EARLY DIAGNOSIS AND PREDICTION MODEL OF OPHTHALMIC DISEASES BASED ON ARTIFICIAL INTELLIGENCE USING DIGITAL RETINAL IMAGES
Keywords:
artificial intelligence, retinal images, early diagnosisAbstract
Early detection of ophthalmic diseases is essential for preventing irreversible vision loss and improving patients’ quality of life. Recent advances in artificial intelligence (AI) and medical imaging have created new opportunities for automated screening and clinical decision support. This study proposes an AI-based model for early diagnosis and prediction of ophthalmic diseases using digital retinal images. The proposed approach employs convolutional neural networks to automatically extract visual features from fundus photographs and generate probabilistic predictions of pathological conditions.
Digital retinal images were preprocessed through normalization, noise reduction, and contrast enhancement to improve feature representation. The model was trained and validated using separated training and testing subsets. Performance was evaluated using standard metrics including accuracy, recall, F1-score, and receiver operating characteristic (ROC) analysis.
Experimental results demonstrate that the proposed model is capable of distinguishing healthy and pathological retinal images and estimating disease progression tendencies. The findings suggest that AI-based retinal image analysis can serve as a supportive tool for early diagnosis and prognosis, potentially reducing diagnostic subjectivity and improving screening efficiency. The proposed system is particularly promising for telemedicine and remote screening applications.
Downloads
References
1. Abdukarimov, Sh. A. (2018). Oftalmologiya. Toshkent: Ibn Sino nomidagi nashriyot.
2. Rahmonova, D. A., & Yuldashev, B. X. (2020). Ko‘z kasalliklari. Toshkent: Yangi asr avlodi.
3. Karimov, F. M. (2019). Ko‘z kasalliklarini zamonaviy diagnostika usullari. Tibbiyot axborotnomasi, (3), 45–49.
4. Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542, 115–118.
5. Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Webster, D. R. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 316(22), 2402–2410.
6. Li, Z., He, Y., Keel, S., Meng, W., Chang, R. T., & He, M. (2018). Efficacy of a deep learning system for detecting glaucomatous optic neuropathy. Ophthalmology, 125(8), 1199–1206.
7. Rajalakshmi, R., Subashini, R., Anjana, R. M., & Mohan, V. (2018). Automated diabetic retinopathy detection in smartphone-based fundus photography. Eye, 32, 1138–1144.
8. Khurbanova, N., Omonova, G., Alimova, M., & Komiljanova, S. (2017). The state of antioxidant system of mitochondrial fraction of the hepotocyte in early terms of ischemic stroke in white rats. Interscience, (12-2), 51-53.
9. Kurbanova NN others. Effect of new herbal preparations on some indicators of apoptosis in rats with acute toxic hepatitis //International Journal of Psychosocial Rehabilitation. – 2020. – T. 24. – No. 08. – pp. 6999-7005.
10. Kurbanova NN et al. The effect of new plant hepatoprotectors on the level of proinflammatory cytokines in acute toxic liver damage. //International Journal of Psychosocial Rehabilitation. – Vol. 24, Issue 08, 2020. – Page. 8910-8920.
11. Navruzovna KN et al. Biochemical changes in hepatocyte subcellular fractions in experimental ischemic stroke // Bulletin of Science and Education. – 2019. – No. 7-2 (61). – pp. 57-59. Olympus LLC.
12. Navruzovna KN et al. Generation of reactive oxygen species in the mitochondrial fraction of hepatocytes in the early stages of experimental ischemic stroke // Bulletin of Science and Education. – 2019. – No. 7-2 (61). – P. 60-62.URL: https://cyberleninka.ru/article/n/generation-of-reactive-oxygen-species-in-the-mitochondrial-fraction-of-hepatocytes
