Fine-grained MRI Reconstruction using Attentive Selection Generative Adversarial Networks
arXiv:2103.07672
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.
arXiv comment5 pages, 2 figures, 1 table, 22 references
References in corpus (5)
- Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
- fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
- CBAM: Convolutional Block Attention Module
- Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation
- MRI Reconstruction via Cascaded Channel-wise Attention Network