Detail publikace

Analýza visuálního vzhledu nervových vláken na sítnici v obrazech s vysokým rozlišením z fundus kamery: Studie na zdravých jedincích

KOLÁŘ, R. TORNOW, R. LAEMMER, R. ODSTRČILÍK, J. GAZÁREK, J. JAN, J. KUBĚNA, T. ČERNOŠEK, P. MAYER, M.

Originální název

Analysis of Visual Appearance of Retinal Nerve Fibers in High Resolution Fundus Images: A Study on Normal Subjects

Český název

Analýza visuálního vzhledu nervových vláken na sítnici v obrazech s vysokým rozlišením z fundus kamery: Studie na zdravých jedincích

Anglický název

Analysis of Visual Appearance of Retinal Nerve Fibers in High Resolution Fundus Images: A Study on Normal Subjects

Typ

článek v časopise

Jazyk

en

Originální abstrakt

The retinal ganglion axons are an important part of the visual system, which can be directly observed by fundus camera. The layer they form together inside the retina is the retinal nerve fiber layer (RNFL). This paper describes results of a texture RNFL analysis in color fundus photographs and compares these results with quantitative measurement of RNFL thickness obtained from optical coherence tomography on normal subjects. It is shown that local mean value, standard deviation, and Shannon entropy extracted from the green and blue channel of fundus images are correlated with corresponding RNFL thickness. The linear correlation coefficients achieved values 0.694, 0.547, and 0.512 for respective features measured on 439 retinal positions in the peripapillary area from 23 eyes of 15 different normal subjects.

Český abstrakt

Článek se zabývá texturní analýzou vrstvy nervových vláken na sítnici v obrazech z fundus kamery. Výsledky této analýzy jsou porovnány s tloušťkou této vrstvy, která byla změřena pomocí optického koherentního tomografu. Korelační koeficient mezi třemi nejlepšími texturními příznaky a tloušťkou byl 0.694, 0.547, and 0.512. Anaýza byla provedena na 439 místech na sítnici ve 23 snímcích získaných z 15 subjektů.

Anglický abstrakt

The retinal ganglion axons are an important part of the visual system, which can be directly observed by fundus camera. The layer they form together inside the retina is the retinal nerve fiber layer (RNFL). This paper describes results of a texture RNFL analysis in color fundus photographs and compares these results with quantitative measurement of RNFL thickness obtained from optical coherence tomography on normal subjects. It is shown that local mean value, standard deviation, and Shannon entropy extracted from the green and blue channel of fundus images are correlated with corresponding RNFL thickness. The linear correlation coefficients achieved values 0.694, 0.547, and 0.512 for respective features measured on 439 retinal positions in the peripapillary area from 23 eyes of 15 different normal subjects.

Rok RIV

2013

Vydáno

27.12.2013

Nakladatel

Hindawi Publishing Corporation

Místo

USA

Strany od

1

Strany do

10

Strany počet

10

BibTex


@article{BUT104083,
  author="Radim {Kolář} and Ralf-Peter {Tornow} and Robert {Laemmer} and Jan {Odstrčilík} and Jiří {Gazárek} and Jiří {Jan} and Tomáš {Kuběna} and Pavel {Černošek} and Markus A. {Mayer}",
  title="Analysis of Visual Appearance of Retinal Nerve Fibers in High Resolution Fundus Images: A Study on Normal Subjects",
  annote="The retinal ganglion axons are an important part of the visual system, which can be directly observed by fundus camera. The layer they form together inside the retina is the retinal nerve fiber layer (RNFL). This paper describes results of a texture RNFL analysis in color fundus photographs and compares these results with quantitative measurement of RNFL thickness obtained from optical coherence tomography on normal subjects. It is shown that local mean value, standard deviation, and Shannon entropy extracted from the green and blue channel of fundus images are correlated with corresponding RNFL thickness. The linear correlation coefficients achieved values 0.694, 0.547, and 0.512 for respective features measured on 439 retinal positions in the peripapillary area from 23 eyes of 15 different normal subjects.",
  address="Hindawi Publishing Corporation",
  chapter="104083",
  doi="10.1155/2013/134543",
  howpublished="online",
  institution="Hindawi Publishing Corporation",
  number="12",
  volume="2013",
  year="2013",
  month="december",
  pages="1--10",
  publisher="Hindawi Publishing Corporation",
  type="journal article"
}