{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:07:39Z","timestamp":1759334859528,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031977800"},{"type":"electronic","value":"9783031977817"}],"license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":[[2026]]},"DOI":"10.1007\/978-3-031-97781-7_18","type":"book-chapter","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T22:19:25Z","timestamp":1759270765000},"page":"261-271","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating Deep Learning Architectures for\u00a0Real-Time Binary Surgical Tool Segmentation in\u00a0Minimally Invasive Surgeries"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0104-7586","authenticated-orcid":false,"given":"Stefano","family":"Mazzocchetti","sequence":"first","affiliation":[]},{"given":"Laura","family":"Cercenelli","sequence":"additional","affiliation":[]},{"given":"Emanuela","family":"Marcelli","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"unstructured":"Allan, M., et\u00a0al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)","key":"18_CR1"},{"issue":"5","key":"18_CR2","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1109\/TMI.2018.2794439","volume":"37","author":"M Allan","year":"2018","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)","journal-title":"IEEE Trans. Med. Imaging"},{"unstructured":"Allan, M., et\u00a0al.: 2017 robotic instrument segmentation challenge. arXiv preprint arXiv:1902.06426 (2019)","key":"18_CR3"},{"unstructured":"Bodenstedt, S., et\u00a0al.: Comparative evaluation of instrument segmentation and tracking methods in minimally invasive surgery. arXiv preprint arXiv:1805.02475 (2018)","key":"18_CR4"},{"issue":"1","key":"18_CR5","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1038\/s41597-020-00622-y","volume":"7","author":"H Borgli","year":"2020","unstructured":"Borgli, H., et al.: Hyperkvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Sci. Data 7(1), 283 (2020)","journal-title":"Sci. Data"},{"doi-asserted-by":"crossref","unstructured":"Cai, H., Li, J., Hu, M., Gan, C., Han, S.: Efficientvit: multi-scale linear attention for high-resolution dense prediction. arXiv preprint arXiv:2205.14756 (2022)","key":"18_CR6","DOI":"10.1109\/ICCV51070.2023.01587"},{"issue":"7328","key":"18_CR7","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1136\/bmj.324.7328.31","volume":"324","author":"A Darzi","year":"2002","unstructured":"Darzi, A., Mackay, S.: Recent advances in minimal access surgery. BMJ 324(7328), 31\u201334 (2002)","journal-title":"BMJ"},{"doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. pp. 248\u2013255. Ieee (2009)","key":"18_CR8","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"18_CR9","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2\u20133","key":"18_CR10","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1049\/htl2.12056","volume":"11","author":"J Hofman","year":"2024","unstructured":"Hofman, J., et al.: First-in-human real-time ai-assisted instrument deocclusion during augmented reality robotic surgery. Healthcare Technol. Lett. 11(2\u20133), 33\u201339 (2024)","journal-title":"Healthcare Technol. Lett."},{"unstructured":"Hong, W.Y., Kao, C.L., Kuo, Y.H., Wang, J.R., Chang, W.L., Shih, C.S.: Cholecseg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80. arXiv preprint arXiv:2012.12453 (2020)","key":"18_CR11"},{"doi-asserted-by":"crossref","unstructured":"Jadon, S.: A survey of loss functions for semantic segmentation. In: 2020 IEEE conference on computational intelligence in bioinformatics and computational biology (CIBCB), pp.\u00a01\u20137. IEEE (2020)","key":"18_CR12","DOI":"10.1109\/CIBCB48159.2020.9277638"},{"doi-asserted-by":"publisher","unstructured":"Jha, D., et al.: Kvasir-Instrument: Diagnostic and Therapeutic Tool Segmentation Dataset in Gastrointestinal Endoscopy. In: Loko\u010d, J., Skopal, T., Schoeffmann, K., Mezaris, V., Li, X., Vrochidis, S., Patras, I. (eds.) MMM 2021. LNCS, vol. 12573, pp. 218\u2013229. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67835-7_19","key":"18_CR13","DOI":"10.1007\/978-3-030-67835-7_19"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)","key":"18_CR14"},{"doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6399\u20136408 (2019)","key":"18_CR15","DOI":"10.1109\/CVPR.2019.00656"},{"doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","key":"18_CR16","DOI":"10.1109\/CVPR.2017.106"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","key":"18_CR17","DOI":"10.1109\/CVPR52688.2022.01167"},{"doi-asserted-by":"publisher","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":"18_CR18","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"18_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101920","volume":"70","author":"T Ro\u00df","year":"2021","unstructured":"Ro\u00df, T.: Comparative validation of multi-instance instrument segmentation in endoscopy: results of the robust-mis 2019 challenge. Med. Image Anal. 70, 101920 (2021)","journal-title":"Med. Image Anal."},{"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\u2013628. IEEE (2018)","key":"18_CR20","DOI":"10.1109\/ICMLA.2018.00100"},{"issue":"1","key":"18_CR21","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., De Mathelin, M., Padoy, N.: Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"18_CR22","doi-asserted-by":"publisher","first-page":"14042","DOI":"10.1038\/s41598-025-94568-z","volume":"15","author":"M Wei","year":"2025","unstructured":"Wei, M., Budd, C., Garcia-Peraza-Herrera, L.C., Dorent, R., Shi, M., Vercauteren, T.: Segmatch: semi-supervised surgical instrument segmentation. Sci. Rep. 15(1), 14042 (2025)","journal-title":"Sci. Rep."},{"doi-asserted-by":"crossref","unstructured":"Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I.S., Xie, S.: Convnext v2: Co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16133\u201316142 (2023)","key":"18_CR23","DOI":"10.1109\/CVPR52729.2023.01548"},{"issue":"4","key":"18_CR24","doi-asserted-by":"publisher","first-page":"6266","DOI":"10.1109\/LRA.2021.3092302","volume":"6","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., Rosa, B., Nageotte, F.: Surgical tool segmentation using generative adversarial networks with unpaired training data. IEEE Robotics Automation Lett. 6(4), 6266\u20136273 (2021)","journal-title":"IEEE Robotics Automation Lett."}],"container-title":["Lecture Notes in Computer Science","Extended Reality"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-97781-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T22:19:29Z","timestamp":1759270769000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97781-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"ISBN":["9783031977800","9783031977817"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97781-7_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"1 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"XR Salento","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Extended Reality","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Otranto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"avr2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.xrsalento.it","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}