{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T01:59:41Z","timestamp":1779328781034,"version":"3.51.4"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>\n                      Preserving neurovascular bundles (NVB) during robot-assisted radical prostatectomy (RARP) is vital for reducing postoperative complications such as urinary incontinence and erectile dysfunction. Building on our previous work in ensemble-based NVB classification, we propose the\n                      <jats:italic>hybrid self-supervised teacher\u2013student model<\/jats:italic>\n                      (Hybrid T\u2013S model) that leverages\n                      <jats:italic>multi-task learning<\/jats:italic>\n                      to predict NVB preservation in prostatectomy videos.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Our approach integrates a\n                      <jats:italic>self-supervised framework (DINO)<\/jats:italic>\n                      as an online self-distillation objective on multi-crop views to learn robust embeddings in a limited data setting, rather than as a stand-alone large-scale pretraining. A\n                      <jats:italic>teacher encoder<\/jats:italic>\n                      , which is an exponential moving average (EMA) of the\n                      <jats:italic>student encoder<\/jats:italic>\n                      , and a\n                      <jats:italic>reconstruction decoder<\/jats:italic>\n                      are trained jointly with a\n                      <jats:italic>classification head<\/jats:italic>\n                      in a single end-to-end framework. This model is evaluated on single frames from patients who underwent RARP surgery.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our experimental evaluation shows that the Hybrid T\u2013S model outperforms previous NVB classification methods. This highlights the benefits of integrating self-supervised learning and multi-task objectives in this surgical context. We achieved an average accuracy of 86.55%, precision of 83.93%, recall of 90.73%, F1-score of 87%, and AUROC of 88.35%, based on fivefold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      Incorporating representation learning through self-distillation, classification, and reconstruction provides complementary signals that enhance the prediction of NVB preservation. Our\n                      <jats:italic>Hybrid T\u2013S model<\/jats:italic>\n                      can assist surgeons in real decision-making and improve patient recovery.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-025-03544-5","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T08:57:49Z","timestamp":1770886669000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A hybrid self-supervised teacher\u2013student model for predicting neurovascular bundle preservation in prostatectomy videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8540-1818","authenticated-orcid":false,"given":"Diego Andr\u00e9s","family":"del Aguila Moraga","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huitao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Ando","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hayato","family":"Hoshina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Kawahira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukihiro","family":"Nomura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toshiya","family":"Nakaguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,12]]},"reference":[{"key":"3544_CR1","unstructured":"Ferlay J, Ervik M, Lam F, Colombet M, Mery L, Pi\u00f1eros M, Znaor A, Soerjomataram I, Bray F (2020) Global cancer observatory: cancer today. lyon: international agency for research. https:\/\/gco.iarc.fr\/today. Accessed February 2021. Accessed 18 Mar 2025"},{"key":"3544_CR2","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1111\/iju.15388","volume":"31","author":"S Ando","year":"2024","unstructured":"Ando S, Sugihara T, Hinotsu S, Kishino H, Hirata D, Watanabe R, Yanase A, Yokoyama H, Hoshina H, Endo K, Kamei J, Takaoka E, Fujimura T (2024) Early recovery of urinary continence after robot-assisted radical prostatectomy is associated with membranous urethra and neurovascular bundle preservation. Int J Urol 31:492\u2013499. https:\/\/doi.org\/10.1111\/iju.15388","journal-title":"Int J Urol"},{"key":"3544_CR3","unstructured":"del Aguila Moraga DA, Wang H, Ando S, Hoshina H, Kawahira H, Nomura Y, Nakaguchi T (2024) Computer-aided classification of robot-assisted radical prostatectomy (RARP) images on neurovascular bundle (NVB) preservation. In: 43rd\u202fannual meeting of the Japanese Association for medical imaging technology (JAMIT 2024)"},{"key":"3544_CR4","doi-asserted-by":"publisher","DOI":"10.1002\/cnr2.1861","author":"W Nakamura","year":"2023","unstructured":"Nakamura W, Sumitomo M, Zennami K, Takenaka M, Ichino M, Takahara K, Teramoto A, Shiroki R (2023) Combination of deep learning and ensemble machine learning using intraoperative video images strongly predicts recovery of urinary continence after robot-assisted radical prostatectomy. Cancer Rep. https:\/\/doi.org\/10.1002\/cnr2.1861","journal-title":"Cancer Rep"},{"key":"3544_CR5","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1007\/s11548-021-02432-y","volume":"16","author":"L Tanzi","year":"2021","unstructured":"Tanzi L, Piazzolla P, Porpiglia F, Vezzetti E (2021) Real-time deep learning semantic segmentation during intra-operative surgery for 3D augmented reality assistance. Int J Comput Assist Radiol Surg 