摘要
本研究提出了一种自动化的模糊连接(fuzzy connectedness,FC)方法,用于3维核磁共振(MRI)图像脑组织分割。方法的主要创新在于提出了FC方法中各项参数的自动指定方法,包括:利用灰质、白质各自的体素尺度(scale)值大小差异,自动估计组织的灰度概率密度函数;根据估计得到的组织灰度概率密度函数,自动指定种子点。从而避免了人工干预,保证了分割过程的自动化和可重复性。所提方法在IBSR(the Intemet Brain SegmentationRepository)数据库所提供的MRI图像上进行了测试,并和同类研究进行了对比,分割精度优于同类研究。作为一种完全自动化的方法,该方法能够被广泛应用到3维可视化、放疗手术计划和医学数据库构造中。
An automated fuzzy connectedness （FC） method is presented for brain tissue classification in 3D brain MRI. The main contribution is the automatic initialization of FC parameters, including estimation of tissue intensity probability density function （PDF） based on voxel scale differences, and assignment of multiple seed voxels based on estimated tissue PDFs. The proposed method requires no user interaction, and is fully automatic and robust. Experiments based on IBSR （the Internet Brain Segmentation Repository） are included, as well as comparisons with other published methods, This method shows better classification accuracy and is expected to find wide applications, such as 3D visualization, radiation therapy planning,and medical database construction.
出处
《中国生物医学工程学报》
CAS
CSCD
北大核心
2006年第4期411-416,共6页
Chinese Journal of Biomedical Engineering
关键词
模糊连接
脑组织分割
尺度
核磁图像
fuzzy connectedness
brain tissue classification
image scale
MRI
