Phenotypic expressions of the optic disc in primary open-angle glaucoma.

BACKGROUND: Which phenotypes are we able to recognize in the optic nerve of patients with primary open angle glaucoma? METHODS: Retrospective interventional case series. 885 eyes from 885 patients at an outpatient tertiary care centre who met specified criteria for POAG were included. Disc photographs were classified by three glaucoma specialists into the following phenotypes according to their predominant characteristics: (1) concentric rim thinning, (2) focal rim thinning, (3) acquired pit of the optic nerve (APON), (4) tilted, (5) extensive peripapillary atrophy (PPA), and (6) broad rim thinning. Demographic, medical, and ocular data were collected. Kruskal-Wallis was used as a non-parametric test and pairwise comparison was performed by using Wilcoxon rank sum test corrected. RESULTS: Phenotypic distribution was as follows: 398(45%) focal thinning, 153(18%) concentric thinning, 153(17%) broad thinning, 109(12%) tilted, 47(5%) extensive PPA and 25(3%) APON. Phenotypic traits of interest included a higher proportion of female patients with the focal thinning phenotype (p = 0.015); myopia (p = 0.000), Asian race (OR: 8.8, p = 0.000), and younger age (p = 0.000) were associated with the tilted phenotype; the concentric thinning patients had thicker RNFL (p = 0.000), higher MD (p = 0.008) and lower PSD (p = 0.043) than broad thinning, despite no difference in disc sizes (p = 0.849). The focal thinning group had a localized VF pattern with high PSD compared to concentric thinning (p = 0.005). CONCLUSION: We report six phenotypic classifications of POAG patients with demographic and ocular differences between phenotypes. Future refinement of phenotypes should allow enhanced identification of genetic associations and improved individualization of patient care.

A Neural Network for Automated Image Quality Assessment of Optic Disc Photographs.

This study describes the development of a convolutional neural network (CNN) for automated assessment of optic disc photograph quality. Using a code-free deep learning platform, a total of 2377 optic disc photographs were used to develop a deep CNN capable of determining optic disc photograph quality. Of these, 1002 were good-quality images, 609 were acceptable-quality, and 766 were poor-quality images. The dataset was split 80/10/10 into training, validation, and test sets and balanced for quality. A ternary classification model (good, acceptable, and poor quality) and a binary model (usable, unusable) were developed. In the ternary classification system, the model had an overall accuracy of 91% and an AUC of 0.98. The model had higher predictive accuracy for images of good (93%) and poor quality (96%) than for images of acceptable quality (91%). The binary model performed with an overall accuracy of 98% and an AUC of 0.99. When validated on 292 images not included in the original training/validation/test dataset, the model's accuracy was 85% on the three-class classification task and 97% on the binary classification task. The proposed system for automated image-quality assessment for optic disc photographs achieves high accuracy in both ternary and binary classification systems, and highlights the success achievable with a code-free platform. There is wide clinical and research potential for such a model, with potential applications ranging from integration into fundus camera software to provide immediate feedback to ophthalmic photographers, to prescreening large databases before their use in research.

The Trajectory of Glaucoma Progression in 2-Dimensional Structural-Functional Space.

PURPOSE: To present a method that allows visualization of functional and structural change in 2-dimensional space. DESIGN: Retrospective, longitudinal, observational study. PARTICIPANTS: Patients from the Stein Eye Institute, UCLA from 1993 through 2017. METHODS: Patients were arranged into 2 cohorts. Cohort 1 was used to create a structural score for the horizontal axis of the structural-functional (S-F) 2-dimensional space. The visual field (VF) index was used for the vertical axis as the functional score. Cohort 2 was used to apply those scores for analysis of S-F progression with a combined vector. The first cohort included eyes with mild glaucoma (abnormal glaucoma hemifield test results, pattern standard deviation <0.05 on 2 examinations, or mean deviation [MD] >-5 dB) and normal control participants. The second cohort included all stages of open-angle glaucoma with ≥5 OCT retinal nerve fiber layer scans, ≥5 reliable visual field (VF) results, and follow-up of ≥4 years. MAIN OUTCOME MEASURES: Vectors were created for each eye to represent the trajectory of glaucoma progression over time. Each vector was defined by structural (x-axis) and functional (y-axis) components. The structural component was calculated with a linear model of Heidelberg Retina Tomograph (Heidelberg Engineering, Heidelberg, Germany) scores over time. The functional component was calculated with a linear model of VF measurements over time. The resultant vector and its confidence interval were plotted in 2-dimensional S-F space. Eyes were divided into severity stages based on baseline MD. A mean vector was calculated for each severity stage. RESULTS: We obtained 290 vectors from 290 eyes of 196 patients. The mean ± standard deviation follow-up period was 14.6±3.1 years. Average age was 58.6±8.8 years. Preperimetric, mild, moderate, and severe categories included 41, 89, 97, and 63 eyes, respectively. Mean baseline MDs were 0.8 dB, -0.95 dB, -3.57 dB, and -11.51 dB, respectively, and mean vector slopes for each severity categories were 0.79, 0.95, 1.95, and 2.08, respectively. Cook's distance removed 131 (7.1%) and 137 (7.4%) outliers from the structure and function regressions, respectively. CONCLUSIONS: We report a method to visualize the trajectory of a patient's glaucoma progression in a 2-dimensional S-F space. The slope of the trajectory of glaucoma progression is a function of the severity of the disease.