Unsupervised deep learning for grading of age-related macular degeneration using retinal fundus images

10/22/2020
by   Baladitya Yellapragada, et al.
0

Many diseases are classified based on human-defined rubrics that are prone to bias. Supervised neural networks can automate the grading of retinal fundus images, but require labor-intensive annotations and are restricted to the specific trained task. Here, we employed an unsupervised network with Non-Parametric Instance Discrimination (NPID) to grade age-related macular degeneration (AMD) severity using fundus photographs from the Age-Related Eye Disease Study (AREDS). Our unsupervised algorithm demonstrated versatility across different AMD classification schemes without retraining, and achieved unbalanced accuracies comparable to supervised networks and human ophthalmologists in classifying advanced or referable AMD, or on the 4-step AMD severity scale. Exploring the networks behavior revealed disease-related fundus features that drove predictions and unveiled the susceptibility of more granular human-defined AMD severity schemes to misclassification by both ophthalmologists and neural networks. Importantly, unsupervised learning enabled unbiased, data-driven discovery of AMD features such as geographic atrophy, as well as other ocular phenotypes of the choroid, vitreous, and lens, such as visually-impairing cataracts, that were not pre-defined by human labels.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/02/2018

A multi-task deep learning model for the classification of Age-related Macular Degeneration

Age-related Macular Degeneration (AMD) is a leading cause of blindness. ...
research
05/16/2020

Improving Robustness using Joint Attention Network For Detecting Retinal Degeneration From Optical Coherence Tomography Images

Noisy data and the similarity in the ocular appearances caused by differ...
research
07/28/2021

Retinal Microvasculature as Biomarker for Diabetes and Cardiovascular Diseases

Purpose: To demonstrate that retinal microvasculature per se is a reliab...
research
11/26/2018

A Consolidated Approach to Convolutional Neural Networks and the Kolmogorov Complexity

The ability to precisely quantify similarity between various entities ha...
research
12/01/2018

Automated segmentaiton and classification of arterioles and venules using Cascading Dilated Convolutional Neural Networks

The change of retinal vasculature is an early sign of many vascular and ...
research
01/07/2023

The 3D Structural Phenotype of the Glaucomatous Optic Nerve Head and its Relationship with The Severity of Visual Field Damage

Purpose: To describe the 3D structural changes in both connective and ne...

Please sign up or login with your details

Forgot password? Click here to reset