东北大学学报:自然科学版 ›› 2019, Vol. 40 ›› Issue (2): 158-163.DOI: 10.12068/j.issn.1005-3026.2019.02.002

• 信息与控制 • 上一篇    下一篇

基于多重分形去趋势波动分析的视网膜图像分割

张石, 佘黎煌, 王雅凡, 苏婷   

  1. (东北大学 计算机科学与工程学院, 辽宁 沈阳110169)
  • 收稿日期:2017-11-14 修回日期:2017-11-14 出版日期:2019-02-15 发布日期:2019-02-12
  • 通讯作者: 张石
  • 作者简介:张石(1963-),男,辽宁抚顺人,东北大学教授,博士生导师.
  • 基金资助:
    中央高校基本科研业务费专项资金资助项目(N150403002).

Retinal Image Segmentation Based on Multifractal Detrended Fluctuation Analysis

ZHANG Shi, SHE Li-huang, WANG Ya-fan, SU Ting   

  1. School of Computer Science & Engineering, Northeastern University, Shenyang 110169, China.
  • Received:2017-11-14 Revised:2017-11-14 Online:2019-02-15 Published:2019-02-12
  • Contact: SHE Li-huang
  • About author:-
  • Supported by:
    -

摘要: 引入善于描述非稳定图像的多重去趋势波动理论,提出一种基于多重去趋势分析的视网膜图像分割方法.该方法采用直方图均衡化对图像进行预处理来增强血管影像,然后采用多重去趋势波动分析计算图像的广义赫斯特指数,并利用血管指数特性来分割血管,最后用形态学进行图像后处理,得到最终的血管图像.基于DIARETDE0和DIARETDE1两个数据库进行实验.结果表明,该方法在处理视网膜病变图像时有较好的完整性和连通性,能够较好地提取血管主体,具有很好的临床应用价值.

关键词: 视网膜, 血管分割, 多重分形, 去趋势波动分析, 病变图像

Abstract: A method based on multifractal detrended fluctuation analysis(DFA), which is adaptable for unsteady images, is introduced to segment retina images. In this method, histogram equalization is first used to precondition images for the enhancement of blood vessels, and then, the generalized Hurst index of images is calculated by multifractal DFA. The blood vessel index is used to segment the blood vessels. Finally, morphological postprocessing is used to get the final blood vessel images. Experiments based on DIARETDE0 and DIARETDE1 databases show that the proposed method has better integrity and connectivity in the treatment of retinal lesions, and it can extract the main body of blood vessels better, which has a good clinical value.

Key words: retina, segmentation of blood vessel, multifractal, detrended fluctuation analysis, lesion image

中图分类号: