[1]孙巧榆,杨冠羽,舒华忠.基于模糊C均值法的CTA图像冠状动脉狭窄量化[J].东南大学学报(自然科学版),2016,46(1):30-34.[doi:10.3969/j.issn.1001-0505.2016.01.006]
 Sun Qiaoyu,Yang Guanyu,Shu Huazhong.Stenosis quantification of coronary artery CTA images based on fuzzy C-means algorithm[J].Journal of Southeast University (Natural Science Edition),2016,46(1):30-34.[doi:10.3969/j.issn.1001-0505.2016.01.006]
点击复制

基于模糊C均值法的CTA图像冠状动脉狭窄量化()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
46
期数:
2016年第1期
页码:
30-34
栏目:
计算机科学与工程
出版日期:
2016-01-20

文章信息/Info

Title:
Stenosis quantification of coronary artery CTA images based on fuzzy C-means algorithm
作者:
孙巧榆13杨冠羽12舒华忠12
1东南大学影像科学与技术实验室, 南京 210096; 2东南大学中法生物医学信息研究中心, 南京 210096; 3 淮海工学院电子信息工程系, 连云港 222005
Author(s):
Sun Qiaoyu13 Yang Guanyu12 Shu Huazhong12
1 Laboratory of Image Science and Technology, Southeast University, Nanjing 210096, China
2 Centre de Recherche en Information Bimédicale Sino-Français, Southeast University, Nanjing 210096, China
3 Department of Electric Information Engineering, Huaihai Institute of Technology, Lianyungang 222005, China
关键词:
模糊C均值 狭窄量化 软斑块 血管分割 CTA
Keywords:
fuzzy C-means stenosis quantification soft plaque vascular segmentation computed tomography angiography(CTA)
分类号:
TP301.5
DOI:
10.3969/j.issn.1001-0505.2016.01.006
摘要:
针对冠状动脉造影图像中由软斑块造成的冠状动脉狭窄,提出了一种基于模糊C均值法的狭窄精确量化方法.首先,在沿冠状动脉中心线的三维数据图上,对专家给定起讫位置的冠状动脉血管片段进行切割和阈值化.其次,利用模糊C均值法分割出血管腔区域,计算血管每个横截面的血管腔面积检测值,通过起讫位置的检测面积拟合得到参考值.然后,通过比较血管横截面面积的检测值和参考值来确定分段中最狭窄的位置及其狭窄比率. 最后,利用该方法对13个病人的CTA数据进行了测试,并将测试结果与专家给出的狭窄比率进行比较.结果表明,所提方法能够对CTA中给定起讫位置的冠状动脉血管片段的狭窄区域进行精确量化,狭窄比率的平均绝对差和均方根差分别为2.21%和3.11%.
Abstract:
As for coronary artery stenosis caused by soft plaques in coronary artery angiography images, an accurate stenosis quantification method based on the fuzzy C-means algorithm is proposed. First, the segment of the coronary artery with starting and ending positions defined by experts is cropped and thresholded on the three-dimensional data along the centerline. Secondly, the fuzzy C-means algorithm is applied to separate the region of vessel lumen from other tissues. The detected value of the vessel lumen area in each slice is computed and the reference value is fitted by the detection area between the starting and ending positions. Then, the location and the ratio of the most stenosis are determined by comparing the detected value with the reference value of the vessel area. Finally, the proposed method is tested on clinical computed tomography angiography(CTA)datasets of thirteen patients and the detection results are compared with the stenosis ratios defined by experts. The experimental results indicate that the proposed method can accurately quantify the stenosis of the coronary artery segment with given starting and ending positions in CTA. The absolute average difference and the root mean squared difference of the stenosis ratios are 2.21% and 3.11%, respectively.

参考文献/References:

[1] Mackay J,Mensah G A,Mendis S,et al.The atlas of heart disease and stroke [M]. Geneva, Switzerland:World Health Organization,2004:5-6.
[2] Vancraeynest D, Pasquet A, Roelants V, et al. Imaging the vulnerable plaque[J]. J Am Coll Cardiol, 2011, 57(20): 1961-1979. DOI:10.1016/j.jacc.2011.02.018.
[3] Dey D, Cheng V Y, Slomka P J, et al. Automated 3-dimensional quantification of noncalcified and calcified coronary plaque from coronary CT angiography[J]. J Cardiovasc Comput Tomogr, 2009, 3(6): 372-382. DOI:10.1016/j.jcct.2009.09.004.
[4] Kelm B,Mittal S,Zheng Y,et al. Detection, grading and classification of coronary stenoses in computed tomography angiography [C]//International Conference on Medical Image Computing and Computer-assisted Intervention.Toronto,Canada, 2011: 25-32.
[5] Xu Y, Liang G, Hu G, et al. Quantification of coronary arterial stenoses in CTA using fuzzy distance transform[J]. Comput Med Imaging Graph, 2012, 36(1): 11-24. DOI:10.1016/j.compmedimag.2011.03.004.
[6] Shahzad R, Kiri瘙塂li H, Metz C, et al. Automatic segmentation, detection and quantification of coronary artery stenoses on CTA[J]. Int J Cardiovasc Imaging, 2013, 29(8): 1847-1859. DOI:10.1007/s10554-013-0271-1.
[7] Yang G, Kitslaar P, Frenay M, et al. Automatic centerline extraction of coronary arteries in coronary computed tomographic angiography[J]. Int J Cardiovasc Imaging, 2012, 28(4): 921-933. DOI:10.1007/s10554-011-9894-2.
[8] Dunn J C.A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters [J].Journal of Cybernetics, 1973,3(3):32-57. DOI:10.1080/01969727308546046.
[9] Xu R,Wunsch D Ⅱ.Survey of clustering algorithms [J].IEEE Transactions on Neural Networks,2005, 16(3):645-678. DOI:10.1109/TNN.2005.845141.
[10] Broersen A,Kitslaar P,Frenay M,et al. French Coast: Fast,robust extraction for the nice challenge on coronary artery segmentation of the tree [C]//MICCAI Workshop 3D Cardiovascular Imaging:a MICCAI segmentation challenge. Nice,France, 2012:1-8.

备注/Memo

备注/Memo:
收稿日期: 2015-09-24.
作者简介: 孙巧榆(1973—),女,博士,副教授;杨冠羽(联系人),男,博士,副教授, yang.list@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(61271312,81101104)、江苏省自然科学基金资助项目(BK2012743)、江苏省“六大人才高峰”资助项目(2012 DZXX-031)、江苏省“333高层次人才培养工程”资助项目(BRA2015288)、江苏省博士后科学研究基金资助项目(1302018C).
引用本文: 孙巧榆,杨冠羽,舒华忠.基于模糊C均值法的CTA图像冠状动脉狭窄量化[J].东南大学学报(自然科学版),2016,46(1):30-34. DOI:10.3969/j.issn.1001-0505.2016.01.006.
更新日期/Last Update: 2016-01-20