Three-dimensional Bone Image Synthesis with Generative Adversarial Networks
This work addresses data scarcity and privacy issues in medical imaging for researchers and clinicians, though it is incremental as it applies existing GAN methods to a new 3D medical domain.
The authors tackled the problem of limited medical data availability and privacy by using 3D generative adversarial networks (GANs) to generate high-resolution synthetic bone images, achieving efficient training and detailed voxel-based architectures validated on a database of distal radius bone micro-architecture.
Medical image processing has been highlighted as an area where deep learning-based models have the greatest potential. However, in the medical field in particular, problems of data availability and privacy are hampering research progress and thus rapid implementation in clinical routine. The generation of synthetic data not only ensures privacy, but also allows to \textit{draw} new patients with specific characteristics, enabling the development of data-driven models on a much larger scale. This work demonstrates that three-dimensional generative adversarial networks (GANs) can be efficiently trained to generate high-resolution medical volumes with finely detailed voxel-based architectures. In addition, GAN inversion is successfully implemented for the three-dimensional setting and used for extensive research on model interpretability and applications such as image morphing, attribute editing and style mixing. The results are comprehensively validated on a database of three-dimensional HR-pQCT instances representing the bone micro-architecture of the distal radius.