Multistage Classification of Eye Diseases Using MATLAB: Diagnosis, Staging, and Real-Time Visualization via ThingSpeak

This research presents a MATLAB-based system utilizing DenseNet and Convolutional Neural Networks (CNNs) for the automated classification and staging of multiple eye diseases, including Diabetic Retinopathy (DR), Macular Edema, Glaucoma, and Exudates. The process begins by inputting an image, which is first analyzed to classify it as either Diabetic Retinopathy or healthy. If DR is detected, the system further categorizes its severity into stages: Mild DR, Moderate DR, Severe DR, or Proliferative DR (PDR). The same image is then assessed for Macular Edema, with the disease classified as either present or absent, and further divided into stages of severity if detected. The system also evaluates the image for Glaucoma, classifying it into healthy or affected categories, and stages it if necessary. Finally, the presence of exudates is examined, and if present, they are classified into stages: Mild, Moderate, Severe, or PDR. The results of these classifications are sent to a ThingSpeak channel for real-time monitoring and visualization. Additionally, treatment options and lifestyle recommendations based on the analysis are sent to the registered user's email. The system’s performance is evaluated using several parameters, including accuracy, sensitivity, specificity, PSNR, precision, recall, F1 score, Area Under the Curve (AUC), and entropy, ensuring reliable and efficient detection of these eye conditions. This approach provides an automated, scalable, and accessible solution for eye disease detection, aiding early diagnosis and monitoring.

Keywords: Fungus Dataset, Deep Learning, Convolution Neural Network, Image Processing Techniques, segmentation and accuracy.