Angle-Closure Detection in Anterior Segment OCT Based on Multilevel Deep Network

doi:10.1109/TCYB.2019.2897162

CORC > 宁波材料技术与工程研究所 > 中国科学院宁波材料技术与工程研究所 > 2020专题

	Angle-Closure Detection in Anterior Segment OCT Based on Multilevel Deep Network
	Fu, Huazhu ; Xu, Yanwu ; Lin, Stephen ; Wong, Damon Wing Kee ; Baskaran, Mani ; Mahesh, Meenakshi ; Aung, Tin ; Liu, Jiang
刊名	IEEE TRANSACTIONS ON CYBERNETICS
	2020
卷号	50 期号:7 页码:3358-3366
关键词	OPTICAL COHERENCE TOMOGRAPHY DIABETIC-RETINOPATHY ORIENTED GRADIENTS NARROW ANGLES GLAUCOMA CLASSIFICATION ASSOCIATION VALIDATION HISTOGRAMS IMAGES
DOI	10.1109/TCYB.2019.2897162
英文摘要	Irreversible visual impairment is often caused by primary angle-closure glaucoma, which could be detected via anterior segment optical coherence tomography (AS-OCT). In this paper, an automated system based on deep learning is presented for angle-closure detection in AS-OCT images. Our system learns a discriminative representation from training data that captures subtle visual cues not modeled by handcrafted features. A multilevel deep network is proposed to formulate this learning, which utilizes three particular AS-OCT regions based on clinical priors: 1) the global anterior segment structure; 2) local iris region; and 3) anterior chamber angle (ACA) patch. In our method, a sliding window-based detector is designed to localize the ACA region, which addresses ACA detection as a regression task. Then, three parallel subnetworks are applied to extract AS-OCT representations for the global image and at clinically relevant local regions. Finally, the extracted deep features of these subnetworks are concatenated into one fully connected layer to predict the angle-closure detection result. In the experiments, our system is shown to surpass previous detection methods and other deep learning systems on two clinical AS-OCT datasets.
学科主题	Automation & Control Systems ; Computer Science
内容类型	期刊论文
源URL	[http://ir.nimte.ac.cn/handle/174433/20683]
专题	2020专题
作者单位	1.Xu, YW (corresponding author), Baidu Inc, Dept Artificial Intelligence Innovat Business, Beijing 100193, Peoples R China. 2.Fu, HZ (corresponding author), Incept Inst Artificial Intelligence, Abu Dhabi, U Arab Emirates.
推荐引用方式 GB/T 7714	Fu, Huazhu,Xu, Yanwu,Lin, Stephen,et al. Angle-Closure Detection in Anterior Segment OCT Based on Multilevel Deep Network[J]. IEEE TRANSACTIONS ON CYBERNETICS,2020,50(7):3358-3366.
APA	Fu, Huazhu.,Xu, Yanwu.,Lin, Stephen.,Wong, Damon Wing Kee.,Baskaran, Mani.,...&Liu, Jiang.(2020).Angle-Closure Detection in Anterior Segment OCT Based on Multilevel Deep Network.IEEE TRANSACTIONS ON CYBERNETICS,50(7),3358-3366.
MLA	Fu, Huazhu,et al."Angle-Closure Detection in Anterior Segment OCT Based on Multilevel Deep Network".IEEE TRANSACTIONS ON CYBERNETICS 50.7(2020):3358-3366.