Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs
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) an...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-04-01
|
| Series: | Frontiers in Cell and Developmental Biology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcell.2021.653692/full |
| _version_ | 1818339029301592064 |
|---|---|
| author | Li Dong Xin Yue Hu Yan Ni Yan Qi Zhang Nan Zhou Lei Shao Ya Xing Wang Jie Xu Yin Jun Lan Yang Li Jian Hao Xiong Cong Xin Liu Zong Yuan Ge Zong Yuan Ge Jost. B. Jonas Wen Bin Wei |
| author_facet | Li Dong Xin Yue Hu Yan Ni Yan Qi Zhang Nan Zhou Lei Shao Ya Xing Wang Jie Xu Yin Jun Lan Yang Li Jian Hao Xiong Cong Xin Liu Zong Yuan Ge Zong Yuan Ge Jost. B. Jonas Wen Bin Wei |
| author_sort | Li Dong |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-13T15:20:30Z |
| format | Article |
| id | doaj.art-b83e84c28e5248a0a95ff8fa384e0f44 |
| institution | Directory Open Access Journal |
| issn | 2296-634X |
| language | English |
| last_indexed | 2024-12-13T15:20:30Z |
| publishDate | 2021-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cell and Developmental Biology |
| spelling | doaj.art-b83e84c28e5248a0a95ff8fa384e0f442022-12-21T23:40:34ZengFrontiers Media S.A.Frontiers in Cell and Developmental Biology2296-634X2021-04-01910.3389/fcell.2021.653692653692Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus PhotographsLi Dong0Xin Yue Hu1Yan Ni Yan2Qi Zhang3Nan Zhou4Lei Shao5Ya Xing Wang6Jie Xu7Yin Jun Lan8Yang Li9Jian Hao Xiong10Cong Xin Liu11Zong Yuan Ge12Zong Yuan Ge13Jost. B. Jonas14Wen Bin Wei15Beijing 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, ChinaBeijing Eaglevision Technology Co., Ltd., Beijing, ChinaBeijing 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, ChinaBeijing Ophthalmology and Visual Science Key Laboratory, Beijing Tongren Eye Center, Beijing Tongren Hospital, Beijing Institute of Ophthalmology, Capital Medical University, Beijing, ChinaBeijing 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, ChinaBeijing 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, ChinaBeijing Ophthalmology and Visual Science Key Laboratory, Beijing Tongren Eye Center, Beijing Tongren Hospital, Beijing Institute of Ophthalmology, Capital Medical University, Beijing, ChinaBeijing Ophthalmology and Visual Science Key Laboratory, Beijing Tongren Eye Center, Beijing Tongren Hospital, Beijing Institute of Ophthalmology, Capital Medical University, Beijing, ChinaBeijing 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, ChinaBeijing 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, ChinaBeijing Eaglevision Technology Co., Ltd., Beijing, ChinaBeijing Eaglevision Technology Co., Ltd., Beijing, ChinaeResearch centre, Monash University, Melbourne, VIC, AustraliaECSE, Faculty of Engineering, Monash University, Melbourne, VIC, AustraliaDepartment of Ophthalmology, Medical Faculty Mannheim, Heidelberg University, Mannheim, GermanyBeijing 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, ChinaThis 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.https://www.frontiersin.org/articles/10.3389/fcell.2021.653692/fulldeep learningconvolution neural networkaxial lengthsubfoveal choroidal thicknessfundus photographyfundus image |
| spellingShingle | Li Dong Xin Yue Hu Yan Ni Yan Qi Zhang Nan Zhou Lei Shao Ya Xing Wang Jie Xu Yin Jun Lan Yang Li Jian Hao Xiong Cong Xin Liu Zong Yuan Ge Zong Yuan Ge Jost. B. Jonas Wen Bin Wei Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs Frontiers in Cell and Developmental Biology deep learning convolution neural network axial length subfoveal choroidal thickness fundus photography fundus image |
| title | Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs |
| title_full | Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs |
| title_fullStr | Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs |
| title_full_unstemmed | Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs |
| title_short | Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs |
| title_sort | deep learning based estimation of axial length and subfoveal choroidal thickness from color fundus photographs |
| topic | deep learning convolution neural network axial length subfoveal choroidal thickness fundus photography fundus image |
| url | https://www.frontiersin.org/articles/10.3389/fcell.2021.653692/full |
| work_keys_str_mv | AT lidong deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT xinyuehu deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT yanniyan deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT qizhang deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT nanzhou deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT leishao deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT yaxingwang deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT jiexu deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT yinjunlan deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT yangli deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT jianhaoxiong deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT congxinliu deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT zongyuange deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT zongyuange deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT jostbjonas deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs AT wenbinwei deeplearningbasedestimationofaxiallengthandsubfovealchoroidalthicknessfromcolorfundusphotographs |