Max-min central vein detection in retinal fundus images

被引:12
作者
Azegrouz, Hind [1 ]
Trucco, Emanuele [1 ]
机构
[1] Heriot Watt Univ, Sch Engn & Phys Sci, Dept Elect Electron & Comp Engn, Edinburgh EH14 4AS, Midlothian, Scotland
来源
2006 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP 2006, PROCEEDINGS | 2006年
关键词
retinal; central; vein; vessel; graph;
D O I
10.1109/ICIP.2006.313145
中图分类号
TP18 [人工智能理论];
学科分类号
081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];
摘要
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.
引用
收藏
页码:1925 / +
页数:2
相关论文
共 20 条
[1]
Mapping the human blood-retinal barrier function [J].
Bernardes, R ;
Dias, J ;
Cunha-Vaz, J .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2005, 52 (01) :106-116
[2]
Chutatape O, 1998, P ANN INT IEEE EMBS, V20, P3144, DOI 10.1109/IEMBS.1998.746160
[3]
Detection and measurement of retinal vessels, in fundus images using amplitude modified second-order Gaussian filter [J].
Gang, L ;
Chutatape, O ;
Krishnan, SM .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2002, 49 (02) :168-172
[4]
A divide et impera strategy for automatic classification of retinal vessels into arteries and veins [J].
Grisan, E ;
Ruggeri, A .
PROCEEDINGS OF THE 25TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-4: A NEW BEGINNING FOR HUMAN HEALTH, 2003, 25 :890-893
[5]
Segmentation of vessels in retinal images by shortest path histogramming [J].
Henderson, TC ;
Choikim, GW .
SEVENTH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, VOL 1, PROCEEDINGS, 2003, :685-688
[6]
Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response [J].
Hoover, A ;
Kouznetsova, V ;
Goldbaum, M .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2000, 19 (03) :203-210
[7]
THINNING METHODOLOGIES - A COMPREHENSIVE SURVEY [J].
LAM, L ;
LEE, SW ;
SUEN, CY .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (09) :869-885
[8]
LI H, IEEE T BIOMEDICAL EN, V51, P246
[9]
Retinal vascular tree morphology: A semi-automatic quantification [J].
Martinez-Perez, ME ;
Hughes, AD ;
Stanton, AV ;
Thom, SA ;
Chapman, N ;
Bharath, AA ;
Parker, KH .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2002, 49 (08) :912-917
[10]
A SIMPLEX-METHOD FOR FUNCTION MINIMIZATION [J].
NELDER, JA ;
MEAD, R .
COMPUTER JOURNAL, 1965, 7 (04) :308-313