A Hybrid Deep Learning Construct for Detecting Keratoconus From Corneal Maps

人工智能 圆锥角膜 深度学习 计算机科学 角膜地形图 接收机工作特性 混乱 眼科 验光服务 角膜 医学 机器学习 精神分析 心理学
作者
Ali H. Al‐Timemy,Zahraa M. Mosa,Zaid Abdi Alkareem Alyasseri,Alexandru Lavric,Marcelo Mastromonico Lui,Rossen Mihaylov Hazarbassanov,Siamak Yousefi
出处
期刊:Translational Vision Science & Technology [Association for Research in Vision and Ophthalmology (ARVO)]
卷期号:10 (14): 16-16 被引量:26
标识
DOI:10.1167/tvst.10.14.16
摘要

To develop and assess the accuracy of a hybrid deep learning construct for detecting keratoconus (KCN) based on corneal topographic maps.We collected 3794 corneal images from 542 eyes of 280 subjects and developed seven deep learning models based on anterior and posterior eccentricity, anterior and posterior elevation, anterior and posterior sagittal curvature, and corneal thickness maps to extract deep corneal features. An independent subset with 1050 images collected from 150 eyes of 85 subjects from a separate center was used to validate models. We developed a hybrid deep learning model to detect KCN. We visualized deep features of corneal parameters to assess the quality of learning subjectively and computed area under the receiver operating characteristic curve (AUC), confusion matrices, accuracy, and F1 score to evaluate models objectively.In the development dataset, 204 eyes were normal, 123 eyes were suspected KCN, and 215 eyes had KCN. In the independent validation dataset, 50 eyes were normal, 50 eyes were suspected KCN, and 50 eyes were KCN. Images were annotated by three corneal specialists. The AUC of the models for the two-class and three-class problems based on the development set were 0.99 and 0.93, respectively.The hybrid deep learning model achieved high accuracy in identifying KCN based on corneal maps and provided a time-efficient framework with low computational complexity.Deep learning can detect KCN from non-invasive corneal images with high accuracy, suggesting potential application in research and clinical practice to identify KCN.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
藤原拓海关注了科研通微信公众号
1秒前
1秒前
2秒前
2秒前
丁杰孟发布了新的文献求助10
3秒前
放开让我学习完成签到,获得积分10
3秒前
暮霭沉沉应助fifteen采纳,获得10
4秒前
彭凯发布了新的文献求助10
4秒前
隐形曼青应助矮小的觅云采纳,获得10
4秒前
4秒前
贺丞完成签到,获得积分10
4秒前
menghuaxijie完成签到,获得积分10
5秒前
meng完成签到,获得积分10
6秒前
7秒前
皮二牛牛完成签到,获得积分10
7秒前
英俊的铭应助陈最采纳,获得30
7秒前
tianzml0应助无奈芮采纳,获得10
7秒前
Charail发布了新的文献求助10
8秒前
9秒前
张yy发布了新的文献求助10
9秒前
10秒前
sissi完成签到,获得积分10
10秒前
斯文败类应助彭凯采纳,获得10
10秒前
13秒前
星沐影发布了新的文献求助10
13秒前
lourahan发布了新的文献求助10
14秒前
李萌萌完成签到 ,获得积分10
14秒前
小马甲应助大聪明采纳,获得10
15秒前
16秒前
彭凯完成签到,获得积分10
16秒前
18秒前
JamesPei应助科研通管家采纳,获得10
19秒前
19秒前
隐形曼青应助科研通管家采纳,获得10
19秒前
19秒前
田様应助科研通管家采纳,获得10
19秒前
Lucas应助科研通管家采纳,获得10
19秒前
苏书白应助科研通管家采纳,获得10
19秒前
脑洞疼应助科研通管家采纳,获得10
19秒前
CipherSage应助科研通管家采纳,获得10
19秒前
高分求助中
Evolution 10000
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 600
Distribution Dependent Stochastic Differential Equations 500
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
A new species of Velataspis (Hemiptera Coccoidea Diaspididae) from tea in Assam 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3157798
求助须知:如何正确求助?哪些是违规求助? 2809143
关于积分的说明 7880515
捐赠科研通 2467613
什么是DOI,文献DOI怎么找? 1313602
科研通“疑难数据库(出版商)”最低求助积分说明 630467
版权声明 601943