Coordinate Translator for Learning Deformable Medical Image Registration

TL;DR

This paper introduces Coordinate Translator, a module that improves deformable medical image registration by explicitly matching features without training, enabling a new hierarchical registration network that outperforms existing methods.

Contribution

The paper presents a novel Coordinate Translator module and a hierarchical registration network, im2grid, enhancing registration accuracy by decoupling coordinate understanding from feature extraction.

Findings

im2grid outperforms state-of-the-art methods in 3D MRI registration

Coordinate Translator effectively matches features without training

Hierarchical approach improves registration accuracy

Abstract

The majority of deep learning (DL) based deformable image registration methods use convolutional neural networks (CNNs) to estimate displacement fields from pairs of moving and fixed images. This, however, requires the convolutional kernels in the CNN to not only extract intensity features from the inputs but also understand image coordinate systems. We argue that the latter task is challenging for traditional CNNs, limiting their performance in registration tasks. To tackle this problem, we first introduce Coordinate Translator, a differentiable module that identifies matched features between the fixed and moving image and outputs their coordinate correspondences without the need for training. It unloads the burden of understanding image coordinate systems for CNNs, allowing them to focus on feature extraction. We then propose a novel deformable registration network, im2grid, that uses multiple Coordinate Translator's with the hierarchical features extracted from a CNN encoder and outputs a deformation field in a coarse-to-fine fashion. We compared im2grid with the state-of-the-art DL and non-DL methods for unsupervised 3D magnetic resonance image registration. Our experiments show that im2grid outperforms these methods both qualitatively and quantitatively.