Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction
arXiv:2006.06270
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.
Submitted to the ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, Vienna, Austria, 2020
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)
- Density estimation using Real NVP
- fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
- Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?
- Guided Image Generation with Conditional Invertible Neural Networks
- Deep Bayesian Inversion
- i-RevNet: Deep Invertible Networks
- Learning Likelihoods with Conditional Normalizing Flows