Segmentation of three-dimensional retinal image data

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

Research output: Contribution to journalArticle

58 Citations (Scopus)

Abstract

We have combined methods from volume visualization and data analysis to support better diagnosis and treatment of human retinal diseases. Many diseases can be identified by abnormalities in the thicknesses of various retinal layers captured using optical coherence tomography (OCT). We used a support vector machine (SVM) to perform semi-automatic segmentation of retinal layers for subsequent analysis including a comparison of layer thicknesses to known healthy parameters. We have extended and generalized an older SVM approach to support better performance in a clinical setting through performance enhancements and graceful handling of inherent noise in OCT data by considering statistical characteristics at multiple levels of resolution. The addition of the multi-resolution hierarchy extends the SVM to have "global awareness." A feature, such as a retinal layer, can therefore be modeled within the SVM as a combination of statistical characteristics across all levels; thus capturing high- and low-frequency information. We have compared our semi-automatically generated segmentations to manually segmented layers for verification purposes. Our main goals were to provide a tool that could (i) be used in a clinical setting; (ii) operate on noisy OCT data; and (iii) isolate individual or multiple retinal layers in both healthy and disease cases that contain structural deformities.

Original languageEnglish (US)
Pages (from-to)1719-1726
Number of pages8
JournalIEEE Transactions on Visualization and Computer Graphics
Volume13
Issue number6
DOIs
StatePublished - Nov 2007

Fingerprint

Support vector machines
Optical tomography
Visualization

Keywords

  • Image analysis
  • Image processing
  • Optical coherence tomography
  • Retinal
  • Segmentation
  • Support vector machine
  • Volume visualization

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Segmentation of three-dimensional retinal image data. / Fuller, Alfred R.; Zawadzki, Robert; Choi, Stacey; Wiley, David F.; Werner, John S; Hamann, Bernd.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 13, No. 6, 11.2007, p. 1719-1726.

Research output: Contribution to journalArticle

Fuller, Alfred R. ; Zawadzki, Robert ; Choi, Stacey ; Wiley, David F. ; Werner, John S ; Hamann, Bernd. / Segmentation of three-dimensional retinal image data. In: IEEE Transactions on Visualization and Computer Graphics. 2007 ; Vol. 13, No. 6. pp. 1719-1726.
@article{382e7d428d7b49e8bd56233a8d547cc4,
title = "Segmentation of three-dimensional retinal image data",
abstract = "We have combined methods from volume visualization and data analysis to support better diagnosis and treatment of human retinal diseases. Many diseases can be identified by abnormalities in the thicknesses of various retinal layers captured using optical coherence tomography (OCT). We used a support vector machine (SVM) to perform semi-automatic segmentation of retinal layers for subsequent analysis including a comparison of layer thicknesses to known healthy parameters. We have extended and generalized an older SVM approach to support better performance in a clinical setting through performance enhancements and graceful handling of inherent noise in OCT data by considering statistical characteristics at multiple levels of resolution. The addition of the multi-resolution hierarchy extends the SVM to have {"}global awareness.{"} A feature, such as a retinal layer, can therefore be modeled within the SVM as a combination of statistical characteristics across all levels; thus capturing high- and low-frequency information. We have compared our semi-automatically generated segmentations to manually segmented layers for verification purposes. Our main goals were to provide a tool that could (i) be used in a clinical setting; (ii) operate on noisy OCT data; and (iii) isolate individual or multiple retinal layers in both healthy and disease cases that contain structural deformities.",
keywords = "Image analysis, Image processing, Optical coherence tomography, Retinal, Segmentation, Support vector machine, Volume visualization",
author = "Fuller, {Alfred R.} and Robert Zawadzki and Stacey Choi and Wiley, {David F.} and Werner, {John S} and Bernd Hamann",
year = "2007",
month = "11",
doi = "10.1109/TVCG.2007.70590",
language = "English (US)",
volume = "13",
pages = "1719--1726",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "6",

}

TY - JOUR

T1 - Segmentation of three-dimensional retinal image data

AU - Fuller, Alfred R.

AU - Zawadzki, Robert

AU - Choi, Stacey

AU - Wiley, David F.

AU - Werner, John S

AU - Hamann, Bernd

PY - 2007/11

Y1 - 2007/11

N2 - We have combined methods from volume visualization and data analysis to support better diagnosis and treatment of human retinal diseases. Many diseases can be identified by abnormalities in the thicknesses of various retinal layers captured using optical coherence tomography (OCT). We used a support vector machine (SVM) to perform semi-automatic segmentation of retinal layers for subsequent analysis including a comparison of layer thicknesses to known healthy parameters. We have extended and generalized an older SVM approach to support better performance in a clinical setting through performance enhancements and graceful handling of inherent noise in OCT data by considering statistical characteristics at multiple levels of resolution. The addition of the multi-resolution hierarchy extends the SVM to have "global awareness." A feature, such as a retinal layer, can therefore be modeled within the SVM as a combination of statistical characteristics across all levels; thus capturing high- and low-frequency information. We have compared our semi-automatically generated segmentations to manually segmented layers for verification purposes. Our main goals were to provide a tool that could (i) be used in a clinical setting; (ii) operate on noisy OCT data; and (iii) isolate individual or multiple retinal layers in both healthy and disease cases that contain structural deformities.

AB - We have combined methods from volume visualization and data analysis to support better diagnosis and treatment of human retinal diseases. Many diseases can be identified by abnormalities in the thicknesses of various retinal layers captured using optical coherence tomography (OCT). We used a support vector machine (SVM) to perform semi-automatic segmentation of retinal layers for subsequent analysis including a comparison of layer thicknesses to known healthy parameters. We have extended and generalized an older SVM approach to support better performance in a clinical setting through performance enhancements and graceful handling of inherent noise in OCT data by considering statistical characteristics at multiple levels of resolution. The addition of the multi-resolution hierarchy extends the SVM to have "global awareness." A feature, such as a retinal layer, can therefore be modeled within the SVM as a combination of statistical characteristics across all levels; thus capturing high- and low-frequency information. We have compared our semi-automatically generated segmentations to manually segmented layers for verification purposes. Our main goals were to provide a tool that could (i) be used in a clinical setting; (ii) operate on noisy OCT data; and (iii) isolate individual or multiple retinal layers in both healthy and disease cases that contain structural deformities.

KW - Image analysis

KW - Image processing

KW - Optical coherence tomography

KW - Retinal

KW - Segmentation

KW - Support vector machine

KW - Volume visualization

UR - http://www.scopus.com/inward/record.url?scp=35948972425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35948972425&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2007.70590

DO - 10.1109/TVCG.2007.70590

M3 - Article

C2 - 17968130

AN - SCOPUS:35948972425

VL - 13

SP - 1719

EP - 1726

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 6

ER -