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.
Highlights
MATERIALS AND METHODSA predicted number of 938 million people of the world’s population may suffer from high myopia by the year 2050 (Holden et al, 2016), leading to a major worldwide concern
Myopic cataract patients usually inevitably have macular complications such as foveoschisis, chorioretinal atrophy, and cicatrices from previous choroidal neovascularization (Chang et al, 2013; Todorich et al, 2013; Gohil et al, 2015; Lichtwitz et al, 2016; Li et al, 2018), which could render the preoperative prediction of visual acuity after cataract surgery very difficult, even though an optical coherence tomography (OCT) scan can be used for morphological diagnosis (Jeon and Kim, 2011)
By using the preoperative OCT scans of macular as input, we developed and validated a deep learning algorithm to predict the postoperative best corrected visual acuity (BCVA) of highly myopic eyes after cataract surgery and revealed that the ensemble model showed stably promising performance in both internal and external test datasets with MAEs of 0.1524 and 0.1602 logarithm of minimal angle of resolution (logMAR) and RMSEs of 0.2612 and 0.2020 logMAR, respectively
Summary
MATERIALS AND METHODSA predicted number of 938 million people of the world’s population may suffer from high myopia by the year 2050 (Holden et al, 2016), leading to a major worldwide concern. For highly myopic cataract patients, due to the more complicated fundus conditions such as foveoschisis, chorioretinal atrophy, or cicatrices from previous choroidal neovascularization (Chang et al, 2013; Todorich et al, 2013; Gohil et al, 2015; Lichtwitz et al, 2016; Li et al, 2018), their visual benefit from cataract surgery remains hard to be determined preoperatively. Due to complicated and variable fundus status of highly myopic eyes, their visual benefit from cataract surgery remains hard to be determined preoperatively. We 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
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.