Automated detection of dilated capillaries on optical coherence tomography angiography

Changlei Dongye; Miao Zhang; Thomas S. Hwang; Jie Wang; Simon S. Gao; Liang Liu; David Huang; David J. Wilson; Yali Jia

doi:10.1364/BOE.8.001101

Automated detection of dilated capillaries on optical coherence tomography angiography

Changlei Dongye
, Miao Zhang
, Thomas S. Hwang
, Jie Wang
, Simon S. Gao
, Liang Liu
, David Huang
, David J. Wilson
, Yali Jia

Ophthalmology

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

Automated detection and grading of angiographic high-risk features in diabetic retinopathy can potentially enhance screening and clinical care. We have previously identified capillary dilation in angiograms of the deep plexus in optical coherence tomography angiography as a feature associated with severe diabetic retinopathy. In this study, we present an automated algorithm that uses hybrid contrast to distinguish angiograms with dilated capillaries from healthy controls and then applies saliency measurement to map the extent of the dilated capillary networks. The proposed algorithm agreed well with human grading.

Original language	English (US)
Article number	#279084
Pages (from-to)	1101-1109
Number of pages	9
Journal	Biomedical Optics Express
Volume	8
Issue number	2
DOIs	https://doi.org/10.1364/BOE.8.001101
State	Published - Feb 1 2017

Funding

This work was supported by grant DP3 DK104397, R01 EY024544, R01 EY023285, P30 EY010572 from the National Institutes of Health (Bethesda, MD), and by unrestricted departmental funding from Research to Prevent Blindness (New York, NY).

Funders
Author National Institutes of Health National Institutes of Health National Institutes of Health National Institutes of Health The Bev Hartig Huntington's Disease Foundation National Institutes of Health
Research to Prevent Blindness

Keywords

Image analysis
Image processing
Medical and biological imaging
Ophthalmology
Optical coherence tomography

ASJC Scopus subject areas

Biotechnology
Atomic and Molecular Physics, and Optics

Access to Document

10.1364/BOE.8.001101

Cite this

@article{4c65421790d746468bd2e798ffe1d0c3,

title = "Automated detection of dilated capillaries on optical coherence tomography angiography",

abstract = "Automated detection and grading of angiographic high-risk features in diabetic retinopathy can potentially enhance screening and clinical care. We have previously identified capillary dilation in angiograms of the deep plexus in optical coherence tomography angiography as a feature associated with severe diabetic retinopathy. In this study, we present an automated algorithm that uses hybrid contrast to distinguish angiograms with dilated capillaries from healthy controls and then applies saliency measurement to map the extent of the dilated capillary networks. The proposed algorithm agreed well with human grading.",

keywords = "Image analysis, Image processing, Medical and biological imaging, Ophthalmology, Optical coherence tomography",

author = "Changlei Dongye and Miao Zhang and Hwang, \{Thomas S.\} and Jie Wang and Gao, \{Simon S.\} and Liang Liu and David Huang and Wilson, \{David J.\} and Yali Jia",

note = "Publisher Copyright: {\textcopyright} 2017 Optical Society of America.",

year = "2017",

month = feb,

day = "1",

doi = "10.1364/BOE.8.001101",

language = "English (US)",

volume = "8",

pages = "1101--1109",

journal = "Biomedical Optics Express",

issn = "2156-7085",

publisher = "Optica Publishing Group (formerly OSA)",

number = "2",

}

TY - JOUR

T1 - Automated detection of dilated capillaries on optical coherence tomography angiography

AU - Dongye, Changlei

AU - Zhang, Miao

AU - Hwang, Thomas S.

AU - Wang, Jie

AU - Gao, Simon S.

AU - Liu, Liang

AU - Huang, David

AU - Wilson, David J.

AU - Jia, Yali

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Automated detection and grading of angiographic high-risk features in diabetic retinopathy can potentially enhance screening and clinical care. We have previously identified capillary dilation in angiograms of the deep plexus in optical coherence tomography angiography as a feature associated with severe diabetic retinopathy. In this study, we present an automated algorithm that uses hybrid contrast to distinguish angiograms with dilated capillaries from healthy controls and then applies saliency measurement to map the extent of the dilated capillary networks. The proposed algorithm agreed well with human grading.

AB - Automated detection and grading of angiographic high-risk features in diabetic retinopathy can potentially enhance screening and clinical care. We have previously identified capillary dilation in angiograms of the deep plexus in optical coherence tomography angiography as a feature associated with severe diabetic retinopathy. In this study, we present an automated algorithm that uses hybrid contrast to distinguish angiograms with dilated capillaries from healthy controls and then applies saliency measurement to map the extent of the dilated capillary networks. The proposed algorithm agreed well with human grading.

KW - Image analysis

KW - Image processing

KW - Medical and biological imaging

KW - Ophthalmology

KW - Optical coherence tomography

UR - https://www.scopus.com/pages/publications/85011596020

UR - https://www.scopus.com/pages/publications/85011596020#tab=citedBy

U2 - 10.1364/BOE.8.001101

DO - 10.1364/BOE.8.001101

M3 - Article

AN - SCOPUS:85011596020

SN - 2156-7085

VL - 8

SP - 1101

EP - 1109

JO - Biomedical Optics Express

JF - Biomedical Optics Express

IS - 2

M1 - #279084

ER -

Automated detection of dilated capillaries on optical coherence tomography angiography

Abstract

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this