Extraction of Blood Vessels in Retinal Images Using Resampling High-Order Background Estimation

Sukritta PARIPURANA; Werapon CHIRACHARIT; Kosin CHAMNONGTHAI; Hideo SAITO

doi:10.1587/transinf.2014EDP7186

Extraction of Blood Vessels in Retinal Images Using Resampling High-Order Background Estimation

Sukritta PARIPURANA, Werapon CHIRACHARIT, Kosin CHAMNONGTHAI, Hideo SAITO

Full Text Views

0

Share
Cite this

Summary :

In retinal blood vessel extraction through background removal, the vessels in a fundus image which appear in a higher illumination variance area are often missing after the background is removed. This is because the intensity values of the vessel and the background are nearly the same. Thus, the estimated background should be robust to changes of the illumination intensity. This paper proposes retinal blood vessel extraction using background estimation. The estimated background is calculated by using a weight surface fitting method with a high degree polynomial. Bright pixels are defined as unwanted data and are set as zero in a weight matrix. To fit a retinal surface with a higher degree polynomial, fundus images are reduced in size by different scaling parameters in order to reduce the processing time and complexity in calculation. The estimated background is then removed from the original image. The candidate vessel pixels are extracted from the image by using the local threshold values. To identify the true vessel region, the candidate vessel pixels are dilated from the candidate. After that, the active contour without edge method is applied. The experimental results show that the efficiency of the proposed method is higher than the conventional low-pass filter and the conventional surface fitting method. Moreover, rescaling an image down using the scaling parameter at 0.25 before background estimation provides as good a result as a non-rescaled image does. The correlation value between the non-rescaled image and the rescaled image is 0.99. The results of the proposed method in the sensitivity, the specificity, the accuracy, the area under the receiver operating characteristic (ROC) curve (AUC) and the processing time per image are 0.7994, 0.9717, 0.9543, 0.9676 and 1.8320 seconds for the DRIVE database respectively.

Publication: IEICE TRANSACTIONS on Information Vol.E98-D No.3 pp.692-703

Publication Date: 2015/03/01

Publicized: 2014/12/12

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014EDP7186

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Authors

Sukritta PARIPURANA
  King Mongkut's University of Technology Thonburi
Werapon CHIRACHARIT
  King Mongkut's University of Technology Thonburi
Kosin CHAMNONGTHAI
  King Mongkut's University of Technology Thonburi
Hideo SAITO
  Keio University

Keyword

retinal blood vessel extraction, retinal background estimation, rescaling image, high order degree polynomial

Cite this

Copy

Sukritta PARIPURANA, Werapon CHIRACHARIT, Kosin CHAMNONGTHAI, Hideo SAITO, "Extraction of Blood Vessels in Retinal Images Using Resampling High-Order Background Estimation" in IEICE TRANSACTIONS on Information, vol. E98-D, no. 3, pp. 692-703, March 2015, doi: 10.1587/transinf.2014EDP7186.
Abstract: In retinal blood vessel extraction through background removal, the vessels in a fundus image which appear in a higher illumination variance area are often missing after the background is removed. This is because the intensity values of the vessel and the background are nearly the same. Thus, the estimated background should be robust to changes of the illumination intensity. This paper proposes retinal blood vessel extraction using background estimation. The estimated background is calculated by using a weight surface fitting method with a high degree polynomial. Bright pixels are defined as unwanted data and are set as zero in a weight matrix. To fit a retinal surface with a higher degree polynomial, fundus images are reduced in size by different scaling parameters in order to reduce the processing time and complexity in calculation. The estimated background is then removed from the original image. The candidate vessel pixels are extracted from the image by using the local threshold values. To identify the true vessel region, the candidate vessel pixels are dilated from the candidate. After that, the active contour without edge method is applied. The experimental results show that the efficiency of the proposed method is higher than the conventional low-pass filter and the conventional surface fitting method. Moreover, rescaling an image down using the scaling parameter at 0.25 before background estimation provides as good a result as a non-rescaled image does. The correlation value between the non-rescaled image and the rescaled image is 0.99. The results of the proposed method in the sensitivity, the specificity, the accuracy, the area under the receiver operating characteristic (ROC) curve (AUC) and the processing time per image are 0.7994, 0.9717, 0.9543, 0.9676 and 1.8320 seconds for the DRIVE database respectively.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2014EDP7186/_p

