Software

MSDNet

Python implementation of the Mixed-Scale Dense Convolutional Neural Network, as published in:

The ASTRA Toolbox

The ASTRA Toolbox is a MATLAB and Python toolbox of high-performance GPU primitives for 2D and 3D tomography. My contribution to ASTRA is mostly the addition of a Python interface to the toolbox and the addition of a plugin system for new reconstruction algorithms.

TomoPy

TomoPy is an open-sourced Python toolbox to perform tomographic data processing and image reconstruction of tomographic synchrotron data. My contribution to TomoPy was to add the ability to reconstruct using the ASTRA toolbox within TomoPy.

SIRT-FILTER

Python package to compute filters and use SIRT-FBP for tomographic reconstruction, as published in:

PyMR-FBP

PyMR-FBP is a Python implementation of the MR-FBP tomographic reconstruction method, published in:

Pelt, D. M., & Batenburg, K. J. (2014). Improving Filtered Backprojection Reconstruction by Data-Dependent Filtering. Image Processing, IEEE Transactions on, 23(11), pp. 4750-4762. [link]

PyNN-FBP

PyNN-FBP is a Python implementation of the NN-FBP tomographic reconstruction method, published in:

Pelt, D., & Batenburg, K. (2013). Fast tomographic reconstruction from limited data using artificial neural networks. Image Processing, IEEE Transactions on, 22(12), pp.5238-5251. [link]

Mondriaan

Mondriaan is a sequential program to partition sparse matrices and input and output vectors for parallel sparse matrix-vector multiplication. My contribution was adding the medium-grain partitioning method to the program, which is published in:

Pelt, D. M., & Bisseling, R. H. (2014). A medium-grain method for fast 2D bipartitioning of sparse matrices. Proceedings IEEE International Parallel & Distributed Processing Symposium 2014, IEEE Press, pp. 529-539. [link]

PyASTRAToolbox

The PyASTRAToolbox code has been merged with the main ASTRA toolbox code.