Detecting glaucomatous wedge shaped defects in polarimetric images

K A Vermeer; F M Vos; H G Lemij; A M Vossepoel

doi:10.1016/s1361-8415(03)00041-0

Detecting glaucomatous wedge shaped defects in polarimetric images

K A Vermeer, F M Vos, H G Lemij, A M Vossepoel

Glaucoma

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

Abstract

Wedge shaped defects of the retinal nerve fiber layer (RNFL) may occur in glaucoma. Currently, automatic detection of wedge shaped defects in Scanning Laser Polarimetry (SLP) images of the RNFL is not available. An automatic classification is currently based only on global parameters, thereby ignoring important local information. Our method works by a modified dynamic programming technique that searches for locally strong edges with a preference for straight edges. These edges are initially classified based on their strength and next combined into wedge shaped defects. Our method yields a sensitivity of 73% and a specificity of 90% on a limited set of 65 images.

Original language	English
Pages (from-to)	503-11
Number of pages	9
Journal	Medical Image Analysis
Volume	7
Issue number	4
DOIs	https://doi.org/10.1016/s1361-8415(03)00041-0
Publication status	Published - Dec 2003

Keywords

Diagnosis, Computer-Assisted
Diagnostic Techniques, Ophthalmological
Glaucoma/diagnosis
Humans
Lasers
Nerve Fibers/pathology
Optic Disk/pathology
Retina/pathology
Sensitivity and Specificity

Access to Document

10.1016/s1361-8415(03)00041-0

Cite this

@article{90c8d722cbe244caac276e764535a39e,

title = "Detecting glaucomatous wedge shaped defects in polarimetric images",

abstract = "Wedge shaped defects of the retinal nerve fiber layer (RNFL) may occur in glaucoma. Currently, automatic detection of wedge shaped defects in Scanning Laser Polarimetry (SLP) images of the RNFL is not available. An automatic classification is currently based only on global parameters, thereby ignoring important local information. Our method works by a modified dynamic programming technique that searches for locally strong edges with a preference for straight edges. These edges are initially classified based on their strength and next combined into wedge shaped defects. Our method yields a sensitivity of 73% and a specificity of 90% on a limited set of 65 images.",

keywords = "Diagnosis, Computer-Assisted, Diagnostic Techniques, Ophthalmological, Glaucoma/diagnosis, Humans, Lasers, Nerve Fibers/pathology, Optic Disk/pathology, Retina/pathology, Sensitivity and Specificity",

author = "Vermeer, {K A} and Vos, {F M} and Lemij, {H G} and Vossepoel, {A M}",

year = "2003",

month = dec,

doi = "10.1016/s1361-8415(03)00041-0",

language = "English",

volume = "7",

pages = "503--11",

number = "4",

}

TY - JOUR

T1 - Detecting glaucomatous wedge shaped defects in polarimetric images

AU - Vermeer, K A

AU - Vos, F M

AU - Lemij, H G

AU - Vossepoel, A M

PY - 2003/12

Y1 - 2003/12

N2 - Wedge shaped defects of the retinal nerve fiber layer (RNFL) may occur in glaucoma. Currently, automatic detection of wedge shaped defects in Scanning Laser Polarimetry (SLP) images of the RNFL is not available. An automatic classification is currently based only on global parameters, thereby ignoring important local information. Our method works by a modified dynamic programming technique that searches for locally strong edges with a preference for straight edges. These edges are initially classified based on their strength and next combined into wedge shaped defects. Our method yields a sensitivity of 73% and a specificity of 90% on a limited set of 65 images.

AB - Wedge shaped defects of the retinal nerve fiber layer (RNFL) may occur in glaucoma. Currently, automatic detection of wedge shaped defects in Scanning Laser Polarimetry (SLP) images of the RNFL is not available. An automatic classification is currently based only on global parameters, thereby ignoring important local information. Our method works by a modified dynamic programming technique that searches for locally strong edges with a preference for straight edges. These edges are initially classified based on their strength and next combined into wedge shaped defects. Our method yields a sensitivity of 73% and a specificity of 90% on a limited set of 65 images.

KW - Diagnosis, Computer-Assisted

KW - Diagnostic Techniques, Ophthalmological

KW - Glaucoma/diagnosis

KW - Humans

KW - Lasers

KW - Nerve Fibers/pathology

KW - Optic Disk/pathology

KW - Retina/pathology

KW - Sensitivity and Specificity

U2 - 10.1016/s1361-8415(03)00041-0

DO - 10.1016/s1361-8415(03)00041-0

M3 - Article

C2 - 14561554

SN - 1361-8415

VL - 7

SP - 503

EP - 511

JO - Medical Image Analysis

JF - Medical Image Analysis

IS - 4

ER -

Detecting glaucomatous wedge shaped defects in polarimetric images

Abstract

Keywords

Access to Document

Fingerprint

Cite this