This repository contains code and supplementary material for the article "Quantitative comparison of deep learning-based image reconstruction methods for low-dose and sparse-angle CT applications".
Information on the environment setup can be found in the folder supp_material/environment_details.
Trained network parameters for the experiments on the Apple CT datasets are available from the supplementing zenodo record. Parameters for the LoDoPaB-CT Dataset of those reconstructors implemented in DIVαℓ can be found in the supplementary repository supp.dival.
Saved reconstructions are provided in two separate records: