您的位置:首页  > 论文页面

基于均值漂移和图割的肺结节检测方法

发表时间:2015-03-31  浏览量:1884  下载量:551
全部作者: 白冰,裴晓敏
作者单位: 辽宁石油化工大学信息与控制工程学院
摘 要: 肺结节的自动检测是肺癌计算机辅助诊断的关键和难点。提出一种基于均值漂移(meanshift)和图割的肺结节自动检测方法。首先,利用均值漂移对图像进行平滑滤波,滤除复杂背景的噪声干扰;其次,利用基于区域的图割方法实现网络图分割,完成肺部分割;然后,基于规则对肺实质区域定位,选择肺实质内感兴趣区域(region of interesting,ROI)作为疑似肺结节,并利用轮廓跟踪和凸包运算检测胸腔粘连结节;最后,依照几何形态特征量化并检测肺结节。实验结果表明:该算法速度较快、检出率满足计算机辅助诊断要求,能较好地检测出孤立性肺结节、低对比度结节和胸腔粘连结节。
关 键 词: 信息处理技术;肺结节;均值漂移;图割
Title: Lung nodule detection method based on meanshift and graphcut
Author: BAI Bing,PEI Xiaomin
Organization: College of Information and Control Engineering,Liaoning Shihua University
Abstract: Automatic lung nodule detection is the key and difficult point in computer aided diagnosis. A method for automatic lung nodule detection is proposed based on meanshift and graph cut. Firstly, we use meanshift to smoothly filter the image and filter out noise in complicated background. Secondly, we use region-based graph cut to achieve network segmentation, and achieve lung segmentation. Afterward, we locate lung parenchyma based on regulation, select region of interesting (ROI) in lung parenchyma as suspected pulmonary nodule, detect attached nodules by contour tracking and convex hull. Finally, we quantize and detect lung nodules according to geometric morphology. Experimental results show that, the proposed algorithm is faster and the detection rate meets the requirement of computer aided diagnosis.This method can better detect isolation nodules, low contrast nodules and nodules which adhere to lung wall.
Key words: information processing technology; lung nodule; meanshift; graphcut
发表期数: 2015年3月第6期
引用格式: 白冰,裴晓敏. 基于均值漂移和图割的肺结节检测方法[J]. 中国科技论文在线精品论文,2015,8(6):534-539.
 
0 评论数 0
暂无评论
友情链接