Fine-grained MRI Reconstruction using Attentive Selection Generative Adversarial Networks

TL;DR

This paper introduces an attention-based GAN framework for MRI reconstruction that integrates contextual features and selective attention to produce high-quality images from extremely low sampling rates, surpassing existing methods.

Contribution

The paper proposes a novel attention-guided GAN model with large-field context integration for improved MRI reconstruction at low sampling rates.

Findings

Superior image quality compared to existing deep learning methods

Effective at extremely low sampling rates

Demonstrates the importance of attention mechanisms in MRI reconstruction

Abstract

Compressed sensing (CS) leverages the sparsity prior to provide the foundation for fast magnetic resonance imaging (fastMRI). However, iterative solvers for ill-posed problems hinder their adaption to time-critical applications. Moreover, such a prior can be neither rich to capture complicated anatomical structures nor applicable to meet the demand of high-fidelity reconstructions in modern MRI. Inspired by the state-of-the-art methods in image generation, we propose a novel attention-based deep learning framework to provide high-quality MRI reconstruction. We incorporate large-field contextual feature integration and attention selection in a generative adversarial network (GAN) framework. We demonstrate that the proposed model can produce superior results compared to other deep learning-based methods in terms of image quality, and relevance to the MRI reconstruction in an extremely low sampling rate diet.