RESUMEN
Purpose: To develop and test a deep learning (DL) algorithm for detecting referable glaucoma in the Los Angeles County (LAC) Department of Health Services (DHS) teleretinal screening program. Methods: Fundus photographs and patient-level labels of referable glaucoma (defined as cup-to-disc ratio [CDR] ≥ 0.6) provided by 21 trained optometrist graders were obtained from the LAC DHS teleretinal screening program. A DL algorithm based on the VGG-19 architecture was trained using patient-level labels generalized to images from both eyes. Area under the receiver operating curve (AUC), sensitivity, and specificity were calculated to assess algorithm performance using an independent test set that was also graded by 13 clinicians with one to 15 years of experience. Algorithm performance was tested using reference labels provided by either LAC DHS optometrists or an expert panel of 3 glaucoma specialists. Results: 12,098 images from 5,616 patients (2,086 referable glaucoma, 3,530 non-glaucoma) were used to train the DL algorithm. In this dataset, mean age was 56.8 ± 10.5 years with 54.8% females and 68.2% Latinos, 8.9% Blacks, 2.7% Caucasians, and 6.0% Asians. 1,000 images from 500 patients (250 referable glaucoma, 250 non-glaucoma) with similar demographics (p ≥ 0.57) were used to test the DL algorithm. Algorithm performance matched or exceeded that of all independent clinician graders in detecting patient-level referable glaucoma based on LAC DHS optometrist (AUC = 0.92) or expert panel (AUC = 0.93) reference labels. Clinician grader sensitivity (range: 0.33-0.99) and specificity (range: 0.68-0.98) ranged widely and did not correlate with years of experience (p ≥ 0.49). Algorithm performance (AUC = 0.93) also matched or exceeded the sensitivity (range: 0.78-1.00) and specificity (range: 0.32-0.87) of 6 LAC DHS optometrists in the subsets of the test dataset they graded based on expert panel reference labels. Conclusions: A DL algorithm for detecting referable glaucoma developed using patient-level data provided by trained LAC DHS optometrists approximates or exceeds performance by ophthalmologists and optometrists, who exhibit variable sensitivity and specificity unrelated to experience level. Implementation of this algorithm in screening workflows could help reallocate eye care resources and provide more reproducible and timely glaucoma care.
RESUMEN
Purpose: The purpose of this study was to develop and test a programmable closed-loop system for tracking, modulating, and assessing dynamic iris behavior, including in the mid-dilated position. Methods: A programmable closed-loop iris control system was developed by customizing an ANTERION OCT device (Heidelberg Engineering, Heidelberg, Germany). Custom software was developed to store camera and optical coherence tomography (OCT) images, track pupillary diameter (PD), control a light-emitting diode (LED), and modulate ambient lighting to maintain the iris in a dilated, constricted, or mid-dilated position in real-time. Study participants underwent 3 consecutive 65-second scan sessions. Dynamic iris behavior in the form of peak constriction velocity (PCV) and mid-dilated iris activity (MDIA) were calculated and analyzed offline. Results: Among 58 participants, 56 (96.6%) were eligible for analysis based on achieving and maintaining mean PD within ±10% of the calculated mid-dilated PD. Mean participant age was 49.8 ± 18.9 years. Mean PCV was 3.92 ± 0.83 mm/s, and mean MDIA was 0.37 ± 0.15 mm. The mean difference between the calculated and achieved mid-dilated PD was 0.166 ± 0.192 mm. There were significant negative correlations between PCV and age (slope = -0.022, P < 0.001) and MDIA and age (slope = -0.004, P < 0.001). Success rates were lower (69.0%) but relationships between dynamic iris behavior and age were similar based on achieving and maintaining mean PD within ±5% of the calculated mid-dilated PD. Conclusions: A programmable closed-loop iris control system can modulate dynamic iris behavior and maintain the iris in a mid-dilated position. Pupillary constriction velocity and iris activity in the mid-dilated position decrease with age. Translational Relevance: This system can be applied to study dynamic disease processes involving the iris and establish novel biometric measures that could serve as risk factors for acute and chronic primary angle closure glaucoma (PACG).