Over-and-Under Complete Convolutional RNN for MRI Reconstruction
This work addresses MRI reconstruction for medical imaging, offering an incremental improvement by enhancing feature learning in deep networks.
The paper tackles the problem of reconstructing MRI images from undersampled data by proposing an Over-and-Under Complete Convolutional Recurrent Neural Network (OUCR), which combines overcomplete and undercomplete branches to focus on local and global features, achieving significant improvements over existing methods with fewer parameters.
Reconstructing magnetic resonance (MR) images from undersampled data is a challenging problem due to various artifacts introduced by the under-sampling operation. Recent deep learning-based methods for MR image reconstruction usually leverage a generic auto-encoder architecture which captures low-level features at the initial layers and high-level features at the deeper layers. Such networks focus much on global features which may not be optimal to reconstruct the fully-sampled image. In this paper, we propose an Over-and-Under Complete Convolutional Recurrent Neural Network (OUCR), which consists of an overcomplete and an undercomplete Convolutional Recurrent Neural Network(CRNN). The overcomplete branch gives special attention in learning local structures by restraining the receptive field of the network. Combining it with the undercomplete branch leads to a network which focuses more on low-level features without losing out on the global structures. Extensive experiments on two datasets demonstrate that the proposed method achieves significant improvements over the compressed sensing and popular deep learning-based methods with less number of trainable parameters.