OPTNet: Optimized Pixel-Transformer Model for Adaptive Retinal Fundus Image Enhancement

Retinal low-quality images present significant challenges for accurate diagnosis and monitoring of eye diseases by obscuring critical anatomical features and reducing analytical precision. This study introduces OPTNet, an optimized pixel-wise transformer model designed to efficiently enhance degrade...

Full description

Saved in:
Bibliographic Details
Main Authors: Faisal Majed Alqahtani, Somaya Adwan, Mohd Yazed Ahmad, Salmah Binti Karman
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11113289/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849223106866970624
author Faisal Majed Alqahtani
Somaya Adwan
Mohd Yazed Ahmad
Salmah Binti Karman
author_facet Faisal Majed Alqahtani
Somaya Adwan
Mohd Yazed Ahmad
Salmah Binti Karman
author_sort Faisal Majed Alqahtani
collection DOAJ
description Retinal low-quality images present significant challenges for accurate diagnosis and monitoring of eye diseases by obscuring critical anatomical features and reducing analytical precision. This study introduces OPTNet, an optimized pixel-wise transformer model designed to efficiently enhance degraded or low-quality retinal images. The proposed approach consists of three main stages: 1) pre-processing to standardize image dimensions and balance color channels, 2) model development, in which a lightweight ANN-based feature extractor learns retinal structures and generates self-measured quality labels, and 3) pixel-level transformation guided by these predicted labels to perform localized enhancement. The performance of OPTNet was evaluated using statistical metrics across various architectures during training and testing, and benchmarked on six public retinal datasets: DRIVE, CHASE-DB1, HRF, DRHAGIS, FIRE, and FIVES. A comprehensive evaluation was conducted using both full-reference and no-reference quality assessment (QA) metrics, supported by qualitative analysis. OPTNet achieved competitive results including a 21.3% improvement in NIQE and 17.8% reduction in BRISQUE compared with existing methods. The final scores included SSIM (0.1925), VIF (0.1911), BIF (1.3018), EME (11.1704), NIQE (4.0730), and BRISQUE (30.3003), indicating perceptual and structural enhancement. Additionally, it effectively preserved brightness and anatomical fidelity while minimizing distortion (CD = 0.4214), blur (0.0889), and artifacts (0.2903). In conclusion, OPTNet outperforms state-of-the-art enhancement techniques by striking a robust balance between quality improvement and artifact suppression, demonstrating its strong potential for integration into clinical ophthalmic diagnostic pipelines.
format Article
id doaj-art-e06e2aa65c734a67806d60b10b18a56c
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e06e2aa65c734a67806d60b10b18a56c2025-08-25T23:12:59ZengIEEEIEEE Access2169-35362025-01-011314541614544110.1109/ACCESS.2025.359604511113289OPTNet: Optimized Pixel-Transformer Model for Adaptive Retinal Fundus Image EnhancementFaisal Majed Alqahtani0https://orcid.org/0009-0004-2676-1825Somaya Adwan1Mohd Yazed Ahmad2https://orcid.org/0000-0002-0674-2609Salmah Binti Karman3https://orcid.org/0000-0002-8635-5368Department of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, MalaysiaDepartment of Electrical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, MalaysiaDepartment of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, MalaysiaDepartment of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, MalaysiaRetinal low-quality images present significant challenges for accurate diagnosis and monitoring of eye diseases by obscuring critical anatomical features and reducing analytical precision. This study introduces OPTNet, an optimized pixel-wise transformer model designed to efficiently enhance degraded or low-quality retinal images. The proposed approach consists of three main stages: 1) pre-processing to standardize image dimensions and balance color channels, 2) model development, in which a lightweight ANN-based feature extractor learns retinal structures and generates self-measured quality labels, and 3) pixel-level transformation guided by these predicted labels to perform localized enhancement. The performance of OPTNet was evaluated using statistical metrics across various architectures during training and testing, and benchmarked on six public retinal datasets: DRIVE, CHASE-DB1, HRF, DRHAGIS, FIRE, and FIVES. A comprehensive evaluation was conducted using both full-reference and no-reference quality assessment (QA) metrics, supported by qualitative analysis. OPTNet achieved competitive results including a 21.3% improvement in NIQE and 17.8% reduction in BRISQUE compared with existing methods. The final scores included SSIM (0.1925), VIF (0.1911), BIF (1.3018), EME (11.1704), NIQE (4.0730), and BRISQUE (30.3003), indicating perceptual and structural enhancement. Additionally, it effectively preserved brightness and anatomical fidelity while minimizing distortion (CD = 0.4214), blur (0.0889), and artifacts (0.2903). In conclusion, OPTNet outperforms state-of-the-art enhancement techniques by striking a robust balance between quality improvement and artifact suppression, demonstrating its strong potential for integration into clinical ophthalmic diagnostic pipelines.https://ieeexplore.ieee.org/document/11113289/Retinal imagelow contrastpixel-transformeradaptive enhancementquantitative metricsvisual assessment
spellingShingle Faisal Majed Alqahtani
Somaya Adwan
Mohd Yazed Ahmad
Salmah Binti Karman
OPTNet: Optimized Pixel-Transformer Model for Adaptive Retinal Fundus Image Enhancement
IEEE Access
Retinal image
low contrast
pixel-transformer
adaptive enhancement
quantitative metrics
visual assessment
title OPTNet: Optimized Pixel-Transformer Model for Adaptive Retinal Fundus Image Enhancement
title_full OPTNet: Optimized Pixel-Transformer Model for Adaptive Retinal Fundus Image Enhancement
title_fullStr OPTNet: Optimized Pixel-Transformer Model for Adaptive Retinal Fundus Image Enhancement
title_full_unstemmed OPTNet: Optimized Pixel-Transformer Model for Adaptive Retinal Fundus Image Enhancement
title_short OPTNet: Optimized Pixel-Transformer Model for Adaptive Retinal Fundus Image Enhancement
title_sort optnet optimized pixel transformer model for adaptive retinal fundus image enhancement
topic Retinal image
low contrast
pixel-transformer
adaptive enhancement
quantitative metrics
visual assessment
url https://ieeexplore.ieee.org/document/11113289/
work_keys_str_mv AT faisalmajedalqahtani optnetoptimizedpixeltransformermodelforadaptiveretinalfundusimageenhancement
AT somayaadwan optnetoptimizedpixeltransformermodelforadaptiveretinalfundusimageenhancement
AT mohdyazedahmad optnetoptimizedpixeltransformermodelforadaptiveretinalfundusimageenhancement
AT salmahbintikarman optnetoptimizedpixeltransformermodelforadaptiveretinalfundusimageenhancement