An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation

被引:716
作者
Fraz, Muhammad Moazam [1 ]
Remagnino, Paolo [1 ]
Hoppe, Andreas [1 ]
Uyyanonvara, Bunyarit [2 ]
Rudnicka, Alicja R. [3 ]
Owen, Christopher G. [3 ]
Barman, Sarah A. [1 ]
机构
[1] Kingston Univ London, Fac Sci Engn & Comp, Digital Imaging Res Ctr, Kingston upon Thames KT1 2EE, Surrey, England
[2] Thammasat Univ, Sirindhorn Int Inst Technol, Dept Informat Technol, Bangkok 10200, Thailand
[3] Univ London, Div Populat Hlth Sci & Educ, London SW17 0RE, England
关键词
Ensemble classification; medical image analysis; retinal blood vessels; segmentation; IMAGES; EXTRACTION; FEATURES; FILTER; LEVEL;
D O I
10.1109/TBME.2012.2205687
中图分类号
R318 [生物医学工程];
学科分类号
100103 [病原生物学];
摘要
This paper presents a new supervised method for segmentation of blood vessels in retinal photographs. This method uses an ensemble system of bagged and boosted decision trees and utilizes a feature vector based on the orientation analysis of gradient vector field, morphological transformation, line strength measures, and Gabor filter responses. The feature vector encodes information to handle the healthy as well as the pathological retinal image. The method is evaluated on the publicly available DRIVE and STARE databases, frequently used for this purpose and also on a new public retinal vessel reference dataset CHASE_DB1 which is a subset of retinal images of multiethnic children from the Child Heart and Health Study in England (CHASE) dataset. The performance of the ensemble system is evaluated in detail and the incurred accuracy, speed, robustness, and simplicity make the algorithm a suitable tool for automated retinal image analysis.
引用
收藏
页码:2538 / 2548
页数:11
相关论文
共 33 条
[1]
An Active Contour Model for Segmenting and Measuring Retinal Vessels [J].
Al-Diri, Bashir ;
Hunter, Andrew ;
Steel, David .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2009, 28 (09) :1488-1497
[2]
Breiman L, 1996, MACH LEARN, V24, P123, DOI 10.1023/A:1018054314350
[3]
Frangi AF, 1998, LECT NOTES COMPUT SC, V1496, P130, DOI 10.1007/BFb0056195
[4]
Fraz M. M., 2011, COMPUT METHODS PROGR
[5]
Fraz M. M., 2012, COMPUT METHODS PROGR
[6]
Additive logistic regression: A statistical view of boosting - Rejoinder [J].
Friedman, J ;
Hastie, T ;
Tibshirani, R .
ANNALS OF STATISTICS, 2000, 28 (02) :400-407
[7]
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
[8]
Diagnosis of plus disease in retinopathy of prematurity using Retinal Image multiScale Analysis [J].
Gelman, R ;
Martinez-Perez, ME ;
Vanderveen, DK ;
Moskowitz, A ;
Fulton, AB .
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2005, 46 (12) :4734-4738
[9]
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
[10]
Adaptive local thresholding by verification-based multithreshold probing with application to vessel detection in retinal images [J].
Jiang, XY ;
Mojon, D .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (01) :131-137