Correlation Between Blue Fundus Autofluorescence and SD-OCT Measurements of Geographic Atrophy in Dry Age-Related Macular Degeneration.

PURPOSE: To compare fundus autofluorescence (FAF) and spectral domain optical coherence tomography (OCT) measurements of geographic atrophy (GA) area and to analyze lesion area changes measured by spectral domain OCT in GATHER1. DESIGN: An assessment reliability analysis using prospective, randomized, double-masked phase 2/3 clinical trial data. METHODS: GATHER1 examined the efficacy and safety of avacincaptad pegol (ACP) for GA treatment. A post hoc analysis was performed to identify correlations between FAF- and OCT-based measurements of GA. GA area was measured on blue-light FAF images using semiautomatic segmentation software with support from OCT and near-infrared imaging. Machine-learning enhanced, multilayer segmentation of OCT scans were reviewed by human readers, and segmentation errors were corrected as needed. GA area was defined as total RPE loss on cross-sectional B scans. Time points included Months 0, 6, 12, and 18. Additionally, OCT-based GA-area changes between ACP and sham were analyzed. RESULTS: There was a strong correlation (r = 0.93) between FAF and OCT GA area measurements that persisted through 18 months. Mean (SD) differences between OCT and FAF GA measurements were negligible: 0.11 mm2 (1.42) at Month 0, 0.03 mm2 (1.62) at Month 6, -0.17 mm2 (1.81) at Month 12, and -0.07 mm2 (1.78) at Month 18. OCT assessments of GA growth revealed a 30% and 27% reduction at Months 12 and 18, respectively, between ACP and sham, replicating FAF measurements from GATHER1. CONCLUSIONS: The strong correlation between blue FAF and OCT measurements of GA area supports OCT as a reliable method to measure GA lesion area in clinical trials.

Automated Identification and Segmentation of Ellipsoid Zone At-Risk Using Deep Learning on SD-OCT for Predicting Progression in Dry AMD.

BACKGROUND: The development and testing of a deep learning (DL)-based approach for detection and measurement of regions of Ellipsoid Zone (EZ) At-Risk to study progression in nonexudative age-related macular degeneration (AMD). METHODS: Used in DL model training and testing were 341 subjects with nonexudative AMD with or without geographic atrophy (GA). An independent dataset of 120 subjects were used for testing model performance for prediction of GA progression. Accuracy, specificity, sensitivity, and intraclass correlation coefficient (ICC) for DL-based EZ At-Risk percentage area measurement was calculated. Random forest-based feature ranking of EZ At-Risk was compared to previously validated quantitative OCT-based biomarkers. RESULTS: The model achieved a detection accuracy of 99% (sensitivity = 99%; specificity = 100%) for EZ At-Risk. Automatic EZ At-Risk measurement achieved an accuracy of 90% (sensitivity = 90%; specificity = 84%) and the ICC compared to ground truth was high (0.83). In the independent dataset, higher baseline mean EZ At-Risk correlated with higher progression to GA at year 5 (p < 0.001). EZ At-Risk was a top ranked feature in the random forest assessment for GA prediction. CONCLUSIONS: This report describes a novel high performance DL-based model for the detection and measurement of EZ At-Risk. This biomarker showed promising results in predicting progression in nonexudative AMD patients.

Machine Learning-Based Automated Detection and Quantification of Geographic Atrophy and Hypertransmission Defects Using Spectral Domain Optical Coherence Tomography.

The current study describes the development and assessment of innovative, machine learning (ML)-based approaches for automated detection and pixel-accurate measurements of regions with geographic atrophy (GA) in late-stage age-related macular degeneration (AMD) using optical coherence tomography systems. 900 OCT volumes, 100266 B-scans, and en face OCT images from 341 non-exudative AMD patients with or without GA were included in this study from both Cirrus (Zeiss) and Spectralis (Heidelberg) OCT systems. B-scan and en face level ground truth GA masks were created on OCT B-scan where the segmented ellipsoid zone (EZ) line, retinal pigment epithelium (RPE) line, and bruchs membrane (BM) line overlapped. Two deep learning-based approaches, B-scan level and en face level, were trained. The OCT B-scan model had detection accuracy of 91% and GA area measurement accuracy of 94%. The en face OCT model had detection accuracy of 82% and GA area measurement accuracy of 96% with primary target of hypertransmission on en face OCT. Accuracy was good for both devices tested (92-97%). Automated lesion size stratification for CAM cRORA definition of 250um minimum lesion size was feasible. High-performance models for automatic detection and segmentation of GA area were achieved using OCT systems and deep learning. The automatic measurements showed high correlation with the ground truth. The en face model excelled at identification of hypertransmission defects. The models performance generalized well across device types tested. Future development will include integration of both models to enhance feature detection across GA lesions as well as isolating hypertransmission defects without GA for pre-GA biomarker extraction.

A systematic review of in vitro cytokine production in eating disorders.

BACKGROUND: Eating disorders (EDs) have been associated with alterations in cytokine concentrations and production. This review examines whether in vitro cytokine production (i) is altered in people with EDs compared to healthy participants; and (ii) changes in response to treatment? METHODS: Using PRISMA guidelines, we systematically reviewed articles reporting group comparisons or longitudinal assessments of spontaneous and/or stimulated cytokine production in vitro in people with EDs. RESULTS: Twelve studies were included. Cross-sectional results were mixed in anorexia nervosa. Only one study measured cytokine production in bulimia nervosa. Two longitudinal studies showed that daily yoghurt consumption increases phytohemagglutinin-stimulated interferon-γ production in anorexia nervosa. CONCLUSION: The mixed results could be accounted for by variations in experimental design. Our findings suggest that cytokine production could possibly be modulated through dietary interventions. However, due to the methodological heterogeneity and shortcomings of the included studies, it seems unreasonable to draw further conclusions.