NeuralBoneReg: An Instance-Specific Label-Free Point Cloud-Based Method for Multi-Modal Bone Surface Registration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Luohong, Seibold, Matthias, Cavalcanti, Nicola A., Ao, Yunke, Flepp, Roman, Massalimova, Aidana, Calvet, Lilian, Fürnstahl, Philipp
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916037481463808
author Wu, Luohong
Seibold, Matthias
Cavalcanti, Nicola A.
Ao, Yunke
Flepp, Roman
Massalimova, Aidana
Calvet, Lilian
Fürnstahl, Philipp
author_facet Wu, Luohong
Seibold, Matthias
Cavalcanti, Nicola A.
Ao, Yunke
Flepp, Roman
Massalimova, Aidana
Calvet, Lilian
Fürnstahl, Philipp
contents In computer- and robot-assisted orthopedic surgery (CAOS), patient-specific surgical plans derived from preoperative imaging define target locations and implant trajectories. During surgery, these plans must be accurately transferred, relying on precise cross-registration between preoperative and intraoperative data. However, substantial modality heterogeneity across imaging modalities makes this registration challenging and error-prone. Robust, automatic, and modality-agnostic bone surface registration is therefore clinically important. We propose NeuralBoneReg, a self-supervised, surface-based framework that registers bone surfaces using 3D point clouds as a modality-agnostic representation. NeuralBoneReg includes two modules: an implicit neural unsigned distance field (UDF) that learns the preoperative bone model, and an MLP-based registration module that performs global initialization and local refinement by generating transformation hypotheses to align the intraoperative point cloud with the neural UDF. Unlike SOTA supervised methods, NeuralBoneReg operates in a self-supervised manner, without requiring inter-subject training data. We evaluated NeuralBoneReg against baseline methods on two publicly available multi-modal datasets: a CT-ultrasound dataset of the fibula and tibia (UltraBones100k) and a CT-RGB-D dataset of spinal vertebrae (SpineDepth). The evaluation also includes a newly introduced CT-ultrasound dataset of cadaveric subjects containing femur and pelvis (UltraBones-Hip), which will be made publicly available. NeuralBoneReg matches or surpasses existing methods across all datasets, achieving mean RRE/RTE of 1.83°/2.02 mm on UltraBones100k, 1.90°/1.56 mm on UltraBones-Hip, and 3.78°/2.80 mm on SpineDepth. These results demonstrate strong generalizability across anatomies and modalities, providing robust and accurate cross-modal alignment for CAOS.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14286
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeuralBoneReg: An Instance-Specific Label-Free Point Cloud-Based Method for Multi-Modal Bone Surface Registration
Wu, Luohong
Seibold, Matthias
Cavalcanti, Nicola A.
Ao, Yunke
Flepp, Roman
Massalimova, Aidana
Calvet, Lilian
Fürnstahl, Philipp
Computer Vision and Pattern Recognition
In computer- and robot-assisted orthopedic surgery (CAOS), patient-specific surgical plans derived from preoperative imaging define target locations and implant trajectories. During surgery, these plans must be accurately transferred, relying on precise cross-registration between preoperative and intraoperative data. However, substantial modality heterogeneity across imaging modalities makes this registration challenging and error-prone. Robust, automatic, and modality-agnostic bone surface registration is therefore clinically important. We propose NeuralBoneReg, a self-supervised, surface-based framework that registers bone surfaces using 3D point clouds as a modality-agnostic representation. NeuralBoneReg includes two modules: an implicit neural unsigned distance field (UDF) that learns the preoperative bone model, and an MLP-based registration module that performs global initialization and local refinement by generating transformation hypotheses to align the intraoperative point cloud with the neural UDF. Unlike SOTA supervised methods, NeuralBoneReg operates in a self-supervised manner, without requiring inter-subject training data. We evaluated NeuralBoneReg against baseline methods on two publicly available multi-modal datasets: a CT-ultrasound dataset of the fibula and tibia (UltraBones100k) and a CT-RGB-D dataset of spinal vertebrae (SpineDepth). The evaluation also includes a newly introduced CT-ultrasound dataset of cadaveric subjects containing femur and pelvis (UltraBones-Hip), which will be made publicly available. NeuralBoneReg matches or surpasses existing methods across all datasets, achieving mean RRE/RTE of 1.83°/2.02 mm on UltraBones100k, 1.90°/1.56 mm on UltraBones-Hip, and 3.78°/2.80 mm on SpineDepth. These results demonstrate strong generalizability across anatomies and modalities, providing robust and accurate cross-modal alignment for CAOS.
title NeuralBoneReg: An Instance-Specific Label-Free Point Cloud-Based Method for Multi-Modal Bone Surface Registration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.14286