通常，临床医师根据经验凭肉眼对肝脏B超图像进行观察和判断。受观察者疏忽、诊断水平的限制等因素的影响，并且超声图像的灰度级对比度较低，使得人的视觉分辨较为困难，容易产生视觉疲劳，从而造成漏诊或误诊。因此需要建立一种客观的方法，为医师诊断肝脏疾病提供必要的辅助手段。 近年来，在针对肝脏B超图像的研究中，对肝脏B超图像的分类大多采用人工神经网络方法，且大多数采用单一特征进行分类，而单一特征对图像的描述比较片面，分类效果不好。针对这一问题，本文将多特征与支持向量机(Support Vector Machine, SVM)相结合的分类方法引入到对肝脏B超图像的分类中。该方法首先提取肝脏B超图像的基于统计矩的特征、基于灰度共生矩阵的特征、基于傅里叶变换的特征和基于小波变换的特征，然后对这四类单一特征进行组合以形成综合特征，最后利用SVM进行分类，确定适合于肝脏B超图像分类的核函数，以及最优的特征组合。 为克服传统SVM由于参数选择不当导致识别率低的问题，本文提出一种粒子群优化算法(Particle Swarm Optimization, PSO)和SVM相结合的肝脏B超图像分类方法。该方法首先采用粒子群优化算法对SVM的参数进行优化，以得到最佳参数，然后在单一特征和多特征结合下运用基于粒子群优化算法的SVM(PSO-SVM)对3类肝脏B超图像进行分类，并将PSO-SVM与基于网格搜索法的SVM进行了对比。实验结果表明，PSO-SVM方法具有较高的分类精度，对肝脏B超图像的分类效果更好。实验说明，粒子群优化算法对支持向量机的参数的优化起到了很好的作用，其优化性能高于网格搜索法对支持向量机的优化性能。 为衡量SVM分类器的性能，将基于SVM的方法与K均值聚类算法和BP神经网络算法进行分类效果的对比。结果表明，基于SVM的方法分类精度较高，对肝脏B超图像分类效果更好。

Typically, clinicians observe and judge liver B ultrasound images with naked eyes based on their experience. It will result in missed diagnosis or misdiagnosis because of the observer’s negligence, limited diagnosis level, and the ultrasound images’ low gray-scale contrast which makes it more difficult for human’s visual resolution and would lead to visual fatigue. So it needs to establish an objective method to provide necessary auxiliary means for doctors to diagnose liver disease. In recent years, in the study of liver B ultrasound images, most of the classification of liver B ultrasound images used artificial neural networks and single feature, while single feature is relatively one-sided description of images. So the classification results were usually not good. To solve this problem, this paper used multi-feature and support vector machine (SVM) to classify liver B ultrasound images. First, features based on statistical moments, features based on gray level concurrence matrix, features based on Fourier transform and features based on wavelet transform were extracted and combined to form integrated features. Finally, SVM was used to conduct classification to determine the kernel function suitable for liver B ultrasound images and the best feature combination. Traditional SVM would gain low recognition rate if its parameters selection are inappropriate. To avoid this, a method for classification of liver B ultrasound images was proposed combining particle swarm optimization (PSO) and SVM. First, PSO algorithm was used to optimize the parameters of SVM to get the best parameters. Then SVM based on particle swarm optimization (PSO-SVM) with single feature and feature combinations was used to classify the three types of liver B ultrasound images. And the PSO-SVM was compared with SVM based on grid-search. The experimental results show that the PSO-SVM algorithm has higher classification accuracy and better performance. Particle swarm optimization has been played a good role in the optimization of support vector machine parameters and its optimize performance is better than the grid search method’s. To measure SVM classifier’s performance, the SVM methods were compared with K-means clustering and BP neural network. Experimental results show that methods based on SVM have higher accuracy and better performance in classifying liver B ultrasound images.