基于形变模型的医学图像分割算法研究

An Algorithm Based on Deformable Contour Models for Medical Image Segmentation

结合形变模型和模糊C-均值(FCM)分割技术,提出了一种基于形变模型的医学图像解剖结构轮廓分割方法,在FCM分类的基础上,利用成员隶属函数定义一种模糊约束力并附加于形变模型的外部约束力中,在该种复合外部约束作用下,使形变模型能更好地收缩于解剖结构的轮廓。图像实验结果表明该方法的有效性和可行性。

This paper provides a new medical image segmentation algorithm using a deformable contour model, which integrates Fuzzy C-Means（FCM） Clustering technique and deformable contour model. An external fuzzy constrain is defined from the membership function value of FCM, which joins the external constrain of the deformable model and drives the deformable model towards the contour ideal edge of the object. Examples are presented to demonstrate the efficiency and feasibility of the approach on spinal MRI images and the results are encouraging.