Supplementary Material for Experiments in "Quantitative comparison of deep learning-based image reconstruction methods for low-dose and sparse-angle CT applications"
Lists
Only you see this
Abstract
Supplementing record containing (trained network) parameters of the reconstruction methods on the <em>Apple CT Datasets</em> in the article "Quantitative comparison of deep learning-based image reconstruction methods for low-dose and sparse-angle CT applications". The experiments include 12 different settings: Noise settings: Noise-free, Gaussian noise, Scattering Numbers of angles: 50, 10, 5, 2 For each setting and each method, trained network parameters (or suitable hyper parameters for non-learned methods) are included. Note: Parameters for the <em>LoDoPaB-CT Dataset</em> of those reconstructors implemented in DIVαℓ can be found in the supplementary repository supp.dival. For details, see the article "Quantitative comparison of deep learning-based image reconstruction methods for low-dose and sparse-angle CT applications". See also the supplementary record containing saved test reconstructions and the supplementary repository providing source code. Below are references for the included methods. <code>cinn</code>: A. Denker et al., 2020, Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction <code>fbp</code>: Filtered back-projection (ODL implementation) <code>fbpistaunet</code>: T. Liu et al., 2020, Interpreting U-Nets via Task-Driven Multiscale Dictionary Learning <code>fbpmsdnet</code>: D. Pelt et al., 2017, A mixed-scale dense convolutional neural network for image analysis <code>fbpunet</code>: K. H. Jin et al., 2017, Deep Convolutional Neural Network for Inverse Problems in Imaging <code>ictnet</code>: D. Bauer et al., 2021, iCTU-Net <code>learnedpd</code>: J. Adler et al., 2018, Learned Primal-Dual Reconstruction <code>tv</code>: Total Variation Regularization (DIVαℓ implementation)
BibTeX
@inproceedings{leuschner2021supplementary,
author = {Johannes Leuschner and Maximilian Schmidt and Poulami Somanya Ganguly and Vladyslav Andriiashen and Sophia Bethany Coban and Alexander Denker and Maureen van Eijnatten},
title = {{Supplementary Material for Experiments in "Quantitative comparison of deep learning-based image reconstruction methods for low-dose and sparse-angle CT applications"}},
booktitle = {Zenodo},
year = {2021},
doi = {10.5281/zenodo.4460055},
}Loading related content...