基于不同尺度增强融合的视网膜血管分割算法

冯河洋; 李柏林; 刘甲甲; 陈少杰

doi:10.13873/J.1000-9787(2017)01-0135-04

Chinese

您当前的位置：

首页 >

文章列表页 >

基于不同尺度增强融合的视网膜血管分割算法

计算与测试 | 更新时间：2025-09-11

- 基于不同尺度增强融合的视网膜血管分割算法
- Segmentation algorithm for retinal vessels based on different scale enhancement and fusion
- 传感器与微系统 2017年36卷第1期页码：135-138+142
- 作者机构：
  
  西南交通大学机械工程学院
- 作者简介：
- 基金信息：
  
  四川省科技支撑计划资助项目（2013GZ0032,2014GZ0005）
- DOI：10.13873/J.1000-9787(2017)01-0135-04
  中图分类号： R774.1;TP391.41
- 纸质出版：2017
- 稿件说明：
移动端阅览
[1]冯河洋,李柏林,刘甲甲,陈少杰.基于不同尺度增强融合的视网膜血管分割算法[J].传感器与微系统,2017,36(01):135-138+142.

FENG He-yang, LI Bai-lin, LIU Jia-jia, et al. Segmentation algorithm for retinal vessels based on different scale enhancement and fusion[J]. 2017, 36(1): 135-138+142.
[1]冯河洋,李柏林,刘甲甲,陈少杰.基于不同尺度增强融合的视网膜血管分割算法[J].传感器与微系统,2017,36(01):135-138+142. DOI： 10.13873/J.1000-9787(2017)01-0135-04.

FENG He-yang, LI Bai-lin, LIU Jia-jia, et al. Segmentation algorithm for retinal vessels based on different scale enhancement and fusion[J]. 2017, 36(1): 135-138+142. DOI： 10.13873/J.1000-9787(2017)01-0135-04.

摘要

针对现有视网膜血管图像提取细小血管准确率较低的问题

提出了一种基于多尺度线性检测器与局部和全局增强相结合的视网膜血管分割方法。对多尺度线检测器进行研究

将其分为小尺度和大尺度两部分;利用小尺度对局部增强后的图像与大尺度对全局增强后的图像分别进行检测

得到不同尺度下的响应函数;将不同尺度下的响应函数进行融合

得到最终的视网膜血管结构。在STARE和DRIVE两个数据库上进行实验

结果表明:该算法得到的平均血管准确率分别达到96.62%和96.45%

平均真阳性率分别达到75.52%和83.07%

分割准确率高

能够得到较好的血管分割结果。

Abstract

Aiming at problem of low accuracy of extracting the small blood vessels of existing retinal images

propose a novel retinal blood vessels segmentation method which is based on combination of multi-scale line detector and both local and global enhancement. The multi-scale line detector is divided into small scales and large scales; detect the local enhanced image with the small scales and the global enhanced image with the large scales

and get the response functions with different scales

respectively; fuse the response functions under different scales to get the final structure image of retinal blood vessels. In the STARE and DRIVE databases

the average blood vessels accuracy rates reach 96. 62 % and 96. 45 %

respectively

and the average true positive rates reach75. 52 % and 83. 07 %

respectively. Segmentation accuracy is high

which can get better result of blood vessels segmentation.

关键词

Keywords

references

彩色眼底图像视网膜血管分割方法研究进展 [J]. 朱承璋,邹北骥,向遥,严权峰,梁毅雄,崔锦恺,刘晴. 计算机辅助设计与图形学学报 . 2015(11)

基于多尺度2D Gabor小波的视网膜血管自动分割 [J]. 王晓红,赵于前,廖苗,邹北骥. 自动化学报 . 2015(05)

基于柔性衬底的三维生物刺激微电极阵列研究 [J]. 周然,陈迪,黄闯,陈翔,刘景全,朱军. 传感器与微系统 . 2010(05)

An effective retinal blood vessel segmentation method using multi-scale line detection [J] . Uyen T.V. Nguyen,Alauddin Bhuiyan,Laurence A.F. Park,Kotagiri Ramamohanarao. Pattern Recognition . 2013 (3)

Vessel segmentation and width estimation in retinal images using multiscale production of matched filter responses [J] . Qin Li,Jane You,David Zhang. Expert Systems With Applications . 2011 (9)

Retinal vessel segmentation using a probabilistic tracking method [J] . Yi Yin,Mouloud Adel,Salah Bourennane. Pattern Recognition . 2011 (4)

Retinal vessel extraction by matched filter with first-order derivative of Gaussian [J] . Bob Zhang,Lin Zhang,Lei Zhang,Fakhri Karray. Computers in Biology and Medicine . 2010 (4)

Segmentation of blood vessels from red-free and fluorescein retinal images [J] . M. Elena Martinez-Perez,Alun D. Hughes,Simon A. Thom,Anil A. Bharath,Kim H. Parker. Medical Image Analysis . 2006 (1)

浏览量

172

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据