Multi-scale approach for retinal vessel segmentation using medialness function

Elahe Moghimirad; Seyed Hamid Rezatofighi; Hamid Soltanian-Zadeh

doi:10.1109/ISBI.2010.5490423

Multi-scale approach for retinal vessel segmentation using medialness function

Elahe Moghimirad, Seyed Hamid Rezatofighi, Hamid Soltanian-Zadeh

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

13 Citations (Scopus)

Abstract

Automated segmentation of retinal vessels in optic fundus images has been the most prevailing effort in many researches during recent years. In this paper, we propose a multi-scale method based on a weighted 2D medialness function. The result of the medialness function is first multiplied by the eigenvalues of the Hessian matrix in every pixel of the image in order to extract vessel's medial-lines. Next, by extracting the centerlines of vessels and estimation of radius of vessels, the retinal vessels are segmented. Finally, the performance of our proposed method is evaluated by the DRIVE and STARE databases and compared with those of several recent methods.

Original language	English
Title of host publication	2010 7th IEEE International Symposium on Biomedical Imaging
Subtitle of host publication	From Nano to Macro, ISBI 2010 - Proceedings
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	29-32
Number of pages	4
ISBN (Print)	9781424441266
DOIs	https://doi.org/10.1109/ISBI.2010.5490423
Publication status	Published - 2010
Externally published	Yes
Event	IEEE International Symposium on Biomedical Imaging (ISBI) 2010 - Rotterdam, Netherlands Duration: 14 Apr 2010 → 17 Apr 2010 Conference number: 7th https://ieeexplore.ieee.org/xpl/conhome/5481762/proceeding (Proceedings)

Conference

Conference	IEEE International Symposium on Biomedical Imaging (ISBI) 2010
Abbreviated title	ISBI 2010
Country/Territory	Netherlands
City	Rotterdam
Period	14/04/10 → 17/04/10
Internet address	https://ieeexplore.ieee.org/xpl/conhome/5481762/proceeding (Proceedings)

Keywords

Eigenvalue
Medialness function
Radius estimation
Retinal vessel segmentation

Access to Document

10.1109/ISBI.2010.5490423

Cite this

@inproceedings{13fa153639024e5b8bcc743a2bd551f6,

title = "Multi-scale approach for retinal vessel segmentation using medialness function",

abstract = "Automated segmentation of retinal vessels in optic fundus images has been the most prevailing effort in many researches during recent years. In this paper, we propose a multi-scale method based on a weighted 2D medialness function. The result of the medialness function is first multiplied by the eigenvalues of the Hessian matrix in every pixel of the image in order to extract vessel's medial-lines. Next, by extracting the centerlines of vessels and estimation of radius of vessels, the retinal vessels are segmented. Finally, the performance of our proposed method is evaluated by the DRIVE and STARE databases and compared with those of several recent methods.",

keywords = "Eigenvalue, Medialness function, Radius estimation, Retinal vessel segmentation",

author = "Elahe Moghimirad and Rezatofighi, {Seyed Hamid} and Hamid Soltanian-Zadeh",

year = "2010",

doi = "10.1109/ISBI.2010.5490423",

language = "English",

isbn = "9781424441266",

pages = "29--32",

booktitle = "2010 7th IEEE International Symposium on Biomedical Imaging",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE International Symposium on Biomedical Imaging (ISBI) 2010, ISBI 2010 ; Conference date: 14-04-2010 Through 17-04-2010",

url = "https://ieeexplore.ieee.org/xpl/conhome/5481762/proceeding",

}

Moghimirad, E, Rezatofighi, SH & Soltanian-Zadeh, H 2010, Multi-scale approach for retinal vessel segmentation using medialness function. in 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers, pp. 29-32, IEEE International Symposium on Biomedical Imaging (ISBI) 2010, Rotterdam, Netherlands, 14/04/10. https://doi.org/10.1109/ISBI.2010.5490423

Multi-scale approach for retinal vessel segmentation using medialness function. / Moghimirad, Elahe; Rezatofighi, Seyed Hamid; Soltanian-Zadeh, Hamid.
2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers, 2010. p. 29-32.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Multi-scale approach for retinal vessel segmentation using medialness function

AU - Moghimirad, Elahe

AU - Rezatofighi, Seyed Hamid

AU - Soltanian-Zadeh, Hamid

N1 - Conference code: 7th

PY - 2010

Y1 - 2010

N2 - Automated segmentation of retinal vessels in optic fundus images has been the most prevailing effort in many researches during recent years. In this paper, we propose a multi-scale method based on a weighted 2D medialness function. The result of the medialness function is first multiplied by the eigenvalues of the Hessian matrix in every pixel of the image in order to extract vessel's medial-lines. Next, by extracting the centerlines of vessels and estimation of radius of vessels, the retinal vessels are segmented. Finally, the performance of our proposed method is evaluated by the DRIVE and STARE databases and compared with those of several recent methods.

AB - Automated segmentation of retinal vessels in optic fundus images has been the most prevailing effort in many researches during recent years. In this paper, we propose a multi-scale method based on a weighted 2D medialness function. The result of the medialness function is first multiplied by the eigenvalues of the Hessian matrix in every pixel of the image in order to extract vessel's medial-lines. Next, by extracting the centerlines of vessels and estimation of radius of vessels, the retinal vessels are segmented. Finally, the performance of our proposed method is evaluated by the DRIVE and STARE databases and compared with those of several recent methods.

KW - Eigenvalue

KW - Medialness function

KW - Radius estimation

KW - Retinal vessel segmentation

UR - http://www.scopus.com/inward/record.url?scp=77955214654&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2010.5490423

DO - 10.1109/ISBI.2010.5490423

M3 - Conference Paper

AN - SCOPUS:77955214654

SN - 9781424441266

SP - 29

EP - 32

BT - 2010 7th IEEE International Symposium on Biomedical Imaging

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE International Symposium on Biomedical Imaging (ISBI) 2010

Y2 - 14 April 2010 through 17 April 2010

ER -

Multi-scale approach for retinal vessel segmentation using medialness function

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this