Segmentation of choroidal neovascularization in fundus fluorescein angiograms

Walid M. Abdelmoula, Syed M. Shah, Ahmed S. Fahmy

Research output: Contribution to journalArticle

Abstract

Choroidal neovascularization (CNV) is a common manifestation of age-related macular degeneration (AMD). It is characterized by the growth of abnormal blood vessels in the choroidal layer causing blurring and deterioration of the vision. In late stages, these abnormal vessels can rupture the retinal layers causing complete loss of vision at the affected regions. Determining the CNV size and type in fluorescein angiograms is required for proper treatment and prognosis of the disease. Computer-aided methods for CNV segmentation is needed not only to reduce the burden of manual segmentation but also to reduce inter-and intraobserver variability. In this paper, we present a framework for segmenting CNV lesions based on parametric modeling of the intensity variation in fundus fluorescein angiograms. First, a novel model is proposed to describe the temporal intensity variation at each pixel in image sequences acquired by fluorescein angiography. The set of model parameters at each pixel are used to segment the image into regions of homogeneous parameters. Preliminary results on datasets from 21 patients with Wet-AMD show the potential of the method to segment CNV lesions in close agreement with the manual segmentation.

Original languageEnglish (US)
Article number6407904
Pages (from-to)1439-1445
Number of pages7
JournalIEEE Transactions on Biomedical Engineering
Volume60
Issue number5
DOIs
StatePublished - 2013
Externally publishedYes

Fingerprint

Pixels
Angiography
Blood vessels
Deterioration

Keywords

  • Choroidal neovascularization
  • fluorescein angiograms
  • modeling
  • segmentation
  • temporal intensity variation

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Segmentation of choroidal neovascularization in fundus fluorescein angiograms. / Abdelmoula, Walid M.; Shah, Syed M.; Fahmy, Ahmed S.

In: IEEE Transactions on Biomedical Engineering, Vol. 60, No. 5, 6407904, 2013, p. 1439-1445.

Research output: Contribution to journalArticle

Abdelmoula, Walid M. ; Shah, Syed M. ; Fahmy, Ahmed S. / Segmentation of choroidal neovascularization in fundus fluorescein angiograms. In: IEEE Transactions on Biomedical Engineering. 2013 ; Vol. 60, No. 5. pp. 1439-1445.
@article{911f977b1b9044729c5affd58fa3ee10,
title = "Segmentation of choroidal neovascularization in fundus fluorescein angiograms",
abstract = "Choroidal neovascularization (CNV) is a common manifestation of age-related macular degeneration (AMD). It is characterized by the growth of abnormal blood vessels in the choroidal layer causing blurring and deterioration of the vision. In late stages, these abnormal vessels can rupture the retinal layers causing complete loss of vision at the affected regions. Determining the CNV size and type in fluorescein angiograms is required for proper treatment and prognosis of the disease. Computer-aided methods for CNV segmentation is needed not only to reduce the burden of manual segmentation but also to reduce inter-and intraobserver variability. In this paper, we present a framework for segmenting CNV lesions based on parametric modeling of the intensity variation in fundus fluorescein angiograms. First, a novel model is proposed to describe the temporal intensity variation at each pixel in image sequences acquired by fluorescein angiography. The set of model parameters at each pixel are used to segment the image into regions of homogeneous parameters. Preliminary results on datasets from 21 patients with Wet-AMD show the potential of the method to segment CNV lesions in close agreement with the manual segmentation.",
keywords = "Choroidal neovascularization, fluorescein angiograms, modeling, segmentation, temporal intensity variation",
author = "Abdelmoula, {Walid M.} and Shah, {Syed M.} and Fahmy, {Ahmed S.}",
year = "2013",
doi = "10.1109/TBME.2013.2237906",
language = "English (US)",
volume = "60",
pages = "1439--1445",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "5",

}

TY - JOUR

T1 - Segmentation of choroidal neovascularization in fundus fluorescein angiograms

AU - Abdelmoula, Walid M.

AU - Shah, Syed M.

AU - Fahmy, Ahmed S.

PY - 2013

Y1 - 2013

N2 - Choroidal neovascularization (CNV) is a common manifestation of age-related macular degeneration (AMD). It is characterized by the growth of abnormal blood vessels in the choroidal layer causing blurring and deterioration of the vision. In late stages, these abnormal vessels can rupture the retinal layers causing complete loss of vision at the affected regions. Determining the CNV size and type in fluorescein angiograms is required for proper treatment and prognosis of the disease. Computer-aided methods for CNV segmentation is needed not only to reduce the burden of manual segmentation but also to reduce inter-and intraobserver variability. In this paper, we present a framework for segmenting CNV lesions based on parametric modeling of the intensity variation in fundus fluorescein angiograms. First, a novel model is proposed to describe the temporal intensity variation at each pixel in image sequences acquired by fluorescein angiography. The set of model parameters at each pixel are used to segment the image into regions of homogeneous parameters. Preliminary results on datasets from 21 patients with Wet-AMD show the potential of the method to segment CNV lesions in close agreement with the manual segmentation.

AB - Choroidal neovascularization (CNV) is a common manifestation of age-related macular degeneration (AMD). It is characterized by the growth of abnormal blood vessels in the choroidal layer causing blurring and deterioration of the vision. In late stages, these abnormal vessels can rupture the retinal layers causing complete loss of vision at the affected regions. Determining the CNV size and type in fluorescein angiograms is required for proper treatment and prognosis of the disease. Computer-aided methods for CNV segmentation is needed not only to reduce the burden of manual segmentation but also to reduce inter-and intraobserver variability. In this paper, we present a framework for segmenting CNV lesions based on parametric modeling of the intensity variation in fundus fluorescein angiograms. First, a novel model is proposed to describe the temporal intensity variation at each pixel in image sequences acquired by fluorescein angiography. The set of model parameters at each pixel are used to segment the image into regions of homogeneous parameters. Preliminary results on datasets from 21 patients with Wet-AMD show the potential of the method to segment CNV lesions in close agreement with the manual segmentation.

KW - Choroidal neovascularization

KW - fluorescein angiograms

KW - modeling

KW - segmentation

KW - temporal intensity variation

UR - http://www.scopus.com/inward/record.url?scp=84876754636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876754636&partnerID=8YFLogxK

U2 - 10.1109/TBME.2013.2237906

DO - 10.1109/TBME.2013.2237906

M3 - Article

C2 - 23314765

AN - SCOPUS:84876754636

VL - 60

SP - 1439

EP - 1445

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 5

M1 - 6407904

ER -