文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > 高等教育 > 工学 > Active contours initialization for ultrasound carotid artery images
侵权投诉

Active contours initialization for ultrasound carotid artery images

active coutour

Active Contours Initialization for Ultrasound Carotid Artery Images

Sherif G. Moursi and Mahmoud R. El-Sakka

Computer Science Department University of Western Ontario London, Ontario, Canada {sherif,elsakka}@csd.uwo.ca

Abstract

One of the major issues of active contouring methods is their sensitivity to the initial contour that is provided by the user. Unless it is drawn close enough to the actual contour, it may lead to unsatisfactory results. Thus, most active contour algorithms require considerable user interaction to provide a good initial contour.

In this paper we present an efficient and fast rule-based algorithm for generating a good carotid artery initial contour from ultrasound images. Our algorithm reduces user interaction, as a user is only required to place a seed point inside the region of interest.

Sensitivity, precision rate, and overlap ratio have been used to assess the amount of correlation between manually segmented lumens by an experienced clinician and by our algorithm, where the obtained 95% confidence interval of the mean value of these measures over all test cases are: [78.32% ± 1.98], [91.77% ± 1.96], and [72.68% ± 1.90], respectively. Furthermore, the output of our proposed scheme can be used as an input to any active contour algorithm to produce even better results

Keywords–Initial contour, active contour methods, ultrasound image, carotid artery.

location. Hence, early detection of plaque build up plays an important role in preventing strokes.

Carotid ultrasound imaging is one of the clinical diagnostic procedures that can be employed to detect plaque buildup. It is an inexpensive and noninvasive procedure that has no known side effects. Yet, the produced ultrasound images have poor quality and contain a lot of noise. Hence it takes considerable amount of time and effort from clinicians to manually delineate the borders of the carotid artery lumen in ultrasound images. Furthermore, carotid artery manual segmentation is generally a non-reproducible process and its results may greatly vary from one clinician to another, due to their experience and subjective judgment. When dealing with a large database of ultrasound carotid artery images, such manual processes become impractical. As a result of this, many researchers attempt to develop automated methods for extracting carotid artery lumen boundaries. These methods include texture based segmentation, edge based segmentation, region based segmentation, and active contouring methods.

Hamou et al. [1] proposed using histogram equalization and Canny edge detection followed by morphological opening as a post processing operation in order to segment carotid artery contours. However their method produces many false segmented regions. Abdel-Dayem et al. [2] proposed using histogram equalization and median filtering as preprocessing operations followed by uniform quantization to quantize the image into three regions: area inside the artery, artery wall and a plaque layer. The method produces many false segmented regions and it may not work well on all images since the quantization levels are empirically selected.

Abdel-Dayem et al. [3] proposed using wavelet transforms and applying watershed segmentation in the multi-resolution domain in order to reduce the computational cost. However this method requires the user to specify an image dependent threshold value to merge regions resulting from watershed segmentation.

1. Introduction

Carotid arteries supply the head and neck with oxygenated blood. Carotid artery stenosis is a narrowing in the carotid arteries caused by the buildup of plaque (composed of fatty materials, calcium and scar tissues) on the carotid artery walls. Strokes are mainly caused by the interruption of blood flow to the brain due to the buildup of plaque at the carotid artery walls. Furthermore, plaque causes the blood to flow abnormally, which can cause the blood to clot. Blood clots can break apart and drift through the bloodstream where it is susceptible to cause a blockage at another

第1页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email