Enhancing Clinical Decision Support: A Deep Learning Approach for Automated Diagnosis of Eye Diseases from Fundus Images

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Hybrid CNN models enhance accuracy for retinal condition classification, suggesting improvements for clinical decision support.

The hybrid deep learning model improved accuracy and precision for classifying eye diseases.
Performance metrics reached 98.77% for area under the curve on the Kaggle dataset for eye disease classification.
Various CNN architectures were evaluated, with DenseNet169 and MobileNetV1 yielding the best results.
Automated detection of retinal diseases may streamline clinical workflows and enhance patient care.

Iqbal et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Hybrid CNN models enhance accuracy for retinal condition classification, suggesting improvements for clinical decision support.

The hybrid deep learning model improved accuracy and precision for classifying eye diseases.
Performance metrics reached 98.77% for area under the curve on the Kaggle dataset for eye disease classification.
Various CNN architectures were evaluated, with DenseNet169 and MobileNetV1 yielding the best results.
Automated detection of retinal diseases may streamline clinical workflows and enhance patient care.

Iqbal et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark