Detection of anatomic structures in human retinal imagery

Kenneth W. Tobin; Edward Chaum; V. Priya Govindasamy; Thomas P. Karnowski

doi:10.1109/TMI.2007.902801

Detection of anatomic structures in human retinal imagery

Kenneth W. Tobin, Edward Chaum, V. Priya Govindasamy, Thomas P. Karnowski

Cyber Resilience and Intelligence Divisi

Research output: Contribution to journal › Article › peer-review

203 Scopus citations

Abstract

The widespread availability of electronic imaging devices throughout the medical community is leading to a growing body of research on image processing and analysis to diagnose retinal disease such as diabetic retinopathy (DR). Productive computer-based screening of large, at-risk populations at low cost requires robust, automated image analysis. In this paper we present results for the automatic detection of the optic nerve and localization of the macula using digital red-free fundus photography. Our method relies on the accurate segmentation of the vasculature of the retina followed by the determination of spatial features describing the density, average thickness, and average orientation of the vasculature in relation to the position of the optic nerve. Localization of the macula follows using knowledge of the optic nerve location to detect the horizontal raphe of the retina using a geometric model of the vasculature. We report 90.4% detection performance for the optic nerve and 92.5% localization performance for the macula for red-free fundus images representing a population of 345 images corresponding to 269 patients with 18 different pathologies associated with DR and other common retinal diseases such as age-related macular degeneration.

Original language	English
Pages (from-to)	1729-1739
Number of pages	11
Journal	IEEE Transactions on Medical Imaging
Volume	26
Issue number	12
DOIs	https://doi.org/10.1109/TMI.2007.902801
State	Published - Dec 2007

Funding

Manuscript received February 13, 2006; revised June 4, 2007. This work was supported by National Eye Institute under Grant R01-EY017065. This paper was prepared by the Oak Ridge National Laboratory, Oak Ridge, TN, operated by UT-BATTELLE, LLC for the U.S. Department of Energy under Contract DE-AC05-00OR22725. Asterisk indicates corresponding author. *K. W. Tobin is with the Image Science and Machine Vision Group, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6010 USA (e-mail: [email protected]). The authors would like to thank The Plough Foundation, Memphis, TN, and Research to Prevent Blindness, New York, along with the Laboratory Directed Research and Development Program of the Oak Ridge National Laboratory for their support of this research.

Keywords

Bayesian classifier
Diabetic retinopathy
Feature analysis
Macula localization
Optic nerve detection
Red-free fundus imagery
Vascular segmentation

Access to Document

10.1109/TMI.2007.902801

Cite this

@article{3045732cdb124db4b137dc097babc74a,

title = "Detection of anatomic structures in human retinal imagery",

abstract = "The widespread availability of electronic imaging devices throughout the medical community is leading to a growing body of research on image processing and analysis to diagnose retinal disease such as diabetic retinopathy (DR). Productive computer-based screening of large, at-risk populations at low cost requires robust, automated image analysis. In this paper we present results for the automatic detection of the optic nerve and localization of the macula using digital red-free fundus photography. Our method relies on the accurate segmentation of the vasculature of the retina followed by the determination of spatial features describing the density, average thickness, and average orientation of the vasculature in relation to the position of the optic nerve. Localization of the macula follows using knowledge of the optic nerve location to detect the horizontal raphe of the retina using a geometric model of the vasculature. We report 90.4% detection performance for the optic nerve and 92.5% localization performance for the macula for red-free fundus images representing a population of 345 images corresponding to 269 patients with 18 different pathologies associated with DR and other common retinal diseases such as age-related macular degeneration.",

keywords = "Bayesian classifier, Diabetic retinopathy, Feature analysis, Macula localization, Optic nerve detection, Red-free fundus imagery, Vascular segmentation",

author = "Tobin, {Kenneth W.} and Edward Chaum and {Priya Govindasamy}, V. and Karnowski, {Thomas P.}",

year = "2007",

month = dec,

doi = "10.1109/TMI.2007.902801",

language = "English",

volume = "26",

pages = "1729--1739",

journal = "IEEE Transactions on Medical Imaging",

issn = "0278-0062",

publisher = "Institute of Electrical and Electronics Engineers",

number = "12",

}

TY - JOUR

T1 - Detection of anatomic structures in human retinal imagery

AU - Tobin, Kenneth W.

AU - Chaum, Edward

AU - Priya Govindasamy, V.

AU - Karnowski, Thomas P.

PY - 2007/12

Y1 - 2007/12

N2 - The widespread availability of electronic imaging devices throughout the medical community is leading to a growing body of research on image processing and analysis to diagnose retinal disease such as diabetic retinopathy (DR). Productive computer-based screening of large, at-risk populations at low cost requires robust, automated image analysis. In this paper we present results for the automatic detection of the optic nerve and localization of the macula using digital red-free fundus photography. Our method relies on the accurate segmentation of the vasculature of the retina followed by the determination of spatial features describing the density, average thickness, and average orientation of the vasculature in relation to the position of the optic nerve. Localization of the macula follows using knowledge of the optic nerve location to detect the horizontal raphe of the retina using a geometric model of the vasculature. We report 90.4% detection performance for the optic nerve and 92.5% localization performance for the macula for red-free fundus images representing a population of 345 images corresponding to 269 patients with 18 different pathologies associated with DR and other common retinal diseases such as age-related macular degeneration.

AB - The widespread availability of electronic imaging devices throughout the medical community is leading to a growing body of research on image processing and analysis to diagnose retinal disease such as diabetic retinopathy (DR). Productive computer-based screening of large, at-risk populations at low cost requires robust, automated image analysis. In this paper we present results for the automatic detection of the optic nerve and localization of the macula using digital red-free fundus photography. Our method relies on the accurate segmentation of the vasculature of the retina followed by the determination of spatial features describing the density, average thickness, and average orientation of the vasculature in relation to the position of the optic nerve. Localization of the macula follows using knowledge of the optic nerve location to detect the horizontal raphe of the retina using a geometric model of the vasculature. We report 90.4% detection performance for the optic nerve and 92.5% localization performance for the macula for red-free fundus images representing a population of 345 images corresponding to 269 patients with 18 different pathologies associated with DR and other common retinal diseases such as age-related macular degeneration.

KW - Bayesian classifier

KW - Diabetic retinopathy

KW - Feature analysis

KW - Macula localization

KW - Optic nerve detection

KW - Red-free fundus imagery

KW - Vascular segmentation

UR - http://www.scopus.com/inward/record.url?scp=36549056512&partnerID=8YFLogxK

U2 - 10.1109/TMI.2007.902801

DO - 10.1109/TMI.2007.902801

M3 - Article

C2 - 18092741

AN - SCOPUS:36549056512

SN - 0278-0062

VL - 26

SP - 1729

EP - 1739

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

IS - 12

ER -

Detection of anatomic structures in human retinal imagery

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this