Semantic-ICP: Iterative Closest Point for Non-rigid Multi-Organ Point Cloud Registration
This addresses the need for more robust and explainable registration methods in clinical applications like trans-oral robotic surgery, though it is incremental as it builds on classical ICP with semantic and biomechanical enhancements.
The paper tackled the problem of non-rigid multi-organ point cloud registration in computer-aided interventions by proposing a semantic ICP method that incorporates semantic labels and biomechanical energy constraints, resulting in improved Hausdorff distance and mean surface distance compared to other point-matching-based methods.
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 required for registration needs to follow biomechanical energy constraints. In this paper, we present a novel semantic ICP (SemICP) 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 novel point cloud deformation representation to apply explicit biomechanical energy regularization. Our experiments on a trans-oral robotic surgery ultrasound-computed tomography registration dataset and two public Learn2reg challenge datasets show that our method improves the Hausdorff distance and mean surface distance compared with other point-matching-based registration methods.