{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T17:16:17Z","timestamp":1786122977904,"version":"build-2736575974"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000272","name":"National Institute for Health and Care Research","doi-asserted-by":"publisher","award":["NIHR II-LA-1116-20005"],"award-info":[{"award-number":["NIHR II-LA-1116-20005"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["203145Z\/16\/Z"],"award-info":[{"award-number":["203145Z\/16\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["EP\/Z534754\/1"],"award-info":[{"award-number":["EP\/Z534754\/1"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T029404\/1"],"award-info":[{"award-number":["EP\/T029404\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"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>Registration between preoperative CT and intraoperative laparoscopic video plays a crucial role in augmented reality (AR) guidance for minimally invasive surgery. Learning-based methods have recently achieved registration errors comparable to optimization-based approaches while offering faster inference. However, many supervised methods produce coarse alignments that rely on additional optimization-based refinement, thereby increasing inference time.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We present a discrete-action reinforcement learning (RL) framework that formulates CT-to-video registration as a sequential decision-making process. A shared feature encoder, warm-started from a supervised pose estimation network to provide stable geometric features and faster convergence, extracts representations from CT renderings and laparoscopic frames, while an RL policy head learns to choose rigid transformations along six degrees of freedom and to decide when to stop the iteration.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experiments on a public laparoscopic dataset demonstrated that our method achieved an average target registration error (TRE) of 15.70 \u00b1 8.18 mm, comparable to supervised approaches with optimization, while achieving faster convergence.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed RL-based formulation enables automated, efficient iterative registration without manually tuned step sizes or stopping criteria. This discrete framework provides a practical foundation for future continuous-action and deformable registration models in surgical AR applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-026-03653-9","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T07:20:44Z","timestamp":1779261644000},"page":"1331-1339","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Warm-started reinforcement learning for iterative 3D\/2D liver registration"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1232-2608","authenticated-orcid":false,"given":"Hanyuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucas","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijie","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdolrahim","family":"Kadkhodamohammadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian R.","family":"Davidson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evangelos B.","family":"Mazomenos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew J.","family":"Clarkson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"key":"3653_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102943","volume":"90","author":"J Ramalhinho","year":"2023","unstructured":"Ramalhinho J, Yoo S, Dowrick T, Koo B, Somasundaram M, Gurusamy K, Hawkes DJ, Davidson B, Blandford A, Clarkson MJ (2023) The value of augmented reality in surgery\u2014a usability study on laparoscopic liver surgery. Med Image Anal 90:102943","journal-title":"Med Image Anal"},{"issue":"10","key":"3653_CR2","doi-asserted-by":"publisher","first-page":"4702","DOI":"10.1007\/s00464-020-07807-x","volume":"34","author":"C Schneider","year":"2020","unstructured":"Schneider C, Thompson S, Totz J, Song Y, Allam M, Sodergren M, Desjardins A, Barratt D, Ourselin S, Gurusamy K et al (2020) Comparison of manual and semi-automatic registration in augmented reality image-guided liver surgery: a clinical feasibility study. Surg Endosc 34(10):4702\u20134711","journal-title":"Surg Endosc"},{"key":"3653_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103371","volume":"99","author":"S Ali","year":"2025","unstructured":"Ali S, Espinel Y, Jin Y, Liu P, G\u00fcttner B, Zhang X, Zhang L, Dowrick T, Clarkson MJ, Xiao S et al (2025) An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion from the miccai2022 challenge. Med Image Anal 99:103371","journal-title":"Med Image Anal"},{"issue":"8","key":"3653_CR4","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1007\/s11548-015-1309-8","volume":"11","author":"M Fusaglia","year":"2016","unstructured":"Fusaglia M, Hess H, Schwalbe M, Peterhans M, Tinguely P, Weber S, Lu H (2016) A clinically applicable laser-based image-guided system for laparoscopic liver procedures. Int J Comput Assist Radiol Surg 11(8):1499\u20131513","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3653_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101946","volume":"69","author":"E Pelanis","year":"2021","unstructured":"Pelanis E, Teatini A, Eigl B, Regensburger A, Alzaga A, Kumar RP, Rudolph T, Aghayan DL, Riediger C, Kvarnstr\u00f6m N et al (2021) Evaluation of a novel navigation platform for laparoscopic liver surgery with organ deformation compensation using injected fiducials. Med Image Anal 69:101946","journal-title":"Med Image Anal"},{"issue":"6","key":"3653_CR6","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1007\/s11548-018-1781-z","volume":"13","author":"MR Robu","year":"2018","unstructured":"Robu MR, Ramalhinho J, Thompson S, Gurusamy K, Davidson B, Hawkes D, Stoyanov D, Clarkson MJ (2018) Global rigid registration of CT to video in laparoscopic liver surgery. Int J Comput Assist Radiol Surg 13(6):947\u2013956","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3653_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.105099","volume":"187","author":"H Luo","year":"2020","unstructured":"Luo H, Yin D, Zhang S, Xiao D, He B, Meng F, Zhang Y, Cai W, He S, Zhang W et al (2020) Augmented