[1]刘志东,林江莉,陈 科*.基于图像分割的视网膜血管图像配准研究[J].四川师范大学学报(自然科学版),2017,(04):554-560.[doi:10.3969/j.issn.1001-8395.2017.04.020 ]
 LIU Zhidong,LIN Jiangli,CHEN Ke.Registration of Retinal Vessel Blood Image Based on Image Segmentation[J].Journal of SichuanNormal University,2017,(04):554-560.[doi:10.3969/j.issn.1001-8395.2017.04.020 ]
点击复制

基于图像分割的视网膜血管图像配准研究()
分享到:

《四川师范大学学报(自然科学版)》[ISSN:1001-8395/CN:51-1295/N]

卷:
期数:
2017年04期
页码:
554-560
栏目:
基础理论
出版日期:
2017-04-30

文章信息/Info

Title:
Registration of Retinal Vessel Blood Image Based on Image Segmentation
文章编号:
1001-8395(2017)04-0554-07
作者:
刘志东12 林江莉1 陈 科1*
1. 四川大学 材料科学与工程学院, 四川 成都 610065;
2. 四川城市职业学院 汽车与信息工程学院, 四川 成都 610010
Author(s):
LIU Zhidong12 LIN Jiangli1 CHEN Ke1
1. College of Materials Science and Engineering, Sichuan University, Chengdu 610065, Sichuan;
2. Department of Automobile and Information Engineering, Urban Vocational College of Sichuan, Chengdu 610010, Sichuan
关键词:
视网膜图像 图像分割 配准 互信息
Keywords:
retinal image image segmentation registration mutual information
分类号:
TP391.4
DOI:
10.3969/j.issn.1001-8395.2017.04.020
文献标志码:
A
摘要:
利用不同波长的视网膜图像可以对视网膜血管血氧饱和度进行计算,但需进行配准处理.提出一种基于视网膜图像血管分割的互信息图像配准方法.为了充分利用血管的轮廓信息和灰度信息,提高配准精度,首先对配准图像进行图像分割,提取视网膜图像中的血管轮廓信息; 然后对分割后图像中的血管进行相似度计算,并采用Powell优化算法中的黄金分割法一维搜索算法来提升运算速度; 最后根据计算的相似度值来完成不同波长图像的配准.研究中算法配准获得变换参数(角度、X方向、Y方向)的误差的均值分别为2.00%、2.53%和2.52%,误差的方差分别为0.57、2.09和0.34,均优于直接互信息配准方法.实验表明:算法可以自动、有效地对不同波长的视网膜血管图像进行配准,并具有良好的可重复性和稳定性.
Abstract:
In order to calculate the blood oxygen saturation of retinal images, different wavelength images should be registered. This paper presents an image registration method based on the segmentation of blood vessel image and mutual information. In the study, in order to reduce the impact of the information on the registration result, the registration of image segmentation, extraction of retinal vessels information in the image; calculating the vascular similarity in the segmented image, and using the Powell optimization algorithm 0.618 one-dimensional search algorithm to improve the speed of operation; the different wavelength of the image registration based on the calculated similarity value. In the study, the error average of parameters(angle, X direction, Y direction)calculated from the registration algorithm is 2.00%, 2.53% and 2.52%, and the variance of the error is 0.57, 2.09 and 0.34, were better than the direct mutual information registration method. Experiments show that the algorithm can automatically and effectively register retinal images with different wavelengths, and has good repeatability and stability.

参考文献/References:

[1] HARRIS A, DINN R B, KAGEMANN L. A review of methods for human retinal oximetry[J]. Ophthalmic Surgery Lasers & Imaging,2003,34(2):152-164.
[2] 李新胜,刘宇. 基于边缘特征的虚实图像精确配准[J]. 四川大学学报(工程科学版),2014,46(5):96-103.
[3] 何敬,李永树,李歆,等. 基于点特征和边缘特征的无人机影像配准方法[J]. 西南交通大学学报(自然科学版),2012,46(6):955-961.
[4] 王红玉,冯筠,崔磊,等. 应用显著纹理特征的医学图像配准[J]. 光学精密工程,2015,23(9):2656-2665.
[5] PLUIM J, MAINTZ J, VIERGEVER M A. Image registration by maximization mutual information and gradient information[J]. IEEE Trans on Medical Imaging,2001,19(8):809-819.
[6] DEEPA M, SARAVANAN T. Automatic image registration using 2D-discrete wavelet transform[J]. Indian J Science & Technology,2016,9(5):1-3.
[7] ARAKI T, IKEDA N, DEY N, et al. A comparative approach of four different image registration techniques for quantitative assessment of coronary artery calcium lesions using intravascular ultrasound[J]. Computer Methods & Programs in Biomedicine,2015,118(2):158-172.
[8] 洪明坚,吕建斌,杨丹,等. 一种新的基于互信息的图像配准方法[J]. 重庆大学学报(自然科学版),2009,32(6):697-700.
[9] 翟利志,王敬东,李鹏. 基于邻域信息的红外与可见光图像互信息配准[J]. 计算机技术与发展,2008,18(10):151-154.
[10] 华梓铮,华泽玺. 结合NSCT高低频特征的图像边缘检测算法[J]. 四川师范大学学报(自然科学版),2014,37(4):612-617.
[11] 高向军. 基于多尺度线性检测的视网膜血管分割[J]. 科学技术与工程,2013,13(23):6820-6824.
[12] NGNYEN U T V, BHUIYAN A, PARK L A F. An effective retinal blood vessel segmentation method using multi-scale line detection[J]. Pattern Recognition,2013,13(3):703-715.
[13] YAMADA M, SIGAL L, RAPTIS M, et al. Cross-domain matching with squared-loss mutual information[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,37(9):1764-76.
[14] 潘婷婷,陆丽婷,顾绮芳. QPSO算法和Powell法结合的多分辨率医学图像配准[J]. 计算机应用与软件,2014,31(7):237-240.
[15] 乔玉龙,赵源萌,张存林,等. 基于混合Powell法的太赫兹/可见光双波段图像配准[J]. 光学学报,2015,35(2):151-157.
[16] SHAMES R, SADEGHI P, KENNEDY R. Parallel computation of mutual information on the GPU with application to real-time registration of 3D medical images[J]. Computer Methods & Programs in Biomedicine,2010,99(2):133-46.

相似文献/References:

[1]罗渝兰,王景熙,郑昌琼,等.基于Snake模型的B超心脏图像的腔体分割及算法研究[J].四川师范大学学报(自然科学版),2002,(01):66.
 LUO Yu-lan,WANG Jin-xi,ZHENG Cang-qiong,et al.[J].Journal of SichuanNormal University,2002,(04):66.
[2]何艳阳,王景熙,罗渝兰,等.生物仿真神经网络图像分割方法中的参数自动确定[J].四川师范大学学报(自然科学版),2001,(02):213.
 HE Yan yang,WANG Jing xi,LUO Yu lan,et al.[J].Journal of SichuanNormal University,2001,(04):213.

备注/Memo

备注/Memo:
收稿日期:2017-02-21
基金项目:国家自然科学基金(81301286)和四川省科技支撑项目(2014GZ0005)
*通信作者简介:陈 科(1982—),男,博士,主要从事医学图像处理的研究,E-mail:chenke@scu.edu.cn
更新日期/Last Update: 2017-04-30