Frontiers in Cell and Developmental Biology (May 2021)
An Optical Coherence Tomography-Based Deep Learning Algorithm for Visual Acuity Prediction of Highly Myopic Eyes After Cataract Surgery
- Ling Wei,
- Ling Wei,
- Ling Wei,
- Wenwen He,
- Wenwen He,
- Wenwen He,
- Jinrui Wang,
- Keke Zhang,
- Keke Zhang,
- Keke Zhang,
- Yu Du,
- Yu Du,
- Yu Du,
- Jiao Qi,
- Jiao Qi,
- Jiao Qi,
- Jiaqi Meng,
- Jiaqi Meng,
- Jiaqi Meng,
- Xiaodi Qiu,
- Xiaodi Qiu,
- Xiaodi Qiu,
- Lei Cai,
- Lei Cai,
- Lei Cai,
- Qi Fan,
- Qi Fan,
- Qi Fan,
- Zhennan Zhao,
- Zhennan Zhao,
- Zhennan Zhao,
- Yating Tang,
- Yating Tang,
- Yating Tang,
- Shuang Ni,
- Haike Guo,
- Yunxiao Song,
- Xixi He,
- Dayong Ding,
- Yi Lu,
- Yi Lu,
- Yi Lu,
- Xiangjia Zhu,
- Xiangjia Zhu,
- Xiangjia Zhu
Affiliations
- Ling Wei
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Ling Wei
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Ling Wei
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Wenwen He
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Wenwen He
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Wenwen He
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Jinrui Wang
- Visionary Intelligence Ltd, Beijing, China
- Keke Zhang
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Keke Zhang
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Keke Zhang
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Yu Du
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Yu Du
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Yu Du
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Jiao Qi
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Jiao Qi
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Jiao Qi
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Jiaqi Meng
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Jiaqi Meng
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Jiaqi Meng
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Xiaodi Qiu
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Xiaodi Qiu
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Xiaodi Qiu
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Lei Cai
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Lei Cai
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Lei Cai
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Qi Fan
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Qi Fan
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Qi Fan
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Zhennan Zhao
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Zhennan Zhao
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Zhennan Zhao
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Yating Tang
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Yating Tang
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Yating Tang
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Shuang Ni
- Department of Ophthalmology, Heping Eye Hospital, Shanghai, China
- Haike Guo
- Department of Ophthalmology, Heping Eye Hospital, Shanghai, China
- Yunxiao Song
- Illinois Computer Science, University of Illinois, Champaign, IL, United States
- Xixi He
- Visionary Intelligence Ltd, Beijing, China
- Dayong Ding
- Visionary Intelligence Ltd, Beijing, China
- Yi Lu
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Yi Lu
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Yi Lu
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- Xiangjia Zhu
- Department of Ophthalmology, Eye and ENT Hospital, Eye Institute, Fudan University, Shanghai, China
- Xiangjia Zhu
- Key Laboratory of Myopia, NHC Key Laboratory of Myopia, Fudan University, Chinese Academy of Medical Sciences, Shanghai, China
- Xiangjia Zhu
- Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China
- DOI
- https://doi.org/10.3389/fcell.2021.652848
- Journal volume & issue
-
Vol. 9
Abstract
BackgroundDue to complicated and variable fundus status of highly myopic eyes, their visual benefit from cataract surgery remains hard to be determined preoperatively. We therefore aimed to develop an optical coherence tomography (OCT)-based deep learning algorithms to predict the postoperative visual acuity of highly myopic eyes after cataract surgery.Materials and MethodsThe internal dataset consisted of 1,415 highly myopic eyes having cataract surgeries in our hospital. Another external dataset consisted of 161 highly myopic eyes from Heping Eye Hospital. Preoperative macular OCT images were set as the only feature. The best corrected visual acuity (BCVA) at 4 weeks after surgery was set as the ground truth. Five different deep learning algorithms, namely ResNet-18, ResNet-34, ResNet-50, ResNet-101, and Inception-v3, were used to develop the model aiming at predicting the postoperative BCVA, and an ensemble learning was further developed. The model was further evaluated in the internal and external test datasets.ResultsThe ensemble learning showed the lowest mean absolute error (MAE) of 0.1566 logMAR and the lowest root mean square error (RMSE) of 0.2433 logMAR in the validation dataset. Promising outcomes in the internal and external test datasets were revealed with MAEs of 0.1524 and 0.1602 logMAR and RMSEs of 0.2612 and 0.2020 logMAR, respectively. Considerable sensitivity and precision were achieved in the BCVA < 0.30 logMAR group, with 90.32 and 75.34% in the internal test dataset and 81.75 and 89.60% in the external test dataset, respectively. The percentages of the prediction errors within ± 0.30 logMAR were 89.01% in the internal and 88.82% in the external test dataset.ConclusionPromising prediction outcomes of postoperative BCVA were achieved by the novel OCT-trained deep learning model, which will be helpful for the surgical planning of highly myopic cataract patients.
Keywords
