摘要
针对医学CT图像的特点,提出了一种基于统计分析的算法。先对CT图像进行预处理,并且保存为常用的BMP格式,以便于后续处理,然后利用改进的区域生长算法提取目标组织或者区域,最后选择合适的数学形态学操作对结果进行处理,以消除可能存在的误分。从实验结果可以看出,上述方法是可行的,达到了较好的分割效果,可以满足三维重建的要求。
According to the characteristics of medical images, this paper puts forward and realizes an algorithm based on statistics to preprocess images and then save them in the form of BMP for further operation. Next, it makes use of an improved region growing method to extract tissues or regions, and then processes the result using suitable mathematical morphology operation to reduce misclassification. The example shows that the method is feasible, and good segmentation results have been achieved to meet the requirement of three-dimensional reconstruction.
出处
《洛阳理工学院学报（自然科学版）》
2009年第4期55-59,共5页
Journal of Luoyang Institute of Science and Technology：Natural Science Edition
基金
国家863高新技术项目(2006AA02Z346)
广东省自然科学基金团队项目
关键词
图像分割
CT
区域生长算法
数学形态学
image segmentation
CT
region growing method
mathematical morphology
