CT-scan image denoising with Generative Adversarial Networks
Loading...
Links to Files
Permanent Link
Author/Creator
Author/Creator ORCID
Date
2020-01-20
Type of Work
Department
Computer Science and Electrical Engineering
Program
Computer Science
Citation of Original Publication
Rights
Distribution Rights granted to UMBC by the author.
This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu
This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu
Abstract
We propose a Generative Adversarial Network (GAN) optimized for noise reduction in CT-scans. The objective of CT scan denoising is to obtain higher quality imagery using a lower radiation exposure to the patient. Recent work in computer vision has shown that the use of Charbonnier distance as a term in the perceptual loss of a GAN can improve the performance of image reconstruction and video super resolution. However, the use of a Charbonnier perceptual distance term has not yet been applied or evaluated for the purpose of CT scan denoising. Our proposed GAN makes use of the Wasserstein distance as an adversarial loss function and our perceptual loss combines Charbonnier distance with pre-trained VGG-19. We evaluate our approach using both simulated Poisson noise, as well as real low-dose CT imagery. Our evaluation on real Low-Dose CT (LDCT) imagery applies published methods for estimating the noise through a uniform medium of Air and/or Soft tissue. We evaluate our CT-denoising GAN by measuring the noise reduction over simulated as well as real Low-Dose CT imagery. Our findings show that the incorporation of the Charbonnier Loss with the VGG-19 network improves the performance of the denoising as measured with Peak Signal-to-noise ratio (PSNR), Structural Similarity Index (SSIM), as well as Air and Soft Tissue noise metrics.