###
DOI:
工程科学与技术:2016,48(3):87-93
←前一篇   |   后一篇→
本文二维码信息
码上扫一扫!
超声左心耳图像的轮廓自动提取
(四川大学电气信息学院)
Automatic Contour Extraction of Left Atrial Appendage from Ultrasound Images
摘要
图/表
参考文献
相似文献
本文已被:浏览 1420次   下载 438
投稿时间:2015-05-12    修订日期:2015-12-22
中文摘要: 针对经食道超声左心耳图像的分辨率低、对比度低、含有斑点噪声等问题,提出了一种结合左心耳解剖位置和超声图像灰度及相位信息的方法,全自动定位常规切片中的左心耳。首先,根据医生采集习惯,以左心耳在标准切面中的解剖位置为先验知识,结合其灰度特性,自动确定分割模型中的初始轮廓;然后,通过线型加权相位和梯度信息构造新的外力项,改进向量场卷积模型,完成左心耳轮廓的自动提取。300张左心耳超声图片测试结果表明,以医生手动勾勒的轮廓作为“金标准”,该方法自动提取左心耳的准确性为0.8969 0.0494、敏感性为0.9058 0.0762、特异性为0.9645 0.1687。分割效果优于传统的向量场卷积模型,能够解决自动定位超声图像中左心耳的初始轮廓和弱边界分割的问题。
Abstract:In order to fulfil the contour extraction of left atrial appendage (LAA) from the low resolution, low contrast and noisy transesophageal ultrasound images automatically, a new method was proposed, which combines the anatomical knowledge of LAA and the information of intensity and phase in ultrasound images. Firstly, to locate the effective initial contour with the characteristic of intensity and geometry from LAA ultrasound images, the anatomy location of LAA in the standard section is taken as the priori-knowledge based on the physicians’ collecting habit. Then, to improve the convergence performance of classical Vector Filed Convolution (VFC) model, a new external force term was proposed by combing phase and gradient information in the linear weighting method. According to the test results conducted from 300 frames, it shows that, this method can reach the accuracy of 0.8969 0.0494, sensitivity of 0.9058 0.0762 and specificity of 0.9645 0.1687 by regarding the contours outlined by physicians as “golden standard”. Comparing with traditional VFC model, this method owns better segmentation performance by determining a more suitable initial contour and is more robust to weak edge.
文章编号:201500444     中图分类号:    文献标志码:
基金项目:四川省科技计划支撑项目2014sz0004-8,项目名称:心血管疾病的早期预警、危险分层及治疗研究,研究手段是超声
Author NameAffiliationE-mail
huangyunzhi  huang_yunzhi@scu.edu.cn 
作者简介:
引用文本:
黄韫栀.超声左心耳图像的轮廓自动提取[J].工程科学与技术,2016,48(3):87-93.
huangyunzhi.Automatic Contour Extraction of Left Atrial Appendage from Ultrasound Images[J].Advanced Engineering Sciences,2016,48(3):87-93.