Convolutional Neural Network Model for Diabetic Retinopathy Feature Extraction and Classification

Artificial intelligence for diabetic retinopathy screening in Africa

Diabetic retinopathy (DR) is a serious complication of diabetes that can result in vision loss if untreated, often progressing silently without warning symptoms. Elevated blood glucose levels damage the retina's microvasculature, initiating the condition. Early detection through retinal fundus imaging, supported by timely analysis and treatment, is critical for managing DR effectively. However, manually inspecting these images is a labour-intensive and time-consuming process, making computer-aided diagnosis (CAD) systems invaluable in supporting ophthalmologists. This research introduces the Fundus Imaging Diabetic Retinopathy Classification using Deep Learning and Fennec Fox Optimization (FIDRC-DLFFO) model, which automates the identification and classification of DR. The model integrates several advanced techniques to enhance performance and accuracy.1.The proposed FIDRC-DLFFO model automates DR detection and classification by combining median filtering for noise reduction, Inception-ResNet-v2 for feature extraction, and a gated recurrent unit (GRU) for classification.2.Fennec Fox Optimization (FFO) fine-tunes the GRU hyperparameters, boosting classification accuracy, with its effectiveness demonstrated on benchmark datasets.3.The results provide insights into the model's effectiveness and potential for real-world application.

Diabetic Retinopathy (DR) is one of the severe microvascular conditions that affect the retina of the eye. It can result in permanent partial or total blindness if not discovered and treated early. Across the world, diabetes impacts in excess of 50% of people below 70 years of age. Many diabetic people, however, fail to notice the disease and suffer visual impairments as a result of the time it takes to see an ophthalmologist who screens and analyses the patient's retina. This research study focuses on the automated detection and categorization of DR based on distinct severity levels using fundus images. The method starts with a pre-processing step to get rid of any extraneous noise from the edges and aids in the focus on the area of interest. The DR fundus images were then categorized into various severity levels using DL models like VGG19, ResNet50, and Inception-V3 Deep Learning (DL) models. The logic for the presented DL model has been tested on the EyePACS (kaggle) DR dataset. In terms of classification accuracy, the suggested DL model with ResNet50 configuration surpassed other models such as VGG19 and Inception-V3 as well as other current models, according to the findings of the research.

Diabetic Retinopathy (DR) has become a widespread illness among diabetics across the globe. Retinal fundus images are generally used by physicians to detect and classify the stages of DR. Since manual examination of DR images is a time-consuming process with the risks of biased results, automated tools using Artificial Intelligence (AI) to diagnose the disease have become essential. In this view, the current study develops an Optimal Deep Learning-enabled Fusion-based Diabetic Retinopathy Detection and Classification (ODL-FDRDC) technique. The intention of the proposed ODL-FDRDC technique is to identify DR and categorize its different grades using retinal fundus images. In addition, ODL-FDRDC technique involves region growing segmentation technique to determine the infected regions. Moreover, the fusion of two DL models namely, CapsNet and MobileNet is used for feature extraction. Further, the hyperparameter tuning of these models is also performed via Coyote Optimization Algorithm (COA). Gated Recurrent Unit (GRU) is also utilized to identify DR. The experimental results of the analysis, accomplished by ODL-FDRDC technique against benchmark DR dataset, established the supremacy of the technique over existing methodologies under different measures.

Purpose: To develop a new domain generalization (DG) framework for diabetic retinopathy (DR) classification using Vision Transformers (VTs). Methods: A deep-learning-based prediction-softening mechanism has been used to allow self-distillation, whereby the knowledge extracted is transferred to intermediate layers. Intermediate representations are further improved with an adaptive convex combination of one-hot labels and internal predictions of the model, which helps regularize the network and counteract overfitting. Various publicly available DR datasets, such as APTOS and EYEPACS, in multi-source and single-source DG settings containing three VT backbones (DeiT, T2T-VT, and CvT) were used. Results: The proposed framework outperforms current DG methods, with better top-1 accuracy, strong calibration and predictive accuracy in unfamiliar domains. Conclusion: The Softening Predictions for Self-Distillation (SPSD)-VT framework is a robust, reliable, and generalizable framework that classifies DR and underscores the important role that domain generalization plays in medical imaging and sets a standard for future studies.

