MR Image Super-Resolution with Squeeze and Excitation Reasoning Attention Network

High-quality high-resolution (HR) magnetic resonance (MR) images afford more detailed information for reliable diagnosis and quantitative image analyses. Deep convolutional neural networks (CNNs) have shown promising ability for MR image super-resolution (SR) given low-resolution (LR) MR images. The LR MR images usually share some visual characteristics: repeating patterns, relatively simpler structures, and less informative background. Most previous CNN-based SR methods treat the spatial pixels (including the background) equally. They also fail to sense the entire space of the input, which is critical for high-quality MR image SR. To address those problems, we propose squeeze and excitation reasoning attention networks (SERAN) for accurate MR image SR. We propose to squeeze attention from global spatial information of the input and obtain global descriptors. Such global descriptors enhance the network's ability to focus on more informative regions and structures in MR images. We further build relationship among those global descriptors and propose primitive relationship reasoning attention. The global descriptors are further refined with learned attention. To fully make use of the aggregated information, we adaptively recalibrate feature responses with learned adaptive attention vectors. These attention vectors select a subset of global descriptors to complement each spatial location for accurate details and texture reconstruction. We propose squeeze and excitation attention with residual scaling, which not only stabilizes the training but also makes it flexible to other basic networks. Extensive experiments show the effectiveness of our proposed SERAN, which clearly surpasses state-of-the-art methods on benchmarks quantitatively and visually.

Automated summary

The paper proposes SERAN network for accurate MR image super-resolution, enhancing the network's focus on more informative regions and structures in the image with global descriptors, refining global descriptors further through adaptive attention vectors, and recalibrating feature responses for accurate details and texture reconstruction. This approach surpasses state-of-the-art methods on benchmarks quantitatively and visually.