摘要
为了提高早期肺癌筛查中肺结节计算机辅助检测、辅助诊断的准确性,提出一种多种方法结合的低剂量CT图像肺实质自动分割算法。首先利用改进的多方向形态学滤波算法进行预处理;然后利用聚类法、flood-fill算法去除背景,实现粗分割;接着利用引入霍夫变换的改进三维区域生长算法去除气管和主支气管树;最后利用分水岭算法和二维凸包算法实现肺实质细分割。实验结果通过对ELCAP数据库中的50个低剂量CT序列利用本研究算法进行处理,验证了该算法的有效性,正确分割率达到95.75%。为肺结节检测等后期的诊断提供了有价值的参考信息。
To improve the accuracy of computer-aided detection of pulmonary nodules in early lung cancer screening,a fully automatic 3-D lung parenchyma segmentation algorithm based on hybrid processing was presented. Firstly,the low dose CT images were preprocessed by using the improved multi-directional morphological filtering algorithm. Secondly,the rough segmented images were achieved using cluster method and flood-fill algorithm to remove the background. Then trachea and the main bronchus tree were removed using improved 3D region with hough transform. Finally the fine segmented image was achieved by using watershed and two dimension convex hull algorithm. 50 low dose CT images in the ELCAP database were collected to segment the lung parenchyma with using the proposed method,obtaining the 95. 75% of accuracy. The proposed algorithm can provide some valuable information for pulmonary nodule detection.
作者
吴凉
吕晓琪
谷宇
李菁
张文莉
任国印
张薇
WU Liang;LU Xiaoqi;GU Yu;LI Jing;ZHANG Wenli;REN Guoyin;ZHANG Wei(Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing,School of Ir~brmation Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,Inner Mongolia,China;Inner Mongolia University of Technology,Hohhot O10051,Inner Mongolia;School of Computer Engineering and Science,Shanghai University,Shanghai 200444,China)
出处
《生物医学工程研究》
2018年第2期163-167,共5页
Journal Of Biomedical Engineering Research
基金
国家自然科学基金资助项目(61771266
61179019)
内蒙古自治区自然科学基金资助项目(2015MS0604)
内蒙古自治区高等学校科学研究项目(NJZY145)
包头市科技计划项目(2015C2006-14)
内蒙古科技大学创新基金资助项目(2014QDL045)
关键词
肺实质分割
低剂量CT图像
霍夫变换
凸包算法
分水岭
检测
Lung parenchyma segmentation
Low dose CT
Hough transform
Algorithm of convexhull
Watershed
Detection
