Abstract
ABSTRACTGlaucoma is a common eye disease that can lead to blindness if not detected and treated early. In this paper, we present a machine learning-based approach for classifying glaucoma. We use a publicly available dataset of retinal images and extract features using convolutional neural networks. We compare the performance of different classifiers, including random forest, support vector machine, and XGBoost, and evaluate their accuracy, precision, recall, and F1 score. Our results show that the XGBoost classifier achieves the highest accuracy and F1 score, indicating its potential for diagnosing glaucoma in clinical practice.
Publisher
Cold Spring Harbor Laboratory
Reference5 articles.
1. Global Prevalence of Glaucoma and Projections of Glaucoma Burden through 2040
2. Optic Disc Detection in Retinal Images With Multi-Scale Line Detection;PLOS ONE,2015
3. Ultrasound Biomicroscopy in the Subtypes of Primary Angle Closure Glaucoma
4. Prajna, N.V. , Krishnan, T. , Raju, B. , and Kim, R. (2016). Glaucoma Detection Using Deep Convolutional Neural Network. In Proceedings of the International Conference on Computational Intelligence and Computing Research (pp. 1–4).
5. Kaggle. (2021). Diabetic Retinopathy Debrecen Data Set. Retrieved from https://www.kaggle.com/sovitrath/diabetic-retinopathy-debrecen-data-set.