LoDoPaB-CT Challenge Reconstructions compared in "Quantitative comparison of deep learning-based image reconstruction methods for low-dose and sparse-angle CT applications"

Supplementing record containing the LoDoPaB-CT challenge submissions compared in the article "Quantitative comparison of deep learning-based image reconstruction methods for low-dose and sparse-angle CT applications".

Below are references for the included methods.

• cinn: A. Denker et al., 2020, Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction
• diptv: D. Otero Baguer et al., 2020, Computed tomography reconstruction using deep image prior and learned reconstruction methods
  (DIVαℓ implementation)
• fbp: Filtered back-projection
  (ODL implementation)
• fbpistaunet: T. Liu et al., 2020, Interpreting U-Nets via Task-Driven Multiscale Dictionary Learning
  (Implementation by T. Liu)
• fbpmsdnet: D. Pelt et al., 2017, A mixed-scale dense convolutional neural network for image analysis
  (Implementation based on msd_pytorch by A. Hendriksen)
• fbpunet: K. H. Jin et al., 2017, Deep Convolutional Neural Network for Inverse Problems in Imaging
  (DIVαℓ implementation)
• fbpunetpp: Z. Zhou et al., 2018, UNet++: A Nested U-Net Architecture for Medical Image Segmentation
  (Implementation and network weights by A. Hadjifaradji)
• ictnet: D. Bauer et al., 2021, iCTU-Net (submitted, based on iCT-Net)
• learnedpd: J. Adler et al., 2018, Learned Primal-Dual Reconstruction
  (DIVαℓ implementation)
• tv: Total Variation Regularization
  (DIVαℓ implementation)