{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T09:58:47Z","timestamp":1763373527591,"version":"3.45.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Registering a preoperative 3D model of an organ with its actual anatomy viewed from an intraoperative video is a fundamental challenge in computer-assisted surgery, especially for surgical augmented reality. To address this, we present a benchmark of state-of-the-art deep learning point-cloud registration methods, offering a transparent evaluation of their generalizability to surgical scenarios and establishing a robust guideline for developing advanced non-rigid algorithms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We systematically evaluate traditional and deep learning GMM-based, correspondence-based, correspondence-free, matching-based, and liver-specific point cloud registration approaches on two surgical datasets: a deformed IRCAD liver set and DePoll dataset. We also propose our complete-to-partial point cloud registration framework that leverages keypoint extraction, overlap estimation, and a Transformer-based architecture, culminating in competitive registration results.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experimental evaluations on deformed IRCAD tests reveal that most deep learning methods achieve good registration performances with TRE&amp;lt;10 mm, MAE(R) &amp;lt; 4 and MAE(t)&amp;lt;5 mm. On DePoll, however, performance drops dramatically due to the large deformations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>In conclusion, deep-learning rigid registration methods remain reliable under small deformations and varying partiality but lose accuracy when faced with severe non-rigid changes. To overcome this, future work should focus on building non-rigid registration architectures that preserve the strengths of self-, cross-attention and overlap modules while enhancing correspondence estimation to handle large deformations in laparoscopic surgery.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frobt.2025.1702360","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T09:56:24Z","timestamp":1763373384000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking complete-to-partial point cloud registration techniques for laparoscopic surgery"],"prefix":"10.3389","volume":"12","author":[{"given":"Alberto","family":"Neri","sequence":"first","affiliation":[]},{"given":"Veronica","family":"Penza","sequence":"additional","affiliation":[]},{"given":"Nazim","family":"Haouchine","sequence":"additional","affiliation":[]},{"given":"Leonardo S.","family":"Mattos","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"B1","first-page":"1","article-title":"Optimal step nonrigid icp algorithms for surface registration","author":"Amberg","year":"2007"},{"key":"B2","doi-asserted-by":"publisher","first-page":"4251","DOI":"10.1118\/1.2969064","article-title":"Feasibility study for image-guided kidney surgery: assessment of required intraoperative surface for accurate physical to image space registrations","volume":"35","author":"Benincasa","year":"2008","journal-title":"Med. Phys."},{"key":"B3","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.media.2017.01.007","article-title":"The status of augmented reality in laparoscopic surgery as of 2016","volume":"37","author":"Bernhardt","year":"2017","journal-title":"Med. Image Anal."},{"key":"B4","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1117\/12.57955","article-title":"Method for registration of 3-d shapes","volume":"1611","author":"Besl","year":"1992","journal-title":"Sens. fusion IV control paradigms data Struct."},{"key":"B5","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s11548-024-03312-x","article-title":"Preoperative and intraoperative laparoscopic liver surface registration using deep graph matching of representative overlapping points","volume":"20","author":"Dai","year":"2025","journal-title":"Int. J. Comput. Assisted Radiology Surg."},{"key":"B6","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1177\/15533506241290412","article-title":"Augmented reality implementation in minimally invasive surgery for future application in pulmonary surgery: a systematic review","volume":"31","author":"Doornbos","year":"2024","journal-title":"Surg. Innov."},{"key":"B7","first-page":"1759","article-title":"Learning multiview 3d point cloud registration","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Gojcic","year":"2020"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1521","DOI":"10.1007\/s11548-023-02846-w","article-title":"Intraoperative laparoscopic liver surface registration with preoperative ct using mixing features and overlapping region masks","volume":"18","author":"Guan","year":"2023","journal-title":"Int. J. Comput. Assisted Radiology Surg."},{"key":"B9","article-title":"A comprehensive survey on point cloud registration","author":"Huang","year":"2021"},{"key":"B10","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnu-net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. methods"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1109\/tpami.2010.223","article-title":"Robust point set registration using gaussian mixture models","volume":"33","author":"Jian","year":"2011","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"B12","article-title":"Hepatomegaly","author":"Jones J","year":"2009"},{"key":"B13","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s11548-021-02518-7","article-title":"Automatic, global registration in laparoscopic liver surgery","volume":"17","author":"Koo","year":"2022","journal-title":"Int. J. Comput. Assisted Radiology Surg."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1007\/s11548-022-02641-z","article-title":"Automatic preoperative 3d model registration in laparoscopic liver resection","volume":"17","author":"Labrunie","year":"2022","journal-title":"Int. J. Comput. Assisted Radiology Surg."