The role of generative adversarial networks in brain MRI: a scoping review

Abstract

The performance of artificial intelligence (AI) for brain MRI can improve if enough data are made available. Generative adversarial networks (GANs) showed a lot of potential to generate synthetic MRI data that can capture the distribution of real MRI. Besides, GANs are also popular for segmentation, noise removal, and super-resolution of brain MRI images. This scoping review aims to explore how GANs methods are being used on brain MRI data, as reported in the literature. The review describes the different applications of GANs for brain MRI, presents the most commonly used GANs architectures, and summarizes the publicly available brain MRI datasets for advancing the research and development of GANs-based approaches. This review followed the guidelines of PRISMA-ScR to perform the study search and selection. The search was conducted on five popular scientific databases. The screening and selection of studies were performed by two independent reviewers, followed by validation by a third reviewer. Finally, the data were synthesized using a narrative approach. This review included 139 studies out of 789 search results. The most common use case of GANs was the synthesis of brain MRI images for data augmentation. GANs were also used to segment brain tumors and translate healthy images to diseased images or CT to MRI and vice versa. The included studies showed that GANs could enhance the performance of AI methods used on brain MRI imaging data. However, more efforts are needed to transform the GANs-based methods in clinical applications.

Artificial Intelligence and Biosensors in Healthcare and its Clinical Relevance: A Review

“…For MRI images, image synthesis is a method to generate new parametric images or tissue contrasts from a collection of images acquired in the same session. Generative adversarial networks [87] could serve as a data augmentation tool as medical datasets tend to have limited numbers of samples, and they have been used to generate synthetic abnormal MRI images for a brain tumor based on pix2pix [88], [89]. Analysis methods for these data, such as principal component analysis, discrete cosine transforms, auto-regressive methods, and wavelet transforms, can extract time and frequency domain features from the physiological signals [91].…”

Diffusion Models for Medical Image Analysis: A Comprehensive Survey

“…Generative approaches have undergone significant advances in medical imaging over the past few decades. Therefore, there have been numerous survey papers published on deep generative models for medical imaging [29,30,31]. Some of these papers focus on a specific application only, while others concentrate on a specific image modality.…”

Unsupervised Harmonization of Brain Mri Using 3d Cycle Gans and Its Effect on Brain Age Prediction

“…Two broad categories of domain adaptation methods have emerged: (1) adversarial methods that map source data into a site-invariant latent space [1,2,7], where features are optimized for the main task (e.g., disease detection) but also adapted to defeat an adversary that tries to predict which site the data came from; and (2) synthetic methods that also synthesize a new image to appear as if it came from another scanner, often using neural style transfer methods [4,5]. Such reconstruction methods can also be extended to cross-modal data synthesis (e.g., simulating PET or CT scans from MRI) or for image enhancement with super-resolution [3].…”