Unsupervised Multi-Modality Registration Network based on Spatially Encoded Gradient Information

TL;DR

This paper introduces MMRegNet, an unsupervised neural network that uses spatially encoded gradient information to effectively register multi-modality medical images, enhancing clinical analysis.

Contribution

It presents a novel unsupervised multi-modality registration network utilizing spatially encoded gradients, addressing training robustness issues in multi-modality image registration.

Findings

Achieved promising results on cardiac registration tasks.

Demonstrated versatility with liver dataset evaluation.

Source code will be publicly available.

Abstract

Multi-modality medical images can provide relevant or complementary information for a target (organ, tumor or tissue). Registering multi-modality images to a common space can fuse these comprehensive information, and bring convenience for clinical application. Recently, neural networks have been widely investigated to boost registration methods. However, it is still challenging to develop a multi-modality registration network due to the lack of robust criteria for network training. In this work, we propose a multi-modality registration network (MMRegNet), which can perform registration between multi-modality images. Meanwhile, we present spatially encoded gradient information to train MMRegNet in an unsupervised manner. The proposed network was evaluated on MM-WHS 2017. Results show that MMRegNet can achieve promising performance for left ventricle cardiac registration tasks. Meanwhile, to demonstrate the versatility of MMRegNet, we further evaluate the method with a liver dataset from CHAOS 2019. Source code will be released publicly\footnote{https://github.com/NanYoMy/mmregnet} once the manuscript is accepted.