},{"key":"B15","first-page":"5554","article-title":"Lepard: learning partial point cloud matching in rigid and deformable scenes","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Li","year":"2022"},{"key":"B16","doi-asserted-by":"publisher","first-page":"105099","DOI":"10.1016\/j.cmpb.2019.105099","article-title":"Augmented reality navigation for liver resection with a stereoscopic laparoscope","volume":"187","author":"Luo","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"B17","first-page":"22","article-title":"Framework for augmented reality in minimally invasive laparoscopic surgery","author":"Marques","year":"2015"},{"key":"B18","first-page":"4511","article-title":"Overlap-guided gaussian mixture models for point cloud registration","volume-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","author":"Mei","year":"2023"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1007\/s11548-019-02001-4","article-title":"An in vivo porcine dataset and evaluation methodology to measure soft-body laparoscopic liver registration accuracy with an extended algorithm that handles collisions","volume":"14","author":"Modrzejewski","year":"2019","journal-title":"Int. J. Comput. Assisted Radiology Surg."},{"key":"B20","doi-asserted-by":"publisher","first-page":"2262","DOI":"10.1109\/tpami.2010.46","article-title":"Point set registration: coherent point drift","volume":"32","author":"Myronenko","year":"2010","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"B21","doi-asserted-by":"publisher","first-page":"102616","DOI":"10.1016\/j.compmedimag.2025.102616","article-title":"Surgical augmented reality registration methods: a review from traditional to deep learning approaches","volume":"124","author":"Neri","year":"","journal-title":"Comput. Med. Imaging Graph."},{"key":"B22","first-page":"638","article-title":"Towards patient-specific deformable registration in laparoscopic surgery","volume-title":"International conference on medical image computing and computer-assisted intervention","author":"Neri","year":""},{"key":"B23","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1002\/jso.27790","article-title":"More than meets the eye: augmented reality in surgical oncology","volume":"130","author":"Prasad","year":"2024","journal-title":"J. Surg. Oncol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"2609","DOI":"10.1109\/tbme.2014.2323999","article-title":"Toward long-term and accurate augmented-reality for monocular endoscopic videos","volume":"61","author":"Puerto-Souza","year":"2014","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B25","doi-asserted-by":"publisher","first-page":"9806","DOI":"10.1109\/tpami.2023.3259038","article-title":"Geotransformer: fast and robust point cloud registration with geometric transformer","volume":"45","author":"Qin","year":"2023","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"B26","unstructured":"3d image reconstruction for comparison of algorithm database\n          \n          \n            \n              Soler\n              L.\n            \n            \n              Hostettler\n              A.\n            \n            \n              Agnus\n              V.\n            \n            \n              Charnoz\n              A.\n            \n            \n              Fasquel\n              J.-B.\n            \n            \n              Moreau\n              J.\n            \n          \n          \n          2010"},{"key":"B27","doi-asserted-by":"publisher","first-page":"109","DOI":"10.2312\/SGP\/SGP07\/109-116","article-title":"As-rigid-as-possible surface modeling","volume":"4","author":"Sorkine","year":"2007","journal-title":"Symposium Geometry Process."},{"key":"B28","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1109\/34.88573","article-title":"Least-squares estimation of transformation parameters between two point patterns","volume":"13","author":"Umeyama","year":"1991","journal-title":"IEEE Trans. Pattern Analysis and Mach. Intell."},{"key":"B29","first-page":"1912","article-title":"3d shapenets: a deep representation for volumetric shapes","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Wu","year":"2015"},{"key":"B30","first-page":"3132","article-title":"Omnet: learning overlapping mask for partial-to-partial point cloud registration","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Xu","year":"2021"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1007\/s11548-023-02893-3","article-title":"Learning feature descriptors for pre-and intra-operative point cloud matching for laparoscopic liver registration","volume":"18","author":"Yang","year":"2023","journal-title":"Int. J. Comput. Assisted Radiology Surg."},{"key":"B32","first-page":"11824","article-title":"Rpm-net: robust point matching using learned features","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Yew","year":"2020"},{"key":"B33","first-page":"6677","article-title":"Regtr: end-to-end point cloud correspondences with transformers","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Yew","year":"2022"},{"key":"B34","first-page":"13","article-title":"Endosurf: neural surface reconstruction of deformable tissues with stereo endoscope videos","volume-title":"International conference on medical image computing and computer-assisted intervention","author":"Zha","year":"2023"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1109\/tbme.2022.3217481","article-title":"Autostereoscopic 3d augmented reality navigation for laparoscopic surgery: a preliminary assessment","volume":"70","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B36","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1109\/tmi.2024.3457228","article-title":"Point cloud registration in laparoscopic liver surgery using keypoint correspondence registration network","volume":"44","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1702360\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T09:56:27Z","timestamp":1763373387000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1702360\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":36,"alternative-id":["10.3389\/frobt.2025.1702360"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2025.1702360","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,17]]},"article-number":"1702360"}}