Prediction of Refractive Error Based on Ultrawide Field Images With Deep Learning Models in Myopia Patients
Open Access
- 30 March 2022
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Medicine
- Vol. 9, 834281
Abstract
Summary: Ultrawide field fundus images could be applied in deep learning models to predict the refractive error of myopic patients. The predicted error was related to the older age and greater spherical power.Purpose: To explore the possibility of predicting the refractive error of myopic patients by applying deep learning models trained with ultrawide field (UWF) images.Methods: UWF fundus images were collected from left eyes of 987 myopia patients of Eye and ENT Hospital, Fudan University between November 2015 and January 2019. The fundus images were all captured with Optomap Daytona, a 200° UWF imaging device. Three deep learning models (ResNet-50, Inception-v3, Inception-ResNet-v2) were trained with the UWF images for predicting refractive error. 133 UWF fundus images were also collected after January 2021 as an the external validation data set. The predicted refractive error was compared with the “true value” measured by subjective refraction. Mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient (R2) value were calculated in the test set. The Spearman rank correlation test was applied for univariate analysis and multivariate linear regression analysis on variables affecting MAE. The weighted heat map was generated by averaging the predicted weight of each pixel.Results: ResNet-50, Inception-v3 and Inception-ResNet-v2 models were trained with the UWF images for refractive error prediction with R2 of 0.9562, 0.9555, 0.9563 and MAE of 1.72(95%CI: 1.62–1.82), 1.75(95%CI: 1.65–1.86) and 1.76(95%CI: 1.66–1.86), respectively. 29.95%, 31.47% and 29.44% of the test set were within the predictive error of 0.75D in the three models. 64.97%, 64.97%, and 64.47% was within 2.00D predictive error. The predicted MAE was related to older age (P < 0.01) and greater spherical power(P < 0.01). The optic papilla and macular region had significant predictive power in the weighted heat map.Conclusions: It was feasible to predict refractive error in myopic patients with deep learning models trained by UWF images with the accuracy to be improved.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 26 references indexed in Scilit:
- Associations between Optic Nerve Head–Related Anatomical Parameters and Refractive Error over the Full Range of Glaucoma SeverityTranslational Vision Science & Technology, 2017
- Ultra-widefield fundus autofluorescence in age-related macular degenerationPLOS ONE, 2017
- Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph searchBiomedical Optics Express, 2017
- Updates of pathologic myopiaProgress in Retinal and Eye Research, 2016
- Refractive Error and Ocular ParametersOptometry and Vision Science, 2015
- Increase in Myopia Prevalence in Clinic‐Based Populations Across a CenturyOptometry and Vision Science, 2013
- Prevalence and Causes of Low Vision and Blindness in a Japanese Adult PopulationOphthalmology, 2006
- Optic disk size correlated with refractive errorAmerican Journal of Ophthalmology, 2005
- Race-, Age-, Gender-, and Refractive Error—Related Differences in the Normal Optic DiscArchives of Ophthalmology (1950), 1994
- The ageing retina: Physiology or pathologyEye, 1987