Publication detail

Towards automated diagnostic evaluation of retina imagess

H.Niemann,R.Chrastek,B.Lausen,L.Kubečka,J.Jan,C.Y. Mardin,G.Michelson

Original Title

Towards automated diagnostic evaluation of retina imagess

Czech Title

Automatizace diagnostického hodnocení retinálních obrazů

English Title

Towards automated diagnostic evaluation of retina imagess

Type

journal article

Language

en

Original Abstract

In this paper we describe the automatic segmentation of the optic nerve head (ONH) with the longterm goal of automatically diagnosing early stages of glaucoma. The images are average images obtained from a scanning laser ophthalmoscope (SLO). The segmentation consists of the main steps of finding a region of interest containing the ONH, constraining the search space for final segmentation, and computing the fine segmentation by an active contour model. The agreement of true positive pixels, i.e., pixels attributed to the ONH by both manual and automatic segmentation, is very good. The classification results from three different classifiers using manual or automatic segmentation still show an advantage of manual segmentation. One means to further improve the automatic segmentation is to use information from an SLO as well as from a fundus camera.

Czech abstract

Automatická segmentace hlavy optického nervu s cílem diagnostiky počátečních stádií glaukomu. Obrazy jsou průměrovány ze skenovacího laserového oftalmoskopu. V článku je popsána metoda segmentace, založená na třech různých klasifikátorech.

English abstract

In this paper we describe the automatic segmentation of the optic nerve head (ONH) with the longterm goal of automatically diagnosing early stages of glaucoma. The images are average images obtained from a scanning laser ophthalmoscope (SLO). The segmentation consists of the main steps of finding a region of interest containing the ONH, constraining the search space for final segmentation, and computing the fine segmentation by an active contour model. The agreement of true positive pixels, i.e., pixels attributed to the ONH by both manual and automatic segmentation, is very good. The classification results from three different classifiers using manual or automatic segmentation still show an advantage of manual segmentation. One means to further improve the automatic segmentation is to use information from an SLO as well as from a fundus camera.

Keywords

retinal images, image segmentation, image recognition

RIV year

2006

Released

01.01.2006

Publisher

Springer

Pages from

671

Pages to

676

Pages count

6

URL

v knihovně UBMI

BibTex


@article{BUT44014,
  author="Radim {Chrástek} and Libor {Kubečka} and Jiří {Jan}",
  title="Towards automated diagnostic evaluation of retina imagess",
  annote="In this paper we describe the automatic segmentation of the optic nerve head (ONH) with the longterm
goal of automatically diagnosing early stages of glaucoma. The images are average images obtained from
a scanning laser ophthalmoscope (SLO). The segmentation consists of the main steps of finding a region of
interest containing the ONH, constraining the search space for final segmentation, and computing the fine segmentation
by an active contour model. The agreement of true positive pixels,  i.e., pixels attributed to the ONH
by both manual and automatic segmentation, is very good. The classification results from three different classifiers
using manual or automatic segmentation still show an advantage of manual segmentation. One means to
further improve the automatic segmentation is to use information from an SLO as well as from a fundus camera.",
  address="Springer",
  chapter="44014",
  institution="Springer",
  number="4",
  volume="2006",
  year="2006",
  month="january",
  pages="671",
  publisher="Springer",
  type="journal article"
}