Estimation of best corrected visual acuity based on deep neural network.

In this study, we investigated a convolutional neural network (CNN)-based framework for the estimation of the best-corrected visual acuity (BCVA) from fundus images. First, we collected 53,318 fundus photographs from the Gyeongsang National University Changwon Hospital, where each fundus photograph is categorized into 11 levels by retrospective medical chart review. Then, we designed 4 BCVA estimation schemes using transfer learning with pre-trained ResNet-18 and EfficientNet-B0 models where both regression and classification-based prediction are taken into account. According to the results of the study, the predicted BCVA by CNN-based schemes is close to the actual value such that 94.37% of prediction accuracy can be achieved when 3 levels of difference can be tolerated during prediction. The mean squared error and [Formula: see text] score were measured as 0.028 and 0.654, respectively. These results indicate that the BCVA can be predicted accurately for extreme cases, i.e., the level of BCVA is close to either 0.0 or 1.0. Moreover, using the Guided Grad-CAM, we confirmed that the macula and the blood vessel surrounding the macula are mainly utilized in the prediction of BCVA, which validates the rationality of the CNN-based BCVA estimation schemes since the same area is also exploited during the retrospective medical chart review. Finally, we applied the t-distributed stochastic neighbor embedding to examine the characteristics of CNN-based BCVA estimation schemes. The developed BCVA estimation schemes can be employed to obtain the objective measurement of BVCA as well as the medical screening of people with poor access to medical care through smartphone-based fundus imaging.

Asymmetry between right and left fundus images identified using convolutional neural networks.

We analyzed fundus images to identify whether convolutional neural networks (CNNs) can discriminate between right and left fundus images. We gathered 98,038 fundus photographs from the Gyeongsang National University Changwon Hospital, South Korea, and augmented these with the Ocular Disease Intelligent Recognition dataset. We created eight combinations of image sets to train CNNs. Class activation mapping was used to identify the discriminative image regions used by the CNNs. CNNs identified right and left fundus images with high accuracy (more than 99.3% in the Gyeongsang National University Changwon Hospital dataset and 91.1% in the Ocular Disease Intelligent Recognition dataset) regardless of whether the images were flipped horizontally. The depth and complexity of the CNN affected the accuracy (DenseNet121: 99.91%, ResNet50: 99.86%, and VGG19: 99.37%). DenseNet121 did not discriminate images composed of only left eyes (55.1%, p = 0.548). Class activation mapping identified the macula as the discriminative region used by the CNNs. Several previous studies used the flipping method to augment data in fundus photographs. However, such photographs are distinct from non-flipped images. This asymmetry could result in undesired bias in machine learning. Therefore, when developing a CNN with fundus photographs, care should be taken when applying data augmentation with flipping.

Development of fully automated anterior chamber cell analysis based on image software.

Optical coherence tomography (OCT) is a noninvasive method that can quickly and accurately examine the eye at the cellular level. Several studies have used OCT for analysis of anterior chamber cells. However, these studies have several limitations. This study was performed to supplement existing reports of automated analysis of anterior chamber cell images using spectral domain OCT (SD-OCT) and to compare this method with the Standardization of Uveitis Nomenclature (SUN) grading system. We analyzed 2398 anterior segment SD-OCT images from 34 patients using code written in Python. Cell density, size, and eccentricity were measured automatically. Increases in SUN grade were associated with significant cell density increases at all stages (p < 0.001). Significant differences were observed in eccentricity in uveitis, post-surgical inflammation, and vitreous hemorrhage (p < 0.001). Anterior segment SD-OCT is reliable, fast, and accurate means of anterior chamber cell analysis. This method showed a strong correlation with the SUN grade system. Also, eccentricity could be helpful as a supplementary evaluation tool.