In computed tomographic imaging, model based iterative reconstruction methods have generally shown better image quality than the more traditional, faster filtered backprojection technique. The cost we have to pay is that MBIR is computationally expensive. In this work we train a 2.5D deep learning (DL) network to mimic MBIR quality image. The network is realized by a modified Unet, and trained using clinical FBP and MBIR image pairs. We achieve the quality of MBIR images faster and with a much smaller computation cost. Visually and in terms of noise power spectrum (NPS), DL-MBIR images have texture similar to that of MBIR, with reduced noise power. Image profile plots, NPS plots, standard deviation, etc. suggest that the DL-MBIR images result from a successful emulation of an MBIR operator.
@article{arxiv.2309.13399,
title = {MBIR Training for a 2.5D DL network in X-ray CT},
author = {Obaidullah Rahman and Madhuri Nagare and Ken D. Sauer and Charles A. Bouman and Roman Melnyk and Brian Nett and Jie Tang},
journal= {arXiv preprint arXiv:2309.13399},
year = {2023}
}