Related Experiment Video
Updated: Jul 12, 2025
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
HDR-EfficientNet: A Classification of Hypertensive and Diabetic Retinopathy Using Optimize EfficientNet Architecture
Qaisar Abbas1, Yassine Daadaa1, Umer Rashid2
1College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi Arabia.
Insights
A new deep learning method, HDR-EfficientNet, efficiently detects hypertensive retinopathy (HR) and diabetic retinopathy (DR) using retinal images. This advanced classifier shows high accuracy, aiding in early diagnosis and blindness prevention.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Hypertensive retinopathy (HR) and diabetic retinopathy (DR) are leading causes of blindness, linked to hypertension and diabetes.
- Current computer-aided detection (CAD) methods for HR and DR often use traditional machine learning, requiring complex image processing and offering limited applications.
- Early identification and assessment of HR are critical for preventing vision loss.
Purpose of the Study:
- To introduce HDR-EfficientNet, a deep learning (DL) model for efficient and accurate detection of hypertensive retinopathy (HR) and diabetic retinopathy (DR).
- To leverage an EfficientNet-V2 architecture with spatial-channel attention and transfer learning for improved classification performance.
- To enhance feature selection capacity through the integration of dense layers.
Main Methods:
- Developed HDR-EfficientNet using an EfficientNet-V2 backbone for end-to-end disease classification.
- Incorporated a spatial-channel attention mechanism to pinpoint retinal damage and differentiate between conditions.
- Utilized transfer learning to address imbalanced datasets and improve model generalization, augmented with dense layers for feature selection.
Main Results:
- Evaluated on over 36,000 augmented retinal fundus images, achieving high performance metrics.
- Demonstrated an average area under the curve (AUC) of 0.98.
- Reported specificity (SP) of 96%, accuracy (ACC) of 98%, and sensitivity (SE) of 95% for HR and DR detection.
Conclusions:
- The HDR-EfficientNet model presents a highly accurate and efficient deep learning-based approach for diagnosing hypertensive retinopathy and diabetic retinopathy.
- The method effectively classifies HR and DR, offering significant support for clinical diagnosis and management.
- This DL approach overcomes limitations of traditional methods, paving the way for improved eye care.
Abstract:
Hypertensive retinopathy (HR) and diabetic retinopathy (DR) are retinal diseases closely associated with high blood pressure. The severity and duration of hypertension directly impact the prevalence of HR. The early identification and assessment of HR are crucial to preventing blindness. Currently, limited computer-aided methods are available for detecting HR and DR. These existing systems rely on traditional machine learning approaches, which require complex image processing techniques and are often limited in their application. To address this challenge, this work introduces a deep learning (DL) method called HDR-EfficientNet, which aims to provide an efficient and accurate approach to identifying various eye-related disorders, including diabetes and hypertensive retinopathy. The proposed method utilizes an EfficientNet-V2 network for end-to-end training focused on disease classification. Additionally, a spatial-channel attention method is incorporated into the approach to enhance its ability to identify specific areas of damage and differentiate between different illnesses. The HDR-EfficientNet model is developed using transfer learning, which helps overcome the challenge of imbalanced sample classes and improves the network's generalization. Dense layers are added to the model structure to enhance the feature selection capacity. The performance of the implemented system is evaluated using a large dataset of over 36,000 augmented retinal fundus images. The results demonstrate promising accuracy, with an average area under the curve (AUC) of 0.98, a specificity (SP) of 96%, an accuracy (ACC) of 98%, and a sensitivity (SE) of 95%. These findings indicate the effectiveness of the suggested HDR-EfficientNet classifier in diagnosing HR and DR. In summary, the HDR-EfficientNet method presents a DL-based approach that offers improved accuracy and efficiency for the detection and classification of HR and DR, providing valuable support in diagnosing and managing these eye-related conditions.
