Automatic quantification of choroidal neovascularization lesion area on OCT angiography based on density cell-like P systems with active membranes

Jie Xue, Acner Camino, Steven Bailey, Xiyu Liu, Dengwang Li, Jia Yali

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Detecting and quantifying the size of choroidal neovascularization (CNV) is important for the diagnosis and assessment of neovascular age-related macular degeneration. Depth-resolved imaging of the retinal and choroidal vasculature by optical coherence tomography angiography (OCTA) has enabled the visualization of CNV. However, due to the prevalence of artifacts, it is difficult to segment and quantify the CNV lesion area automatically. We have previously described a saliency algorithm for CNV detection that could identify a CNV lesion area with 83% accuracy. However, this method works under the assumption that the CNV region is the most salient area for visual attention in the whole image and consequently, errors occur when this requirement is not met (e.g. when the lesion occupies a large portion of the image). Moreover, saliency image processing methods cannot extract the edges of the salient object very accurately. In this paper, we propose a novel and automatic CNV segmentation method based on an unsupervised and parallel machine learning technique named density cell-like P systems (DEC P systems). DEC P systems integrate the idea of a modified clustering algorithm into cell-like P systems. This method improved the accuracy of detection to 87.2% on 22 subjects and obtained clear boundaries of the CNV lesions.

Original languageEnglish (US)
Article number#330211
Pages (from-to)3208-3219
Number of pages12
JournalBiomedical Optics Express
Volume9
Issue number7
DOIs
StatePublished - Jul 1 2018

Fingerprint

angiogenesis
Choroidal Neovascularization
angiography
lesions
Angiography
Cell Count
membranes
Membranes
cells
machine learning
degeneration
Optical Coherence Tomography
Macular Degeneration
Artifacts
Cluster Analysis
image processing
artifacts
tomography
requirements

ASJC Scopus subject areas

  • Biotechnology
  • Atomic and Molecular Physics, and Optics

Cite this

Automatic quantification of choroidal neovascularization lesion area on OCT angiography based on density cell-like P systems with active membranes. / Xue, Jie; Camino, Acner; Bailey, Steven; Liu, Xiyu; Li, Dengwang; Yali, Jia.

In: Biomedical Optics Express, Vol. 9, No. 7, #330211, 01.07.2018, p. 3208-3219.

Research output: Contribution to journalArticle

@article{1437c032bab24994a23304b842c7ead5,
title = "Automatic quantification of choroidal neovascularization lesion area on OCT angiography based on density cell-like P systems with active membranes",
abstract = "Detecting and quantifying the size of choroidal neovascularization (CNV) is important for the diagnosis and assessment of neovascular age-related macular degeneration. Depth-resolved imaging of the retinal and choroidal vasculature by optical coherence tomography angiography (OCTA) has enabled the visualization of CNV. However, due to the prevalence of artifacts, it is difficult to segment and quantify the CNV lesion area automatically. We have previously described a saliency algorithm for CNV detection that could identify a CNV lesion area with 83{\%} accuracy. However, this method works under the assumption that the CNV region is the most salient area for visual attention in the whole image and consequently, errors occur when this requirement is not met (e.g. when the lesion occupies a large portion of the image). Moreover, saliency image processing methods cannot extract the edges of the salient object very accurately. In this paper, we propose a novel and automatic CNV segmentation method based on an unsupervised and parallel machine learning technique named density cell-like P systems (DEC P systems). DEC P systems integrate the idea of a modified clustering algorithm into cell-like P systems. This method improved the accuracy of detection to 87.2{\%} on 22 subjects and obtained clear boundaries of the CNV lesions.",
author = "Jie Xue and Acner Camino and Steven Bailey and Xiyu Liu and Dengwang Li and Jia Yali",
year = "2018",
month = "7",
day = "1",
doi = "10.1364/BOE.9.003208",
language = "English (US)",
volume = "9",
pages = "3208--3219",
journal = "Biomedical Optics Express",
issn = "2156-7085",
publisher = "The Optical Society",
number = "7",

}

TY - JOUR

T1 - Automatic quantification of choroidal neovascularization lesion area on OCT angiography based on density cell-like P systems with active membranes

AU - Xue, Jie

AU - Camino, Acner

AU - Bailey, Steven

AU - Liu, Xiyu

AU - Li, Dengwang

AU - Yali, Jia

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Detecting and quantifying the size of choroidal neovascularization (CNV) is important for the diagnosis and assessment of neovascular age-related macular degeneration. Depth-resolved imaging of the retinal and choroidal vasculature by optical coherence tomography angiography (OCTA) has enabled the visualization of CNV. However, due to the prevalence of artifacts, it is difficult to segment and quantify the CNV lesion area automatically. We have previously described a saliency algorithm for CNV detection that could identify a CNV lesion area with 83% accuracy. However, this method works under the assumption that the CNV region is the most salient area for visual attention in the whole image and consequently, errors occur when this requirement is not met (e.g. when the lesion occupies a large portion of the image). Moreover, saliency image processing methods cannot extract the edges of the salient object very accurately. In this paper, we propose a novel and automatic CNV segmentation method based on an unsupervised and parallel machine learning technique named density cell-like P systems (DEC P systems). DEC P systems integrate the idea of a modified clustering algorithm into cell-like P systems. This method improved the accuracy of detection to 87.2% on 22 subjects and obtained clear boundaries of the CNV lesions.

AB - Detecting and quantifying the size of choroidal neovascularization (CNV) is important for the diagnosis and assessment of neovascular age-related macular degeneration. Depth-resolved imaging of the retinal and choroidal vasculature by optical coherence tomography angiography (OCTA) has enabled the visualization of CNV. However, due to the prevalence of artifacts, it is difficult to segment and quantify the CNV lesion area automatically. We have previously described a saliency algorithm for CNV detection that could identify a CNV lesion area with 83% accuracy. However, this method works under the assumption that the CNV region is the most salient area for visual attention in the whole image and consequently, errors occur when this requirement is not met (e.g. when the lesion occupies a large portion of the image). Moreover, saliency image processing methods cannot extract the edges of the salient object very accurately. In this paper, we propose a novel and automatic CNV segmentation method based on an unsupervised and parallel machine learning technique named density cell-like P systems (DEC P systems). DEC P systems integrate the idea of a modified clustering algorithm into cell-like P systems. This method improved the accuracy of detection to 87.2% on 22 subjects and obtained clear boundaries of the CNV lesions.

UR - http://www.scopus.com/inward/record.url?scp=85049363411&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049363411&partnerID=8YFLogxK

U2 - 10.1364/BOE.9.003208

DO - 10.1364/BOE.9.003208

M3 - Article

AN - SCOPUS:85049363411

VL - 9

SP - 3208

EP - 3219

JO - Biomedical Optics Express

JF - Biomedical Optics Express

SN - 2156-7085

IS - 7

M1 - #330211

ER -