肿瘤亚型识别研究中智能算法的应用  

Application of An Intelligent Algorithm in Tumor Subtype Recognition

作　　者：程慧杰[1] 陈滨[1] 刘芷余[1] 何颖[1] 卜宪庚[1] 高越[2] CHENG Hui-jie;CHEN Bin;LIU Zhi-yu;HE Ying;BU Xian-geng;GAO Yue(Basic Medical College,Harbin Medical University,Harbin,Heilongjiang,150086,China;The Fourth Affiliated Hospital of Harbin Medical University,Harbin,Heilongjiang,150001,China)

机构地区：[1]哈尔滨医科大学基础医学院,黑龙江哈尔滨150086 [2]哈尔滨医科大学附属第四医院,黑龙江哈尔滨150001

出　　处：《现代生物医学进展》2019年第5期960-964,共5页Progress in Modern Biomedicine

基　　金：黑龙江省教育厅科学技术研究项目(12521258)

摘　　要：目的:为解决肿瘤亚型识别过程中易出现的维数灾难和过拟合问题,提出了一种改进的粒子群BP神经网络集成算法。方法:算法采用欧式距离和互信息来初步过滤冗余基因,之后用Relief算法进一步处理,得到候选特征基因集合。采用BP神经网络作为基分类器,将特征基因提取与分类器训练相结合,改进的粒子群对其权值和阈值进行全局搜索优化。结果:当隐含层神经元个数为5时,候选特征基因个数为110时,QPSO/BP算法全局优化和搜索,此时的分类准确率最高。结论:该算法不但提高了肿瘤分型识别的准确率,而且降低了学习的复杂度。Objective:In order to solve the dimension disaster and over-fitting problems in the process of tumor subtype recognition,a particle swarm optimization(PSO)BP neural network ensemble algorithm was proposed.Methods:The Euclidean distance and mutual information was used to preliminarily filter redundant genes,and then Relief algorithm was adopted to further process the candidate feature genes set.The BP neural network was used as the base classifier,which combines feature genes extraction with classifier training.Results:When the number of hidden layer neurons is 5 and the number of candidate feature genes is 110,the QPSO/BP algorithm can optimize and search globally.Conclusion:The algorithm not only improves the accuracy of tumor classification and recognition,but also reduces the complexity of learning.

关 键 词：特征基因 BP神经网络 粒子群优化算法 肿瘤亚型识别 集成分类器 

分 类 号：R73-3[医药卫生—肿瘤] Q-33[医药卫生—临床医学]