Purpose: To develop a deep learning model that can predict the axial lengths of eyes using ultra-widefield (UWF) fundus photography. Methods: 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. Results: 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. Conclusions We developed a deep learning-based model for predicting the axial length from UWF images with good performance.

Purpose: To develop a deep learning model classifying the laterality of optical coherence tomography (OCT) images. Methods: The study included two-dimensional OCT images (horizontal/vertical macular section) from Seoul National University Hospital. A deep learning model based on ResNet-18 was developed and trained to classify whether OCT images were horizontal or vertical sections and to predict the laterality of the images. Analysis of the results included calculating a mean area under the receiver operating characteristic curve (AUROC) and evaluating accuracy, specificity, and sensitivity. Gradient-weighted class activation for mapping visualization highlighted critical regions for classification. Results: A total of 5,000 eyes of 2,500 patients (10,000 images) was included in the development process. The test dataset consisted of 1,000 eyes of 500 patients (590 eyes without macular abnormalities, 208 epiretinal membranes, 111 age-related macular degenerations, 56 central macular edemas, 23 macular holes, and 12 other macular abnormalities). The deep learning model predicted the OCT section of the eyes in the test dataset with a mean AUROC of 0.9967. The accuracy, sensitivity, and specificity were 0.9835, 0.9870, and 0.9800, respectively. The model predicted the laterality of the eyes in horizontal OCT images with a mean AUROC of 1.0000. The accuracy, sensitivity, and specificity were 0.9970, 1.0000, and 0.9940, respectively. Using vertical OCT images, deep learning models failed to demonstrate any predictive performance in laterality classification. Conclusions We developed a deep learning model to classify the horizontal/vertical sections of OCT images and predict the laterality of horizontal OCT images with high accuracy, sensitivity, and specificity.