Angle-closure assessment in anterior segment OCT images via deep learning

Hao，Huaying1,4; Zhao，Yitian1,4; Yan，Qifeng1,4; Higashita，Risa3,6; Zhang，Jiong5; Zhao，Yifan7; Xu，Yanwu1,4; Li，Fei2,4; Zhang，Xiulan2,4; Liu，Jiang1,3,4

2021-04-01

10.1016/j.media.2021.101956

MEDICAL IMAGE ANALYSIS   影响因子和分区

1361-8415

1361-8423

Precise characterization and analysis of anterior chamber angle (ACA) are of great importance in facilitating clinical examination and diagnosis of angle-closure disease. Currently, the gold standard for diagnostic angle assessment is observation of ACA by gonioscopy. However, gonioscopy requires direct contact between the gonioscope and patients’ eye, which is uncomfortable for patients and may deform the ACA, leading to false results. To this end, in this paper, we explore a potential way for grading ACAs into open-, appositional- and synechial angles by Anterior Segment Optical Coherence Tomography (AS-OCT), rather than the conventional gonioscopic examination. The proposed classification schema can be beneficial to clinicians who seek to better understand the progression of the spectrum of angle-closure disease types, so as to further assist the assessment and required treatment at different stages of angle-closure disease. To be more specific, we first use an image alignment method to generate sequences of AS-OCT images. The ACA region is then localized automatically by segmenting an important biomarker - the iris - as this is a primary structural cue in identifying angle-closure disease. Finally, the AS-OCT images acquired in both dark and bright illumination conditions are fed into our Multi-Sequence Deep Network (MSDN) architecture, in which a convolutional neural network (CNN) module is applied to extract feature representations, and a novel ConvLSTM-TC module is employed to study the spatial state of these representations. In addition, a novel time-weighted cross-entropy loss (TC) is proposed to optimize the output of the ConvLSTM, and the extracted features are further aggregated for the purposes of classification. The proposed method is evaluated across 66 eyes, which include 1584 AS-OCT sequences, and a total of 16,896 images. The experimental results show that the proposed method outperforms existing state-of-the-art methods in applicability, effectiveness, and accuracy.

Angle-closure Anterior chamber angle AS-OCT Deep learning Glaucoma

SCI ; EI

英语

通讯

Zhejiang Provincial Natural Science Foundation of China["LZ19F010001","LQ19H180 0 01"] ; Key Research and Development Program of Zhejiang Province[2020C03036] ; Ningbo '2025 ST Megaprojects'["2019B10033","2019B10061"]

Computer Science ; Engineering ; Radiology, Nuclear Medicine & Medical Imaging

Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging

WOS:000639620600009

ELSEVIER

20210609891561

Convolutional neural networks ; Diagnosis ; Grading ; Image segmentation ; Optical tomography

Medicine and Pharmacology:461.6 ; Optical Devices and Systems:741.3

COMPUTER SCIENCE

2-s2.0-85100386118

Scopus

1.Cixi Institute of Biomedical Engineering,Ningbo Institute of Materials Technology and Engineering,Chinese Academy of Sciences,Ningbo,China
2.Zhongshan Ophthalmic Center,State Key Laboratory of Ophthalmology,Sun Yat-sen University,Guangzhou,China
3.Department of Computer Science and Engineering,Southern University of Science and Technology,China
4.Glaucoma Artificial Intelligence Diagnosis and Imaging Analysis Joint Research Lab,Guangzhou & Ningbo,China
5.Laboratory of Neuro Imaging (LONI),Keck School of Medicine,University of Southern,California,United States
6.Tomey Corporation,Nagoya,Japan
7.School of Aerospace,Transport and Manufacturing,Cranfield University,Bedford,United Kingdom

Hao，Huaying,Zhao，Yitian,Yan，Qifeng,et al. Angle-closure assessment in anterior segment OCT images via deep learning[J]. MEDICAL IMAGE ANALYSIS,2021,69.

Hao，Huaying.,Zhao，Yitian.,Yan，Qifeng.,Higashita，Risa.,Zhang，Jiong.,...&Liu，Jiang.(2021).Angle-closure assessment in anterior segment OCT images via deep learning.MEDICAL IMAGE ANALYSIS,69.

Hao，Huaying,et al."Angle-closure assessment in anterior segment OCT images via deep learning".MEDICAL IMAGE ANALYSIS 69(2021).