Adaptation of a support vector machine algorithm for segmentation and visualization of retinal structures in volumetric optical coherence tomography data sets

Robert Zawadzki, Alfred R. Fuller, David F. Wiley, Bernd Hamann, Stacey S. Choi, John S Werner

Research output: Contribution to journalArticle

49 Citations (Scopus)

Abstract

Recent developments in Fourier domain-optical coherence tomography (Fd-OCT) have increased the acquisition speed of current ophthalmic Fd-OCT instruments sufficiently to allow the acquisition of volumetric data sets of human retinas in a clinical setting. The large size and three-dimensional (3D) nature of these data sets require that intelligent data processing, visualization, and analysis tools are used to take full advantage of the available information. Therefore, we have combined methods from volume visualization, and data analysis in support of better visualization and diagnosis of Fd-OCT retinal volumes. Custom-designed 3D visualization and analysis software is used to view retinal volumes reconstructed from registered B-scans. We use a support vector machine (SVM) to perform semiautomatic segmentation of retinal layers and structures for subsequent analysis including a comparison of measured layer thicknesses. We have modified the SVM to gracefully handle OCT speckle noise by treating it as a characteristic of the volumetric data. Our software has been tested successfully in clinical settings for its efficacy in assessing 3D retinal structures in healthy as well as diseased cases. Our tool facilitates diagnosis and treatment monitoring of retinal diseases.

Original languageEnglish (US)
Article number041206
JournalJournal of Biomedical Optics
Volume12
Issue number4
DOIs
StatePublished - Jul 2007

Fingerprint

Optical tomography
Optical Coherence Tomography
Support vector machines
Visualization
tomography
acquisition
Software
computer programs
Retinal Diseases
retina
Retina
Speckle
Support Vector Machine
Datasets
Monitoring

Keywords

  • Ophthalmology
  • Optical coherence tomography
  • Optical diagnostics for medicine
  • Pattern recognition and feature extraction
  • Support vector machine
  • Volume visualization

ASJC Scopus subject areas

  • Biomedical Engineering
  • Biomaterials
  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology
  • Clinical Biochemistry

Cite this

Adaptation of a support vector machine algorithm for segmentation and visualization of retinal structures in volumetric optical coherence tomography data sets. / Zawadzki, Robert; Fuller, Alfred R.; Wiley, David F.; Hamann, Bernd; Choi, Stacey S.; Werner, John S.

In: Journal of Biomedical Optics, Vol. 12, No. 4, 041206, 07.2007.

Research output: Contribution to journalArticle

@article{af0eb5bb7af6445a8cff180a84b95fb6,
title = "Adaptation of a support vector machine algorithm for segmentation and visualization of retinal structures in volumetric optical coherence tomography data sets",
abstract = "Recent developments in Fourier domain-optical coherence tomography (Fd-OCT) have increased the acquisition speed of current ophthalmic Fd-OCT instruments sufficiently to allow the acquisition of volumetric data sets of human retinas in a clinical setting. The large size and three-dimensional (3D) nature of these data sets require that intelligent data processing, visualization, and analysis tools are used to take full advantage of the available information. Therefore, we have combined methods from volume visualization, and data analysis in support of better visualization and diagnosis of Fd-OCT retinal volumes. Custom-designed 3D visualization and analysis software is used to view retinal volumes reconstructed from registered B-scans. We use a support vector machine (SVM) to perform semiautomatic segmentation of retinal layers and structures for subsequent analysis including a comparison of measured layer thicknesses. We have modified the SVM to gracefully handle OCT speckle noise by treating it as a characteristic of the volumetric data. Our software has been tested successfully in clinical settings for its efficacy in assessing 3D retinal structures in healthy as well as diseased cases. Our tool facilitates diagnosis and treatment monitoring of retinal diseases.",
keywords = "Ophthalmology, Optical coherence tomography, Optical diagnostics for medicine, Pattern recognition and feature extraction, Support vector machine, Volume visualization",
author = "Robert Zawadzki and Fuller, {Alfred R.} and Wiley, {David F.} and Bernd Hamann and Choi, {Stacey S.} and Werner, {John S}",
year = "2007",
month = "7",
doi = "10.1117/1.2772658",
language = "English (US)",
volume = "12",
journal = "Journal of Biomedical Optics",
issn = "1083-3668",
publisher = "SPIE",
number = "4",

}

TY - JOUR

T1 - Adaptation of a support vector machine algorithm for segmentation and visualization of retinal structures in volumetric optical coherence tomography data sets

AU - Zawadzki, Robert

AU - Fuller, Alfred R.

AU - Wiley, David F.

AU - Hamann, Bernd

AU - Choi, Stacey S.

AU - Werner, John S

PY - 2007/7

Y1 - 2007/7

N2 - Recent developments in Fourier domain-optical coherence tomography (Fd-OCT) have increased the acquisition speed of current ophthalmic Fd-OCT instruments sufficiently to allow the acquisition of volumetric data sets of human retinas in a clinical setting. The large size and three-dimensional (3D) nature of these data sets require that intelligent data processing, visualization, and analysis tools are used to take full advantage of the available information. Therefore, we have combined methods from volume visualization, and data analysis in support of better visualization and diagnosis of Fd-OCT retinal volumes. Custom-designed 3D visualization and analysis software is used to view retinal volumes reconstructed from registered B-scans. We use a support vector machine (SVM) to perform semiautomatic segmentation of retinal layers and structures for subsequent analysis including a comparison of measured layer thicknesses. We have modified the SVM to gracefully handle OCT speckle noise by treating it as a characteristic of the volumetric data. Our software has been tested successfully in clinical settings for its efficacy in assessing 3D retinal structures in healthy as well as diseased cases. Our tool facilitates diagnosis and treatment monitoring of retinal diseases.

AB - Recent developments in Fourier domain-optical coherence tomography (Fd-OCT) have increased the acquisition speed of current ophthalmic Fd-OCT instruments sufficiently to allow the acquisition of volumetric data sets of human retinas in a clinical setting. The large size and three-dimensional (3D) nature of these data sets require that intelligent data processing, visualization, and analysis tools are used to take full advantage of the available information. Therefore, we have combined methods from volume visualization, and data analysis in support of better visualization and diagnosis of Fd-OCT retinal volumes. Custom-designed 3D visualization and analysis software is used to view retinal volumes reconstructed from registered B-scans. We use a support vector machine (SVM) to perform semiautomatic segmentation of retinal layers and structures for subsequent analysis including a comparison of measured layer thicknesses. We have modified the SVM to gracefully handle OCT speckle noise by treating it as a characteristic of the volumetric data. Our software has been tested successfully in clinical settings for its efficacy in assessing 3D retinal structures in healthy as well as diseased cases. Our tool facilitates diagnosis and treatment monitoring of retinal diseases.

KW - Ophthalmology

KW - Optical coherence tomography

KW - Optical diagnostics for medicine

KW - Pattern recognition and feature extraction

KW - Support vector machine

KW - Volume visualization

UR - http://www.scopus.com/inward/record.url?scp=35948985554&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35948985554&partnerID=8YFLogxK

U2 - 10.1117/1.2772658

DO - 10.1117/1.2772658

M3 - Article

VL - 12

JO - Journal of Biomedical Optics

JF - Journal of Biomedical Optics

SN - 1083-3668

IS - 4

M1 - 041206

ER -