Data from: Quantifying changes on optical coherence tomography in eyes receiving treatment for neovascular age-related macular degeneration
Data files
Aug 23, 2024 version files 16 MB
-
AMD_longitudinal_MEH_v2.csv
16 MB
-
README.md
2.68 KB
Nov 01, 2024 version files 15.71 MB
-
AMD_longitudinal_MEH_v4.csv
15.71 MB
-
README.md
2.78 KB
Abstract
Purpose
Application of artificial intelligence (AI) to macular optical coherence tomography (OCT) scans to segment and quantify volumetric change of anatomical and pathological features during intravitreal treatment for neovascular age-related macular degeneration (AMD).
Design
Retrospective analysis of OCT images from the Eye Hospital AMD Database.
Participants
2115 eyes from 1883 patients that started anti-vascular endothelial growth factor (anti-VEGF) treatment between 1st June 2012 and 30th June 2017.
Methods
The Eye Hospital neovascular AMD database was queried for first and second eyes that received anti-VEGF treatment and had an OCT scan at baseline and at 12 months. Follow-up scans were input into the AI system to derive volumetric outputs for the following variables: intraretinal fluid (IRF), subretinal fluid (SRF), pigment epithelial detachment (PED), subretinal hyperreflective material (SHRM), hyperreflective foci (HRF), neurosensory retina (NSR) and retinal pigment epithelium (RPE). Volumes were studied at different time points and comparisons made with respect to baseline volume groups. Cross-sectional comparisons between time points were conducted using Mann-Whitney U test.
Results
Mean volumes of analysed features decreased significantly from baseline to both four and 12 months, in both first and second-treated eyes. Pathological features that reflect exudation, including pure fluid components (IRF and SRF) and those with a mixture of fluid and fibrovascular tissue (PED and SHRM), displayed similar response to treatment over 12 months. Mean PED and SHRM volumes showed less pronounced but also substantial decreases over the first two months, reaching a plateau post loading phase, and minimal change to 12 months. Both NSR and RPE volumes showed gradual reductions over time, and not as substantial as exudative features.
Conclusion
We report the results of a quantitative analysis of change in retinal segmented features over time, enabled by an AI segmentation system. Cross-sectional analysis at multiple time points demonstrated significant associations between baseline OCT-derived segmented features and the volume of biomarkers at follow-up. Demonstrating how certain OCT biomarkers progress with treatment and the impact of pre-treatment retinal morphology on different structural volumes may provide novel insights into disease mechanisms and aid personalization of care. Data will be made public for future studies.
README: Data from: Quantifying changes on optical coherence tomography in eyes receiving treatment for neovascular age-related macular degeneration
INTRODUCTION
This CSV dataset (AMD_longitudinal_MEH_v1.csv) is associated with the paper Moraes et al. Quantifying changes on optical coherence tomography in eyes receiving treatment for neovascular age-related macular degeneration. Ophthalmology Science. (2024). Available at: https://doi.org/10.1016/j.xops.2024.100570
The dataset comprises anonymised metadata and OCT segmentation data of patients undergoing treatment for wet AMD.
DATA FIELDS
ID Anonymous ID - an integer indicating the ID of the patient
DaysSinceBaseline Replaces visit dates of patient. Baseline is denoted as '0' for the day the first eye was treated with an injection
Eye Left or Right
FirstTreatedEye The eye that first received an injection (Left or Right)
Gender Male or female
Neurosensory Number of voxels segmented as the feature neurosensory retina (NSR)
RPE Number of voxels segmented as the feature retinal pigment epithelium (RPE)
IRF Number of voxels segmented as the feature intraretinal fluid (IRF)
SRF Number of voxels segmented as the feature subretinal fluid (SRF)
SHRM Number of voxels segmented as the feature subretinal hyperreflective material (SHRM)
Drusenoid_PED Number of voxels segmented as the feature drusen
Serous_PED Number of voxels segmented as the feature serous pigment epithelium detachment (sPED)
Fibrovascular_PED Number of voxels segmented as the feature fibrovascular pigment epithelium detachment (fvPED)
grouped_ethnicity Ethnic groups combined into: 'White', 'Black', 'Asian', 'Other or unknown'
grouped_VA Visual acuity groups
grouped_age Age groups of 50-59, 60-69, 70-79, >80, or NULL if unknown.
NOTES
* Cells with NA indicate missing data
* Each voxel equates to 2.60 x 11.72 x 47.24 μm in the A-scan, B-scan, and C-scan directions, respectively
* Each eye included in the dataset is given a unique ID. To ensure anonymisation, it is not possible to link a patient’s two eyes if the individual has both eyes in the dataset
* All OCT data is captured using 3DOCT-2000 devices (Topcon Corp., Tokyo, Japan). All images comprise 512*885*128 voxels covering a volume of 6x6x2.3mm
* Segmentation data was output using a deep learning segmentation model described further in De Fauw et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nature Medicine (2018); and Yim and Chopra et al. Predicting conversion to wet age-related macular degeneration using deep learning. Nature Medicine. (2020)
Version changes
24-Oct-2024
Provided IDs for longitudinal tracking.