Purpose: We aimed to evaluate the feasibility of using a novel device, the Smart Eye Camera (SEC), for assessing tear meniscus height (TMH) after fluorescein staining and the agreement of the results with measurements obtained using standard slit lamp examination. Methods: TMH was assessed using both SEC and conventional slit lamp examination. The images were analyzed using the software ImageJ 1.53t (National Institutes of Health, Bethesda, MD, USA). A common measurement unit scale was established based on a paper strip, which was used as a calibration marker to convert pixels into metric scale. A color threshold was applied using uniform parameters for brightness, saturation, and hue. The images were then binarized to black and white to enhance the representation of the tear menisci. A 2 mm area around the upper and lower meniscus in the central eye lid zone was selected and magnified 3200 times to facilitate manual measurement. The values obtained using SEC were compared with those obtained with a slit lamp. Results: The upper and lower TMH values measured using the SEC were not statistically different from those obtained with a slit lamp (0.209 ± 0.073 mm vs. 0.235 ± 0.085, p = 0.073, and 0.297 ± 0.168 vs. 0.260 ± 0.173, p = 0.275, respectively). The results of Bland–Altman analysis demonstrated strong agreement between the two instruments, with a mean bias of −0.016 mm (agreement limits: −0.117 to 0.145 mm) for upper TMH and 0.031 mm (agreement limits: −0.306 to 0.368 mm) for lower TMH. Conclusions: The SEC demonstrated sufficient validity and reliability for assessing TMH in healthy eyes in a clinical setting, demonstrating concordance with the conventional slit lamp examination.
Primary angle closure glaucoma (PACG) is a major cause of visual impairment, particularly in Asia. Although effective screening tools are necessary, the current gold standard is complex and time-consuming, requiring extensive expertise. Artificial intelligence has introduced new opportunities for innovation in ophthalmic imaging. Anterior chamber depth (ACD) is a key risk factor for angle closure and has been suggested as a quick screening parameter for PACG. This study aims to develop an AI algorithm to quantitatively predict ACD from anterior segment photographs captured using a portable smartphone slit-lamp microscope. We retrospectively collected 204,639 frames from 1586 eyes, with ACD values obtained by anterior-segment OCT. We developed two models, (Model 1) diagnosable frame extraction and (Model 2) ACD estimation, using SWSL ResNet as the machine learning model. Model 1 achieved an accuracy of 0.994. Model 2 achieved an MAE of 0.093 ± 0.082 mm, an MSE of 0.123 ± 0.170 mm, and a correlation of R = 0.953. Furthermore, our model’s estimation of the risk for angle closure showed a sensitivity of 0.943, specificity of 0.902, and an area under the curve (AUC) of 0.923 (95%CI: 0.878–0.968). We successfully developed a high-performance ACD estimation model, laying the groundwork for predicting other quantitative measurements relevant to PACG screening.
Ophthalmological services face global inadequacies, especially in low- and middle-income countries, which are marked by a shortage of practitioners and equipment. This study employed a portable slit lamp microscope with video capabilities and cloud storage for more equitable global diagnostic resource distribution. To enhance accessibility and quality of care, this study targets corneal opacity, which is a global cause of blindness. This study has two purposes. The first is to detect corneal opacity from videos in which the anterior segment of the eye is captured. The other is to develop an AI pipeline to detect corneal opacities. First, we extracted image frames from videos and processed them using a convolutional neural network (CNN) model. Second, we manually annotated the images to extract only the corneal margins, adjusted the contrast with CLAHE, and processed them using the CNN model. Finally, we performed semantic segmentation of the cornea using annotated data. The results showed an accuracy of 0.8 for image frames and 0.96 for corneal margins. Dice and IoU achieved a score of 0.94 for semantic segmentation of the corneal margins. Although corneal opacity detection from video frames seemed challenging in the early stages of this study, manual annotation, corneal extraction, and CLAHE contrast adjustment significantly improved accuracy. The incorporation of manual annotation into the AI pipeline, through semantic segmentation, facilitated high accuracy in detecting corneal opacity.
Ophthalmological services face global inadequacies, especially in low- and middle-income countries, which are marked by a shortage of both practitioners and equipment. This study employed a portable slit-lamp microscope with video capabilities and cloud storage for a more equitable global diagnostic resource distribution. To enhance accessibility and quality of care, this study targeted corneal opacity, a global cause of blindness. To boost the online diagnosis efficiency, an AI pipeline was developed using anterior segment videos to detect corneal opacity. First, we extracted image frames from videos and learned them using a Convolutional Neural Network(CNN) model. Second, we manually annotated to extract only the corneal margins, adjusted the contrast with CLAHE, and learned using the CNN model. Finally, we performed semantic segmentation of the cornea using the annotated data. The results showed an accuracy of 0.8 for image frames, and 0.96 for corneal margins. Dice and IoU were 0.94 for semantic segmentation of corneal margins. While corneal opacity detection from video frames seemed challenging in the early stages of this study, manual annotation, corneal extraction, and CLAHE contrast adjustment significantly improved accuracy. Integrating manual annotation into the AI pipeline through semantic segmentation achieved a high accuracy in detecting corneal opacity.