基于血管内超声图像自动识别易损斑块

张麒; 汪源源; 马剑英; 钱菊英; 施俊; 严壮志

doi:10.3788/OPE.20111910.2507

您当前的位置：

首页 >

文章列表页 >

基于血管内超声图像自动识别易损斑块

信息科学 | 更新时间：2020-08-12

- 基于血管内超声图像自动识别易损斑块
- Automatic identification of vulnerable plaques based on intravascular ultrasound images
- 光学精密工程 2011年19卷第10期页码：2507-2519
- 作者机构：
  
  1. 复旦大学电子工程系上海,200433
  2. 上海大学通信与信息工程学院上海,200072
  3. 复旦大学附属中山医院心内科上海,200032
- 作者简介：
- 基金信息：
  
  上海市教委"();晨光计划"();项目(No.11CG45)();上海市教委重点学科建设项目(No.J50104)();上海市教委科研创新项目(No.0
- DOI：10.3788/OPE.20111910.2507
  中图分类号： TB559;TP391.4
- 收稿日期：2010-12-13，
  
  修回日期：2011-02-17，
  
  网络出版日期：2011-10-27，
  
  纸质出版日期：2011-10-25
- 稿件说明：
移动端阅览
张麒, 汪源源, 马剑英, 钱菊英, 施俊, 严壮志. 基于血管内超声图像自动识别易损斑块[J]. 光学精密工程, 2011,19(10): 2507-2519

ZHANG Qi, WANG Yuan-yuan, MA Jian-ying, QIAN Ju-ying, SHI Jun, YAN Zhuang-zhi . Automatic identification of vulnerable plaques based on intravascular ultrasound images[J]. Editorial Office of Optics and Precision Engineering, 2011,19(10): 2507-2519
张麒, 汪源源, 马剑英, 钱菊英, 施俊, 严壮志. 基于血管内超声图像自动识别易损斑块[J]. 光学精密工程, 2011,19(10): 2507-2519 DOI： 10.3788/OPE.20111910.2507.

ZHANG Qi, WANG Yuan-yuan, MA Jian-ying, QIAN Ju-ying, SHI Jun, YAN Zhuang-zhi . Automatic identification of vulnerable plaques based on intravascular ultrasound images[J]. Editorial Office of Optics and Precision Engineering, 2011,19(10): 2507-2519 DOI： 10.3788/OPE.20111910.2507.

摘要

为克服手工判别动脉粥样硬化易损斑块耗时耗力、主观性强、重复性差等缺点

研究了基于血管内超声自动识别易损斑块的方法。首先将Contourlet变换与Snake模型相结合进行斑块的图像分割

提取内腔轮廓与外弹力膜。接着实现经典形态特征的计算机自动提取

并提取纹理、弹性两类新特征以量化斑块属性

其中纹理特征包括一阶统计量和灰度共生矩阵特征

弹性特征的提取则基于非刚性图像配准。最后设计Fisher线性判别、支撑向量机、广义相关学习矢量量化3种分类器进行分类判决。对124例斑块(36例易损

88例非易损)的实验结果表明:20个形态特征、24个纹理特征和6个弹性特征在两类斑块间存在显著性差异(

0.05);采用三类特征由支撑向量机进行分类时效果最好

在测试集上敏感性、特异性、准确率和约登指数分别达到91.7%、97.7%、96.7%和89.4%

表明利用血管内超声图像中斑块的三类特征能自动、准确地识别易损斑块。

Abstract

In order to overcome drawbacks in manual identification of vulnerable atherosclerotic plaques

a method for automatic identification of vulnerable plaques is proposed based on computerized analysis of intravascular ultrasound images. First

the Contourlet transform is combined with the Snake model to segment images and detect lumen borders and external elastic membranes. Two categories of new features representing texture and elasticity of plaques are then automatically extracted to quantitate the features of plaques. The texture features consist of first-order statistics and features from the gray-level coocurrence matrix

and the elastic features are extracted from strain tensors estimated by nonrigid image registration. Finally

three types of features are used to design classifiers including Fisher linear discrimination

support vector machines

and generalized relevance learning vector quantization. The experimental results on 124 plaques

consisting of 36 vulnerable and 88 nonvulnerable ones

reveals that 20 morphological features

24 texture features and 6 elastic features has significant difference (

0.05) between the two types of plaques.The Support Vector Machine(SVM) outperformes the other two classifiers with the sensitivity

specificity

correct rate

and Youdens index of 91.7%

97.7%

96.7%

and 89.4%

respectively. Therefore

the proposed method can automatically and accurately identify vulnerable plaques.

