Publication detail

Optic Nerve Head Segmentation in Multimodal Retinal Images

NIEMANN, H., CHRASTEK, R., HOTHORN, T., LAUSEN, B., KUBECKA, L., JAN, J., MICHELSON, G

Original Title

Optic Nerve Head Segmentation in Multimodal Retinal Images

Czech Title

Segmentace optického disku v multimodálních obrazech

English Title

Optic Nerve Head Segmentation in Multimodal Retinal Images

Type

conference paper

Language

en

Original Abstract

In this paper we address automatic segmentation of the optic nerve head (ONH) with the long-term goal of automatic diagnosis of the early stages of glaucoma. The images discussed are average images obtained from a scanning laser ophthalmoscope (SLO). The segmentation consists of the following main steps: 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 obtained from three different classifiers using manual or automatic segmentation still reveal the superiority of manual segmentation. One means to further improve automatic segmentation is to use information from an SLO as well as from a fundus camera.

Czech abstract

In this paper we address automatic segmentation of the optic nerve head (ONH) with the long-term goal of automatic diagnosis of the early stages of glaucoma. The images discussed are average images obtained from a scanning laser ophthalmoscope (SLO). The segmentation consists of the following main steps: 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 obtained from three different classifiers using manual or automatic segmentation still reveal the superiority of manual segmentation. One means to further improve automatic segmentation is to use information from an SLO as well as from a fundus camera.

English abstract

In this paper we address automatic segmentation of the optic nerve head (ONH) with the long-term goal of automatic diagnosis of the early stages of glaucoma. The images discussed are average images obtained from a scanning laser ophthalmoscope (SLO). The segmentation consists of the following main steps: 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 obtained from three different classifiers using manual or automatic segmentation still reveal the superiority of manual segmentation. One means to further improve automatic segmentation is to use information from an SLO as well as from a fundus camera.

Keywords

retina, glaucoma, scanning-laser-tomography, color fundus photograph, registration, segmentation, active contours

RIV year

2005

Released

01.01.2005

Publisher

MAIK Nauka Interperiodica Publishing Moscow

Location

St. Petersburg

Pages from

101

Pages to

106

Pages count

6

BibTex


@inproceedings{BUT14719,
  author="Radim {Chrástek} and Libor {Kubečka} and Jiří {Jan}",
  title="Optic Nerve Head Segmentation in Multimodal Retinal Images",
  annote="In this paper we address automatic segmentation of the optic nerve head (ONH) with the long-term goal of automatic diagnosis of the early stages of glaucoma. The images discussed are average images obtained from a scanning laser ophthalmoscope (SLO). The segmentation consists of the following main steps: 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 obtained from three different classifiers using manual or automatic segmentation still reveal the superiority of manual segmentation. One means to further improve automatic segmentation is to use information from an SLO as well as from a fundus camera.",
  address="MAIK Nauka Interperiodica Publishing Moscow",
  booktitle="Proceed. of the 7th International Conference on Pattern Recognition and Image Analysis: New Information Technologies Conferrence (PRIA-7-2004)",
  chapter="14719",
  institution="MAIK Nauka Interperiodica Publishing Moscow",
  number="1",
  year="2005",
  month="january",
  pages="101",
  publisher="MAIK Nauka Interperiodica Publishing Moscow",
  type="conference paper"
}