reality navigation for liver resection with a stereoscopic laparoscope. Comput Methods Programs Biomed 187:105099","journal-title":"Comput Methods Programs Biomed"},{"issue":"2","key":"3653_CR8","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1109\/TMI.2024.3457228","volume":"44","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Zou Y, Liu PX (2024) Point cloud registration in laparoscopic liver surgery using keypoint correspondence registration network. IEEE Trans Med Imaging 44(2):749\u2013760","journal-title":"IEEE Trans Med Imaging"},{"issue":"6","key":"3653_CR9","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1007\/s11548-023-02893-3","volume":"18","author":"Z Yang","year":"2023","unstructured":"Yang Z, Simon R, Linte CA (2023) Learning feature descriptors for pre-and intra-operative point cloud matching for laparoscopic liver registration. Int J Comput Assist Radiol Surg 18(6):1025\u20131032","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"1","key":"3653_CR10","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s11548-021-02518-7","volume":"17","author":"B Koo","year":"2022","unstructured":"Koo B, Robu MR, Allam M, Pfeiffer M, Thompson S, Gurusamy K, Davidson B, Speidel S, Hawkes D, Stoyanov D et al (2022) Automatic, global registration in laparoscopic liver surgery. Int J Comput Assist Radiol Surg 17(1):167\u2013176","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3653_CR11","doi-asserted-by":"crossref","unstructured":"Monta\u00f1a-Brown N, Ramalhinho J, Koo B, Allam M, Davidson B, Gurusamy K, Hu Y, Clarkson MJ (2022) Towards multi-modal self-supervised video and ultrasound pose estimation for laparoscopic liver surgery. In: International workshop on advances in simplifying medical ultrasound, Springer, pp 183\u2013192","DOI":"10.1007\/978-3-031-16902-1_18"},{"issue":"7","key":"3653_CR12","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1007\/s11548-025-03418-w","volume":"20","author":"H Zhang","year":"2025","unstructured":"Zhang H, Bulathsinhala S, Davidson BR, Clarkson MJ, Ramalhinho J (2025) Deep hashing for global registration of preoperative CT and video images for laparoscopic liver surgery. Int J Comput Assist Radiol Surg 20(7):1461\u20131469","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"4","key":"3653_CR13","doi-asserted-by":"publisher","first-page":"70124","DOI":"10.1002\/ima.70124","volume":"35","author":"J Hao","year":"2025","unstructured":"Hao J, He B, Dai Y, Li Y, Wang Y, Zhao R, Lian R, Zeng X, Tao H, Yang J et al (2025) A 3d\u20132d rigid liver registration method using pre-training and transfer learning with staged alignment of anatomical landmarks. Int J Imaging Syst Technol 35(4):70124","journal-title":"Int J Imaging Syst Technol"},{"key":"3653_CR14","doi-asserted-by":"crossref","unstructured":"Gadoux E, Bartoli A (2025) Automatic deep deformable registration using domain adaptation and run-time optimisation. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 65\u201374","DOI":"10.1007\/978-3-032-05114-1_7"},{"key":"3653_CR15","unstructured":"Labrunie M, Pizarro D, Tilmant C, Bartoli A (2023) Automatic 3d\/2d deformable registration in minimally invasive liver resection using a mesh recovery network. In: MIDL, pp 1104\u20131123"},{"issue":"8","key":"3653_CR16","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1007\/s11548-022-02641-z","volume":"17","author":"M Labrunie","year":"2022","unstructured":"Labrunie M, Ribeiro M, Mourthadhoi F, Tilmant C, Le Roy B, Buc E, Bartoli A (2022) Automatic preoperative 3d model registration in laparoscopic liver resection. Int J Comput Assist Radiol Surg 17(8):1429\u20131436","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3653_CR17","doi-asserted-by":"publisher","unstructured":"Zhang H, He L, He R, Kadkhodamohammadi A, Stoyanov D, Davidson BR, Mazomenos EB, Clarkson MJ (2026) Foundationpose-initialized 3d\u20132d liver registration for surgical augmented reality. https:\/\/doi.org\/10.48550\/arXiv.2602.17517","DOI":"10.48550\/arXiv.2602.17517"},{"issue":"5","key":"3653_CR18","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1007\/s12555-025-0193-4","volume":"23","author":"J Seo","year":"2025","unstructured":"Seo J, Yoo S, Chang J, An H, Ryu H, Lee S, Kruthiventy A, Choi J, Horowitz R (2025) Se (3)-equivariant robot learning and control: a tutorial survey. Int J Control Autom Syst 23(5):1271\u20131306","journal-title":"Int J Control Autom Syst"},{"key":"3653_CR19","doi-asserted-by":"crossref","unstructured":"Barfoot TD (2017) Matrix lie groups. State estimation for robotics. Cambridge University Press, Cambridge, pp 205\u2013284","DOI":"10.1017\/9781316671528.008"},{"issue":"4","key":"3653_CR20","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1080\/21681163.2021.1997642","volume":"10","author":"N Rabbani","year":"2022","unstructured":"Rabbani N, Calvet L, Espinel Y, Le Roy B, Ribeiro M, Buc E, Bartoli A (2022) A methodology and clinical dataset with ground-truth to evaluate registration accuracy quantitatively in computer-assisted laparoscopic liver resection. Comput Methods Biomech Biomed Eng Imaging Vis 10(4):441\u2013450","journal-title":"Comput Methods Biomech Biomed Eng Imaging Vis"},{"issue":"1","key":"3653_CR21","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s11548-024-03231-x","volume":"20","author":"I Mhiri","year":"2025","unstructured":"Mhiri I, Pizarro D, Bartoli A (2025) Neural patient-specific 3d\u20132d registration in laparoscopic liver resection. Int J Comput Assist Radiol Surg 20(1):57\u201364","journal-title":"Int J Comput Assist Radiol Surg"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03653-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-026-03653-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03653-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T13:20:01Z","timestamp":1786108801000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-026-03653-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":21,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["3653"],"URL":"https:\/\/doi.org\/10.1007\/s11548-026-03653-9","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]},"assertion":[{"value":"23 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}