A comparative study of machine learning models for automated detection and classification of retinal diseases in Ghana

Abstract

Introduction: Retinal diseases, a significant global health concern, often lead to severe vision impairment and blindness, resulting in substantial functional and social limitations. This study explored a novel goal of developing and comparing the performance of multiple state-of-the-art convolutional neural network (CNN) models for the automated detection and classification of retinal diseases using optical coherence tomography (OCT) images.

Method: The study utilized several models, including DenseNet121, ResNet50, Inception V3, MobileNet, and OCT images obtained from the WATBORG Eye Clinic, to detect and classify multiple retinal diseases such as glaucoma, macular edema, posterior vitreous detachment (PVD), and normal eye cases. The preprocessing techniques employed included data augmentation, resizing, and one-hot encoding. We also used the Gaussian Process-based Bayesian Optimization (GPBBO) approach to fine-tune the hyperparameters. Model performance was evaluated using the F1-Score, precision, recall, and area under the curve (AUC).

Result: All the CNN models evaluated in this study demonstrated a strong capability to detect and classify various retinal diseases with high accuracy. MobileNet achieved the highest accuracy at 96% and AUC of 0.975, closely followed by DenseNet121, which had 95% accuracy and an AUC of 0.963. Inception V3 and ResNet50, while not as high in accuracy, showed potential in specific contexts, with 83% and 79% accuracy, respectively.

Conclusion: These results underscore the potential of advanced CNN models for diagnosing retinal diseases. With the exception of ResNet50, the other CNN models displayed accuracy levels that are comparable to other state-of-the-art deep learning models. Notably, MobileNet and DenseNet121 showed considerable promise for use in clinical settings, enabling healthcare practitioners to make rapid and accurate diagnoses of retinal diseases. Future research should focus on expanding datasets, integrating multi-modal data, exploring hybrid models, and validating these models in clinical environments to further enhance their performance and real-world applicability.

Fig 1. Sample retinal OCT images.

Fig 2. MobileNet ROC Curve per class.

MobileNet ROC Curve for each class performs exceptionally well. It achieves an AUC of 1.00 for glaucoma, macular edema, and PVD, indicating perfect performance. The model also shows higher performance with an AUC of 0.98 for normal eye conditions, indicating its effectiveness in distinguishing between normal and diseased states

Fig 3. Inception V3 ROC Curve per class.

Inception V3 ROC Curve for each class shows impressive results. It achieves an AUC of 1.00 for glaucoma, macular edema, and PVD, indicating perfect performance. The model also demonstrates high performance with an AUC of 0.97 for normal eye conditions, indicating its strong capability in classifying healthy eyes effectively.

Fig 4. DenseNet121 ROC Curve per class.

DenseNet121 ROC Curve for each class shows impressive results. It achieves an AUC of 1.00 for glaucoma, macular edema, and PVD, indicating perfect performance. The model also performs strongly with an AUC of 0.97 for normal eye conditions.

Fig 5. ResNet50 ROC Curve per class.

ResNet50 ROC Curve for each class achieves an AUC of 1.00 for glaucoma and 0.91 for macular edema, indicating strong performance. However, it struggles to identify normal cases (AUC=0.79) and PVD (AUC=0.82).

Fig 6. Model accuracy vs model loss per Epoch for MobileNet.

Fig 7. Model accuracy vs model loss per Epoch for Inception V3.

Fig 8. Model accuracy vs model loss per Epoch for DenseNet121.

Fig 9. Model accuracy vs model loss per Epoch for ResNet50.

Fig 10. Gradcam and saliency map for MobileNet.

Fig 11. Gradcam and saliency map for MobileNet.

Fig 12. Gradcam and saliency map for DenseNet121.

Fig 13. Gradcam and saliency map for DenseNet121.

Fig 14. Gradcam and saliency map for Inception V3.

Fig 15. Grad-cam and saliency map for Inception V3.

Fig 16. Grad-cam and saliency map for ResNet50.

Fig 17. Grad-cam and saliency map for ResNet50.