Automated detection of photoreceptor disruption in mild diabetic retinopathy on volumetric optical coherence tomography

Zhuo Wang, Acner Camino, Miao Zhang, Jie Wang, Thomas Hwang, David Wilson, David Huang, Dengwang Li, Jia Yali

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Diabetic retinopathy is a pathology where microvascular circulation abnormalities ultimately result in photoreceptor disruption and, consequently, permanent loss of vision. Here, we developed a method that automatically detects photoreceptor disruption in mild diabetic retinopathy by mapping ellipsoid zone reflectance abnormalities from en face optical coherence tomography images. The algorithm uses a fuzzy c-means scheme with a redefined membership function to assign a defect severity level on each pixel and generate a probability map of defect category affiliation. A novel scheme of unsupervised clustering optimization allows accurate detection of the affected area. The achieved accuracy, sensitivity and specificity were about 90% on a population of thirteen diseased subjects. This method shows potential for accurate and fast detection of early biomarkers in diabetic retinopathy evolution.

Original languageEnglish (US)
Article number#307477
Pages (from-to)5384-5398
Number of pages15
JournalBiomedical Optics Express
Volume8
Issue number12
DOIs
StatePublished - Dec 1 2017

Fingerprint

photoreceptors
Optical Coherence Tomography
abnormalities
Diabetic Retinopathy
tomography
membership functions
biomarkers
defects
pathology
ellipsoids
pixels
reflectance
optimization
Cluster Analysis
sensitivity
Biomarkers
Pathology
Sensitivity and Specificity
Population

ASJC Scopus subject areas

  • Biotechnology
  • Atomic and Molecular Physics, and Optics

Cite this

Automated detection of photoreceptor disruption in mild diabetic retinopathy on volumetric optical coherence tomography. / Wang, Zhuo; Camino, Acner; Zhang, Miao; Wang, Jie; Hwang, Thomas; Wilson, David; Huang, David; Li, Dengwang; Yali, Jia.

In: Biomedical Optics Express, Vol. 8, No. 12, #307477, 01.12.2017, p. 5384-5398.

Research output: Contribution to journalArticle

@article{e8004edfa4c949f9bf23dc46bc6e85d8,
title = "Automated detection of photoreceptor disruption in mild diabetic retinopathy on volumetric optical coherence tomography",
abstract = "Diabetic retinopathy is a pathology where microvascular circulation abnormalities ultimately result in photoreceptor disruption and, consequently, permanent loss of vision. Here, we developed a method that automatically detects photoreceptor disruption in mild diabetic retinopathy by mapping ellipsoid zone reflectance abnormalities from en face optical coherence tomography images. The algorithm uses a fuzzy c-means scheme with a redefined membership function to assign a defect severity level on each pixel and generate a probability map of defect category affiliation. A novel scheme of unsupervised clustering optimization allows accurate detection of the affected area. The achieved accuracy, sensitivity and specificity were about 90{\%} on a population of thirteen diseased subjects. This method shows potential for accurate and fast detection of early biomarkers in diabetic retinopathy evolution.",
author = "Zhuo Wang and Acner Camino and Miao Zhang and Jie Wang and Thomas Hwang and David Wilson and David Huang and Dengwang Li and Jia Yali",
year = "2017",
month = "12",
day = "1",
doi = "10.1364/BOE.8.005384",
language = "English (US)",
volume = "8",
pages = "5384--5398",
journal = "Biomedical Optics Express",
issn = "2156-7085",
publisher = "The Optical Society",
number = "12",

}

TY - JOUR

T1 - Automated detection of photoreceptor disruption in mild diabetic retinopathy on volumetric optical coherence tomography

AU - Wang, Zhuo

AU - Camino, Acner

AU - Zhang, Miao

AU - Wang, Jie

AU - Hwang, Thomas

AU - Wilson, David

AU - Huang, David

AU - Li, Dengwang

AU - Yali, Jia

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Diabetic retinopathy is a pathology where microvascular circulation abnormalities ultimately result in photoreceptor disruption and, consequently, permanent loss of vision. Here, we developed a method that automatically detects photoreceptor disruption in mild diabetic retinopathy by mapping ellipsoid zone reflectance abnormalities from en face optical coherence tomography images. The algorithm uses a fuzzy c-means scheme with a redefined membership function to assign a defect severity level on each pixel and generate a probability map of defect category affiliation. A novel scheme of unsupervised clustering optimization allows accurate detection of the affected area. The achieved accuracy, sensitivity and specificity were about 90% on a population of thirteen diseased subjects. This method shows potential for accurate and fast detection of early biomarkers in diabetic retinopathy evolution.

AB - Diabetic retinopathy is a pathology where microvascular circulation abnormalities ultimately result in photoreceptor disruption and, consequently, permanent loss of vision. Here, we developed a method that automatically detects photoreceptor disruption in mild diabetic retinopathy by mapping ellipsoid zone reflectance abnormalities from en face optical coherence tomography images. The algorithm uses a fuzzy c-means scheme with a redefined membership function to assign a defect severity level on each pixel and generate a probability map of defect category affiliation. A novel scheme of unsupervised clustering optimization allows accurate detection of the affected area. The achieved accuracy, sensitivity and specificity were about 90% on a population of thirteen diseased subjects. This method shows potential for accurate and fast detection of early biomarkers in diabetic retinopathy evolution.

UR - http://www.scopus.com/inward/record.url?scp=85037361720&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037361720&partnerID=8YFLogxK

U2 - 10.1364/BOE.8.005384

DO - 10.1364/BOE.8.005384

M3 - Article

AN - SCOPUS:85037361720

VL - 8

SP - 5384

EP - 5398

JO - Biomedical Optics Express

JF - Biomedical Optics Express

SN - 2156-7085

IS - 12

M1 - #307477

ER -