Accurate Retinal Blood Vessel Segmentation by Using Multi-Resolution Matched Filtering and Directional Region Growing

Mitsutoshi HIMAGA; David USHER; James F.  BOYCE

Accurate Retinal Blood Vessel Segmentation by Using Multi-Resolution Matched Filtering and Directional Region Growing

Mitsutoshi HIMAGA, David USHER, James F. BOYCE

Full Text Views

0

Share
Cite this

Summary :

A new method to extract retinal blood vessels from a colour fundus image is described. Digital colour fundus images are contrast enhanced in order to obtain sharp edges. The green bands are selected and transformed to correlation coefficient images by using two sets of Gaussian kernel patches of distinct scales of resolution. Blood vessels are then extracted by means of a new algorithm, directional recursive region growing segmentation or D-RRGS. The segmentation results have been compared with clinically-generated ground truth and evaluated in terms of sensitivity and specificity. The results are encouraging and will be used for further application such as blood vessel diameter measurement.

Publication: IEICE TRANSACTIONS on Information Vol.E87-D No.1 pp.155-163

Publication Date: 2004/01/01

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Section on Machine Vision Applications)

Category: ME and Human Body

Cite this

Copy

Mitsutoshi HIMAGA, David USHER, James F. BOYCE, "Accurate Retinal Blood Vessel Segmentation by Using Multi-Resolution Matched Filtering and Directional Region Growing" in IEICE TRANSACTIONS on Information, vol. E87-D, no. 1, pp. 155-163, January 2004, doi: .
Abstract: A new method to extract retinal blood vessels from a colour fundus image is described. Digital colour fundus images are contrast enhanced in order to obtain sharp edges. The green bands are selected and transformed to correlation coefficient images by using two sets of Gaussian kernel patches of distinct scales of resolution. Blood vessels are then extracted by means of a new algorithm, directional recursive region growing segmentation or D-RRGS. The segmentation results have been compared with clinically-generated ground truth and evaluated in terms of sensitivity and specificity. The results are encouraging and will be used for further application such as blood vessel diameter measurement.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e87-d_1_155/_p

Copy

@ARTICLE{e87-d_1_155,
author={Mitsutoshi HIMAGA, David USHER, James F. BOYCE, },
journal={IEICE TRANSACTIONS on Information},
title={Accurate Retinal Blood Vessel Segmentation by Using Multi-Resolution Matched Filtering and Directional Region Growing},
year={2004},
volume={E87-D},
number={1},
pages={155-163},
abstract={A new method to extract retinal blood vessels from a colour fundus image is described. Digital colour fundus images are contrast enhanced in order to obtain sharp edges. The green bands are selected and transformed to correlation coefficient images by using two sets of Gaussian kernel patches of distinct scales of resolution. Blood vessels are then extracted by means of a new algorithm, directional recursive region growing segmentation or D-RRGS. The segmentation results have been compared with clinically-generated ground truth and evaluated in terms of sensitivity and specificity. The results are encouraging and will be used for further application such as blood vessel diameter measurement.},
keywords={},
doi={},
ISSN={},
month={January},}

Copy

TY - JOUR
TI - Accurate Retinal Blood Vessel Segmentation by Using Multi-Resolution Matched Filtering and Directional Region Growing
T2 - IEICE TRANSACTIONS on Information
SP - 155
EP - 163
AU - Mitsutoshi HIMAGA
AU - David USHER
AU - James F. BOYCE
PY - 2004
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E87-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2004
AB - A new method to extract retinal blood vessels from a colour fundus image is described. Digital colour fundus images are contrast enhanced in order to obtain sharp edges. The green bands are selected and transformed to correlation coefficient images by using two sets of Gaussian kernel patches of distinct scales of resolution. Blood vessels are then extracted by means of a new algorithm, directional recursive region growing segmentation or D-RRGS. The segmentation results have been compared with clinically-generated ground truth and evaluated in terms of sensitivity and specificity. The results are encouraging and will be used for further application such as blood vessel diameter measurement.
ER -