Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives

Abstract

Magnetic Resonance Imaging (MRI) is a vital component of medical imaging. When compared to other image modalities, it has advantages such as the absence of radiation, superior soft tissue contrast, and complementary multiple sequence information. However, one drawback of MRI is its comparatively slow scanning and reconstruction compared to other image modalities, limiting its usage in some clinical applications when imaging time is critical. Traditional compressive sensing based MRI (CS-MRI) reconstruction can speed up MRI acquisition, but suffers from a long iterative process and noise-induced artefacts. Recently, Deep Neural Networks (DNNs) have been used in sparse MRI reconstruction models to recreate relatively high-quality images from heavily undersampled k -space data, allowing for much faster MRI scanning. However, there are still some hurdles to tackle. For example, directly training DNNs based on L1/L2 distance to the target fully sampled images could result in blurry reconstruction because L1/L2 loss can only enforce overall image or patch similarity and does not take into account local information such as anatomical sharpness. It is also hard to preserve fine image details while maintaining a natural appearance. More recently, Generative Adversarial Networks (GAN) based methods are proposed to solve fast MRI with enhanced image perceptual quality. The encoder obtains a latent space for the undersampling image, and the image is reconstructed by the decoder using the GAN loss. In this chapter, we review the GAN powered fast MRI methods with a comparative study on various anatomical datasets to demonstrate the generalisability and robustness of this kind of fast MRI while providing future perspectives.

Automatic generation of artificial images of leukocytes and leukemic cells using generative adversarial networks (syntheticcellgan)

“…Recently, the manipulation of pixels to reconstruct medical images has been considered, being a topic of interest due to the numerous applications focused on diagnosis powered by classification convolutional neural networks. The work in [29] proposes a comparative study between variants of GANs to reconstruct knee magnetic resonance images, managing to enhance the reconstruction time of an MR. Work in [30] provides the use of GANs to create artificial CT images in lesions of cystic hepatic metastases and hemangiomas.…”

Human Activity Recognition Data Analysis: History, Evolutions, and New Trends

“…The antagonistic generative networks consist of using 2 artificial neural networks and opposing them to each other (that is why they are known as antagonistic) to generate new content or synthetic data that can be passed as real [85]. One of the networks generates and the other works as a "discriminator".…”

Swin Transformer for Fast MRI

“…On top of the CNNs, conditional generative adversarial networks (cGANs) exploited the advantages of deep learning further and proved to enhance the quality of the MR image reconstruction to a large extent [48,49]. Such a competitive network introduced a two-player generator-discriminator training mechanism to competitively improve reconstruction performance by alternatively optimising θ G and θ D of the generator G and the discriminator D, in a general form as:…”