支持向量机在医学图像分割中的应用

Application of support vector machine in medical image segmentation

脑组织图像分割在医学图像分析中具有重要的意义。支持向量机是近些年机器学习领域发展起来的新的研究热点,在小样本、高维情况下,具有较好的泛化性能。本文采用支持向量机方法对磁共振脑组织图像进行分割研究。实验结果表明:适当选择核函数及模型参数对支持向量机的分割性能有较大的影响,本文提出的支持向量机方法在脑图像分割应用是有效的。

The Segmentation of brain tissues images is very important in medical image processing. Support vector machine （SVM） is a research hotspot in machine learning field. It has a good generalization performance, especially for dataset with small number of samples in high dimensional feature space. This paper presents the segmentation method of brain tissues from magnetic resonance images based on SVM. Experimental results show that the selections of kernel function and model parameters on the generalization performance of SVM are important. Application of SVM is available.