关键词

Keywords

references

NAGHAVI M, LIBBY P, FALK E, et al. From vulnerable plaque to vulnerable patient: A call for new definitions and risk assessment strategies: Part I [J]. Circulation, 2003, 108(14): 1664-1672.[2] WAXMAN S, ISHIBASHI F, MULLER J E. Detection and treatment of vulnerable plaques and vulnerable patients: Novel approaches to prevention of coronary events [J]. Circulation, 2006, 114(22): 2390-2411.[3] GIL D, HERNANDEZ A, RODRIGUEZ O, et al. Statistical strategy for anisotropic adventitia modelling in IVUS [J]. IEEE Transactions on Medical Imaging, 2006, 25(6): 768-778.[4] BOVENKAMP E G P, DIJKSTRA J, BOSCH J G, et al. Multi-agent segmentation of IVUS images [J]. Pattern Recognition, 2004, 37(4): 647-663.[5] GIANNOGLOU G D, CHATZIZISIS Y S, KOUTKIAS V, et al. A novel active contour model for fully automated segmentation of intravascular ultrasound images: In vivo validation in human coronary arteries [J]. Computers in Biology and Medicine, 2007, 37(9): 1292-1302.[6] GE J, CHIRILLO F, SCHWEDTMANN J, et al. Screening of ruptured plaques in patients with coronary artery disease by intravascular ultrasound [J]. Heart, 1999, 81(6): 621-627.[7] YAMAGISHI M, TERASHIMA M, AWANO K, et al. Morphology of vulnerable coronary plaque: Insights from follow-up of patients examined by intravascular ultrasound before an acute coronary syndrome [J]. Journal of the American College of Cardiology, 2000, 35(1): 106-111.[8] LIANG Y, ZHU H, FRIEDMAN M H. The correspondence between coronary arterial wall strain and histology in a porcine model of atherosclerosis [J]. Physics in Medicine and Biology, 2009, 54(18): 5625-5641.[9] 刘露, 刘宛予, 楚春雨, 等. 胸部CT图像中孤立性肺结节良恶性快速分类 [J]. 光学精密工程, 2009, 17(8): 2060-2068. LIU L, LIU W-Y, CHU C-Y, et al. Fast classification of benign and malignant solitary pulmonary nodules in CT image [J]. Optics and Precision Engineering, 2009, 17(8): 2060-2068.[10] 温江涛, 王伯雄. 应用小波包能量谱及支持向量机实现安瓿内浮类异物的识别 [J]. 光学精密工程, 2009, 17(11): 2794-2799. WEN J-T, WANG B-X. Recognition of floating particles in ampoules by wavelet packet energy spectrum and SVM [J]. Optics and Precision Engineering, 2009, 17(11): 2794-2799.[11] 张麒, 汪源源, 王威琪, 等. 活动轮廓模型和contourlet多分辨率分析分割血管内超声图像 [J]. 光学精密工程, 2008, 16(11): 2303-2311. ZHANG Q, WANG Y-Y, WANG W-Q, et al. Intravascular ultrasound image segmentation based on active contour model and contourlet multiresolution analysis [J]. Optics and Precision Engineering, 2008, 16(11): 2303-2311.[12] PO D D, DO M N. Directional multiscale modeling of images using the contourlet transform [J]. IEEE Transactions on Image Processing, 2006, 15(6): 1610-1620.[13] ZHANG Q, WANG Y, WANG W, et al. Automatic segmentation of calcifications in intravascular ultrasound images using snakes and the contourlet transform [J]. Ultrasound in Medicine and Biology, 2010, 36(1): 111-129.[14] BERGLUND H, LUO H, NISHIOKA T, et al. Highly localized arterial remodeling in patients with coronary atherosclerosis : An intravascular ultrasound study [J]. Circulation, 1997, 96(5): 1470-1476.[15] HARALICK R M, SHANMUGAM K, DINSTEIN I H. Textural features for image classification [J]. IEEE Transactions on Systems, Man and Cybernetics, 1973, 3(6): 610-621.[16] 姜永林, 屈桢深, 王常虹. 基于纹理及统计特征的视频背景提取 [J]. 光学精密工程, 2008, 16(1): 172-177. J IANG Y-L, QU Z-S, WANG C-H. Video background extraction based on textural and statistical features [J]. Optics and Precision Engineering, 2008, 16(1): 172-177.[17] 边肇祺, 张学工, 等, 模式识别 [M]. 2000, 北京: 清华大学出版社. BIAN Z, ZHANG X, et al. Pattern recognition [M]. 2000, Beijing: Tsinghua University Press.[18] SCHNEIDER P, BUNTE K, STIEKEMA H, et al. Regularization in matrix relevance learning [J]. Neural Networks, IEEE Transactions on, 2010, 21(5): 831-840.[19] 王志蕴, 张梅, 张运, 等. 速度向量成像评价冠心病患者颈动脉粥样斑块力学特性的临床研究 [J]. 中华超声影像学杂志, 2009, 18(1): 27-30. WANG Z-Y, ZHANG M, ZHANG Y, et al. Primary study of carotid atherosclerosis plaque biomechnics using ultrasonic velocity vector imaging in patients with coronary artery disease [J]. Chinese Journal of Ultrasonography, 2009, 18(1): 27-30.

浏览量

356

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于图像处理的光纤预警系统模式识别

融合条形注意力机制的电芯极片计算机断层图像分割

增强型金枪鱼群优化指数熵的砂粒显微图像分割

语义流引导采样结合注意力机制的脑肿瘤图像分割

基于分数阶微分的高光谱图像特征提取与分类