Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction
Abstract
Image reconstruction from computed tomography (CT) measurement is a challenging statistical inverse problem since a high-dimensional conditional distribution needs to be estimated. Based on training data obtained from high-quality reconstructions, we aim to learn a conditional density of images from noisy low-dose CT measurements. To tackle this problem, we propose a hybrid conditional normalizing flow, which integrates the physical model by using the filtered back-projection as conditioner. We evaluate our approach on a low-dose CT benchmark and demonstrate superior performance in terms of structural similarity of our flow-based method compared to other deep learning based approaches.
Cite
@article{arxiv.2006.06270,
title = {Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction},
author = {Alexander Denker and Maximilian Schmidt and Johannes Leuschner and Peter Maass and Jens Behrmann},
journal= {arXiv preprint arXiv:2006.06270},
year = {2020}
}
Comments
Submitted to the ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, Vienna, Austria, 2020