Extraction of Blood Vessels in Retinal Images Using Resampling High-Order Background Estimation

被引:2
作者
Paripurana, Sukritta [1 ]
Chiracharit, Werapon [1 ]
Chamnongthai, Kosin [1 ]
Saito, Hideo [2 ]
机构
[1] King Mongkuts Univ Technol Thonburi, Fac Engn, Dept Elect & Telecommun Engn, Bangkok 10140, Thailand
[2] Keio Univ, Fac Sci & Technol, Dept Informat & Comp Sci, Yokohama, Kanagawa 2238522, Japan
来源
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2015年 / E98D卷 / 03期
关键词
retinal blood vessel extraction; retinal background estimation; rescaling image; high order degree polynomial; MICROVASCULAR ABNORMALITIES; ATHEROSCLEROSIS RISK; GRAY-LEVEL; SEGMENTATION; CLASSIFICATION; FUNDUS; COMMUNITIES; DISEASE;
D O I
10.1587/transinf.2014EDP7186
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In retinal blood vessel extraction through background removal, the vessels in a fundus image which appear in a higher illumination variance area are often missing after the background is removed. This is because the intensity values of the vessel and the background are nearly the same. Thus, the estimated background should be robust to changes of the illumination intensity. This paper proposes retinal blood vessel extraction using background estimation. The estimated background is calculated by using a weight surface fitting method with a high degree polynomial. Bright pixels are defined as unwanted data and are set as zero in a weight matrix. To fit a retinal surface with a higher degree polynomial, fundus images are reduced in size by different scaling parameters in order to reduce the processing time and complexity in calculation. The estimated background is then removed from the original image. The candidate vessel pixels are extracted from the image by using the local threshold values. To identify the true vessel region, the candidate vessel pixels are dilated from the candidate. After that, the active contour without edge method is applied. The experimental results show that the efficiency of the proposed method is higher than the conventional low-pass filter and the conventional surface fitting method. Moreover, rescaling an image down using the scaling parameter at 0.25 before background estimation provides as good a result as a non-rescaled image does. The correlation value between the non-rescaled image and the rescaled image is 0.99. The results of the proposed method in the sensitivity, the specificity, the accuracy, the area under the receiver operating characteristic (ROC) curve (AUC) and the processing time per image are 0.7994, 0.9717, 0.9543, 0.9676 and 1.8320 seconds for the DRIVE database respectively.
引用
收藏
页码:692 / 703
页数:12
相关论文
共 36 条
[11]   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
[12]   Retinal vessel tortuosity measures and their applications [J].
Kalitzeos, Angelos A. ;
Lip, Gregory Y. H. ;
Heitmar, Rebekka .
EXPERIMENTAL EYE RESEARCH, 2013, 106 :40-46
[13]   The Medical Image Perception Society Update on Key Issues for Image Perception Research [J].
Krupinski, Elizabeth A. ;
Berbaum, Kevin S. .
RADIOLOGY, 2009, 253 (01) :230-233
[14]   Adaptive image enhancement for retinal blood vessel segmentation [J].
Lin, TS ;
Zheng, YB .
ELECTRONICS LETTERS, 2002, 38 (19) :1090-1091
[15]   AUTOMATIC OPTIC DISC DETECTION THROUGH BACKGROUND ESTIMATION [J].
Lu, Shijian ;
Lim, Joo Hwee .
2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, :833-836
[16]   A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Gray-Level and Moment Invariants-Based Features [J].
Marin, Diego ;
Aquino, Arturo ;
Emilio Gegundez-Arias, Manuel ;
Manuel Bravo, Jose .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2011, 30 (01) :146-158
[17]   Segmentation of blood vessels from red-free and fluorescein retinal images [J].
Martinez-Perez, M. Elena ;
Hughes, Alun D. ;
Thom, Simon A. ;
Bharath, Anil A. ;
Parker, Kim H. .
MEDICAL IMAGE ANALYSIS, 2007, 11 (01) :47-61
[18]   EVALUATION OF RETINAL VESSEL SEGMENTATION METHODS FOR MICROANEURYSMS DETECTION [J].
Martins, C. I. O. ;
Medeiros, F. N. S. ;
Veras, R. M. S. ;
Bezerra, F. N. ;
Cesar, R. M., Jr. .
2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, :3365-+
[19]   Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction [J].
Mendonca, Ana Maria ;
Campilho, Aurelio .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2006, 25 (09) :1200-1213
[20]   Retinal Image Analysis Using Curvelet Transform and Multistructure Elements Morphology by Reconstruction [J].
Miri, Mohammad Saleh ;
Mahloojifar, Ali .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2011, 58 (05) :1183-1192