Over the last years, deep learning methods have become an increasingly popular choice to solve tasks from the field of inverse problems. Many of these new data-driven methods have produced impressive results, although most only give point estimates for the reconstruction. However, especially in the analysis of ill-posed inverse problems, the study of uncertainties is essential. In our work, we apply generative flow-based models based on invertible neural networks to two challenging medical imaging tasks, i.e. low-dose computed tomography and accelerated medical resonance imaging. We test different architectures of invertible neural networks and provide extensive ablation studies. In most applications, a standard Gaussian is used as the base distribution for a flow-based model. Our results show that the choice of a radial distribution can improve the quality of reconstructions.
@article{arxiv.2110.14520,
title = {Conditional Invertible Neural Networks for Medical Imaging},
author = {Alexander Denker and Maximilian Schmidt and Johannes Leuschner and Peter Maass},
journal= {arXiv preprint arXiv:2110.14520},
year = {2021}
}