ESCRS - FPS12.11 - Prediction Of Refractive Error Based On Ultrawide Field Images With Deep Learning Models In Myopia Patients

Prediction Of Refractive Error Based On Ultrawide Field Images With Deep Learning Models In Myopia Patients

Published 2022 - 40th Congress of the ESCRS

Reference: FPS12.11 | Type: Free paper | DOI: 10.82333/t77z-1h90

Authors: Danjuan Yang* 1 , Meiyan Li 1 , Weizhen Li 2 , Yunzhe Wang 1 , Lingling Niu 1 , Yang Shen 1 , Xiaoyu Zhang 1 , Bo Fu 2 , Xingtao Zhou 1

1Ophthalmology,Eye and ENT Hospital, Fudan University,Shanghai,China;NHC Key Laboratory of Myopia,Fudan University,Shanghai,China, 2School of Data Science,Fudan University,Shanghai,China

Purpose

To explore the possibility of predicting the refractive error of myopic patients by applying deep learning models trained with ultrawide field (UWF) images.

Setting

Ophthalmology Department of Eye and ENT Hospital, Fudan University

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-degree 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 collected after January 2021 as an external validation data set. The predicted refractive error was compared with the “true value” measured by subjective refraction with mean absolute error (MAE), mean absolute percentage error (MAPE) and R2 calculated. 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% were 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.