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

Abstract

This research introduces a MATLAB-based system using DenseNet and CNNs for automated classification and staging of eye diseases like Diabetic Retinopathy (DR), Macular Edema, Glaucoma, and Exudates. Input images are analyzed to detect diseases, classify severity, and stage conditions. Results are shared via ThingSpeak for real-time monitoring, while treatment advice is emailed to users. The system\'s accuracy, sensitivity, specificity, and other metrics ensure reliability in early diagnosis and monitoring. It provides a scalable, accessible solution for automated eye disease detection, aiding healthcare professionals and patients in timely interventions.

Introduction

The history of fundus imaging began with Helmholtz's ophthalmoscope in 1851, allowing visualization of the retina and aiding in ocular disease diagnosis, particularly Diabetic Retinopathy (DR). DR progresses through several stages—Mild, Moderate, Severe NPDR, and Proliferative DR (PDR). Early diagnosis is critical, and modern AI-based systems now enable automated detection through fundus images.

2. Proposed System

A MATLAB-based AI platform integrates DenseNet and Convolutional Neural Networks (CNNs) for diagnosing multiple eye diseases:

• Diabetic Retinopathy: Detected and classified into four stages.

• Macular Edema: Presence detected and staged.

• Glaucoma: Detected and classified.

• Exudates: Detected and staged.

Results and recommendations are sent via email and visualized on ThingSpeak for real-time monitoring.

3. Literature Survey Highlights

• Ravala & Rajini (2021): Used Jaya-based feature selection and RNNs for DR detection.

• Athalye & Vijay (2022): Proposed Taylor series-based Deep Belief Network for DR with high specificity and sensitivity.

• Jadhav et al. (2021): Developed MGS-ROA-DBN, achieving superior accuracy over standard models like SVM and NN.

4. Image Processing Pipeline

The system applies advanced image pre-processing:

• Resize: Normalize image dimensions.

• Noise Removal: Use of Gaussian/median filters.

• Contrast Enhancement: Adaptive histogram equalization (CLAHE).

• Segmentation: MFORG algorithm enhances region growing based on mayfly optimization.

5. Feature Extraction & Classification

• Gabor Filters: Capture textures and patterns.

• Otsu Thresholding: Distinguish lesion vs. background.

• DenseNet Backbone: Feature reuse and efficiency.

• Hybrid CNN + SVM Classifier: Enhances decision boundaries for accurate staging.

6. Platform Workflow

• Upload Interface: Drag-and-drop retinal images.

• Preprocessing: Resize, denoise, enhance contrast.

• Classification: Multistage CNN identifies disease and severity.

• Physician Dashboard: Shows patient and clinician info.

• Real-time Output: Displays metrics and generates reports.

7. Evaluation Metrics

• Accuracy: 89.1%

• AUC: 92.4%

• Precision: 86.2%

• F1-Score: 85.3%

• PSNR: 29.74 dB (indicates effective noise suppression)

8. AI Diagnosis & Clinical Recommendations

• Prediction: “No DR” with 90% confidence

• Summary: No abnormalities found

• Advice: Continue regular screening and glycemic control

9. Clinical Relevance & Future Scope

• Impact: Fast, accurate screening suitable for high-volume clinics

• Future Directions:

  • Add other diseases (e.g., AMD)

  • Longitudinal tracking

  • Explainability features (e.g., saliency maps)

  • Mobile-friendly deployment

10. Comparative Performance

The system outperforms previous models from 2020 to 2022 in:

• Accuracy, speed, and multistage classification

•  

Conclusion

In conclusion, this research demonstrates an efficient MATLAB- based system integrating 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. By employing advanced image processing and classification techniques, the system achieves reliable detection of these conditions, identifying their presence and staging their severity. This step-by-step evaluation of the patient\'s eye health, providing detailed diagnostic insights. The integration with ThingSpeak enables real-time monitoring and visualization of the results, while personalized treatment suggestions and lifestyle recommendations enhance the system\'s usability. The performance of the model is rigorously validated using metrics such as accuracy, sensitivity, specificity, precision, recall, F1 score, AUC, PSNR, and entropy, ensuring robustness and reliability in detection and staging. This automated system is a scalable, accessible solution for early diagnosis and monitoring of eye diseases, reducing the burden on healthcare professionals and improving patient outcomes. Its ability to streamline the diagnostic process and offer tailored recommendations makes it a significant advancement in the field of ophthalmology and AI-driven healthcare.

References

[1] L. Ravala and G. K. Rajini, ‘‘Automatic diagnosis of diabetic retinopathy from retinal abnormalities: Improved Jaya-based feature selection and recurrent neural network,’’ Comput. J., vol. 65, no. 7, pp. 1904– 1922, Jun. 10, 2021. [2] S. S. Athalye and G. Vijay, ‘‘Taylor series-based deep belief network for automatic classification of diabetic retinopathy using retinal fundus images,’’ Int. J. Imag. Syst. Technol., vol. 32, no. 3, pp. 882–901, May 2022. [3] A. S. Jadhav, P. B. Patil, and S. Biradar, ‘‘Optimal feature selection-based diabetic retinopathy detection using improved rider optimization algorithm enabled with deep learning,’’ Evol. Intell., vol. 14, no. 4, pp. 1431–1448, Dec. 2021. [4] P. R. R. Chandni, J. Justin, and R. Vanithamani, ‘‘Fundus image enhancement using EAL- CLAHE technique,’’ Adv. Data Inf. Sci., vol. 318, pp. 613–624, Feb. 2022. [5] Joshi, S., Partibane, B., Hatamleh, W. A., Tarazi, H., Yadav, C. S., & Krah, D. (2022). Glaucoma detection using image processing and supervised learning for classification. Journal of Healthcare Engineering, 2022, 1–12. https://doi.org/10.1155/2022/2988262 [6] Monemian, M., & Rabbani, H. (2023). Exudate identification in retinal fundus images using precise textural verifications. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023- 29916-y

Copyright

Copyright © 2025 Jaspreet Kaur, Shivam Mishra, Asiya Siddiqui, Aditya Khevaria, Divyanshu Rai, Neelam Srivastava. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.