Format

Send to

Choose Destination
Comput Biol Med. 2017 Mar 1;82:80-86. doi: 10.1016/j.compbiomed.2017.01.018. Epub 2017 Jan 27.

Comparing humans and deep learning performance for grading AMD: A study in using universal deep features and transfer learning for automated AMD analysis.

Author information

1
Applied Physics Laboratory, The Johns Hopkins University, MD, USA; Retina Division, Wilmer Eye Institute, Johns Hopkins University School of Medicine, USA; Department of Computer Science, The Johns Hopkins University, MD, USA.
2
Retina Division, Brazilian Center of Vision Eye Hospital, DF, Brazil.
3
Applied Physics Laboratory, The Johns Hopkins University, MD, USA.
4
Applied Physics Laboratory, The Johns Hopkins University, MD, USA. Electronic address: David.Freund@jhuapl.edu.
5
Retina Division, Wilmer Eye Institute, Johns Hopkins University School of Medicine, USA.

Abstract

BACKGROUND:

When left untreated, age-related macular degeneration (AMD) is the leading cause of vision loss in people over fifty in the US. Currently it is estimated that about eight million US individuals have the intermediate stage of AMD that is often asymptomatic with regard to visual deficit. These individuals are at high risk for progressing to the advanced stage where the often treatable choroidal neovascular form of AMD can occur. Careful monitoring to detect the onset and prompt treatment of the neovascular form as well as dietary supplementation can reduce the risk of vision loss from AMD, therefore, preferred practice patterns recommend identifying individuals with the intermediate stage in a timely manner.

METHODS:

Past automated retinal image analysis (ARIA) methods applied on fundus imagery have relied on engineered and hand-designed visual features. We instead detail the novel application of a machine learning approach using deep learning for the problem of ARIA and AMD analysis. We use transfer learning and universal features derived from deep convolutional neural networks (DCNN). We address clinically relevant 4-class, 3-class, and 2-class AMD severity classification problems.

RESULTS:

Using 5664 color fundus images from the NIH AREDS dataset and DCNN universal features, we obtain values for accuracy for the (4-, 3-, 2-) class classification problem of (79.4%, 81.5%, 93.4%) for machine vs. (75.8%, 85.0%, 95.2%) for physician grading.

DISCUSSION:

This study demonstrates the efficacy of machine grading based on deep universal features/transfer learning when applied to ARIA and is a promising step in providing a pre-screener to identify individuals with intermediate AMD and also as a tool that can facilitate identifying such individuals for clinical studies aimed at developing improved therapies. It also demonstrates comparable performance between computer and physician grading.

KEYWORDS:

Age-related macular degeneration, (AMD); Deep Convolutional Neural Networks, (DCNNs); Deep learning; Retinal image analysis; Transfer learning; Universal features

PMID:
28167406
PMCID:
PMC5373654
DOI:
10.1016/j.compbiomed.2017.01.018
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center