摘要
在自动诊断大量带有病变区域的CT图像时,计算机辅助诊断起着重要的作用。提出了一种自动检测肺结节感兴趣区域的方法。对肺实质进行分割;利用Top-hat滤波提取包含血管和结节在内的初始感兴趣区域;用Gaborfilter对图像进行第二次处理;对图像进行比对,从而得到更为精确的疑似结节的病灶区域。实验证明该方法能准确完整地提取出感兴趣区域。
Computer aided diagnosis plays an important role in automatic detection of abnormal shadow area on CT images. The method of an automatic detection of lung nodules Regions Of Interest(ROI) is presented in this paper. The lung areas are segmented from CT images. The first ROI including nodules and blood vessels in lung areas are extracted by Top-hat filter. The second ROI are extracted by Gabor filter. It contrasts the images to get more accurate lesion areas suspected nodule. Experimental results show that the method can accurately extract the complete region of interest.
出处
《计算机工程与应用》
CSCD
2012年第4期190-192,共3页
Computer Engineering and Applications
基金
辽宁省高校科研计划(No.L2010376)
作者简介
范立南(1964-),男,博士,教授,主要研究领域为图像工程、人工智能、模式识别;
李道静(1985-),女,硕士研究生;
孙申申(1980-),女,博士,讲师;
常朝海(1983-),男,硕士研究生。E-mail:linanfan@163.com