{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T06:40:46Z","timestamp":1778740846705,"version":"3.51.4"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T00:00:00Z","timestamp":1772064000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>Robotic systems are transforming image-guided interventions by enhancing accuracy and minimizing radiation exposure. A significant challenge in robotic assistance lies in surgical path planning, which often relies on the registration of intraoperative 2D images with preoperative 3D CT scans. This requirement can be burdensome and costly, particularly in procedures like vertebroplasty, where preoperative CT scans are not routinely performed. To address this issue, we introduce a differentiable rendering-based framework for 3D transpedicular path planning utilizing bi-planar 2D X-rays. Our method integrates differentiable rendering with a vertebral atlas generated through a Statistical Shape Model (SSM) and employs a learned similarity loss to refine the SSM shape and pose dynamically, independent of fixed imaging geometries. We evaluated our framework in two stages: first, through vertebral reconstruction from orthogonal X-rays for benchmarking, and second, via clinician-in-the-loop path planning using arbitrary-view X-rays. Our results indicate that our method outperformed a normalized cross-correlation baseline in reconstruction metrics (DICE: 0.75 vs. 0.65) and achieved comparable performance to the state-of-the-art model ReVerteR (DICE: 0.77), while maintaining generalization to arbitrary views. Success rates for bipedicular planning reached 82% with synthetic data and 75% with cadaver data, exceeding the 66% and 31% rates of a 2D-to-3D baseline, respectively. In conclusion, our framework demonstrates the feasibility of versatile, CT-free 3D path planning for robot-assisted vertebroplasty, accommodating diverse intraoperative imaging conditions without requiring preoperative CT scans.<\/jats:p>","DOI":"10.3389\/frobt.2026.1759366","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:48:39Z","timestamp":1772095719000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["3D path planning for robot-assisted vertebroplasty from arbitrary Bi-plane X-ray via differentiable rendering"],"prefix":"10.3389","volume":"13","author":[{"given":"Blanca","family":"Inigo","sequence":"first","affiliation":[{"name":"Johns Hopkins Whiting School of Engineering","place":["Baltimore, MD, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin D.","family":"Killeen","sequence":"additional","affiliation":[{"name":"Johns Hopkins Whiting School of Engineering","place":["Baltimore, MD, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rebecca","family":"Choi","sequence":"additional","affiliation":[{"name":"Johns Hopkins School of Medicine","place":["Baltimore, MD, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michelle","family":"Song","sequence":"additional","affiliation":[{"name":"Johns Hopkins Whiting School of Engineering","place":["Baltimore, MD, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Uneri","sequence":"additional","affiliation":[{"name":"Johns Hopkins School of Medicine","place":["Baltimore, MD, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Majid","family":"Khan","sequence":"additional","affiliation":[{"name":"Johns Hopkins School of Medicine","place":["Baltimore, MD, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Bailey","sequence":"additional","affiliation":[{"name":"Johns Hopkins School of Medicine","place":["Baltimore, MD, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Axel","family":"Krieger","sequence":"additional","affiliation":[{"name":"Johns Hopkins Whiting School of Engineering","place":["Baltimore, MD, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathias","family":"Unberath","sequence":"additional","affiliation":[{"name":"Johns Hopkins Whiting School of Engineering","place":["Baltimore, MD, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,26]]},"reference":[{"key":"B1","first-page":"183","article-title":"Statistical shape models: understanding and mastering variation in anatomy","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2019","author":"Ambellan","year":"2019"},{"key":"B2","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/s00586-004-0822-1","article-title":"A new cannula to ease cement injection during vertebroplasty","volume":"14","author":"Baroud","year":"2005","journal-title":"Eur. Spine J."},{"key":"B3","first-page":"269","article-title":"Multi-view classification using hybrid fusion and mutual distillation","author":"Black","year":"2024"},{"key":"B4","doi-asserted-by":"publisher","first-page":"58","DOI":"10.3389\/fbioe.2014.00058","article-title":"Development and validation of a statistical shape modeling-based finite element model of the cervical spine under low-level multiple direction loading conditions","volume":"2","author":"Bredbenner","year":"2014","journal-title":"Front. Bioeng. Biotechnol."},{"key":"B5","article-title":"MMDetection: open mmlab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"B6","doi-asserted-by":"publisher","first-page":"106615","DOI":"10.1016\/j.compbiomed.2023.106615","article-title":"Bx2s-net: learning to reconstruct 3d spinal structures from bi-planar x-ray images","volume":"154","author":"Chen","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B7","doi-asserted-by":"publisher","first-page":"16165","DOI":"10.1038\/s41598-024-65795-7","article-title":"Automatic 3d reconstruction of vertebrae from orthogonal bi-planar radiographs","volume":"14","author":"Chen","year":"2024","journal-title":"Sci. Rep."