Recon-GLGAN: A Global-Local Context Based Generative Adversarial Network for MRI Reconstruction

Abstract

Magnetic resonance imaging (MRI) is one of the best medical imaging modalities as it offers excellent spatial resolution and softtissue contrast. But, the usage of MRI is limited by its slow acquisition time, which makes it expensive and causes patient discomfort. In order to accelerate the acquisition, multiple deep learning networks have been proposed. Recently, Generative Adversarial Networks (GANs) have shown promising results in MRI reconstruction. The drawback with the proposed GAN based methods is it does not incorporate the prior information about the end goal which could help in better reconstruction. For instance, in the case of cardiac MRI, the physician would be interested in the heart region which is of diagnostic relevance while excluding the peripheral regions. In this work, we show that incorporating prior information about a region of interest in the model would offer better performance. Thereby, we propose a novel GAN based architecture, Reconstruction Global-Local GAN (Recon-GLGAN) for MRI reconstruction. The proposed model contains a generator and a context discriminator which incorporates global and local contextual information from images. Our model offers significant performance improvement over the baseline models. Our experiments show that the concept of a context discriminator can be extended to existing GAN based reconstruction models to offer better performance. We also demonstrate that the reconstructions from the proposed method give segmentation results similar to fully sampled images.

A review on generative based methods for MRI reconstruction

“…Li et al [25] proposed a Structure-Enhanced GAN, namely SEGAN, which was used to recover the structural information of MRI images in local and global domains. Murugesan et al [26] employed a novel GAN-based architecture for reconstructing MR image. The model consisted of a U-Net generator and a context discriminator that combined global and local context information in the image.…”

“…All of these were end-to-end methods that directly established the mapping between undersampled image and full-sampled real image. With the deep research of these methods, another unrolled optimization method has been proposed [4] [5][6] [7] [8]. The unrolled optimization method iteratively expanded the traditional physically-driven algorithm into a multi-layer data-driven deep neural network, in which some parameters in the traditional iterative algorithm can be learned by the neural network.…”

A Review of the Recent Advances in Ultra-High Field Magnetic Resonance Imaging

“…There is broad interest in the MR research community to use various deep learning techniques to tackle the reconstruction task. These techniques have often outperformed the conventional parallel imaging reconstruction methods [50], [52]- [58]. It is inevitable that, after further extensive validation of these techniques in terms of anatomical fidelity, they will be integrated into the clinical MR systems (e.g.…”

Which GAN? A comparative study of generative adversarial network-based fast MRI reconstruction

“…The loss function consisted of MSE in the image domain, structural similarity index measure (SSIM) and patch correlation regularization terms. Murugesan et al [38] developed a novel GAN-based architecture named Reconstruction Global-Local GAN (Recon-GLGAN). This model was composed of a U-Net generator and a context discriminator, which incorporated global and local contextual information from images.…”