Abstract
Within the next 1.5 decades, 1 in 7 U.S. adults is anticipated to suffer from age-related macular degeneration (AMD), a degenerative retinal disease which leads to blindness if untreated. Optical coherence tomography angiography (OCTA) has become a prime technique for AMD diagnosis, specifically for late-stage neovascular (NV) AMD. Such technologies generate massive amounts of data, challenging to parse by experts alone, transforming artificial intelligence into a valuable partner. We describe a deep learning (DL) approach which achieves multi-class detection of non-AMD vs. non-neovascular (NNV) AMD vs. NV AMD from a combination of OCTA, OCT structure, 2D b-scan flow images, and high definition (HD) 5-line b-scan cubes; DL also detects ocular biomarkers indicative of AMD risk. Multimodal data were used as input to 2D-3D Convolutional Neural Networks (CNNs). Both for CNNs and experts, choroidal neovascularization and geographic atrophy were found to be important biomarkers for AMD. CNNs predict biomarkers with accuracy up to 90.2% (positive-predictive-value up to 75.8%). Just as experts rely on multimodal data to diagnose AMD, CNNs also performed best when trained on multiple inputs combined. Detection of AMD and its biomarkers from OCTA data via CNNs has tremendous potential to expedite screening of early and late-stage AMD patients.
Highlights
Age-related macular degeneration (AMD) is a leading cause of blindness, impacting millions of people worldwide[1,2]
Building on our past w ork[18,19], this study offers three key contributions: (1) multi-class detection of non-age-related macular degeneration (AMD) vs. NNV AMD vs. neovascular AMD (NV AMD) from a multimodal combination of Optical coherence tomography angiography (OCTA), optical coherence tomography (OCT) structure, 2D b-scan flow images, as well as high definition (HD) 5-line b-scan cubes, (2) model ablation studies with subsets of the above input modalities to arrive at the input set(s) which optimize multiclass accuracy, and (3) detection of features/biomarkers within these volumes that can be used independently for diagnosis
Results of labeling five AMD biomarkers showed that Choroidal neovascularization (CNV) and geographic atrophy (GA) are important predictors for all (NNV or NV) AMD compared to non-AMD eyes based on Fisher’s Exact Test odds ratios[20]; CNV and GA had odds ratios of 36 and 32 for experts, respectively, and 32 and 26 for the convolutional neural networks (CNNs), respectively
Summary
Age-related macular degeneration (AMD) is a leading cause of blindness, impacting millions of people worldwide[1,2]. Building on our past w ork[18,19], this study offers three key contributions: (1) multi-class detection of non-AMD vs NNV AMD vs NV AMD from a multimodal combination of OCTA, OCT structure, 2D b-scan flow images, as well as HD 5-line b-scan cubes, (2) model ablation studies with subsets of the above input modalities to arrive at the input set(s) which optimize multiclass accuracy, and (3) detection of features/biomarkers within these volumes that can be used independently for diagnosis. Through this second goal, we compare ocular biomarkers detected by humans with those detected by CNNs as a means by which to corroborate/explain the CNN’s decision-making mechanism
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
