摘要
为了提高医学病理图像分类的准确率,提出了一种带有粒子位置权重和粒子之间相关度函数的PSO(particle swarm optimization)参数寻优算法.首先,在经典PSO算法的基础上提出了一种基于适应性原则的位置更新策略.然后,在粒子进行参数寻优的过程中,设计了一个增加粒子之间相关性的函数.该算法可以在不考虑速度影响的情况下进行参数最优解的搜索.最后,用经过PSO优化的支持向量机(SVM)算法分类检测病理图像.实验结果表明,该算法的分类准确率达到了98.5%,较高于另外几种算法.分类检测结果符合临床诊断结果,满足医学研究要求.
In order to improve the accuracy of medical pathological image classification,a PSO parameter optimization algorithm with adaptive iterative optimization function is proposed.First,a position updating strategy based on the adaptive principle is proposed on the basis of the classical PSO algorithm.Then,an adaptive iterative optimization function is designed in the process of particle parameter optimization.The algorithm can search for optimal solution without considering the influence of speed.Finally,the PSO optimized support vector machine algorithm is used to classify and detect pathological images.The experimental results show that the classification accuracy of the algorithm is 98.5%,which is higher than that of the other two algorithms.The results of classified detection are in accordance with the results of clinical diagnosis and meet the requirements of medical research.
作者
董斌
王云涛
贾立男
王娅南
DONG Bin;WANG Yuntao;JIA Li'nan;WANG Ya'nan(Development and Planning Office,Affiliated Hospital of Hebei University,Baoding 071002,China;School of Electronic Information Engineering,Hebei University,Baoding 071002,China;Department of Pathology,Affiliated Hospital of Hebei University,Baoding 071002,China)
出处
《河北大学学报（自然科学版）》
CAS
北大核心
2020年第5期543-551,共9页
Journal of Hebei University(Natural Science Edition)
基金
河北省自然科学基金资助项目(F2017201192)
河北省医学科学研究重点课题(ZL20140223)。
关键词
支持向量机
参数优化
病理图像
图像分类
support vector machine
parameter optimization
pathological image
image classification
