DUG-RECON: A Framework for Tomographic Image Reconstruction with Generative Convolutional Networks

(Developped by Sai Sundar Kandarpa)

Tomographic Medical Image Reconstruction involves the mapping from projection space data collected by detectors to images that can be analysed for diagnosis. This work is an attempt to use Deep Learning to entirely perform the task of Reconstruction.

The code is available on Gitlab.


[1] V. S. S. Kandarpa, A. Bousse, D. Benoit, and D. Visvikis, “Dug-recon: A framework for direct image reconstruction using convolutional generative networks,” IEEE Transactions on Radiation and Plasma Medical Sciences, 2020. doi: 10.1109/TRPMS.2020.3033172.

Alexandre Bousse
Associate Professor