摘要
医学图像配准在临床诊断和治疗计划中起着重要的作用。应用特征图像的第一主方向提出了自动配准计算机层析术(CT)和磁共振(MR)大脑图像的方法。方案中,先应用主成分分析-神经网络来计算特征图像的第一主方向,然后通过调整特征图像的第一主方向和质心来完成配准问题。此外,还以MR-MR图像配准和CT-MR图像配准为例,对此方法的配准效果进行了简单分析。
Medical image registration plays an important role in clinical diagnosis and therapy planning. An automatic method is proposed to register computed tomography (CT) and magnetic resonance (MR) brain images by using first principal directions of feature images. In this method, principal component analysis (PCA) neural net-work is used to calculate the first principal directions from feature images, and then the registration is accomplished by simply aligning feature images, first principal directions and centroid. Simulations for MR-MR ( MR and MR images) registration and CT - MR (CT and MR images) registration are carried out to illustrate the method.
出处
《科学技术与工程》
2011年第22期5317-5322,共6页
Science Technology and Engineering
关键词
图像配准
主成分分析
Oja学习算法
神经网络
image registration principal component analysis Oja's learning algorithm neural net-work