This is a collection of Python and MATLAB scripts for loading, pre-processing and reconstructing X-ray CT projection data of 42 walnuts as described in
Henri Der Sarkissian, Felix Lucka, Maureen van Eijnatten, Giulia Colacicco, Sophia Bethany Coban, Kees Joost Batenburg, "A Cone-Beam X-Ray CT Data Collection Designed for Machine Learning", Sci Data 6, 215 (2019) or arXiv:1905.04787 (2019)
Henri Der Sarkissian, Felix Lucka, Maureen van Eijnatten, Giulia Colacicco, Sophia Bethany Coban, Kees Joost Batenburg, "A Cone-Beam X-Ray CT Data Collection Designed for Machine Learning", or arXiv:1905.04787 (2019)
FDKReconstruction.m
andFDKReconstruction.py
compute FDK reconstructions for data from a single source-detector orbit, which leads to high cone angle artifacts.GroundTruthReconstruction.m
andGroundTruthReconstruction.py
compute an iterative reconstructions using the data from all three source-detector orbits, which leads to a reconstruction free of high cone angle artifacts.- The complete data set can be found via the following links: 1-8, 9-16, 17-24, 25-32, 33-37, 38-42.
- All scripts make use of the ASTRA toolbox. For obtaining a comparable scaling of the image intensities between FDK and iterative reconstructions, it is required to use a development version of the ASTRA toolbox more recent than 1.9.0dev.
GroundTruthReconstruction.m
makes use of the SPOT toolbox.
Henri Der Sarkissian (henri.dersarkissian@gmail.com), Felix Lucka (Felix.Lucka@cwi.nl), CWI, Amsterdam