电子学报 ›› 2019, Vol. 47 ›› Issue (10): 2149-2157.DOI: 10.3969/j.issn.0372-2112.2019.10.017

所属专题: 机器学习与智慧医疗

• 学术论文 • 上一篇    下一篇

结合双树复小波变换和改进密度峰值快速搜索聚类的乳腺MR图像分割

范虹1, 张程程1, 侯存存1, 朱艳春2, 姚若侠1   

  1. 1. 陕西师范大学计算机科学学院, 陕西西安 710062;
    2. 中国科学院深圳先进技术研究院生物医学与健康工程研究所, 广东深圳 518055
  • 收稿日期:2018-07-21 修回日期:2019-02-14 出版日期:2019-10-25
    • 作者简介:
    • 范虹 女,1969年出生,宁夏平罗人.博士,教授,CCF会员,主要研究领域为图像处理、模式识别、智能信息处理.E-mail:fanhong@snnu.edu.cn;张程程 女,1994年出生,山东济宁人.硕士生,主要研究领域为医学图像处理.
    • 基金资助:
    • 国家自然科学基金 (No.11471004); 陕西省重点研发展计划 (No.2018SF-251); 陕西省自然科学基金 (No.2014JM2-6115)

Dual-Tree Complex Wavelet Transform and Improved Density Peak Fast Search and Clustering Method for Breast MR Image Segmentation

FAN Hong1, ZHANG Cheng-cheng1, HOU Cun-cun1, ZHU Yan-chun2, YAO Ruo-xia1   

  1. 1. School of Computer Science, Shaanxi Normal University, Xi'an, Shaanxi 710062, China;
    2. Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, The Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China
  • Received:2018-07-21 Revised:2019-02-14 Online:2019-10-25 Published:2019-10-25
    • Supported by:
    • National Natural Science Foundation of China (No.11471004); Key Research and Development Project of Shaanxi Province (No.2018SF-251); Natural Science Foundation of Shaanxi Province,  China (No.2014JM2-6115)

摘要: 针对乳腺MR图像组织复杂、灰度不均匀、难分割的特点,本文提出双树复小波(DTCWT)变换结合密度聚类的图像分割方法.首先利用复小波域双变量模型结合各向异性扩散函数对图像进行去噪处理;进而通过简单线性迭代聚类(SLIC)算法将图像划分成一定数量的超像素区域,根据事先设置的阈值搜索每个超像素的近邻,从而降低基于K近邻的密度峰值快速搜索聚类(KNN-DPC)算法寻找每个样本近邻的时间;最终,引入超像素区域的近邻信息度量样本密度,采用KNN-DPC算法的分配策略自适应聚类.仿真和临床数据分割结果表明,所提算法能有效的实现乳腺MR图像的分割.

关键词: 乳腺MR图像分割, 双树复小波变换, 双变量模型, 超像素分类, 密度峰值快速搜索聚类

Abstract: Breast MR image segmentation is difficult because of complex organization and intensity inhomogeneity. This paper proposes a segmentation method based on dual-tree complex wavelet transform and density clustering. Firstly, the image is denoised by using complex wavelet domain bivariate model combined with anisotropic diffusion function; Then simple linear iterative clustering (SLIC) algorithm is used to obtain the neighbors of each superpixel, thereby reducing the time of searching for the nearest neighbor of each sample in KNN-DPC algorithm. Finally, nearest neighbor sample density information of superpixel region is introduced,and distribution strategies from KNN-DPC algorithm are used for adaptive clustering. The segmentation results of simulation and clinical data show that the proposed algorithm can segment breast MR images effectively.

Key words: breast MR image segmentation, dual tree complex wavelet transform, bivariate model, hyper pixel classification, density peak fast search clustering

中图分类号: