Single MR Image Super-Resolution using Generative Adversarial Network

Shawkh Ibne Rashid; Elham Shakibapour; Mehran Ebrahimi

Single MR Image Super-Resolution using Generative Adversarial Network

Image and Video Processing 2022-07-19 v1 Computer Vision and Pattern Recognition Machine Learning

Authors: Shawkh Ibne Rashid , Elham Shakibapour , Mehran Ebrahimi

Abstract

Spatial resolution of medical images can be improved using super-resolution methods. Real Enhanced Super Resolution Generative Adversarial Network (Real-ESRGAN) is one of the recent effective approaches utilized to produce higher resolution images, given input images of lower resolution. In this paper, we apply this method to enhance the spatial resolution of 2D MR images. In our proposed approach, we slightly modify the structure of the Real-ESRGAN to train 2D Magnetic Resonance images (MRI) taken from the Brain Tumor Segmentation Challenge (BraTS) 2018 dataset. The obtained results are validated qualitatively and quantitatively by computing SSIM (Structural Similarity Index Measure), NRMSE (Normalized Root Mean Square Error), MAE (Mean Absolute Error), and VIF (Visual Information Fidelity) values.

Keywords

generative adversarial networks image super-resolution medical image generation and analysis

Cite

@article{arxiv.2207.08036,
  title  = {Single MR Image Super-Resolution using Generative Adversarial Network},
  author = {Shawkh Ibne Rashid and Elham Shakibapour and Mehran Ebrahimi},
  journal= {arXiv preprint arXiv:2207.08036},
  year   = {2022}
}

Comments

To be published in the Proceedings of the International Conference E-Health 2022 (part of MCCSIS 2022), July 2022

Single MR Image Super-Resolution using Generative Adversarial Network

Abstract

Keywords

Cite

Comments

Related papers