Quantitative analysis of optical coherence tomography for neovascular age-related macular degeneration using deep learning
Moraes, Gabriella et al. (2020), Quantitative analysis of optical coherence tomography for neovascular age-related macular degeneration using deep learning, Dryad, Dataset, https://doi.org/10.5061/dryad.2rbnzs7m4
Purpose: To apply a deep learning algorithm for automated, objective, and comprehensive quantification of optical coherence tomography (OCT) scans to a large real-world dataset of eyes with neovascular age-related macular degeneration (AMD), and make the raw segmentation output data openly available for further research.
Design: Retrospective analysis of OCT images from the Moorfields Eye Hospital AMD Database.
Participants: 2473 first-treated eyes and another 493 second-treated eyes that commenced therapy for neovascular AMD between June 2012 and June 2017.
Methods: A deep learning algorithm was used to segment all baseline OCT scans. Volumes were calculated for segmented features such as neurosensory retina (NSR), drusen, intraretinal fluid (IRF), subretinal fluid (SRF), subretinal hyperreflective material (SHRM), retinal pigment epithelium (RPE), hyperreflective foci (HRF), fibrovascular pigment epithelium detachment(fvPED), and serous PED (sPED). Analyses included comparisons between first and second eyes, by visual acuity (VA) and by race/ethnicity, and correlations between volumes.
Main outcome measures: Volumes of segmented features (mm3), central subfield thickness (CST).
Results: In first-treated eyes, the majority had both IRF and SRF (54.7%). First-treated eyes had greater volumes for all segmented tissues, with the exception of drusen, which was greater in second-treated eyes. In first-treated eyes, older age was associated with lower volumes for RPE, SRF, NSR and sPED; in second-treated eyes, older age was associated with lower volumes of NSR, RPE, sPED, fvPED and SRF. Eyes from black individuals had higher SRF, RPE and serous PED volumes, compared with other ethnic groups. Greater volumes of the vast majority of features were associated with worse VA.
Conclusion: We report the results of large scale automated quantification of a novel range of baseline features in neovascular AMD. Major differences between first and second-treated eyes, with increasing age, and between ethnicities are highlighted. In the coming years, enhanced, automated OCT segmentation may assist personalization of real-world care, and the detection of novel structure-function correlations. These data will be made publicly available for replication and future investigation by the AMD research community.
This dataset comprises anonymised metadata and OCT segmentation data of patients undergoing treatment for wet AMD at Moorfields Eye Hospital, London, United Kingdom. The Moorfields AMD dataset for this study included all treatment-naive eyes that began anti-VEGF therapy for neovascular AMD between 1st June 2012 and 30th June 2017. Imaging data included macular OCT scans captured using 3DOCT-2000 devices (Topcon Corp., Tokyo, Japan) comprising 128 B-scans covering a volume of 6x6x2.3mm. Patient demographics recorded in Moorfields' electronic medical record including age, self-reported gender identity and race/ethnicity, along with associated clinical metadata including visual acuity (VA) in ETDRS (early treatment diabetic retinopathy study) letters and whether an injection was administered, was available for each visit. Whenever an OCT scan was not available on the exact day of the first injection for the first-treated eye, a scan from up to 14 days prior was used. Second-treated eyes that sequentially converted to neovascular AMD and started treatment in the time period of this study were also analysed, with their baseline scan at their first injection visit used for analysis. Second-treated eyes were not required to have contributed to the first-treated eye cohort. All eyes were analysed independently.
Each row of the CSV is associated with OCT segmentation data. This data was obtained by inputting each OCT into a deep learning-based 3D segmentation network that automatically predicts segmented features present in each voxel of the image. Voxels can be summed and multiplied by the real world voxel size to provide volumetric measurements of each feature. For this study, the following segmented features were analysed: neurosensory retina (NSR), retinal pigment epithelium (RPE), IRF, SRF, SHRM, hyperreflective foci (HRF), drusen, fibrovascular pigment epithelium detachment (fvPED), and serous PED (sPED). The CST measurements were defined as average thickness in the central 1mm diameter circle of the ETDRS grid, measured in μm. The CST comprised all segmented features above the RPE to the inner boundary of the NSR, including SHRM, SRF, HRF, and IRF.
ReadMe file attached
Macular Society, Award: 179050