A Study Validating the Estimation of Anterior Chamber Depth and Iridocorneal Angle with Portable and Non-Portable Slit-Lamp Microscopy.

This study assessed the anterior chamber depth (ACD) and iridocorneal angle using a portable smart eye camera (SEC) compared to the conventional slit-lamp microscope and anterior-segment optical coherence tomography (AS-OCT). This retrospective case-control study included 170 eyes from 85 Japanese patients. The correlation between the ACD evaluations conducted with the SEC and conventional slit-lamp was high (r = 0.814). The correlation between the Van-Herick Plus grade obtained using two devices was also high (r = 0.919). A high kappa value was observed for the Van-Herick Plus grading (Kappa = 0.757). A moderate correlation was observed between the ACD measured using AS-OCT and the slit-lamp image acquired with the conventional slit-lamp microscope and SEC (r = 0.609 and 0.641). A strong correlation was observed between the trabecular-iris angle (TIA) measured using AS-OCT and Van-Herick Plus grade obtained with the conventional slit-lamp microscope and SEC (r = 0.702 and 0.764). Strong correlations of ACD evaluation and high kappa value of the Van-Herick Plus grading indicated the adequate subjective assessment function of the SEC. Moderate correlations between the ACD objective measurement and evaluation and strong correlation between the TIA and Van-Herick Plus grade suggested the good objective assessment function of the SEC. The SEC demonstrated adequate performance for ACD evaluation and angle estimation.

AI-based diagnosis of nuclear cataract from slit-lamp videos.

In ophthalmology, the availability of many fundus photographs and optical coherence tomography images has spurred consideration of using artificial intelligence (AI) for diagnosing retinal and optic nerve disorders. However, AI application for diagnosing anterior segment eye conditions remains unfeasible due to limited standardized images and analysis models. We addressed this limitation by augmenting the quantity of standardized optical images using a video-recordable slit-lamp device. We then investigated whether our proposed machine learning (ML) AI algorithm could accurately diagnose cataracts from videos recorded with this device. We collected 206,574 cataract frames from 1812 cataract eye videos. Ophthalmologists graded the nuclear cataracts (NUCs) using the cataract grading scale of the World Health Organization. These gradings were used to train and validate an ML algorithm. A validation dataset was used to compare the NUC diagnosis and grading of AI and ophthalmologists. The results of individual cataract gradings were: NUC 0: area under the curve (AUC) = 0.967; NUC 1: AUC = 0.928; NUC 2: AUC = 0.923; and NUC 3: AUC = 0.949. Our ML-based cataract diagnostic model achieved performance comparable to a conventional device, presenting a promising and accurate auto diagnostic AI tool.

Artificial intelligence to estimate the tear film breakup time and diagnose dry eye disease.

The use of artificial intelligence (AI) in the diagnosis of dry eye disease (DED) remains limited due to the lack of standardized image formats and analysis models. To overcome these issues, we used the Smart Eye Camera (SEC), a video-recordable slit-lamp device, and collected videos of the anterior segment of the eye. This study aimed to evaluate the accuracy of the AI algorithm in estimating the tear film breakup time and apply this model for the diagnosis of DED according to the Asia Dry Eye Society (ADES) DED diagnostic criteria. Using the retrospectively corrected DED videos of 158 eyes from 79 patients, 22,172 frames were annotated by the DED specialist to label whether or not the frame had breakup. The AI algorithm was developed using the training dataset and machine learning. The DED criteria of the ADES was used to determine the diagnostic performance. The accuracy of tear film breakup time estimation was 0.789 (95% confidence interval (CI) 0.769-0.809), and the area under the receiver operating characteristic curve of this AI model was 0.877 (95% CI 0.861-0.893). The sensitivity and specificity of this AI model for the diagnosis of DED was 0.778 (95% CI 0.572-0.912) and 0.857 (95% CI 0.564-0.866), respectively. We successfully developed a novel AI-based diagnostic model for DED. Our diagnostic model has the potential to enable ophthalmology examination outside hospitals and clinics.