islam","year":"2021","unstructured":"Islam, M., Vibashan, V., Lim, C.M., Ren, H.: St-mtl: spatio-temporal multitask learning model to predict scanpath while tracking instruments in robotic surgery. Med. Image Anal. 67, 101837 (2021)","journal-title":"Med. Image Anal."},{"key":"32_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1007\/978-3-030-67835-7_19","volume-title":"MultiMedia Modeling","author":"D Jha","year":"2021","unstructured":"Jha, D., et al.: Kvasir-instrument: diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy. In: Loko\u010d, J., et al. (eds.) MMM 2021. LNCS, vol. 12573, pp. 218\u2013229. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67835-7_19"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Jha, D., Riegler, M.A., Johansen, D., Halvorsen, P., Johansen, H.D.: Doubleu-net: a deep convolutional neural network for medical image segmentation. In: 2020 IEEE 33rd International symposium on computer-based medical systems (CBMS), pp. 558\u2013564. IEEE (2020)","DOI":"10.1109\/CBMS49503.2020.00111"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Jha, D., et al.: Resunet++: an advanced architecture for medical image segmentation. In: 2019 IEEE International Symposium on Multimedia (ISM), pp. 225\u20132255. IEEE (2019)","DOI":"10.1109\/ISM46123.2019.00049"},{"key":"32_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/978-3-030-32254-0_49","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"Y Jin","year":"2019","unstructured":"Jin, Y., Cheng, K., Dou, Q., Heng, P.-A.: Incorporating temporal prior from motion flow for instrument segmentation in minimally invasive surgery video. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11768, pp. 440\u2013448. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32254-0_49"},{"key":"32_CR15","doi-asserted-by":"publisher","first-page":"178486","DOI":"10.1109\/ACCESS.2019.2958384","volume":"7","author":"X Liu","year":"2019","unstructured":"Liu, X., et al.: Msdf-net: multi-scale deep fusion network for stroke lesion segmentation. IEEE Access 7, 178486\u2013178495 (2019)","journal-title":"IEEE Access"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer v2: Scaling up capacity and resolution. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"32_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117420","volume":"202","author":"T Mahmood","year":"2022","unstructured":"Mahmood, T., Cho, S.W., Park, K.R.: Dsrd-net: dual-stream residual dense network for semantic segmentation of instruments in robot-assisted surgery. Expert Syst. Appl. 202, 117420 (2022)","journal-title":"Expert Syst. Appl."},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Mohammed, A., Yildirim, S., Farup, I., Pedersen, M., Hovde, \u00d8.: Streoscennet: surgical stereo robotic scene segmentation. In: Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling, vol. 10951, pp. 174\u2013182. SPIE (2019)","DOI":"10.1117\/12.2512518"},{"issue":"5","key":"32_CR20","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1007\/s11263-021-01445-z","volume":"129","author":"R Mohan","year":"2021","unstructured":"Mohan, R., Valada, A.: Efficientps: efficient panoptic segmentation. Int. J. Comput. Vision 129(5), 1551\u20131579 (2021)","journal-title":"Int. J. Comput. Vision"},{"issue":"4","key":"32_CR21","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1002\/rcs.408","volume":"7","author":"GP Moustris","year":"2011","unstructured":"Moustris, G.P., Hiridis, S.C., Deliparaschos, K.M., Konstantinidis, K.M.: Evolution of autonomous and semi-autonomous robotic surgical systems: a review of the literature. Inter. J. Med. Robotics Comput. Assisted Surg. 7(4), 375\u2013392 (2011)","journal-title":"Inter. J. Med. Robotics Comput. Assisted Surg."},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Ni, Z.L., et al.: Pyramid attention aggregation network for semantic segmentation of surgical instruments. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11782\u201311790 (2020)","DOI":"10.1609\/aaai.v34i07.6850"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Ni, Z.L., et al.: Barnet: bilinear attention network with adaptive receptive fields for surgical instrument segmentation. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 832\u2013838 (2021)","DOI":"10.24963\/ijcai.2020\/116"},{"key":"32_CR24","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":"32_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"32_CR26","unstructured":"Tan, M., Le, Q.: Efficientnetv2: smaller models and faster training. In: International Conference on Machine Learning, pp. 10096\u201310106. PMLR (2021)"},{"key":"32_CR27","unstructured":"Watanabe, T., Tanioka, K., Hiwa, S., Hiroyasu, T.: Performance comparison of deep learning architectures for artifact removal in gastrointestinal endoscopic imaging. arXiv e-prints. arXiv-2201 (2021)"},{"key":"32_CR28","doi-asserted-by":"publisher","unstructured":"Wightman, R.: Pytorch image models. https:\/\/github.com\/rwightman\/pytorch-image-models (2019). https:\/\/doi.org\/10.5281\/zenodo.4414861","DOI":"10.5281\/zenodo.4414861"},{"key":"32_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"issue":"2","key":"32_CR30","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s10278-019-00277-1","volume":"33","author":"L Yu","year":"2020","unstructured":"Yu, L., Wang, P., Yu, X., Yan, Y., Xia, Y.: A holistically-nested u-net: Surgical instrument segmentation based on convolutional neural network. J. Digit. Imaging 33(2), 341\u2013347 (2020)","journal-title":"J. Digit. Imaging"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8145-8_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T18:58:53Z","timestamp":1710356333000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8145-8_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,27]]},"ISBN":["9789819981441","9789819981458"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8145-8_32","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023,11,27]]},"assertion":[{"value":"27 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","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":"650","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":"51% - 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":"4.14","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":"2.46","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)"}}]}}