Abstract
Currently generative adversarial networks (GANs) are rarely applied to medical images of large sizes, especially 3D volumes, due to their large computational demand. We propose a novel multi-scale patch-based GAN approach to generate large high resolution 2D and 3D images. Our key idea is to first learn a low-resolution version of the image and then generate patches of successively growing resolutions conditioned on previous scales. In a domain translation use-case scenario, 3D thorax CTs of size 512 3 and thorax X-rays of size 2048 2 are generated and we show that, due to the constant GPU memory demand of our method, arbitrarily large images of high resolution can be generated. Moreover, compared to common patch-based approaches, our multi-resolution scheme enables better image quality and prevents patch artifacts.
Original language | English |
---|---|
Title of host publication | MICCAI 2019: Medical Image Computing and Computer Assisted Intervention – MICCAI 2019 |
Editors | Dinggang Shen, Tianming Liu, Terry M. Peters, Lawrence H. Staib, Caroline Essert, Sean Zhou, Pew-Thian Yap, Ali Khan |
Number of pages | 9 |
Volume | 11769 |
Place of Publication | Cham |
Publisher | Springer Verlag |
Publication date | 10.10.2019 |
Pages | 112-120 |
ISBN (Print) | 978-3-030-32225-0 |
ISBN (Electronic) | 978-3-030-32226-7 |
DOIs | |
Publication status | Published - 10.10.2019 |
Event | 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention - Shenzhen, China Duration: 13.10.2019 → 17.10.2019 Conference number: 232939 |
Research Areas and Centers
- Academic Focus: Biomedical Engineering