Large Scale Unsupervised Brain MRI Image Registration Solution for Learn2Reg 2024

TL;DR

This paper presents an unsupervised brain MRI image registration method for the learn2reg 2024 challenge, achieving high accuracy without segmentation labels by using an efficient network and regularization techniques.

Contribution

We developed a novel unsupervised registration approach with an optimized backbone network and regularization schemes, improving accuracy over existing methods in large-scale brain MRI registration.

Findings

Achieved a Dice coefficient of 77.34%, outperforming TransMorph by 1.4%.

Secured second place in the learn2reg 2024 challenge for Task 2.

Demonstrated effective registration without segmentation labels on large datasets.

Abstract

In this paper, we summarize the methods and experimental results we proposed for Task 2 in the learn2reg 2024 Challenge. This task focuses on unsupervised registration of anatomical structures in brain MRI images between different patients. The difficulty lies in: (1) without segmentation labels, and (2) a large amount of data. To address these challenges, we built an efficient backbone network and explored several schemes to further enhance registration accuracy. Under the guidance of the NCC loss function and smoothness regularization loss function, we obtained a smooth and reasonable deformation field. According to the leaderboard, our method achieved a Dice coefficient of 77.34%, which is 1.4% higher than the TransMorph. Overall, we won second place on the leaderboard for Task 2.