基于人工生命的医学图像自动分割蠕虫模型

A Worm Model Based on Artificial Life for Automatic Segmentation of Medical Image

构造了一种具有初步生命特征的可变形模型——蠕虫模型·该模型包含神经中枢、视觉、触觉和运动系统,具有记忆、认知和支配躯体运动等功能;能智能地处理多种复杂情况,利用综合信息进行图像分割,具有常规图像分割方法不具备的能力·应用实例表明,该模型可以将胼胝体从二维MR矢状位图像中自动、完整地分割出来·对于边界有间断的较复杂的图像,该模型的优势更加明显·

We constructed an intelligent deformable model called worm model. The model has a central nervous system, vision, perception and motor systems. It is able to memorize, recognize objects and control the motion of its body. The new model overcomes the defects of existing methods since it is able to intelligently process the image segmentation using more pieces of in{ormation available rather than using merely pixels and gradients. The experimental results of segmentation of the corpus callosum from MRI brain images showed that the proposed worm model is able to segment medical images automatically and accurately. For those images that are more complex or with fragmentary boundaries, the superiority of the worm model is particularly evident.