Interpretable deformable image registration: A geometric deep learning perspective

TL;DR

This paper introduces an interpretable geometric deep learning framework for deformable image registration, emphasizing feature separation, dynamic receptive fields, and deformation functions to improve robustness, interpretability, and performance.

Contribution

The work provides a theoretical foundation and a novel architecture that enhances interpretability and performance in deformable image registration using geometric deep learning principles.

Findings

Significant performance improvements over state-of-the-art methods.

Enhanced interpretability of the registration process.

Effective application to brain and retinal image registration tasks.

Abstract

Deformable image registration poses a challenging problem where, unlike most deep learning tasks, a complex relationship between multiple coordinate systems has to be considered. Although data-driven methods have shown promising capabilities to model complex non-linear transformations, existing works employ standard deep learning architectures assuming they are general black-box solvers. We argue that understanding how learned operations perform pattern-matching between the features in the source and target domains is the key to building robust, data-efficient, and interpretable architectures. We present a theoretical foundation for designing an interpretable registration framework: separated feature extraction and deformation modeling, dynamic receptive fields, and a data-driven deformation functions awareness of the relationship between both spatial domains. Based on this foundation, we formulate an end-to-end process that refines transformations in a coarse-to-fine fashion. Our architecture employs spatially continuous deformation modeling functions that use geometric deep-learning principles, therefore avoiding the problematic approach of resampling to a regular grid between successive refinements of the transformation. We perform a qualitative investigation to highlight interesting interpretability properties of our architecture. We conclude by showing significant improvement in performance metrics over state-of-the-art approaches for both mono- and multi-modal inter-subject brain registration, as well as the challenging task of longitudinal retinal intra-subject registration. We make our code publicly available