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.

翻译：医学图像处理已被认为是深度学习模型最具潜力的应用领域之一。然而，在医学领域，数据可用性和隐私问题尤其阻碍了研究进展及临床常规应用的快速推广。合成数据的生成不仅能确保隐私保护，还可以"绘制"具有特定特征的新患者数据，从而支持更大规模的数据驱动模型开发。本研究证明了三维生成对抗网络可以高效训练，生成具有精细体素结构的高分辨率医学体数据。此外，成功实现了面向三维场景的GAN逆映射，并将其用于模型可解释性及图像变形、属性编辑、风格混合等应用的深入研究。基于表征桡骨远端骨微结构的三维HR-pQCT实例数据库，研究结果得到了全面验证。