# How Can We Make GAN Perform Better in Single Medical Image Super-Resolution? A Lesion Focused Multi-Scale Approach

arXiv: https://arxiv.org/abs/1901.03419 · HTML: https://mlsanity.com/paper/1901.03419/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jan 2019.

## Built on by (most cited first, 7 of 7)

- [Anomaly Detection in Additive Manufacturing Processes using Supervised Classification with Imbalanced Sensor Data based on Generative Adversarial Network](https://mlsanity.com/paper/2210.17274/) (2022)
- [Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives](https://mlsanity.com/paper/2105.01800/) (2021)
- [Diverse Image Generation with Diffusion Models and Cross Class Label Learning for Polyp Classification](https://mlsanity.com/paper/2502.05444/) (2025)
- [MIASSR: An Approach for Medical Image Arbitrary Scale Super-Resolution](https://mlsanity.com/paper/2105.10738/) (2021)
- [A residual dense vision transformer for medical image super-resolution with segmentation-based perceptual loss fine-tuning](https://mlsanity.com/paper/2302.11184/) (2023)
- [DCAE-SR: Design of a Denoising Convolutional Autoencoder for reconstructing Electrocardiograms signals at Super Resolution](https://mlsanity.com/paper/2404.15307/) (2024)
- [Virtual Coil Augmentation Technology for MR Coil Extrapolation via Deep Learning](https://mlsanity.com/paper/2201.07540/) (2022)

## Abstract (arXiv)

Single image super-resolution (SISR) is of great importance as a low-level computer vision task. The fast development of Generative Adversarial Network (GAN) based deep learning architectures realises an efficient and effective SISR to boost the spatial resolution of natural images captured by digital cameras. However, the SISR for medical images is still a very challenging problem. This is due to (1) compared to natural images, in general, medical images have lower signal to noise ratios, (2) GAN based models pre-trained on natural images may synthesise unrealistic patterns in medical images which could affect the clinical interpretation and diagnosis, and (3) the vanilla GAN architecture may suffer from unstable training and collapse mode that can also affect the SISR results. In this paper, we propose a novel lesion focused SR (LFSR) method, which incorporates GAN to achieve perceptually realistic SISR results for brain tumour MRI images. More importantly, we test and make comparison using recently developed GAN variations, e.g., Wasserstein GAN (WGAN) and WGAN with Gradient Penalty (WGAN-GP), and propose a novel multi-scale GAN (MS-GAN), to achieve a more stabilised and efficient training and improved perceptual quality of the super-resolved results. Based on both quantitative evaluations and our designed mean opinion score, the proposed LFSR coupled with MS-GAN has performed better in terms of both perceptual quality and efficiency.