Johannes Bereiter-Payr
Research Subjects
Johannes Bereiter-Payr has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Christoph Angermann
Department of Mathematics, University of Innsbruck, Innsbruck, Austria
1 shared publication - Gerald Degenhart
Department of Radiology, Medical University of Innsbruck, Innsbruck, Austria
1 shared publication - Kerstin Stock
University Hospital for Orthopaedics and Traumatology, Innsbruck Medical University, Innsbruck, Austria
1 shared publication - Markus Haltmeier
Universität Innsbruck
1 shared publication
Latest Publications
- Open Access
- 11 December 2024
- Published by MDPI AG in Journal of Imaging
- Vol. 10 (12) , 318
Three-Dimensional Bone-Image Synthesis with Generative Adversarial Networks
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.
- 11 December 2024
- Published by MDPI AG in Journal of Imaging
- Vol. 10 (12) , 318
Open AccessThree-Dimensional Bone-Image Synthesis with Generative Adversarial Networks
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.