SITReg: Multi-resolution architecture for symmetric, inverse consistent, and topology preserving image registration

TL;DR

SITReg introduces a multi-resolution deep learning architecture for medical image registration that inherently enforces symmetry, inverse consistency, and topology preservation, achieving state-of-the-art accuracy efficiently.

Contribution

The paper presents a novel deep learning architecture that enforces key classical registration properties by design, unlike previous methods relying on loss functions.

Findings

Achieves state-of-the-art registration accuracy on three datasets.

Enforces symmetry, inverse consistency, and topology preservation by construction.

Develops an implicit layer for memory-efficient deformation field inversion.

Abstract

Deep learning has emerged as a strong alternative for classical iterative methods for deformable medical image registration, where the goal is to find a mapping between the coordinate systems of two images. Popular classical image registration methods enforce the useful inductive biases of symmetricity, inverse consistency, and topology preservation by construction. However, while many deep learning registration methods encourage these properties via loss functions, no earlier methods enforce all of them by construction. Here, we propose a novel registration architecture based on extracting multi-resolution feature representations which is by construction symmetric, inverse consistent, and topology preserving. We also develop an implicit layer for memory efficient inversion of the deformation fields. Our method achieves state-of-the-art registration accuracy on three datasets. The code is available at https://github.com/honkamj/SITReg.