Deep Attentive Wasserstein Generative Adversarial Networks for MRI Reconstruction with Recurrent Context-Awareness

TL;DR

This paper introduces a novel deep learning framework combining Wasserstein GANs with recurrent and attentive mechanisms to improve MRI reconstruction quality, especially at high acceleration factors, by better utilizing sequential slice information.

Contribution

It presents a new deep learning-based CS-MRI reconstruction method that leverages recurrent context-awareness and attention to enhance anatomical accuracy and noise reduction.

Findings

Outperforms state-of-the-art methods in MRI reconstruction quality.

Effectively reduces residual noise in reconstructed images.

Demonstrates robustness across different MRI datasets.

Abstract

The performance of traditional compressive sensing-based MRI (CS-MRI) reconstruction is affected by its slow iterative procedure and noise-induced artefacts. Although many deep learning-based CS-MRI methods have been proposed to mitigate the problems of traditional methods, they have not been able to achieve more robust results at higher acceleration factors. Most of the deep learning-based CS-MRI methods still can not fully mine the information from the k-space, which leads to unsatisfactory results in the MRI reconstruction. In this study, we propose a new deep learning-based CS-MRI reconstruction method to fully utilise the relationship among sequential MRI slices by coupling Wasserstein Generative Adversarial Networks (WGAN) with Recurrent Neural Networks. Further development of an attentive unit enables our model to reconstruct more accurate anatomical structures for the MRI data. By experimenting on different MRI datasets, we have demonstrated that our method can not only achieve better results compared to the state-of-the-arts but can also effectively reduce residual noise generated during the reconstruction process.