A Study of Ocular Disease Prediction Based on Convolutional Neural Network Algorithm

Authors

  • Zimo Zhang

DOI:

https://doi.org/10.54097/mhmfj132

Keywords:

Eye disease; CNN algorithm; Eye fundus.

Abstract

With the widespread use of electronic devices and the accelerated development of an aging society worldwide, more and more people are facing the threat of eye diseases, which are often irreversible once they occur. Therefore, it is important to detect and prevent these eye diseases as early as possible. Many people would like to be able to detect potential disease risks in a timely manner by performing self-examinations at home, especially by performing preliminary analysis of fundus images and disease prediction, and by having the fundus examined on a regular basis. It is in this context that this study was conducted with the aim of developing a disease prediction model based on fundus images using a Convolutional Neural Networks (CNN) algorithm. By analyzing a patient's fundus, the model is able to make a preliminary assessment of whether he or she is suffering from a retina-related disease. After extensive training and testing, the model achieves a prediction accuracy of 90.3% on the test dataset, which is highly reliable and can help patients get some diagnostic help before going to the hospital and help doctors make a diagnosis to a certain extent. In the future, with the further development of the technology and the continuous improvement of the dataset, this deep learning-based ocular disease prediction model is expected to play a greater role in clinical practice.

Downloads

Download data is not yet available.

References

[1] Centers for Disease Control and Prevention. Common eye disorders and diseases. Centers for Disease Control and Prevention, 2020.

[2] Kalloniatis M, Bui B B, Phu J. Glaucoma: challenges and opportunities. Clinical and Experimental Optometry, 2024, 107(2): 107-109

[3] Liu Y C, Wilkins M, Kim T, et al. Cataracts. The Lancet, 2017, 390(10094): 600-612.

[4] Age-Related Eye Disease Study Research Group. The Age-Related Eye Disease Study system for classifying age-related macular degeneration from stereoscopic color fundus photographs: the Age-Related Eye Disease Study Report Number 6. American journal of ophthalmology, 2001, 132(5): 668-681.

[5] Zimmerman R. You are here: Home/Cleveland Clinic Microvascular Complications of Diabetes Microvascular Complications of Diabetes.

[6] Morgan I G, Ohno-Matsui K, Saw S M. Myopia. The Lancet, 2012, 379(9827): 1739-1748.

[7] Sateesan A, Sinha S, KG S, et al. A survey of algorithmic and hardware optimization techniques for vision convolutional neural networks on FPGAs. Neural Processing Letters, 2021, 53(3): 2331-2377.

[8] Larxel. Ocular disease recognition. Kaggle, 2020.

[9] Bock R, Meier J, Michelson G, et al. Classifying glaucoma with image-based features from fundus photographs//Pattern Recognition: 29th DAGM Symposium, Heidelberg, Germany, September 12-14, 2007. Proceedings 29. Springer Berlin Heidelberg, 2007: 355-364.

[10] Li B, Yu S, Lu Q. An improved k-nearest neighbor algorithm for text categorization. arXiv preprint cs/0306099, 2003.

Downloads

Published

18-02-2025