一种基于遗传神经网络的医学图像分割方法

Medical Image Segmentation Method Based on Genetic Neural Network and Texture Information

针对一类具有纹理特征的医学图像,提出一种结合纹理信息,利用遗传神经网络的图像分割方法。该方法以混合递阶遗传算法优化径向基神经网络,同时优化其结构及参数。试验表明,该方法应用于生物医学图像,能够区分图像不同的纹理区域,获得较好的分割效果。

A new method for medical image segmentation with adequate texture information is proposed by using genetic neural network and texture information .This method train RBF by Hybrid hiergrchy genetic algorithm （HHGA）, This method is able to determine the structure and parameters of RBF from data. The experiment results show that this method can distinguish different texture and produce good segmentation result when applied to certain medical images.