An Application of Generative Adversarial Networks for Super Resolution Medical Imaging
Abstract
Acquiring High Resolution (HR) Magnetic Resonance (MR) images requires the patient to remain still for long periods of time, which causes patient discomfort and increases the probability of motion induced image artifacts. A possible solution is to acquire low resolution (LR) images and to process them with the Super Resolution Generative Adversarial Network (SRGAN) to create an HR version. Acquiring LR images requires a lower scan time than acquiring HR images, which allows for higher patient comfort and scanner throughput. This work applies SRGAN to MR images of the prostate to improve the in-plane resolution by factors of 4 and 8. The term 'super resolution' in the context of this paper defines the post processing enhancement of medical images as opposed to 'high resolution' which defines native image resolution acquired during the MR acquisition phase. We also compare the SRGAN to three other models: SRCNN, SRResNet, and Sparse Representation. While the SRGAN results do not have the best Peak Signal to Noise Ratio (PSNR) or Structural Similarity (SSIM) metrics, they are the visually most similar to the original HR images, as portrayed by the Mean Opinion Score (MOS) results.
Keywords
Cite
@article{arxiv.1912.09507,
title = {An Application of Generative Adversarial Networks for Super Resolution Medical Imaging},
author = {Rewa Sood and Binit Topiwala and Karthik Choutagunta and Rohit Sood and Mirabela Rusu},
journal= {arXiv preprint arXiv:1912.09507},
year = {2019}
}
Comments
International Conference on Machine Learning Applications, 6 pages, 5 figures, 2 tables