Copy

@ARTICLE{e98-d_3_692,
author={Sukritta PARIPURANA, Werapon CHIRACHARIT, Kosin CHAMNONGTHAI, Hideo SAITO, },
journal={IEICE TRANSACTIONS on Information},
title={Extraction of Blood Vessels in Retinal Images Using Resampling High-Order Background Estimation},
year={2015},
volume={E98-D},
number={3},
pages={692-703},
abstract={In retinal blood vessel extraction through background removal, the vessels in a fundus image which appear in a higher illumination variance area are often missing after the background is removed. This is because the intensity values of the vessel and the background are nearly the same. Thus, the estimated background should be robust to changes of the illumination intensity. This paper proposes retinal blood vessel extraction using background estimation. The estimated background is calculated by using a weight surface fitting method with a high degree polynomial. Bright pixels are defined as unwanted data and are set as zero in a weight matrix. To fit a retinal surface with a higher degree polynomial, fundus images are reduced in size by different scaling parameters in order to reduce the processing time and complexity in calculation. The estimated background is then removed from the original image. The candidate vessel pixels are extracted from the image by using the local threshold values. To identify the true vessel region, the candidate vessel pixels are dilated from the candidate. After that, the active contour without edge method is applied. The experimental results show that the efficiency of the proposed method is higher than the conventional low-pass filter and the conventional surface fitting method. Moreover, rescaling an image down using the scaling parameter at 0.25 before background estimation provides as good a result as a non-rescaled image does. The correlation value between the non-rescaled image and the rescaled image is 0.99. The results of the proposed method in the sensitivity, the specificity, the accuracy, the area under the receiver operating characteristic (ROC) curve (AUC) and the processing time per image are 0.7994, 0.9717, 0.9543, 0.9676 and 1.8320 seconds for the DRIVE database respectively.},
keywords={},
doi={10.1587/transinf.2014EDP7186},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Extraction of Blood Vessels in Retinal Images Using Resampling High-Order Background Estimation
T2 - IEICE TRANSACTIONS on Information
SP - 692
EP - 703
AU - Sukritta PARIPURANA
AU - Werapon CHIRACHARIT
AU - Kosin CHAMNONGTHAI
AU - Hideo SAITO
PY - 2015
DO - 10.1587/transinf.2014EDP7186
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2015
AB - In retinal blood vessel extraction through background removal, the vessels in a fundus image which appear in a higher illumination variance area are often missing after the background is removed. This is because the intensity values of the vessel and the background are nearly the same. Thus, the estimated background should be robust to changes of the illumination intensity. This paper proposes retinal blood vessel extraction using background estimation. The estimated background is calculated by using a weight surface fitting method with a high degree polynomial. Bright pixels are defined as unwanted data and are set as zero in a weight matrix. To fit a retinal surface with a higher degree polynomial, fundus images are reduced in size by different scaling parameters in order to reduce the processing time and complexity in calculation. The estimated background is then removed from the original image. The candidate vessel pixels are extracted from the image by using the local threshold values. To identify the true vessel region, the candidate vessel pixels are dilated from the candidate. After that, the active contour without edge method is applied. The experimental results show that the efficiency of the proposed method is higher than the conventional low-pass filter and the conventional surface fitting method. Moreover, rescaling an image down using the scaling parameter at 0.25 before background estimation provides as good a result as a non-rescaled image does. The correlation value between the non-rescaled image and the rescaled image is 0.99. The results of the proposed method in the sensitivity, the specificity, the accuracy, the area under the receiver operating characteristic (ROC) curve (AUC) and the processing time per image are 0.7994, 0.9717, 0.9543, 0.9676 and 1.8320 seconds for the DRIVE database respectively.
ER -