A Review on the Applications of GANs for 3D Medical Image Analysis

Three-dimensional medical images, such as those obtained from MRI scans, offer a comprehensive view that aids in understanding complex shapes and abnormalities better than 2D images, such as X-ray, mammogram, ultrasound, and 2D CT slices. However, MRI machines are often inaccessible in certain regions due to their high cost, space and infrastructure requirements, a lack of skilled technicians, and safety concerns regarding metal implants. A viable alternative is generating 3D images from 2D scans, which can enhance medical analysis and diagnosis and also offer earlier detection of tumors and other abnormalities. This systematic review is focused on Generative Adversarial Networks (GANs) for 3D medical image analysis over the last three years, due to their dominant role in 3D medical imaging, offering unparalleled flexibility and adaptability for volumetric medical data, as compared to other generative models. GANs offer a promising solution by generating high-quality synthetic medical images, even with limited data, improving disease detection and classification. The existing surveys do not offer an up-to-date overview of the use of GANs in 3D medical imaging. This systematic review focuses on advancements in GAN technology for 3D medical imaging, analyzing studies, particularly from the recent years 2022–2025, and exploring applications, datasets, methods, algorithms, challenges, and outcomes. It affords particular focus to the modern GAN architectures, datasets, and codes that can be used for 3D medical imaging tasks, so readers looking to use GANs in their research could use this review to help them design their study. Based on PRISMA standards, five scientific databases were searched, including IEEE, Scopus, PubMed, Google Scholar, and Science Direct. A total of 1530 papers were retrieved on the basis of the inclusion criteria. The exclusion criteria were then applied, and after screening the title, abstract, and full-text volume, a total of 56 papers were extracted from these, which were then carefully studied. An overview of the various datasets that are used in 3D medical imaging is also presented. This paper concludes with a discussion of possible future work in this area.