English

Arbitrary Scale Super-Resolution for Brain MRI Images

Image and Video Processing 2020-06-05 v2 Computer Vision and Pattern Recognition Machine Learning

Abstract

Recent attempts at Super-Resolution for medical images used deep learning techniques such as Generative Adversarial Networks (GANs) to achieve perceptually realistic single image Super-Resolution. Yet, they are constrained by their inability to generalise to different scale factors. This involves high storage and energy costs as every integer scale factor involves a separate neural network. A recent paper has proposed a novel meta-learning technique that uses a Weight Prediction Network to enable Super-Resolution on arbitrary scale factors using only a single neural network. In this paper, we propose a new network that combines that technique with SRGAN, a state-of-the-art GAN-based architecture, to achieve arbitrary scale, high fidelity Super-Resolution for medical images. By using this network to perform arbitrary scale magnifications on images from the Multimodal Brain Tumor Segmentation Challenge (BraTS) dataset, we demonstrate that it is able to outperform traditional interpolation methods by up to 20%\% on SSIM scores whilst retaining generalisability on brain MRI images. We show that performance across scales is not compromised, and that it is able to achieve competitive results with other state-of-the-art methods such as EDSR whilst being fifty times smaller than them. Combining efficiency, performance, and generalisability, this can hopefully become a new foundation for tackling Super-Resolution on medical images. Check out the webapp here: https://metasrgan.herokuapp.com/ Check out the github tutorial here: https://github.com/pancakewaffles/metasrgan-tutorial

Keywords

Cite

@article{arxiv.2004.02086,
  title  = {Arbitrary Scale Super-Resolution for Brain MRI Images},
  author = {Chuan Tan and Jin Zhu and Pietro Lio'},
  journal= {arXiv preprint arXiv:2004.02086},
  year   = {2020}
}

Comments

12 pages, 8 figures, 1 table, to appear as a full paper with oral contribution in AIAI 2020

R2 v1 2026-06-23T14:39:37.053Z