基于Kohonen神经网络算法的医学图像分割  

Medical Image Segmentation Based on Kohonen Neural Network Algorithm

作　　者：李琼 甘永进 宁维莲 Li Qiong;Gan Yongjin;Ning Weilian(School of Physics and Telecommunication Engineering,Yulin Normal University,Yulin Guangxi,537000)

机构地区：[1]玉林师范学院物理与电信工程学院

出　　处：《电子测试》2020年第5期65-67,共3页Electronic Test

基　　金：广西高校中青年教师基础能力提升项目(KY2016YB367);玉林师范学院校级科研项目(2017YJKY23)

摘　　要：长期以来,在医学图像处理方面,图像分割一直是该项工作中的重点,同时也是其中的难点。所谓的图像分割实质上就是遵照相关的原则对图像进行分割,使其被分为几个部分的过程。它是以图像测量、配准、融合和三维重建作为基础,所以在临床医学研究中起着举足轻重的作用。文中研究的Kohonen聚类神经网络算法是以VC++为基础,并在此基础上进行了一定的优化,为图像分割的具体应用提供基础条件,提高效果,这对医生临床诊断具有十分重要的意义。For a long time, image segmentation has been the focus of medical image processing, but it is also difficult.The so-called image segmentation which is essentially in accordance with the relevant principles of an image and so divided, so that the process is divided into several parts.It is based on image measurement,registration, fusion and 3 D reconstruction, so it plays a very important role in clinical medicine research. Kohonen neural network clustering algorithm based on VC++ in the process of application, and on the basis, it has been optimized to provide basic conditions for the speci fic application of image segmentation and improve the effect,which is of great significance to the clinical diagnosis of doctors.

关 键 词：图像分割 DICOM图像 神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程] R318[医药卫生—生物医学工程]