异常
青光眼
白内障
验光服务
医学
黄斑变性
卡帕
人工智能
眼底(子宫)
计算机科学
眼科
模式识别(心理学)
数学
几何学
精神科
作者
Sai Dheeraj Gummadi,Amitabha Ghosh
出处
期刊:Lecture notes in networks and systems
日期:2023-01-01
卷期号:: 325-337
标识
DOI:10.1007/978-981-99-2602-2_25
摘要
In this study, a custom Vision Transformer is used for classifying abnormal fundus images and differentiating them from normal ones. The abnormality in images might be due to any of the following six ocular diseases: age-related macular degeneration, cataracts, diabetes, glaucoma, hypertension, and myopia. Three different Vision Transformer architectures with 8, 14, and 24 layers have been used for the classification problem to identify the optimum one. The entire dataset is classified into seven different labels—healthy and six different diseases. The proposed implementation improves on the existing F1-score, precision, sensitivity, and Kappa scores of ocular disease identification presenting a maximum F1-score of 83.49% with 84% sensitivity, 83% precision, and 0.802 Kappa score using Vision Transformer-14.
科研通智能强力驱动
Strongly Powered by AbleSci AI