基于多分类AdaBoost改进算法的TEE标准切面分类  

TEE standard plane classification based on improved multi-class AdaBoost algorithm

作　　者：王莉莉[1,2] 付忠良[1,2] 陶攀[1,2] 朱锴[1,2] 

机构地区：[1]中国科学院成都计算机应用研究所,成都610041 [2]中国科学院大学,北京100049

出　　处：《计算机应用》2017年第8期2253-2257,2269,共6页journal of Computer Applications

基　　金：四川省科技支撑计划项目(2016JZ0035);中国科学院西部之光项目~~

摘　　要：针对超声图像样本冗余、不同标准切面因疾病导致的高度相似性、感兴趣区域定位不准确问题,提出一种结合特征袋(BOF)特征、主动学习方法和多分类AdaBoost改进算法的经食管超声心动图(TEE)标准切面分类方法。首先采用BOF方法对超声图像进行描述;然后采用主动学习方法选择对分类器最有价值的样本作为训练集;最后,在AdaBoost算法对弱分类器的迭代训练中,根据临时强分类器的分类情况调整样本更新规则,实现对多分类AdaBoost算法的改进和TEE标准切面的分类。在TEE数据集和三个UCI数据集上的实验表明,相比AdaBoost.SAMME算法、多分类支持向量机(SVM)算法、BP神经网络和AdaBoost.M2算法,所提算法在各个数据集上的G-mean指标、整体分类准确率和大多数类别分类准确率都有不同程度的提升,且比较难分的类别分类准确率提升最为显著。实验结果表明,在包含类间相似样本的数据集上,分类器的性能有显著提升。Due to redundancy of ultrasound image samples, high similarity between different planes caused by disease, and inaccurate positioning of region-of-interest, a classification method of Trans Esophageal Echocardiography（ TEE） standard plane was proposed by combining with Bag of Features（ BOF） model, active learning and improved multi-class Ada Boost algorithm.Firstly, BOF model was constructed to describe ultrasound image. Secondly, active learning was adopted to select the most informative samples for classifiers as training data set. Lastly, improved multi-class Ada Boost algorithm was proposed, where the weight update rule of multi-class Ada Boost was modified according to the classfication results of temporary strong learner, and the TEE standard plane was classified by the improved multi-class Ada Boost algorithm. The experimental results on TEE data set and three UCI data sets showed that, compared with Ada Boost. SAMME, multi-class Support Vector Machine（ SVM）, BP neural network and Ada Boost. M2, the G-mean value, the total classification accuracy and the classification accuracy in most classes of the proposed method were improved in varying degrees, the classification accuracy of easily misclassified class was improved most significantly. The experimental results illustrate that the improved multi-class Ada Boost algorithm can significantly improve the G-mean value and accuracy of easily misclassified class in the datasets containing similar samples between classes.

关 键 词：多分类AdaBoost 主动学习 特征袋模型 标准切面分类 超声图像分类 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TP181[自动化与计算机技术—计算机科学与技术]