Diabetic retinopathy, a retinal disorder resulting from diabetes mellitus, is a prominent cause of visual degradation and loss among the global population. Therefore, the identification and classification of diabetic retinopathy are of utmost importance in the clinical diagnosis and therapy. Currently, these duties are extensively carried out by manual examination utilizing the human visual system. Nevertheless, manual examination is sometimes arduous, time-consuming, and prone to errors. Deep learning-based methods have recently demonstrated encouraging results in several areas, such as image categorization and natural language mining. The majority of deep learning techniques developed for medical image analysis rely on convolutional modules to extract the inherent structure of images within a certain local receptive field. Furthermore, transformer-based models have been utilized to tackle medical image processing problems by capitalizing on global connections among distant pixels in the images. Considering these analyses, this work presents a comprehensive deep learning model that combines convolutional neural network and vision mamba models. This model is designed to accurately identify and classify diabetic retinopathy lesions displayed in fundus images. Furthermore, the vision mamba component incorporates the bidirectional state space method and positional embedding to enable the location sensitivity of visual data samples and meet the conditions for global relationship context. An evaluation of the suggested method was carried out by comparison experiments between state-of-the-art algorithms and the proposed methodology. Empirical findings demonstrate that the suggested methodology surpasses the most advanced algorithms on the datasets that are accessible openly. Hence, the suggested approach may be regarded as a helpful tool for therapeutic processes.

Diabetic Retinopathy (DR) is a progressive eye disease that can lead to vision loss and blindness if left untreated. Ophthalmologists diagnose DR using medical imaging modalities such as fundus photography and optical coherence tomography (OCT); however, manual interpretation of these images is time-consuming and subject to inter-observer variability. While DR is irreversible, vision loss can be prevented through early detection and timely intervention. Regular eye examinations and systematic DR monitoring are essential for preventing blindness in diabetic patients. Therefore, there is an urgent need for computer-assisted diagnosis (CAD) systems to support ophthalmologists in detecting and grading DR accurately and efficiently. This paper proposes a novel CAD system for automated DR classification. The proposed methodology consists of three stages: (1) image preprocessing through grayscale conversion and resizing, (2) retinal vessel segmentation using a local thresholding approach, and (3) classification using a hybrid architecture that integrates a Convolutional Neural Network (CNN) with a Support Vector Machine (SVM) classifier. The proposed model, OptiCNN (Optimized CNN), aligns its predictions with the International Clinical Diabetic Retinopathy (ICDR) severity scale. Experimental results demonstrate that OptiCNN achieves an accuracy of 94%, precision of 96%, recall of 91%, F1-score of 93%, and area under the curve (AUC) of 92% on benchmark datasets. The proposed system provides reliable DR staging to assist ophthalmologists in treatment planning and clinical decision-making, potentially reducing diagnostic workload while maintaining high diagnostic accuracy.

BackgroundAccurate segmentation of the foveal avascular zone (FAZ) is valuable for retinal imaging, as FAZ alterations are key biomarkers for diabetic retinopathy (DR). This study presents an automated framework exploring the feasibility of FAZ segmentation and DR classification using optical coherence tomography angiography (OCTA) images.MethodsIn this cross-sectional study conducted at Farabi Eye Hospital, Tehran, Iran, a two-step deep learning pipeline was developed. First, a neural network combining DeepLabv3+, EfficientNetB0, Squeeze-and-Excitation (SE) blocks, and Atrous Spatial Pyramid Pooling (ASPP) was trained to segment the FAZ from superficial capillary plexus (SCP) and deep capillary plexus (DCP) OCTA slabs. Second, a GoogLeNet-based convolutional neural network (CNN) classified segmented FAZ images into binary (normal vs. DR) and three-class (normal, non-proliferative DR [NPDR], proliferative DR [PDR]) categories to differentiate DR stages based on FAZ shape characteristics. For the classification task using the deep learning-generated segmented FAZ images as input, the data was split into 70% training, 10% validation, and 20% testing, with 5-fold cross-validation to mitigate overfitting. Data augmentation and Synthetic Minority Oversampling Technique (SMOTE) were applied to improve classification performance.ResultsThe final dataset comprised 253 OCTA scans (126 SCP, 127 DCP) from 161 eyes of 161 participants (one eye per participant), with 39 normal participants (24.2%), 78 patients with NPDR (48.4%), and 44 with PDR (27.3%). The mean age was 49.7 ± 11.8 years, and 54% were male. The FAZ segmentation network achieved a Dice similarity coefficient (DSC) of 97.5% across the dataset, achieving high precision even in challenging images. The classification model, using the deep learning generated segmented FAZ images as input, reached an area under the curve (AUC) of 100% for binary classification (normal vs. DR) and 87% for three-class classification (normal, NPDR, PDR) with oversampling.ConclusionThis system, with its potential for integrating into clinical workflows, offers a promising assistive tool for clinicians, which could enable earlier and more accurate diagnosis of diabetic retinopathy from OCTA images.Clinical trial numberNot applicable.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12886-025-04473-2.

