Preoperative-to-intraoperative Liver Registration for Laparoscopic Surgery via Latent-Grounded Correspondence Constraints
This addresses a critical challenge in laparoscopic liver surgery by providing more interpretable and stable registration for augmented reality guidance, though it appears incremental as it builds on existing registration methods with novel constraints.
The paper tackles the problem of aligning preoperative 3D liver models with intraoperative 2D laparoscopic views for augmented reality surgery, introducing Land-Reg which learns explicit 2D-3D landmark correspondences to improve registration; it demonstrates superior performance on the P2ILF dataset for both rigid pose estimation and non-rigid deformation.
In laparoscopic liver surgery, augmented reality technology enhances intraoperative anatomical guidance by overlaying 3D liver models from preoperative CT/MRI onto laparoscopic 2D views. However, existing registration methods lack explicit modeling of reliable 2D-3D geometric correspondences supported by latent evidence, leading to limited interpretability and potentially unstable alignment in clinical scenarios. In this work, we introduce Land-Reg, a correspondence-driven deformable registration framework that explicitly learns latent-grounded 2D-3D landmark correspondences as an interpretable intermediate representation to bridge cross-modal alignment. For rigid registration, Land-Reg embraces a Cross-modal Latent Alignment module to map multi-modal features into a unified latent space. Further, an Uncertainty-enhanced Overlap Landmark Detector with similarity matching is proposed to robustly estimate explicit 2D-3D landmark correspondences. For non-rigid registration, we design a novel shape-constrained supervision strategy that anchors shape deformation to matched landmarks through reprojection consistency and incorporates local-isometric regularization to alleviate inherent 2D-3D depth ambiguity, while a rendered-mask alignment enforces global shape consistency. Experimental results on the P2ILF dataset demonstrate the superiority of our method on both rigid pose estimation and non-rigid deformation. Our code will be available at https://github.com/cuiruize/Land-Reg.