Emmanuel Eric Pazo

← Publications

Structure-preserving super-resolution of retinal fundus images via a dual-transformer residual network

Emmanuel Eric Pazo, Salissou Moutari, Fei Gao, Liying Hu, Muhammad Usama, Xiaorong Li, Juping Liu

Frontiers in Medicine, 2026 · article · doi:10.3389/fmed.2025.1730678 · cited by 8 · Open access (CC BY)

Retina & vascular imagingAI & deep learning

Abstract

High-resolution retinal fundus images are critical for diagnosing diabetic retinopathy, yet clinical datasets often contain low-resolution images that obscure fine vascular structures essential for accurate diagnosis. Existing super-resolution methods face a fundamental trade-off: convolutional neural networks produce overly smooth results, while generative adversarial networks (GANs) risk creating hallucinated artifacts. We propose the Dual-Transformer Residual Super-Resolution Network (DTRSRN), a hybrid architecture combining Swin Transformers for global context modeling with a parallel residual Convolutional Neural Network (CNN) pathway for fine-grained vascular detail preservation. Our key innovation lies in using Fractal Dimension analysis to quantitatively measure retinal vascular morphology preservation. Experimental results on three benchmark datasets demonstrate that DTRSRN achieves 33.64 dB PSNR for 2 × super-resolution, out performing state-of-the-art methods including SwinIR (+0.96 dB), HAT (+0.37 dB), and ResShift (+0.30 dB). Critically, DTRSRN achieves 17.0% improvement in vascular structure preservation (Δ D f = 0.0987) compared to the best baseline, demonstrating superior clinical relevance for retinal image enhancement.

Keywords: diabetic retinopathy; Swin Transformer; residual convolutional neural network; CNN-Transformer hybrid; fractal dimension

Access

How to cite

Pazo, E. E., Moutari, S., Gao, F., Hu, L., Usama, M., Li, X., Liu, J. (2026). Structure-preserving super-resolution of retinal fundus images via a dual-transformer residual network. Frontiers in Medicine. https://doi.org/10.3389/fmed.2025.1730678

@article{pazo2026structure,
  title = {{Structure-preserving super-resolution of retinal fundus images via a dual-transformer residual network}},
  author = {Pazo, Emmanuel Eric and Moutari, Salissou and Gao, Fei and Hu, Liying and Usama, Muhammad and Li, Xiaorong and Liu, Juping},
  journal = {Frontiers in Medicine},
  year = {2026},
  doi = {10.3389/fmed.2025.1730678},
  url = {https://doi.org/10.3389/fmed.2025.1730678},
}

Related work