Chapter 3 - Classification of Diabetic Retinopathy

Automatic Detection and Classification of Diabetic Retinopathy from Retinal Fundus Images by Abdullah Biran, Master of Applied Science, lectrical and computer engineering Department, Ryerson University, 2017. Diabetic Retinopathy (DR) is an eye disease that leads to blindness when it progresses to proliferative level. The earliest signs of DR are the appearance of red and yellow lesions on the retina called hemorrhages and exudates. Early diagnosis of DR prevents from blindness. In this thesis, an automatic algorithm for detecting diabetic retinopathy is presented. The algorithm is based on combination of several image processing techniques including Circular Hough Transform (CHT), Contrast Limited Adaptive Histogram Equalization (CLAHE), Gabor filter and thresholding. In addition, Support Vector Machine (SVM) classifier is used to classify retinal images into normal or abnormal cases of DR including non-proliferative (NPDR) or proliferative diabetic retinopathy (PDR). The proposed method has been tested on fundus images from Standard Diabetic Retinopathy Database (DIARETDB). The implementation of the presented methodology was done in MATLAB. The methodology is tested for sensitivity and accuracy.

Diabetic retinopathy is one of the leading disabling chronic diseases, and one of the leading causes of preventable blindness in the world. Early diagnosis of diabetic retinopathy enables timely treatment and in order to achieve it a major effort will have to be invested into screening programs and especially into automated screening programs. For automated screening programs to work robustly a representative fundus image database is required. In this paper we give an overview of currently available databases and present a new diabetic retinopathy database. Our database is to our knowledge the first and only database which has diabetic retinopathy pathologies and major fundus structures annotated for every image from the database which makes it perfect for design and evaluation of currently available and new image processing algorithms for early detection of diabetic retinopathy using color fundus images.

Diabetic retinopathy (DR) is one of the most threatening complications in diabetic patients, leading to permanent blindness without timely treatment. However, DR screening is not only a time-consuming task that requires experienced ophthalmologists but also easy to produce misdiagnosis. In recent years, deep learning techniques based on convolutional neural networks have attracted increasing research attention in medical image analysis, especially for DR diagnosis. However, dataset labeling is expensive work and it is necessary for existing deep-learning-based DR detection models. For this study, a novel domain adaptation method (multi-model domain adaptation) is developed for unsupervised DR classification in unlabeled retinal images. At the same time, it only exploits discriminative information from multiple source models without access to any data. In detail, we integrate a weight mechanism into the multi-model-based domain adaptation by measuring the importance of each source domain in a novel way, and a weighted pseudo-labeling strategy is attached to the source feature extractors for training the target DR classification model. Extensive experiments are performed on four source datasets (DDR, IDRiD, Messidor, and Messidor-2) to a target domain APTOS 2019, showing that MMDA produces competitive performance for present state-of-the-art methods for DR classification. As a novel DR detection approach, this article presents a new domain adaptation solution for medical image analysis when the source data is unavailable.

Advanced Practices on Detection and Classification of Diabetic Retinopathy from Fundus Images

Diabetic Retinopathy (DR) is one of the leading causes of preventable blindness worldwide, and early detection with precise severity classification is critical to reduce vision loss.Retinal fundus imaging is the most widely used modality for DR screening, but manual diagnosis is time-consuming, subjective, and prone to variability.Existing deep learning methods often suffer from noise sensitivity, overfitting, and limited ability to classify across all severity levels, which reduces their clinical applicability in large-scale screening.To address these limitations, this work is motivated by the need for an automated, accurate, and robust DR detection framework that can effectively support ophthalmologists in timely intervention.The novelty of this study lies in the development of a Fuzzy-Embedded Recurrent Neural Network (FERNN) combined with a Bilinear Double-Order Filter (BDOF).The BDOF enhances fundus image clarity by suppressing noise while preserving fine retinal details, and FERNN integrates fuzzy logic with recurrent learning to manage uncertainty and capture sequential dependencies in retinal features capabilities not achieved by conventional CNN or hybrid models.Using the Indian Diabetic Retinopathy Image Database (IDRiD), the proposed framework classifies DR into five clinically significant stages, from mild non-proliferative DR to proliferative DR.Experimental results demonstrate that FERNN achieves 89.20% accuracy and 85.44% precision, outperforming advanced baselines such as hybrid Inception-ResNet, DCGAN, and graph neural network models by up to 30.29%.These findings confirm that the proposed FERNN-BDOF framework provides a novel, robust, and scalable solution for automated DR detection, with strong potential for real-world clinical deployment.

At present, it is difficult to determine Foveal Avascular Zone (FAZ) enlargement based on colour fundus images. Fundus image analysis presents several challenges such as high image variability, improper illumination and artifacts. A new approach for grading Diabetic Retinopathy (DR) by analysing FAZ enlargement in colour fundus image has been developed. Investigations show that FAZ area ranges can be used to indicate progression of the disease. The mean accuracy and standard deviation of ranges obtained are 92.2% and 3.22, respectively. This new approach is reliable, accurate and fast compared to the current method based on DR pathologies.