Triple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy Diagnosis

2025-03-03

AI Summary

Accurate staging of hypertensive retinopathy (HR) is critical for preventing vision loss, yet existing diagnostic approaches suffer from subjectivity and poor generalizability. To address this, we propose a novel three-stage intelligent diagnostic framework: (1) parallel deep feature extraction using DenseNet169, MobileNet, and ResNet152; (2) multi-source feature fusion followed by SVM-based classification; and (3) Harris Hawk Optimization (HHO)—employed here for the first time in ophthalmic deep feature optimization—to perform interpretable and robust deep feature subset selection. This work introduces the first triple-stream collaborative feature learning paradigm specifically designed for multi-stage HR recognition. Evaluated on a standard benchmark dataset, our framework achieves 94.66% accuracy, 94.64% F1-score, and a Cohen’s Kappa of 0.9286—significantly outperforming single-model baselines and state-of-the-art methods—enabling highly accurate automated four-stage HR classification.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Hypertensive retinopathy (HR) is a severe eye disease that may cause permanent vision loss if not diagnosed early. Traditional diagnostic methods are time-consuming and subjective, highlighting the need for an automated, reliable system. Existing studies often use a single Deep Learning (DL) model, struggling to distinguish HR stages. This study introduces a three-stage approach to enhance HR diagnosis accuracy. Initially, 14 CNN models were tested, identifying DenseNet169, MobileNet, and ResNet152 as the most effective. DenseNet169 achieved 87.73% accuracy, 87.75% precision, 87.73% recall, 87.67% F1-score, and 0.8359 Cohen's Kappa. MobileNet followed with 86.40% accuracy, 86.60% precision, 86.40% recall, 86.31% F1-score, and 0.8180 Cohen's Kappa. ResNet152 ranked third with 85.87% accuracy, 86.01% precision, 85.87% recall, 85.83% F1-score, and 0.8188 Cohen's Kappa. In the second stage, deep features from these models were fused and classified using Machine Learning (ML) algorithms (SVM, RF, XGBoost). SVM (sigmoid kernel) performed best with 92.00% accuracy, 91.93% precision, 92.00% recall, 91.91% F1-score, and 0.8930 Cohen's Kappa. The third stage applied meta-heuristic optimization (GA, ABC, PSO, HHO) for feature selection. HHO yielded 94.66% accuracy, precision, and recall, 94.64% F1-score, and 0.9286 Cohen's Kappa. The proposed approach surpassed single CNN models and previous studies in HR diagnosis accuracy and generalization.

Problem

• Automated diagnosis of hypertensive retinopathy stages.
• Improving accuracy using triple-stream deep feature fusion.
• Enhancing feature selection with metaheuristic optimization techniques.

Innovation

• Triple-stream deep feature fusion enhances accuracy.
• Metaheuristic optimization optimizes feature selection effectively.
• Machine learning algorithms classify fused features precisely.