16:1435\u20131445. https:\/\/doi.org\/10.1007\/s11548-021-02432-y","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3544_CR6","doi-asserted-by":"crossref","unstructured":"Caron M, Touvron H, Misra I, J\u00e9gou H, Mairal J, Bojanowski P, Joulin A (2021) Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9650\u20139660","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"3544_CR7","doi-asserted-by":"crossref","unstructured":"Dellis S, Ricci E, Gerakinis D-P, Vergadou N, Giannakopoulos G (2024) Self-adaptive optimization of coefficients in multi-objective loss functions. In: Proceedings of the 13th Hellenic conference on artificial intelligence. Association for Computing Machinery, New York, NY, USA","DOI":"10.1145\/3688671.3688742"},{"key":"3544_CR8","unstructured":"Standley T, Zamir AR, Chen D, Guibas L, Malik J, Savarese S (2019) Which tasks should be learned together in multi-task learning? In: International conference on machine learning, pp 9120\u20139132"},{"key":"3544_CR9","doi-asserted-by":"publisher","first-page":"551","DOI":"10.4111\/icu.20240159","volume":"65","author":"S Pak","year":"2024","unstructured":"Pak S, Park SG, Park J, Choi HR, Lee JH, Lee W, Cho ST, Lee YG, Ahn H (2024) Application of deep learning for semantic segmentation in robotic prostatectomy: comparison of convolutional neural networks and visual transformers. Investig Clin Urol 65:551\u2013558. https:\/\/doi.org\/10.4111\/icu.20240159","journal-title":"Investig Clin Urol"},{"key":"3544_CR10","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1111\/bju.14735","volume":"124","author":"AJ Hung","year":"2019","unstructured":"Hung AJ, Chen J, Ghodoussipour S, Oh PJ, Liu Z, Nguyen J, Purushotham S, Gill IS, Liu Y (2019) A deep-learning model using automated performance metrics and clinical features to predict urinary continence recovery after robot-assisted radical prostatectomy. BJU Int 124:487\u2013495. https:\/\/doi.org\/10.1111\/bju.14735","journal-title":"BJU Int"},{"key":"3544_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106496","author":"Y Zhao","year":"2023","unstructured":"Zhao Y, Wang X, Che T, Bao G, Li S (2023) Multi-task deep learning for medical image computing and analysis: a review. Comput Biol Med. https:\/\/doi.org\/10.1016\/j.compbiomed.2022.106496","journal-title":"Comput Biol Med"},{"key":"3544_CR12","doi-asserted-by":"crossref","unstructured":"Zia A, Hung A, Essa I, Jarc A (2018) Surgical activity recognition in robot-assisted radical prostatectomy using deep learning. In: Medical image computing and computer assisted intervention\u2014MICCAI 2018. Springer, pp 273\u2013280","DOI":"10.1007\/978-3-030-00937-3_32"},{"key":"3544_CR13","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE Computer Society, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3544_CR14","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u2014MICCAI 2015. Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3544_CR15","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1561\/2200000056","volume":"12","author":"DP Kingma","year":"2019","unstructured":"Kingma DP, Welling M et al (2019) An introduction to variational autoencoders. Found Trends Mach Learn 12:307\u2013392","journal-title":"Found Trends Mach Learn"},{"key":"3544_CR16","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","volume":"9","author":"M-H Guo","year":"2023","unstructured":"Guo M-H, Lu C-Z, Liu Z-N, Cheng M-M, Hu S-M (2023) Visual attention network. Comput Vis Media 9:733\u2013752","journal-title":"Comput Vis Media"},{"key":"3544_CR17","doi-asserted-by":"publisher","first-page":"6486","DOI":"10.1109\/TPAMI.2024.3382294","volume":"46","author":"P Zhou","year":"2024","unstructured":"Zhou P, Xie X, Lin Z, Yan S (2024) Towards understanding convergence and generalization of AdamW. IEEE Trans Pattern Anal Mach Intell 46:6486\u20136493. https:\/\/doi.org\/10.1109\/TPAMI.2024.3382294","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3544_CR18","first-page":"2387","volume":"11","author":"MD Reid","year":"2010","unstructured":"Reid MD, Williamson RC (2010) Composite binary losses. J Mach Learn Res 11:2387\u20132422","journal-title":"J Mach Learn Res"},{"key":"3544_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"3544_CR20","doi-asserted-by":"crossref","unstructured":"Wang Z, Liu C, Zhang S, Dou Q (2023) Foundation model for endoscopy video analysis via large-scale self-supervised pre-train. In: International conference on medical image computing and computer-assisted intervention, pp 101\u2013111","DOI":"10.1007\/978-3-031-43996-4_10"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03544-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-025-03544-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03544-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T08:57:53Z","timestamp":1770886673000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-025-03544-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,12]]},"references-count":20,"alternative-id":["3544"],"URL":"https:\/\/doi.org\/10.1007\/s11548-025-03544-5","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,12]]},"assertion":[{"value":"9 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All procedures involving human participants followed the ethical standards of relevant research committees. Ethical approval for this study was granted by Jichi Medical University Hospital's Ethics Review Committee (approval no. 23-155).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"It was waived by the ethics review committee due to the retrospective and anonymized nature of the dataset","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}