Enhancing Diabetic Retinopathy Classification Accuracy through Dual Attention Mechanism in Deep Learning

2025-07-25

AI Summary

To address the degraded generalization of deep models caused by severe class imbalance in automated diabetic retinopathy (DR) classification, this paper proposes a dual-attention fusion framework. Specifically, we integrate a Global Attention Block (GAB) and a Class-wise Attention Block (CAB) into lightweight backbones—including MobileNetV3-small, EfficientNet-b0, and DenseNet-169—to jointly model spatial and class-level discriminative features, thereby mitigating long-tail distribution bias. The framework achieves high parameter efficiency (e.g., only 0.90M parameters for MobileNetV3-small) and computational efficiency. Evaluated on APOTOS and EyePACS datasets, it attains an average accuracy of 83.2%, an F1-score of 82.0%, and a specificity of 95.5%, matching state-of-the-art performance. This work establishes a new paradigm for clinical DR screening that balances accuracy, inference efficiency, and robustness under imbalanced data conditions.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Automatic classification of Diabetic Retinopathy (DR) can assist ophthalmologists in devising personalized treatment plans, making it a critical component of clinical practice. However, imbalanced data distribution in the dataset becomes a bottleneck in the generalization of deep learning models trained for DR classification. In this work, we combine global attention block (GAB) and category attention block (CAB) into the deep learning model, thus effectively overcoming the imbalanced data distribution problem in DR classification. Our proposed approach is based on an attention mechanism-based deep learning model that employs three pre-trained networks, namely, MobileNetV3-small, Efficientnet-b0, and DenseNet-169 as the backbone architecture. We evaluate the proposed method on two publicly available datasets of retinal fundoscopy images for DR. Experimental results show that on the APTOS dataset, the DenseNet-169 yielded 83.20% mean accuracy, followed by the MobileNetV3-small and EfficientNet-b0, which yielded 82% and 80% accuracies, respectively. On the EYEPACS dataset, the EfficientNet-b0 yielded a mean accuracy of 80%, while the DenseNet-169 and MobileNetV3-small yielded 75.43% and 76.68% accuracies, respectively. In addition, we also compute the F1-score of 82.0%, precision of 82.1%, sensitivity of 83.0%, specificity of 95.5%, and a kappa score of 88.2% for the experiments. Moreover, in our work, the MobileNetV3-small has 1.6 million parameters on the APTOS dataset and 0.90 million parameters on the EYEPACS dataset, which is comparatively less than other methods. The proposed approach achieves competitive performance that is at par with recently reported works on DR classification.

Problem

• Overcoming imbalanced data in diabetic retinopathy classification
• Improving DR classification accuracy with dual attention mechanisms
• Evaluating deep learning models on public retinal fundoscopy datasets

Innovation

• Dual attention mechanism enhances DR classification
• Pre-trained networks as backbone architecture
• Competitive performance with fewer parameters