},{"key":"B8","doi-asserted-by":"publisher","first-page":"108444","DOI":"10.1016\/j.cmpb.2024.108444","article-title":"2d\/3d registration based on biplanar x-ray and ct images for surgical navigation","volume":"257","author":"Demin","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"B9","article-title":"Ctspine1k: a large-scale dataset for spinal vertebrae segmentation computed tomography","volume-title":"International conference on medical image computing and computer-assisted intervention (MICCAI)","author":"Deng","year":"2023"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.59275\/j.melba.2024-AAAA","article-title":"Ctspine1k: a large-scale dataset for spinal vertebrae segmentation in computed tomography","volume":"2","author":"Deng","year":"2024","journal-title":"J. Mach. Learn. Biomed. Imaging"},{"key":"B11","first-page":"1","article-title":"Hierarchical image registration with an active contour-based atlas registration model","author":"Duay","year":"2008"},{"key":"B12","doi-asserted-by":"publisher","first-page":"9","DOI":"10.2147\/RSRR.S190720","article-title":"Robotic-assisted spine surgery: history, efficacy, cost, and future trends","volume":"6","author":"D\u2019Souza","year":"2019","journal-title":"Robotic Surg. Res. Rev."},{"key":"B13","volume-title":"3D reconstruction of anatomical structures from 2D X-ray images","author":"Ehlke","year":"2020"},{"key":"B14","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1038\/s42256-023-00629-1","article-title":"Synthetic data accelerates the development of generalizable learning-based algorithms for x-ray image analysis","volume":"5","author":"Gao","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.01108","article-title":"Intraoperative 2d\/3d image registration via differentiable x-ray rendering","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","author":"Gopalakrishnan","year":"2024"},{"key":"B16","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/BF02291478","article-title":"Generalized procrustes analysis","volume":"40","author":"Gower","year":"1975","journal-title":"Psychometrika"},{"key":"B17","doi-asserted-by":"publisher","first-page":"095022","DOI":"10.1088\/1361-6560\/ab1456","article-title":"Atlas-based automatic planning and 3d-2d fluoroscopic guidance in pelvic trauma surgery","volume":"64","author":"Han","year":"2019","journal-title":"Phys. Med. & Biol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"271","DOI":"10.3390\/jimaging8100271","article-title":"X23D\u2014Intraoperative 3D lumbar spine shape reconstruction based on sparse multi-view X-ray data","volume":"8","author":"Jecklin","year":"2022","journal-title":"J. Imaging"},{"key":"B19","doi-asserted-by":"publisher","first-page":"103322","DOI":"10.1016\/j.media.2024.103322","article-title":"Domain adaptation strategies for 3d reconstruction of the lumbar spine using real fluoroscopy data","volume":"98","author":"Jecklin","year":"2024","journal-title":"Med. Image Anal."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1201","DOI":"10.1007\/s11548-023-02941-y","article-title":"An autonomous x-ray image acquisition and interpretation system for assisting percutaneous pelvic fracture fixation","volume":"18","author":"Killeen","year":"","journal-title":"Int. J. Comput. Assisted Radiology Surg."},{"key":"B21","first-page":"133","article-title":"Pelphix: surgical phase recognition from x-ray images in percutaneous pelvic fixation","volume-title":"Proceedings of the medical image computing and computer-assisted intervention (MICCAI)","author":"Killeen","year":""},{"key":"B22","first-page":"1","article-title":"Perspective projection-based 3d ct reconstruction from biplanar x-rays","author":"Kyung","year":"2023"},{"key":"B23","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1109\/ICPR.2006.279","article-title":"Atlas-based 3d-shape reconstruction from x-ray images","volume":"1","author":"Lamecker","year":"2006","journal-title":"18th Int. Conf. Pattern Recognit. (ICPR\u201906)"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","author":"Liu","year":"2021"},{"key":"B25","doi-asserted-by":"publisher","first-page":"185","DOI":"10.3390\/jimaging8070185","article-title":"A hybrid 3d-2d image registration framework for pedicle screw trajectory registration between intraoperative x-ray image and preoperative ct image","volume":"8","author":"Naik","year":"2022","journal-title":"J. Imaging"},{"key":"B26","article-title":"New Mexico decedent image database (nmdid)","year":"2025"},{"key":"B27","first-page":"1","article-title":"Feasibility of a cannula-mounted piezo robot for image-guided vertebral augmentation: toward a low cost, semi-autonomous approach","author":"Opfermann","year":"2021"},{"key":"B28","doi-asserted-by":"publisher","first-page":"241","DOI":"10.3390\/medicina58020241","article-title":"Computed tomography-based navigation system in current spine surgery: a narrative review","volume":"58","author":"Otomo","year":"2022","journal-title":"Medicina"},{"key":"B29","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1227\/00006123-198007000-00014","article-title":"Basic biomechanics of the spine","volume":"7","author":"Panjabi","year":"1980","journal-title":"Neurosurgery"},{"key":"B30","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1109\/TMRB.2022.3155288","article-title":"An automatic path planning method of pedicle screw placement based on preoperative ct images","volume":"4","author":"Qi","year":"2022","journal-title":"IEEE Trans. Med. Robotics Bionics"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.3390\/jpm13121642","article-title":"Synthetic 3d spinal vertebrae reconstruction from biplanar x-rays utilizing generative adversarial networks","volume":"13","author":"Saravi","year":"2023","journal-title":"J. Personalized Med."