期刊导航

论文摘要

基于Centripetal Catmull Rom曲线的经食道超声心动图左心室分割方法

Left Ventricle Segmentation in Transesophageal Echocardiography Based on Centripetal Catmull Rom Curve

作者:纪祥虎(中国科学院 成都计算机应用研究所,中国科学院大学);高思聪(悉尼科技大学);黄志标(中国科学院 成都计算机应用研究所,中国科学院大学);付忠良(中国科学院 成都计算机应用研究所)

Author:Ji Xianghu(Chengdu Inst. of Computer Application,Chinese Academy of Sciences,Univ. of Chinese Academy of Sciences);Gao Sicong(Univ. of Technol. Sydney);Huang Zhibiao(Chengdu Inst. of Computer Application,Chinese Academy of Sciences,Univ. of Chinese Academy of Sciences);Fu Zhongliang(Chengdu Inst. of Computer Application,Chinese Academy of Sciences)

收稿日期:2016-01-27          年卷(期)页码:2016,48(5):84-90

期刊名称:工程科学与技术

Journal Name:Advanced Engineering Sciences

关键字:经食道超声心动图;左心室分割;活动形状模型;Log Gabor;Centripetal Catmull Rom曲线

Key words:transesophageal echocardiography;left ventricle segmentation;active shape model;Log Gabor;Centripetal Catmull Rom spline

基金项目:四川省科技创新苗子工程资助项目(2015060);中科院西部之光人才培养计划资助项目

中文摘要

针对2维超声心动图像噪声大且难于分割的特点,提出基于Centripetal Catmull Rom曲线的多尺度活动形状模型的左心室分割方法。该算法在金字塔上层提取2维轮廓法线向量特征并采用马氏距离寻找新的特征点位置;在图像金字塔底层快速提取特征点周围的Log Gabor特征并使用Gentle AdaBoost训练分类器,选择置信度水平最高的点作为新的特征点位置。实验证明,这种方法较之传统活动形状模型分割更为精确且分割结果交互方便,有利于对结果的再编辑。

英文摘要

In order to treat the problem that left ventricle is hard to segment in two dimensional transesophageal echocardiography because of the speckle noise,a multi scale active shape model based on centripetal Catmull Rom spline was proposed.In the upper pyramid levels,2D profiles were extracted for each landmark and Mahalanobis distance was used searching new position for each landmark. In the bottom level,fast Log Gabor feature was extracted and trained using Gentle AdaBoost.The point with highest confidence level was the new position for each landmark in the fitting process.Experiments proved that this method is more accurate than traditional Active Shape Model and the segmentation result is interactive and easy to edit.

关闭

Copyright © 2020四川大学期刊社 版权所有.

地址:成都市一环路南一段24号

邮编:610065