摘要
为了提升医疗信息系统对健康档案数据的分析效率,文中采用图像采集、降噪、配准与差分等技术提取医疗图像信息,进而有效提升信息系统的数据采集效率。同时还对传统的K-means算法加以改进,并提出了一种基于类间、类内距离的聚类初始化评价指标体系(BWP),将其应用于采集到的档案数据中,以实现快速的聚类分析。将所提算法在CUDA计算平台上进行了实现,测试结果表明,该方法的聚类精度和运行效率较现有算法均有显著提升。此外,改进后K-means算法的正确聚类样本数量占比提升了4.88%,高于现有的主流指标体系,且当聚类数k的取值为16或32时,运行时间大幅降低。
In order to improve the data analysis efficiency of the medical information system for health records,the paper uses image acquisition,noise reduction,registration,difference and other technologies to extract medical image information,which effectively improves the data collection efficiency of the information system.At the same time,the traditional K⁃means algorithm is improved,and a cluster initialization evaluation index system(BWP)based on the inter class and intra class distance is proposed.This method is applied to the collected archive data to achieve rapid cluster analysis.The proposed algorithm is implemented on CUDA computing platform.The test results show that the clustering accuracy and running efficiency of the proposed method are significantly improved compared with the existing algorithms.The proportion of correct clustering samples in the improved K⁃means algorithm has increased by 4.88%,which is higher than the existing mainstream index system.Moreover,when the number of clusters k is 16 or 32,the running time is greatly reduced.
作者
崔雨晴
CUI Yuqing(Jining NO.1 People’s Hospital,Jining 272000,China)
出处
《电子设计工程》
2024年第2期191-195,共5页
Electronic Design Engineering
基金
2021年度济宁市重点研发计划(软科学项目)(2021JNZC003)。
