Publication detail

Analysis of the Retinal Nerve Fiber Layer Texture Related to the Thickness Measured by Optical Coherence Tomography

ODSTRČILÍK, J. KOLÁŘ, R. TORNOW, R. BUDAI, A. JAN, J. MACKOVÁ, P. VODÁKOVÁ, M.

Original Title

Analysis of the Retinal Nerve Fiber Layer Texture Related to the Thickness Measured by Optical Coherence Tomography

Czech Title

Analysis of the Retinal Nerve Fiber Layer Texture Related to the Thickness Measured by Optical Coherence Tomography

English Title

Analysis of the Retinal Nerve Fiber Layer Texture Related to the Thickness Measured by Optical Coherence Tomography

Type

book chapter

Language

en

Original Abstract

The retinal nerve fiber layer (RNFL) is one of the most affected retinal structures due to the glaucoma disease. Progression of this disease results in the RNFL atrophy that can be detected as the decrease of the layers thickness. Usually, the RNFL thickness can be assessed by optical coherence tomography (OCT). However, an examination using OCT is rather expensive and still not widely available. On the other hand, fundus camera is considered as a common and fundamental diagnostic device utilized at many ophthalmic facilities worldwide. This contribution presents a novel approach to texture analysis enabling assessment of the RNFL thickness in widely used colour fundus photographs. The aim is to propose a regression model based on different texture features effective for description of changes in the RNFL textural appearance related to the variations of RNFL thickness. The performance evaluation uses OCT as a gold standard modality for validation of the proposed approach. The results show high correlation between the models predicted output and RNFL thickness directly measured by OCT.

Czech abstract

The retinal nerve fiber layer (RNFL) is one of the most affected retinal structures due to the glaucoma disease. Progression of this disease results in the RNFL atrophy that can be detected as the decrease of the layers thickness. Usually, the RNFL thickness can be assessed by optical coherence tomography (OCT). However, an examination using OCT is rather expensive and still not widely available. On the other hand, fundus camera is considered as a common and fundamental diagnostic device utilized at many ophthalmic facilities worldwide. This contribution presents a novel approach to texture analysis enabling assessment of the RNFL thickness in widely used colour fundus photographs. The aim is to propose a regression model based on different texture features effective for description of changes in the RNFL textural appearance related to the variations of RNFL thickness. The performance evaluation uses OCT as a gold standard modality for validation of the proposed approach. The results show high correlation between the models predicted output and RNFL thickness directly measured by OCT.

English abstract

The retinal nerve fiber layer (RNFL) is one of the most affected retinal structures due to the glaucoma disease. Progression of this disease results in the RNFL atrophy that can be detected as the decrease of the layers thickness. Usually, the RNFL thickness can be assessed by optical coherence tomography (OCT). However, an examination using OCT is rather expensive and still not widely available. On the other hand, fundus camera is considered as a common and fundamental diagnostic device utilized at many ophthalmic facilities worldwide. This contribution presents a novel approach to texture analysis enabling assessment of the RNFL thickness in widely used colour fundus photographs. The aim is to propose a regression model based on different texture features effective for description of changes in the RNFL textural appearance related to the variations of RNFL thickness. The performance evaluation uses OCT as a gold standard modality for validation of the proposed approach. The results show high correlation between the models predicted output and RNFL thickness directly measured by OCT.

Keywords

glaucoma, retinal nerve fiber layer, texture analysis, fundus images, local binary patterns, markov random fields

Released

01.05.2015

Publisher

Springer International Publishing

Location

Switzerland

ISBN

978-3-319-13406-2

Book

Developments in Medical Image Processing and Computational Vision

Edition

Lecture Notes in Computational Vision and Biomechanics

Edition number

19

Pages from

19

Pages to

40

Pages count

22

BibTex


@inbook{BUT114386,
  author="Jan {Odstrčilík} and Radim {Kolář} and Ralf-Peter {Tornow} and Attila {Budai} and Jiří {Jan} and Pavlína {Macková} and Martina {Vodáková}",
  title="Analysis of the Retinal Nerve Fiber Layer Texture Related to the Thickness Measured by Optical Coherence Tomography",
  annote="The retinal nerve fiber layer (RNFL) is one of the most affected retinal structures due to the glaucoma disease. Progression of this disease results in the RNFL atrophy that can be detected as the decrease of the layers thickness. Usually, the RNFL thickness can be assessed by optical coherence tomography (OCT). However, an examination using OCT is rather expensive and still not widely available. On the other hand, fundus camera is considered as a common and fundamental diagnostic device utilized at many ophthalmic facilities worldwide. This contribution presents a novel approach to texture analysis enabling assessment of the RNFL thickness in widely used colour fundus photographs. The aim is to propose a regression model based on different texture features effective for description of changes in the RNFL textural appearance related to the variations of RNFL thickness. The performance evaluation uses OCT as a gold standard modality for validation of the proposed approach. The results show high correlation between the models predicted output and RNFL thickness directly measured by OCT.",
  address="Springer International Publishing",
  booktitle="Developments in Medical Image Processing and Computational Vision",
  chapter="114386",
  doi="10.1007/978-3-319-13407-9",
  edition="Lecture Notes in Computational Vision and Biomechanics",
  howpublished="print",
  institution="Springer International Publishing",
  year="2015",
  month="may",
  pages="19--40",
  publisher="Springer International Publishing",
  type="book chapter"
}