详细信息
病毒进化的离散差分进化超声图像特征选择
Virus-evolutionary discrete differential evolution algorithm for feature selection of cervical lymph nodes in ultrasound images
文献类型:期刊文献
中文题名:病毒进化的离散差分进化超声图像特征选择
英文题名:Virus-evolutionary discrete differential evolution algorithm for feature selection of cervical lymph nodes in ultrasound images
作者:张巧荣[1];朱长明[2,3];倪军[3];刘海波[2]
第一作者:张巧荣
机构:[1]河南财经政法大学计算机与信息工程学院;[2]哈尔滨工程大学计算机科学与技术学院;[3]美国爱荷华大学卡佛医学院
第一机构:河南财经政法大学计算机与信息工程学院
年份:2012
卷号:17
期号:7
起止页码:866-872
中文期刊名:中国图象图形学报
外文期刊名:Journal of Image and Graphics
收录:CSTPCD;;北大核心:【北大核心2011】;CSCD:【CSCD2011_2012】;
基金:国家自然科学基金项目(60803036);国家教育部博士点专项基金项目(20092304120013);中央高校基本科研业务费专项资金(HEUCFZ1010;HEUCF100604)
语种:中文
中文关键词:病毒进化;离散差分进化;超声图像;特征选择
外文关键词:virus-evolutionary; discrete differential evolution; ultrasound images ; features selection
摘要:选择具有识别作用的超声图像淋巴结区域特征对临床诊断具有重要价值。针对目前特征选择算法收敛速度慢和容易陷入局部极小值的问题,提出病毒协同进化的离散差分进化的颈部淋巴结超声图像特征选择算法。该算法主要利用病毒感染操作进行宿主个体的变异,在维持宿主个体多样性的同时保留最优的搜索信息,提高了算法的适应度函数值和进化速度。在临床颈部淋巴结超声图像中进行实验验证,分类精度达到98%,而算法平均收敛迭代次数仅为30次,表明本文所提算法是正确有效的。
Selecting regional features in uhrasound images of lymph nodes is important for clinical diagnosis. Most of the current feature selection algorithms are time-consuming and lead easily to a premature convergence. In this paper, a new novel discrete differential evolution (DDE) algorithm based on virus-evolution is presented to solve the cervical lymph nodes features selection problem. We call it virus-evolutionary discrete differential evolution (VEDDE) algorithm Biological virus mechanism and the infection-based operation between host and virus are introduced in the DDE which can maintain the diversity of individuals while retaining the best search information and improve the fitness function value and the speed of evolution. The proposed algorithm has been tested on many clinical ultrasound images of cervical lymph nodes. The classification accuracy is 98% and the average number of iterations is only 30 times, which indicates that the proposed algorithm is valid.
参考文献:
正在载入数据...