Semantic-ICP: Iterative Closest Point for Non-rigid Multi-Organ Point Cloud Registration

2025-03-02

AI Summary

Poor generalizability and limited interpretability plague multi-organ non-rigid point cloud registration in medical computer-assisted intervention (CAI). To address this, we propose a semantics- and biomechanics-aware ICP framework. Our method innovatively incorporates multi-class anatomical semantic labels into the ICP correspondence search to enable semantic-guided nearest-neighbor matching; introduces, for the first time in ICP, an explicit biomechanical regularization based on a linear elastic finite element model to enforce physically plausible deformations; and designs a multi-label-weighted distance metric to enhance anatomical consistency. Evaluated on the Learn2Reg abdominal MR–CT and oral ultrasound–CT datasets, our approach significantly reduces Hausdorff distance and demonstrates superior convergence robustness against initial pose misalignment and partial visibility variations—achieving a favorable balance among registration accuracy, clinical interpretability, and practical applicability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Point cloud registration is important in computer-aided interventions (CAI). While learning-based point cloud registration methods have been developed, their clinical application is hampered by issues of generalizability and explainability. Therefore, classical point cloud registration methods, such as Iterative Closest Point (ICP), are still widely applied in CAI. ICP methods fail to consider that: (1) the points have well-defined semantic meaning, in that each point can be related to a specific anatomical label; (2) the deformation needs to follow biomechanical energy constraints. In this paper, we present a novel semantic ICP (sem-ICP) method that handles multiple point labels and uses linear elastic energy regularization. We use semantic labels to improve the robustness of the closest point matching and propose a new point cloud deformation representation to apply explicit biomechanical energy regularization. Our experiments on the Learn2reg abdominal MR-CT registration dataset and a trans-oral robotic surgery ultrasound-CT registration dataset show that our method improves the Hausdorff distance compared with other state-of-the-art ICP-based registration methods. We also perform a sensitivity study to show that our rigid initialization achieves better convergence with different initializations and visible ratios.

Problem

• Improves point cloud registration in medical imaging.
• Addresses lack of semantic and biomechanical considerations in ICP.
• Enhances robustness and accuracy in multi-organ registration.

Innovation

• Semantic labels enhance closest point matching robustness.
• Linear elastic energy regularization for biomechanical constraints.
• Improved Hausdorff distance in MR-CT and ultrasound-CT registrations.