Max-min central vein detection in retinal fundus images

Hind Azegrouz; Emanuele Trucco

doi:10.1109/ICIP.2006.313145

Max-min central vein detection in retinal fundus images

Hind Azegrouz, Emanuele Trucco

School of Engineering & Physical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

13 Citations (Scopus)

Abstract

This paper describes a new framework for the automated tracking of the central retinal vein in retinal images. The procedure first computes a binary image of the retinal vasculature, then obtains the skeleton (medial axis) of the vascular network. Terminal and branching points of the network are then located, and the network converted into a graph representation including length and thickness information for all vessels. Finally, a MaxMin approach is used to locate the central vein:The candidates central vein are the minimal paths from the optic disk to all terminal nodes found using Dijkstra algorithm. The actual central vein is selected among the all candidates by maximizing a merit function estimating the total vessel area in the image. Results are presented and compared with those provided by a manual classification on 20 images of the DRIVE set. An overall performance ratio of 92% is achieved. ©2006 IEEE.

Original language	English
Title of host publication	2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings
Pages	1925-1928
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2006.313145
Publication status	Published - 2006
Event	13th IEEE International Conference on Image Processing 2006 - Atlanta, GA, United States Duration: 8 Oct 2006 → 11 Oct 2006

Conference

Conference	13th IEEE International Conference on Image Processing 2006
Abbreviated title	ICIP 2006
Country/Territory	United States
City	Atlanta, GA
Period	8/10/06 → 11/10/06

Keywords

Central
Graph
Retinal
Vein
Vessel

Access to Document

10.1109/ICIP.2006.313145

Cite this

@inproceedings{7a2764fae17241f2810b0ca28166433e,

title = "Max-min central vein detection in retinal fundus images",

abstract = "This paper describes a new framework for the automated tracking of the central retinal vein in retinal images. The procedure first computes a binary image of the retinal vasculature, then obtains the skeleton (medial axis) of the vascular network. Terminal and branching points of the network are then located, and the network converted into a graph representation including length and thickness information for all vessels. Finally, a MaxMin approach is used to locate the central vein:The candidates central vein are the minimal paths from the optic disk to all terminal nodes found using Dijkstra algorithm. The actual central vein is selected among the all candidates by maximizing a merit function estimating the total vessel area in the image. Results are presented and compared with those provided by a manual classification on 20 images of the DRIVE set. An overall performance ratio of 92% is achieved. {\textcopyright}2006 IEEE.",

keywords = "Central, Graph, Retinal, Vein, Vessel",

author = "Hind Azegrouz and Emanuele Trucco",

year = "2006",

doi = "10.1109/ICIP.2006.313145",

language = "English",

isbn = "1424404819",

pages = "1925--1928",

booktitle = "2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings",

note = "13th IEEE International Conference on Image Processing 2006, ICIP 2006 ; Conference date: 08-10-2006 Through 11-10-2006",

}

TY - GEN

T1 - Max-min central vein detection in retinal fundus images

AU - Azegrouz, Hind

AU - Trucco, Emanuele

PY - 2006

Y1 - 2006

N2 - This paper describes a new framework for the automated tracking of the central retinal vein in retinal images. The procedure first computes a binary image of the retinal vasculature, then obtains the skeleton (medial axis) of the vascular network. Terminal and branching points of the network are then located, and the network converted into a graph representation including length and thickness information for all vessels. Finally, a MaxMin approach is used to locate the central vein:The candidates central vein are the minimal paths from the optic disk to all terminal nodes found using Dijkstra algorithm. The actual central vein is selected among the all candidates by maximizing a merit function estimating the total vessel area in the image. Results are presented and compared with those provided by a manual classification on 20 images of the DRIVE set. An overall performance ratio of 92% is achieved. ©2006 IEEE.

AB - This paper describes a new framework for the automated tracking of the central retinal vein in retinal images. The procedure first computes a binary image of the retinal vasculature, then obtains the skeleton (medial axis) of the vascular network. Terminal and branching points of the network are then located, and the network converted into a graph representation including length and thickness information for all vessels. Finally, a MaxMin approach is used to locate the central vein:The candidates central vein are the minimal paths from the optic disk to all terminal nodes found using Dijkstra algorithm. The actual central vein is selected among the all candidates by maximizing a merit function estimating the total vessel area in the image. Results are presented and compared with those provided by a manual classification on 20 images of the DRIVE set. An overall performance ratio of 92% is achieved. ©2006 IEEE.

KW - Central

KW - Graph

KW - Retinal

KW - Vein

KW - Vessel

UR - http://www.scopus.com/inward/record.url?scp=78649839959&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2006.313145

DO - 10.1109/ICIP.2006.313145

M3 - Conference contribution

SN - 1424404819

SN - 9781424404810

SP - 1925

EP - 1928

BT - 2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings

T2 - 13th IEEE International Conference on Image Processing 2006

Y2 - 8 October 2006 through 11 October 2006

ER -

Max-min central vein detection in retinal fundus images

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this