基于邻域关系模糊粗糙集的医学图像分类研究

对医学图像进行分类时,特征选择是影响分类准确率的非常重要的因素。针对医学图像的特殊性,以及目前提出的特征选择算法在应用于医学图像分类时效果不够理想等问题,提出一种基于邻域关系的模糊粗糙集模型,基于该模型给出特征选择算法,并将其应用于乳腺X光图像。实验结果表明,同已有的算法相比,该方法能有效选择特征,分类精度有较大的提升。...

Full description

Saved in:
Bibliographic Details
Published in计算机工程与科学 Vol. 38; no. 4; pp. 739 - 746
Main Author 胡学伟 蒋芸 邹丽 李志磊 沈健
Format Journal Article
LanguageChinese
Published 西北师范大学计算机科学与工程学院,甘肃兰州,730070 2016
Subjects
医学图像分类
特征选择
邻域关系
特征选择
neighborhood relation
medical image classification
邻城关系
feature selection
医学图像分类
Online AccessGet full text
ISSN1007-130X
DOI10.3969/j.issn.1007-130X.2016.04.019

Cover

More Information
Summary:对医学图像进行分类时,特征选择是影响分类准确率的非常重要的因素。针对医学图像的特殊性,以及目前提出的特征选择算法在应用于医学图像分类时效果不够理想等问题,提出一种基于邻域关系的模糊粗糙集模型,基于该模型给出特征选择算法,并将其应用于乳腺X光图像。实验结果表明,同已有的算法相比,该方法能有效选择特征,分类精度有较大的提升。
Bibliography:For medical images classification,feature selection is an important factor that affects classification accuracy.Aiming at the particularity of medical image as well as undesirable effects of current feature selection methods,we propose a fuzzy rough set model based on neighborhood relation,and a feature selection algorithm based on the model as well.We apply our algorithm to mammography,and the experimental results show that it can effectively select features and improve classification accuracy in comparison with the existing algorithms.
43-1258/TP
medical image classification; feature selection; neighborhood relation
HU Xue-wei,JIANG Yun,ZOU Li,LI Zhi-lei,SHEN Jian （School of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070,China）
ISSN:1007-130X
DOI:10.3969/j.issn.1007-130X.2016.04.019