Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs

Frontiers in Cell and Developmental Biology

Cong Xin Liu¹  Xin Yue Hu¹  Jian Hao Xiong¹  Nan Zhou²  Wen Bin Wei²  Yan Ni Yan²  Li Dong²  Yang Li²  Lei Shao²  Yin Jun Lan²  Jie Xu³  Qi Zhang³  Ya Xing Wang³  Jost. B. Jonas⁴  Zong Yuan Ge⁵ 

[1] Beijing Eaglevision Technology Co., Ltd., Beijing, China;Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology and Visual Sciences Key Laboratory, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing, China;Beijing Ophthalmology and Visual Science Key Laboratory, Beijing Tongren Eye Center, Beijing Tongren Hospital, Beijing Institute of Ophthalmology, Capital Medical University, Beijing, China;Department of Ophthalmology, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany;ECSE, Faculty of Engineering, Monash University, Melbourne, VIC, Australia;eResearch centre, Monash University, Melbourne, VIC, Australia;

关键词: deep learning;    convolution neural network;    axial length;    subfoveal choroidal thickness;    fundus photography;    fundus image;   

DOI  :  10.3389/fcell.2021.653692

来源: DOAJ

【 摘 要 】

This study aimed to develop an automated computer-based algorithm to estimate axial length and subfoveal choroidal thickness (SFCT) based on color fundus photographs. In the population-based Beijing Eye Study 2011, we took fundus photographs and measured SFCT by optical coherence tomography (OCT) and axial length by optical low-coherence reflectometry. Using 6394 color fundus images taken from 3468 participants, we trained and evaluated a deep-learning-based algorithm for estimation of axial length and SFCT. The algorithm had a mean absolute error (MAE) for estimating axial length and SFCT of 0.56 mm [95% confidence interval (CI): 0.53,0.61] and 49.20 μm (95% CI: 45.83,52.54), respectively. Estimated values and measured data showed coefficients of determination of r2 = 0.59 (95% CI: 0.50,0.65) for axial length and r2 = 0.62 (95% CI: 0.57,0.67) for SFCT. Bland–Altman plots revealed a mean difference in axial length and SFCT of −0.16 mm (95% CI: −1.60,1.27 mm) and of −4.40 μm (95% CI, −131.8,122.9 μm), respectively. For the estimation of axial length, heat map analysis showed that signals predominantly from overall of the macular region, the foveal region, and the extrafoveal region were used in the eyes with an axial length of < 22 mm, 22–26 mm, and > 26 mm, respectively. For the estimation of SFCT, the convolutional neural network (CNN) used mostly the central part of the macular region, the fovea or perifovea, independently of the SFCT. Our study shows that deep-learning-based algorithms may be helpful in estimating axial length and SFCT based on conventional color fundus images. They may be a further step in the semiautomatic assessment of the eye.

【 授权许可】

Unknown