},{"key":"B32","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102166","article-title":"Verse: a vertebrae labelling and segmentation benchmark for multi-detector ct images","author":"Sekuboyina","year":"2021","journal-title":"Med. Image Anal."},{"key":"B33","doi-asserted-by":"publisher","first-page":"15249","DOI":"10.1038\/s41598-021-94634-2","article-title":"2d\u20133d reconstruction of distal forearm bone from actual x-ray images of the wrist using convolutional neural networks","volume":"11","author":"Shiode","year":"2021","journal-title":"Sci. Rep."},{"key":"B34","doi-asserted-by":"publisher","first-page":"143","DOI":"10.5152\/dir.2019.19268","article-title":"Approach-based techniques of ct-guided percutaneous vertebral biopsy","volume":"26","author":"Singh","year":"2020","journal-title":"Diagnostic Interventional Radiology"},{"key":"B35","first-page":"164","article-title":"Cannula-mounted robots for semi-autonomous vertebroplasty: a comparison of piezo-based and screw-based inchworm drive designs","author":"Song","year":"2025"},{"key":"B36","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/978-3-030-00937-3_12","article-title":"Deepdrr \u2013 a catalyst for machine learning in fluoroscopy-guided procedures","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2018","author":"Unberath","year":"2018"},{"key":"B37","doi-asserted-by":"crossref","DOI":"10.1007\/s11548-019-02011-2","article-title":"Enabling machine learning in X-ray-based procedures via realistic simulation of image formation","author":"Unberath","year":"2019","journal-title":"Int. Journal Computer Assisted Radiology Surgery (IJCARS)"},{"key":"B38","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1088\/0031-9155\/59\/2\/271","article-title":"3D-2D registration for surgical guidance: effect of projection view angles on registration accuracy","volume":"59","author":"Uneri","year":"2014","journal-title":"Phys. Med. Biol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"165020","DOI":"10.1088\/1361-6560\/ab2d66","article-title":"Automatic pedicle screw planning using atlas-based registration of anatomy and reference trajectories","volume":"64","author":"Vijayan","year":"2019","journal-title":"Phys. Med. & Biol."},{"key":"B40","doi-asserted-by":"crossref","DOI":"10.1117\/12.2513722","article-title":"Automatic trajectory and instrument planning for robot-assisted spine surgery","volume-title":"Medical imaging 2019: image-guided procedures, robotic interventions, and modeling","author":"Vijayan","year":"2019"},{"key":"B41","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s10237-022-01636-8","article-title":"Statistical shape modelling of the thoracic spine for the development of pedicle screw insertion guides","volume":"22","author":"Wai","year":"2023","journal-title":"Biomechanics Model. Mechanobiol."},{"key":"B42","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.3390\/bioengineering11111094","article-title":"Development and validation of deep learning preoperative planning software for automatic lumbosacral screw selection using computed tomography","volume":"11","author":"Wang","year":"2024","journal-title":"Bioengineering"},{"key":"B43","doi-asserted-by":"publisher","first-page":"e230024","DOI":"10.1148\/ryai.230024","article-title":"Totalsegmentator: robust segmentation of 104 anatomic structures in ct images","volume":"5","author":"Wasserthal","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"B44","article-title":"Gsplat: an open-source library for gaussian splatting","author":"Ye","year":"2024"},{"key":"B45","first-page":"10611","article-title":"X2ct-gan: reconstructing ct from biplanar x-rays with generative adversarial networks","author":"Ying","year":"2019"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1808","DOI":"10.1109\/TBME.2011.2122306","article-title":"Improved labeling of subcortical brain structures in atlas-based segmentation of magnetic resonance images","volume":"59","author":"Yousefi","year":"2011","journal-title":"IEEE Transactions Bio-Medical Engineering"},{"key":"B47","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-63416-2_179","article-title":"Iterative closest point (icp)","volume-title":"Encyclopedia of computer vision","author":"Zhang","year":"2021"}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2026.1759366\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:48:42Z","timestamp":1772095722000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2026.1759366\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,26]]},"references-count":47,"alternative-id":["10.3389\/frobt.2026.1759366"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2026.1759366","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,26]]},"article-number":"1759366"}}