Retinal-ESRGAN: A Hybrid GAN Model Approach for Retinal Image Super-Resolution Coupled With Reduced Training Time and Computational Resources for Improved Diagnostic Accuracy

Medical Image Super-Resolution has always been a subject of interest in medical image processing. However, super-resolved retinal images are a requisite tool for doctors to properly diagnose and treat ophthalmic diseases. The acquisition of high-quality images is challenging owing to several factors...

Full description

Saved in:
Bibliographic Details
Published inIEEE access Vol. 13; pp. 53366 - 53376
Main Authors Deepthi, K., Shastry, Aditya K.
Format Journal Article
LanguageEnglish
Published IEEE 2025
Subjects
Accuracy
Computational modeling
Convolution
ESRGAN
Feature extraction
Fréchet inception distance
Generative adversarial networks
Generators
high resolution (HR) image
inception score
low resolution (LR) image
Medical diagnostic imaging
PSNR
Retina
retinal image
SRGAN
SSIM
Superresolution
Training
Online AccessGet full text
ISSN2169-3536
2169-3536
DOI10.1109/ACCESS.2025.3553457

Cover

More Information
Summary:Medical Image Super-Resolution has always been a subject of interest in medical image processing. However, super-resolved retinal images are a requisite tool for doctors to properly diagnose and treat ophthalmic diseases. The acquisition of high-quality images is challenging owing to several factors including technical hardware limitations, high cost, operator skills, data compatibility, and maintenance issues. This paper proposes Retinal-ESRGAN, a novel hybrid unsupervised GAN model particularly designed for retinal image super-resolution. The model incorporates architectural modifications with respect to generator and discriminator network using Google Colaboratory and TensorFlow 2.0 facilitating limited resource usage. To address resource constraints, a training strategy involving pausing and resuming in batches is implemented. The experiments conducted have demonstrated Retinal-ESRGAN's potential that achieved an average PSNR of 35.22 dB and SSIM of 0.916, outperforming both SRGAN and ESRGAN showing PSNR metric improvement of 4.8% over SRGAN and 10.5% improvement over ESRGAN. Also, a 5.7% improvement over SRGAN and 22.4% improvement over ESRGAN in SSIM metric, Inception score of 6.02, Fréchet Inception Distance of 25.31 and accuracy of 94.98% utilizing significantly less training time and computational resources.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2025.3553457