DIABETIC RETINOPATHY DETECTION AND RETINAL FEATURE OPTIMIZATION USING MACHINE LEARNING WITH INTELLIGENT CLASSIFICATION APPROACH
Keywords:
Diabetic Retinopathy, Machine Learning, Retinal Fundus Images, Image Preprocessing, Feature Selection, Classification, APTOS 2019 Dataset, Deep Feature Extraction, CLAHE Enhancement, Automated Disease Detection, Medical Image Analysis, Intelligent Diagnosis.Abstract
Diabetic retinopathy is a chronic eye disease that results from long-term diabetes and damages the blood
vessels in the retina which can cause vision loss if caught early enough. To detect this disease, retinal fundus
imaging is used and machine learning methods are used to analyse and classify the disease based on its severity.
In most cases, the overall process can be broken down into image acquisition, image preprocessing, feature
extraction, and classification, but traditional methods frequently suffer from image quality issues, noise, and the
inability to efficiently select the optimal features, all of which can compromise the accuracy and dependability of
classification. To address these issues, the proposed model uses the APTOS 2019 Blindness Detection dataset that
consists of labelled retinal images divided into 5 different stages of diabetic retinopathy. The proposed framework
has a structured workflow that enhances the image quality by removing the noise, resizing and enhancing the
contrast of the image, and then select the most relevant features of the retina using the Optimized Machine
Learning Feature Selection Algorithm (OMLFSA) for identification and selection. Intelligent Diabetic
Retinopathy Classification Algorithm (IDRCA) is the final classification process which is based on a machine
learning classification model that classifies the severity of DR. This holistic method will increase sensitivity of
detection and better diabetic retinopathy classification.
Downloads
References
1) Banerjee, Tathagat, Davinder Paul Singh, and Pawandeep Kour. "Advances in deep neural,
transformer learning, and kernel-based methods for diabetic retinopathy detection: a
comprehensive review." Archives of Computational Methods in Engineering (2025): 1-49.
2) Singh, Davinder Paul, et al. "A comprehensive study on deep learning models for the detection
of diabetic retinopathy using pathological images." Archives of Computational Methods in
Engineering 33.1 (2026): 503-532.
3) Ran, An Ran, et al. "Real-world prospective validation and economic evaluation of deep
learning–based diabetic retinopathy detection from fundus photographs: a systematic review
and meta-analysis." Diabetes Care 49.3 (2026): 510-525.
4) Akram, Mohsin, et al. "Uncertainty-aware diabetic retinopathy detection using deep learning
enhanced by Bayesian approaches." Scientific Reports 15.1 (2025): 1342.
5) Muthusamy, Dharmalingam, and Parimala Palani. "Deep neural network model for diagnosing
diabetic retinopathy detection: An efficient mechanism for diabetic management." Biomedical
Signal Processing and Control 100 (2025): 107035.
6) Abbasi, Rashid, et al. "Diabetic retinopathy detection using adaptive deep convolutional neural
networks on fundus images." Scientific Reports 15.1 (2025): 24647.
7) Rahat, SK Rakib Ul Islam, et al. "Advancing diabetic retinopathy detection with AI and deep
learning: Opportunities, limitations, and clinical barriers." British journal of nursing studies 5.2
(2025): 01-13.
8) Alanazi, Saad, and Rayan Alanazi. "Enhancing diabetic retinopathy detection through federated
convolutional neural networks: Exploring different stages of progression." Alexandria
Engineering Journal 120 (2025): 215-228.
9) Guefrachi, Sarra, Amira Echtioui, and Habib Hamam. "Diabetic retinopathy detection using
deep learning multistage training method." Arabian Journal for Science and Engineering 50.2
(2025): 1079-1096.
10) Mutawa, A. M., et al. "Randomization-Driven hybrid deep learning for diabetic retinopathy
Detection." IEEE access 13 (2025): 38901-38913.
11) Zafar, Amad, et al. "A lightweight multi-deep learning framework for accurate diabetic
retinopathy detection and multi-level severity identification." Frontiers in Medicine 12 (2025):
1551315.
12) Dib, Omar. "A decentralized privacy-preserving framework for diabetic retinopathy detection
using federated learning and blockchain." Results in Engineering 26 (2025): 105456.
13) Gencer, Kerem, et al. "Photodiagnosis with deep learning: A GAN and autoencoder-based
approach for diabetic retinopathy detection." Photodiagnosis and Photodynamic Therapy 53
(2025): 104552.
14) Ainapur, Santoshkumar S. "Automated diabetic retinopathy detection using a multi-step
framework with stacked ensemble-based classification model." Expert Systems with
Applications 284 (2025): 127709.
15) Sushith, Mishmala, et al. "Attention dual transformer with adaptive temporal convolutional for
diabetic retinopathy detection." Scientific Reports 15.1 (2025): 7694.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
