A Transformer-based Network for Deformable Medical Image Registration

TL;DR

This paper introduces a transformer-based neural network for deformable medical image registration, leveraging self-attention to enhance global and local feature extraction, resulting in improved accuracy over existing methods.

Contribution

The proposed method uniquely integrates transformer architecture with unsupervised registration, effectively capturing comprehensive image features for better registration accuracy.

Findings

Achieves higher dice scores on brain MR datasets

Outperforms traditional and DL-based registration methods

Enhances registration accuracy with self-attention mechanism

Abstract

Deformable medical image registration plays an important role in clinical diagnosis and treatment. Recently, the deep learning (DL) based image registration methods have been widely investigated and showed excellent performance in computational speed. However, these methods cannot provide enough registration accuracy because of insufficient ability in representing both the global and local features of the moving and fixed images. To address this issue, this paper has proposed the transformer based image registration method. This method uses the distinctive transformer to extract the global and local image features for generating the deformation fields, based on which the registered image is produced in an unsupervised way. Our method can improve the registration accuracy effectively by means of self-attention mechanism and bi-level information flow. Experimental results on such brain MR image datasets as LPBA40 and OASIS-1 demonstrate that compared with several traditional and DL based registration methods, our method provides higher registration accuracy in terms of dice values.