The training data for developing the neural networks for DL sparse-view CT are contained in this repository.All files are compressed with gzip in order to facilate faster downloads.Data are partitioned into four batches, which also facilates downloading of theindividual files. Data are in python numpy's .npy format.After uncompressing with gunzip the .npy files can be read into pythonwith the numpy.load command, yielding single precision floating point arraysof the proper dimensions. Description of data files:Phantom_batch?.npyThese arrays are 1000x512x512.1000 images of pixel dimensions 512x512.These are the true images. FBP128_batch?.npyThese arrays are 1000x512x512.1000 images of pixel dimensions 512x512.These are the FBP reconstructed images from the 128-view sinograms. Sinogram_batch?.npyThese arrays are 1000x128x1024.1000 sinograms of 128 projections over 360 degree scanning onto a 1024-pixel linear detector. There are four batches. Thus 4000 sets of data/image pairs are available for trainingthe neural networks for image reconstruction.The goal is to train a network that accepts the FBP128 image (and/or the 128-view sinogram)to yield an image that is as close as possible to the corresponding Phantom image. The python code metric_script.py was used to score the submissions to DL sparse-view CT. Challenge report is published in Medical Phyiscs: Sidky EY, Pan X. Report on the AAPM deep-learning sparse-view CT grand challenge. Med Phys. 2022; 49: 4935–4943. See link below in Related Works.