Swin Deformable Attention U-Net Transformer (SDAUT) for Explainable Fast MRI

TL;DR

This paper introduces a novel Transformer-based U-Net model with deformable attention for fast MRI reconstruction, achieving superior performance, reduced complexity, and enhanced explainability compared to existing methods.

Contribution

It proposes a new SDAUT architecture combining Shifted Windows Transformer, U-Net, and deformable attention to improve MRI reconstruction efficiency and interpretability.

Findings

Achieves better reconstruction accuracy than state-of-the-art models.

Uses fewer network parameters while maintaining performance.

Provides explainability through deformable attention mechanisms.

Abstract

Fast MRI aims to reconstruct a high fidelity image from partially observed measurements. Exuberant development in fast MRI using deep learning has been witnessed recently. Meanwhile, novel deep learning paradigms, e.g., Transformer based models, are fast-growing in natural language processing and promptly developed for computer vision and medical image analysis due to their prominent performance. Nevertheless, due to the complexity of the Transformer, the application of fast MRI may not be straightforward. The main obstacle is the computational cost of the self-attention layer, which is the core part of the Transformer, can be expensive for high resolution MRI inputs. In this study, we propose a new Transformer architecture for solving fast MRI that coupled Shifted Windows Transformer with U-Net to reduce the network complexity. We incorporate deformable attention to construe the explainability of our reconstruction model. We empirically demonstrate that our method achieves consistently superior performance on the fast MRI task. Besides, compared to state-of-the-art Transformer models, our method has fewer network parameters while revealing explainability. The code is publicly available at https://github.com/ayanglab/SDAUT.