Metric-Driven Learning of Correspondence Weighting for 2-D/3-D Image Registration

TL;DR

This paper introduces a novel method using PointNet to learn optimal correspondence weights for 2-D/3-D image registration, significantly improving accuracy and robustness in medical procedures.

Contribution

It proposes an end-to-end learning framework that optimizes correspondence weights based on registration error, integrating point-to-plane motion estimation and projection error.

Findings

Achieved 0.74mm registration accuracy for single-vertebra cases.

Increased success rate from 79.3% to 94.3%.

Expanded capture range from 3mm to 13mm.

Abstract

Registration of pre-operative 3-D volumes to intra-operative 2-D X-ray images is important in minimally invasive medical procedures. Rigid registration can be performed by estimating a global rigid motion that optimizes the alignment of local correspondences. However, inaccurate correspondences challenge the registration performance. To minimize their influence, we estimate optimal weights for correspondences using PointNet. We train the network directly with the criterion to minimize the registration error. We propose an objective function which includes point-to-plane correspondence-based motion estimation and projection error computation, thereby enabling the learning of a weighting strategy that optimally fits the underlying formulation of the registration task in an end-to-end fashion. For single-vertebra registration, we achieve an accuracy of 0.74$\pm$0.26 mm and highly improved robustness. The success rate is increased from 79.3 % to 94.3 % and the capture range from 3 mm to 13 mm.