Preoperative-to-intraoperative Liver Registration for Laparoscopic Surgery via Latent-Grounded Correspondence Constraints

TL;DR

This paper introduces Land-Reg, a novel framework for liver registration in laparoscopic surgery that explicitly models 2D-3D correspondences using latent representations, improving alignment accuracy and interpretability.

Contribution

Land-Reg is the first to explicitly learn latent-grounded 2D-3D landmark correspondences for deformable liver registration, enhancing interpretability and robustness in clinical scenarios.

Findings

Outperforms existing methods on rigid pose estimation.

Achieves superior non-rigid deformation accuracy.

Demonstrates robustness in clinical datasets.

Abstract

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.