Department of Ophthalmology, Seoul National University Hospital, Seoul, Korea.
Department of Ophthalmology, Seoul National University College of Medicine, Seoul, Korea.
Korean J Ophthalmol. 2023 Apr;37(2):95-104. doi: 10.3341/kjo.2022.0059. Epub 2023 Feb 9.
To develop a deep learning model that can predict the axial lengths of eyes using ultra-widefield (UWF) fundus photography.
We retrospectively enrolled patients who visited the ophthalmology clinic at the Seoul National University Hospital between September 2018 and December 2021. Patients with axial length measurements and UWF images taken within 3 months of axial length measurement were included in the study. The dataset was divided into a development set and a test set at an 8:2 ratio while maintaining an equal distribution of axial lengths (stratified splitting with binning). We used transfer learning-based on EfficientNet B3 to develop the model. We evaluated the model's performance using mean absolute error (MAE), R-squared (R2), and 95% confidence intervals (CIs). We used vanilla gradient saliency maps to illustrate the regions predominantly used by convolutional neural network.
In total, 8,657 UWF retinal fundus images from 3,829 patients (mean age, 63.98 ±15.25 years) were included in the study. The deep learning model predicted the axial lengths of the test dataset with MAE and R2 values of 0.744 mm (95% CI, 0.709-0.779 mm) and 0.815 (95% CI, 0.785-0.840), respectively. The model's accuracy was 73.7%, 95.9%, and 99.2% in prediction, with error margins of ±1.0, ±2.0, and ±3.0 mm, respectively.
We developed a deep learning-based model for predicting the axial length from UWF images with good performance.
开发一种能够使用超广角（UWF）眼底照相术预测眼睛轴长的深度学习模型。
我们回顾性地招募了 2018 年 9 月至 2021 年 12 月期间在首尔国立大学医院眼科诊所就诊的患者。纳入的患者均有轴向长度测量值，且在轴向长度测量后 3 个月内拍摄了 UWF 图像。数据集按照 8:2 的比例分为开发集和测试集，同时保持轴向长度的均衡分布（分层分箱）。我们使用基于 EfficientNet B3 的迁移学习来开发模型。我们使用平均绝对误差（MAE）、R2 和 95%置信区间（CI）来评估模型的性能。我们使用常规梯度显著图来说明卷积神经网络主要使用的区域。
共纳入 3829 名患者的 8657 张 UWF 视网膜眼底图像（平均年龄为 63.98±15.25 岁）。深度学习模型对测试数据集的轴向长度预测具有 MAE 和 R2 值分别为 0.744mm（95%CI，0.709-0.779mm）和 0.815（95%CI，0.785-0.840）。模型在预测时的准确率分别为 73.7%、95.9%和 99.2%，误差幅度分别为±1.0、±2.0 和±3.0mm。
我们开发了一种基于深度学习的 UWF 图像轴向长度预测模型，具有良好的性能。
