Revolutionizing diabetic eye disease detection: retinal image analysis with cutting-edge deep learning techniques

Abstract

Globally, glaucoma is a leading cause of visual impairment and vision loss, emphasizing the critical need for early diagnosis and intervention. This research explores the application of deep learning for automated glaucoma diagnosis using retinal fundus photographs. We introduce a novel cross-sectional optic nerve head (ONH) feature derived from optical coherence tomography (OCT) images to enhance existing diagnostic procedures. Our approach leverages deep learning to automatically detect key optic disc characteristics, eliminating the need for manual feature engineering. The deep learning classifier then categorizes images as normal or abnormal, streamlining the diagnostic process. Deep learning techniques have proven effective in classifying and segmenting retinal fundus images, enabling the analysis of a growing number of images. This study introduces a novel mixed loss function that combines the strengths of focal loss and correntropy loss to handle complex biomedical data with class imbalance and outliers, particularly in OCT images. We further refine a multi-task deep learning model that capitalizes on similarities across major eye-fundus activities and metrics for glaucoma detection. The model is rigorously evaluated on a real-world ophthalmic dataset, achieving impressive accuracy, specificity, and sensitivity of 100%, 99.8%, and 99.2%, respectively, surpassing state-of-the-art methods. These promising results underscore the potential of our deep learning algorithm for automated glaucoma diagnosis, with significant implications for clinical applications. By simultaneously addressing segmentation and classification challenges, our approach demonstrates its effectiveness in accurately identifying ocular diseases, paving the way for improved glaucoma diagnosis and early intervention.

Keywords: CNN; Glaucoma; Multi-task deep learning; Optic Nerve Head; Retinal fundus.

Figure 1. Prediction accuracy of the training process for our multi-task method.

(A) The accuracy of REFUGE; (B) the accuracy of the ACRIMA dataset; (C) the accuracy of the ORIGA dataset.

Figure 2. Prediction loss of the training process for our multi-task method.

(A) The loss of REFUGE; (B) the loss of the ACRIMA dataset; (C) the loss of the ORIGA dataset.

Figure 3. Confusion matrix of the training process for our multi-task method.

(A) The classification of REFUGE; (B) the classification of the ACRIMA dataset; (C) the classification of the ORIGA dataset.

Figure 4. Performance of various multi task learning algorithms.