Angermann Christoph, Bereiter-Payr Johannes, Stock Kerstin, Degenhart Gerald, Haltmeier Markus
VASCage-Centre on Clinical Stroke Research, Adamgasse 23, A-6020 Innsbruck, Austria.
Core Facility Micro-CT, University Clinic for Radiology, Anichstraße 35, A-6020 Innsbruck, Austria.
J Imaging. 2024 Dec 11;10(12):318. doi: 10.3390/jimaging10120318.
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 the drawing of 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.
医学图像处理已成为基于深度学习的模型最具潜力的领域。然而，特别是在医学领域，数据可用性和隐私问题正阻碍着研究进展，从而也阻碍了在临床常规中的快速应用。合成数据的生成不仅能确保隐私，还能生成具有特定特征的新患者数据，从而能够在更大规模上开发数据驱动模型。这项工作表明，三维生成对抗网络（GAN）可以有效地进行训练，以生成具有精细体素架构的高分辨率医学体积数据。此外，GAN反演在三维环境中成功实现，并用于模型可解释性以及图像变形、属性编辑和风格混合等应用的广泛研究。研究结果在一个代表桡骨远端骨微结构的三维高分辨率外周定量计算机断层扫描（HR-pQCT）实例数据库上得到了全面验证。
