Toward Patient-specific Partial Point Cloud to Surface Completion for Pre- to Intra-operative Registration in Image-guided Liver Interventions

2025-05-26

AI Summary

In liver interventional procedures, intraoperative point clouds are locally visible and lack surface information around lesions, leading to challenges in preoperative-to-intraoperative rigid registration. To address this, we propose a patient-specific point cloud completion method based on a rotationally equivariant implicit occupancy network (VN-OccNet), integrated with physics-informed, patient-specific deformation modeling and data augmentation. We establish the first VN-OccNet training paradigm and empirically validate the efficacy of its rotational equivariance for liver surface completion. Our method reconstructs complete liver surfaces from incomplete intraoperative point clouds to guide Go-ICP registration. Evaluated on multiple real and synthetic datasets, it reduces mean registration error by 32.7% compared to baseline methods, significantly mitigating registration failures caused by partial observability and thereby enhancing the robustness and accuracy of image-guided interventions.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

Intra-operative data captured during image-guided surgery lacks sub-surface information, where key regions of interest, such as vessels and tumors, reside. Image-to-physical registration enables the fusion of pre-operative information and intra-operative data, typically represented as a point cloud. However, this registration process struggles due to partial visibility of the intra-operative point cloud. In this research, we propose a patient-specific point cloud completion approach to assist with the registration process. Specifically, we leverage VN-OccNet to generate a complete liver surface from a partial intra-operative point cloud. The network is trained in a patient-specific manner, where simulated deformations from the pre-operative model are used to train the model. First, we conduct an in-depth analysis of VN-OccNet's rotation-equivariant property and its effectiveness in recovering complete surfaces from partial intra-operative surfaces. Next, we integrate the completed intra-operative surface into the Go-ICP registration algorithm to demonstrate its utility in improving initial rigid registration outcomes. Our results highlight the promise of this patient-specific completion approach in mitigating the challenges posed by partial intra-operative visibility. The rotation equivariant and surface generation capabilities of VN-OccNet hold strong promise for developing robust registration frameworks for variations of the intra-operative point cloud.

Problem

• Completing partial intra-operative liver point clouds
• Improving pre- to intra-operative registration accuracy
• Addressing subsurface visibility challenges in guided surgery

Innovation

• Patient-specific VN-OccNet for surface completion
• Rotation-equivariant network for partial point clouds
• Go-ICP registration with completed liver surfaces