Deep learning models for screening of high myopia using optical coherence tomography.

This study aimed to validate and evaluate deep learning (DL) models for screening of high myopia using spectral-domain optical coherence tomography (OCT). This retrospective cross-sectional study included 690 eyes in 492 patients with OCT images and axial length measurement. Eyes were divided into three groups based on axial length: a "normal group," a "high myopia group," and an "other retinal disease" group. The researchers trained and validated three DL models to classify the three groups based on horizontal and vertical OCT images of the 600 eyes. For evaluation, OCT images of 90 eyes were used. Diagnostic agreements of human doctors and DL models were analyzed. The area under the receiver operating characteristic curve of the three DL models was evaluated. Absolute agreement of retina specialists was 99.11% (range: 97.78-100%). Absolute agreement of the DL models with multiple-column model was 100.0% (ResNet 50), 90.0% (Inception V3), and 72.22% (VGG 16). Areas under the receiver operating characteristic curves of the DL models with multiple-column model were 0.99 (ResNet 50), 0.97 (Inception V3), and 0.86 (VGG 16). The DL model based on ResNet 50 showed comparable diagnostic performance with retinal specialists. The DL model using OCT images demonstrated reliable diagnostic performance to identify high myopia.

Occurrence of ocular injury and orbital fracture in orbital blunt trauma patients at tertiary care center emergency room.

PURPOSE: To analyze the prevalence and association of ocular injury and orbital fracture in orbital trauma patients METHODS: Patients with periocular trauma who visited the emergency room at the referral center from 2014 to 2016 were screened. Patients examined by ophthalmologists and evaluated by CT scan were included. Patients' age, gender, cause of trauma, and injury patterns were retrieved. The location of the fracture and morphologic parameters were reviewed. The patients were divided into groups based on the presence of orbital fracture and/or the presence of ocular injury and clinical data were compared. RESULTS: Two hundred patients were included and 158 presented with fracture. Ocular injuries occurred in 129 of 158 (81.6%) in the fracture group, and in 40 of 42 (95.2%) in the no fracture group; ocular injuries were found more often in the no fracture group (p = 0.031). Open globe injuries occurred in 5 of 158 (3.2%) in the fracture group and in 6 of 42 (14.3%) in the no fracture group; open globe injuries were found more often in the no fracture group (p = 0.012). Patients with ocular injuries showed shorter depth of the orbit (41.9 vs. 44.1 mm; p = 0.003) compared to the patients without ocular injuries. Logistic regression revealed that short orbit was associated with the presence of ocular injury (p = 0.004). CONCLUSION: The incidence of ocular injuries was significantly higher in patients without orbital fracture than in those with fractures of the orbit. The orbital fracture may play a protective role against ocular injury by providing a decompressive effect on the orbital tissue.

Computer-aided recognition of myopic tilted optic disc using deep learning algorithms in fundus photography.

BACKGROUND: It is necessary to consider myopic optic disc tilt as it seriously impacts normal ocular parameters. However, ophthalmologic measurements are within inter-observer variability and time-consuming to get. This study aimed to develop and evaluate deep learning models that automatically recognize a myopic tilted optic disc in fundus photography. METHODS: This study used 937 fundus photographs of patients with normal or myopic tilted disc, collected from Samsung Medical Center between April 2016 and December 2018. We developed an automated computer-aided recognition system for optic disc tilt on color fundus photographs via a deep learning algorithm. We preprocessed all images with two image resizing techniques. GoogleNet Inception-v3 architecture was implemented. The performances of the models were compared with the human examiner's results. Activation map visualization was qualitatively analyzed using the generalized visualization technique based on gradient-weighted class activation mapping (Grad-CAM++). RESULTS: Nine hundred thirty-seven fundus images were collected and annotated from 509 subjects. In total, 397 images from eyes with tilted optic discs and 540 images from eyes with non-tilted optic discs were analyzed. We included both eye data of most included patients and analyzed them separately in this study. For comparison, we conducted training using two aspect ratios: the simple resized dataset and the original aspect ratio (AR) preserving dataset, and the impacts of the augmentations for both datasets were evaluated. The constructed deep learning models for myopic optic disc tilt achieved the best results when simple image-resizing and augmentation were used. The results were associated with an area under the receiver operating characteristic curve (AUC) of 0.978 ± 0.008, an accuracy of 0.960 ± 0.010, sensitivity of 0.937 ± 0.023, and specificity of 0.963 ± 0.015. The heatmaps revealed that the model could effectively identify the locations of the optic discs, the superior retinal vascular arcades, and the retinal maculae. CONCLUSIONS: We developed an automated deep learning-based system to detect optic disc tilt. The model demonstrated excellent agreement with the previous clinical criteria, and the results are promising for developing future programs to adjust and identify the effect of optic disc tilt on ophthalmic measurements.