3D Brain and Heart Volume Generative Models: A Survey

TL;DR

This survey reviews recent advances in 3D generative models like GANs and autoencoders for medical imaging of the brain and heart, categorizing their applications and outlining future research directions.

Contribution

It introduces a detailed taxonomy of 3D generative models for medical tasks, covering both unconditional and conditional approaches for brain and heart imaging.

Findings

Comprehensive classification of 3D generative models for medical imaging

Analysis of applications such as synthesis, segmentation, and registration

Guidance for future research directions in 3D medical generative modeling

Abstract

Generative models such as generative adversarial networks and autoencoders have gained a great deal of attention in the medical field due to their excellent data generation capability. This paper provides a comprehensive survey of generative models for three-dimensional (3D) volumes, focusing on the brain and heart. A new and elaborate taxonomy of unconditional and conditional generative models is proposed to cover diverse medical tasks for the brain and heart: unconditional synthesis, classification, conditional synthesis, segmentation, denoising, detection, and registration. We provide relevant background, examine each task and also suggest potential future directions. A list of the latest publications will be updated on Github to keep up with the rapid influx of papers at https://github.com/csyanbin/3D-Medical-Generative-Survey.