Retinal artery/vein classification using genetic-search feature selection

被引:38
作者
Huang, Fan [1 ]
Dashtbozorg, Behdad [1 ]
Tan, Tao [1 ,3 ]
Romeny, Bart M. ter Haar [1 ,2 ]
机构
[1] Eindhoven Univ Technol, Dept Biomed Engn, Eindhoven, Netherlands
[2] Northeastern Univ, Dept Biomed & Informat Engn, Shenyang, Liaoning, Peoples R China
[3] ScreenPoint Med, Mammog, Nijmegen, Netherlands
关键词
Fundus image; Artery/vein classification; Genetic search feature selection; BLOOD-VESSELS; VEIN CLASSIFICATION; COLOR IMAGES; FILTERS; DISEASE;
D O I
10.1016/j.cmpb.2018.04.016
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Background and objectives: The automatic classification of retinal blood vessels into artery and vein (A/V) is still a challenging task in retinal image analysis. Recent works on A/V classification mainly focus on the graph analysis of the retinal vasculature, which exploits the connectivity of vessels to improve the classification performance. While they have overlooked the importance of pixel-wise classification to the final classification results. This paper shows that a complicated feature set is efficient for vessel centerline pixels classification. Methods: We extract enormous amount of features for vessel centerline pixels, and apply a genetic-search based feature selection technique to obtain the optimal feature subset for A/V classification. Results: The proposed method achieves an accuracy of 90.2%, the sensitivity of 89.6%, the specificity of 91.3% on the INSPIRE dataset. It shows that our method, using only the information of centerline pixels, gives a comparable performance as the techniques which use complicated graph analysis. In addition, the results on the images acquired by different fundus cameras show that our framework is capable for discriminating vessels independent of the imaging device characteristics, image resolution and image quality. Conclusion: The complicated feature set is essential for A/V classification, especially on the individual vessels where graph-based methods receive limitations. And it could provide a higher entry to the graph-analysis to achieve a better A/V labeling. (C) 2018 The Authors. Published by Elsevier B.V.
引用
收藏
页码:197 / 207
页数:11
相关论文
共 35 条
[1]   Trainable COSFIRE filters for vessel delineation with application to retinal images [J].
Azzopardi, George ;
Strisciuglio, Nicola ;
Vento, Mario ;
Petkov, Nicolai .
MEDICAL IMAGE ANALYSIS, 2015, 19 (01) :46-57
[2]  
Bekkers E. J., 2015, P OPHTHALMIC MEDICAL, P113, DOI [10.17077/omia.1034, DOI 10.17077/OMIA.1034]
[3]   Retinal vascular network architecture in low-birth-weight men [J].
Chapman, N ;
Mohamudally, A ;
Cerutti, A ;
Stanton, A ;
Sayer, AA ;
Cooper, C ;
Barker, D ;
Rauf, A ;
Evans, J ;
Wormald, R ;
Sever, P ;
Hughes, A ;
Thom, S .
JOURNAL OF HYPERTENSION, 1997, 15 (12) :1449-1453
[4]  
Chapman N, 2002, CLIN SCI, V103, P111
[5]   Retinal Vascular Tortuosity, Blood Pressure, and Cardiovascular Risk Factors [J].
Cheung, Carol Yim-lui ;
Zheng, Yingfeng ;
Hsu, Wynne ;
Lee, Mong Li ;
Lau, Qiangfeng Peter ;
Mitchell, Paul ;
Wang, Jie Jin ;
Klein, Ronald ;
Wong, Tien Yin .
OPHTHALMOLOGY, 2011, 118 (05) :812-818
[6]  
Dashtbozorg B., 2017, P SPIE MED IM INT SO
[7]   Automatic Optic Disc and Fovea Detection in Retinal Images Using Super-Elliptical Convergence Index Filters [J].
Dashtbozorg, Behdad ;
Zhang, Jiong ;
Huang, Fan ;
Romeny, Bart M. ter Haar .
IMAGE ANALYSIS AND RECOGNITION (ICIAR 2016), 2016, 9730 :697-706
[8]  
Dashtbozorg B, 2014, IEEE ENG MED BIO, P6328, DOI 10.1109/EMBC.2014.6945076
[9]   An Automatic Graph-Based Approach for Artery/Vein Classification in Retinal Images [J].
Dashtbozorg, Behdad ;
Mendonca, Ana Maria ;
Campilho, Aurelio .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2014, 23 (03) :1073-1083
[10]  
Eiben A. E., 2003, INTRO EVOLUTIONARY C, P53