基于双重边缘检测和区域生长的大脑皮层分割算法  

A segmentation algorithm of cerebral cortex based on dual edge detections and regional growing

作　　者：刘宁[1] 罗洪艳[1] 谭立文[2] 李敏[1] 文丽丽[1] 

机构地区：[1]重庆大学生物工程学院,重庆400030 [2]第三军医大学基础部解剖学教研室,重庆400038

出　　处：《中国介入影像与治疗学》2012年第8期629-632,共4页Chinese Journal of Interventional Imaging and Therapy

基　　金：国家自然科学基金(60871099);中央高校基本科研业务费资助项目(CDJZR10230024);重庆大学大型仪器开放基金资助项目(2011121522)

摘　　要：目的设计一种数字人脑切片图像自动分割算法,以实现对大脑皮层的准确分割。方法采用RGB空间彩色边缘检测与Canny算子边缘检测,联合种子点自动选择的区域生长算法,提取并分割大脑皮层,并与手工分割结果进行对比分析。结果自动分割的大脑皮层边缘完整、清晰、平滑,与手工分割结果的吻合度较高。结论采用该方法可较为准确地分割数字人脑切片图像中的大脑皮层。Objective To design a automatic segmentation algorithm for digital cross-section slice images of human brain, in order to segment the cerebral cortex accurately. Methods Cerebral cortex was obtained and extracted from gray matter using RGB space edge detection, Canny operator detection and regional growing algorithm. A comparative analysis between the segmentation results of automatic algorithm and manual method was performed. Results Highly coincident to that segmented by manual method, cere- bral cortex segmented by automatic algorithm was characterized by complete, clear and smooth edge. Conclusion This algorithm is suitable for the segmentation of cerebral cortex in digital cross-section slice images.

关 键 词：脑皮质 彩色边缘检测 区域生长 图像分割 

分 类 号：R318.0[医药卫生—生物医学工程]