Retinal microaneurysms extraction by fusing relationship among features

LAI Xiao-bo; LIU Hua-shan; FANG Chun-jie

doi:10.3788/OPE.20132108.2187

您当前的位置：

首页 >

文章列表页 >

Retinal microaneurysms extraction by fusing relationship among features

更新时间：2020-08-12

- Retinal microaneurysms extraction by fusing relationship among features
- Optics and Precision Engineering Vol. 21, Issue 8, Pages: 2187-2194(2013)
- 作者机构：
  
  1. 浙江中医药大学信息技术学院,浙江杭州,310053
  2. 东华大学信息科学与技术学院上海,201620
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20132108.2187
  CLC： R774.1;TP391.41
- Received：17 January 2013，
  
  Revised：26 March 2013，
  
  Published Online：20 August 2013，
  
  Published：15 August 2013
- 稿件说明：
移动端阅览
赖小波刘华山方纯洁. 融合特征相互关系的视网膜微动脉瘤提取[J]. 光学精密工程, 2013,21(8): 2187-2194

LAI Xiao-bo LIU Hua-shan FANG Chun-jie. Retinal microaneurysms extraction by fusing relationship among features[J]. Editorial Office of Optics and Precision Engineering, 2013,21(8): 2187-2194
赖小波刘华山方纯洁. 融合特征相互关系的视网膜微动脉瘤提取[J]. 光学精密工程, 2013,21(8): 2187-2194 DOI： 10.3788/OPE.20132108.2187.

LAI Xiao-bo LIU Hua-shan FANG Chun-jie. Retinal microaneurysms extraction by fusing relationship among features[J]. Editorial Office of Optics and Precision Engineering, 2013,21(8): 2187-2194 DOI： 10.3788/OPE.20132108.2187.

摘要

为了抑制视网膜不同结构特征之间的影响，提高视网膜微动脉瘤的检测精度，提出了一种基于特征相互关系的视网膜微动脉瘤提取算法。首先，对视网膜灰度图像进行均值滤波，检测圆形边界和视盘，并构建视盘掩模。然后，对视网膜绿色分量图像自适应直方图均衡化，利用Canny方法提取边缘，移除图像圆形边界并填充封闭的小面积对象。最后，考虑不同特征之间的相互关系，消除较大面积对象后进行"逻辑与"运算移除视网膜渗出物、血管和视盘，得到视网膜微动脉瘤图像。实验结果表明：该算法能够有效提取视网膜眼底图像中的微动脉瘤，其敏感度、特异性、阳性预测值和检测精度分别达到了94.81%、96.04%、91.64 %和95.66%，基本能够满足临床应用对稳定性和精度的要求。

Abstract

To suppress the mutual affects among different structure features of retinal and improve the detection precision of retinal microaneurysms

a microaneurysm extraction algorithm by fusing relationship among features was proposed. Firstly

the mean filter was applied to a retinal grayscale image

both the circular border and optic disc were detected

and the optic disc mask was created. Then

the green component of the retinal image was equalized with an adaptive histogram and Canny method was used to extract the edges before removing the image circular border and to fill the enclosed small area objects. Finally

with consideration of the relationship among different features

larger area objects were removed and an AND logic was used to remove the retinal exudates

blood vessels as well as optic disc to obtain the retinal microaneurysm image. Experimental results indicate that the proposed method can effectively extract the microaneurysms in the retinal fundus image

and their sensitivity

specificity

positive predictive value and accuracy are 94.81%

96.04%

91.64 % and 95.66%

respectively. It can satisfy the clinical application requirements for strong stabilization and higher precision.

关键词

Keywords

references

MULLINS J.China registers success with TB-diabetes screening initiative[J]. Lancet, 2012, 380(9842): 635-636.[2]ASKEW D A, CROSSLAND L, WARE R S, et al.. Diabetic retinopathy screening and monitoring of early stage disease in general practice: design and methods [J]. Contemporary clinical trials, 2012, 33(5): 969-975.[3]SJOLIE A K, KLEIN R, PORTA M, et al.. Rtinal microaneurysm count predicts progression and regression of diabetic retinopathy[J]. Diabetic Medicine, 2011, 28(3): 345-351.[4]KANDE G B, SAVITHRI T S, SUBBAIAH P V. Automatic detection of microaneurysms and hemorrhages in digital fundus images[J]. Journal of Digital Imaging, 2010, 23(4): 430-437.[5]WALTER T, MASSIN P, ERGINAY A, et al.. Automatic detection of microaneurysms in color fundus images [J]. Medical Image Analysis, 2007, 11(6): 555-566.[6]AKRAM M U, KHALID S, KHAN S A. Identification and classification of microaneurysms for early detection of diabetic retinopathy [J]. Pattern Recognition, 2013, 46(1): 107-116.[7]JIMENEZ S, ALEMANY P, NUNEZ F J, et al.. Automated detection of microaneurysms by using region growing and fuzzy artmap neural network[J]. Archivos de la Sociedad Espanola de Oftalmologia, 2012, 87(9): 284-289.[8]SHAEIDI A. An algorithm for identification of retinal microaneurysms[J]. Journal of the Serbian Society for Computational Mechanics, 2010, 4(1): 43-51.[9]ZHANG B, KARRAY F, LI Q, et al.. Sparse representation classifier for microaneurysm detection and retinal blood vessel extraction [J]. Information Sciences, 2012, 200: 78-90.[10]ANTAL B, HAJDU A. An ensemble-based system for microaneurysm detection and diabetic retinopathy grading [J]. IEEE Transactions on Biomedical Engineering, 2012, 59(6): 1720-1726.[11]AKRAM M U, KHAN A, IQBAL K, et al.. Retinal images: optic disk localization and detection [C]. International Conference on Image Analysis and Recognition, 2010, 6112: 40-49.[12]YAZID H, AROF H, ISA H M. Exudates segmentation using inverse surface adaptive thresholding [J]. Measurement, 2012, 45(6): 1599-1608.[13]NIEMEIJER M, GINNEKEN B V, CREE M, et al.. Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs [J]. IEEE Transactions on Medical Imaging, 2010, 1(29): 185-195.[14]FLEMING A D, PHILIP S, GOATMAN K A, et al.. Automated microaneurysms detection using local contrast normalization and local vessel detection[J]. IEEE Transactions on Medical Imaging, 2006, 25(9): 1223-1232.[15]QUELLEC G, LAMARD M, JOSSELIN P M, et al.. Optimal wavelet transform for the detection of microaneurysms in retina photographs[J]. IEEE Transactions on Medical Imaging, 2008, 27(9): 1230-1241.[16]RAM K, JOSHI G D, SIVASWAMY J．A successive clutter-rejection-based approach for early detection of diabetic retinopathy [J]. IEEE Transactions on Biomedical Engineering, 2011, 58(3): 664-673.[17]QUELLEC G, RUSSELL S R, MICHAEL D, et al.. Optimal filter framework for automated, instantaneous detection of lesions in retinal images[J]. IEEE Transactions on Biomedical Engineering, 2011, 30(2): 523-533.

Views

102

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Hyperspectral images feature extraction and classification based on fractional differentiation

Lightweight deep global-local knowledge distillation network for hyperspectral image scene classification

Dense pedestrian detection algorithm in multi-branch non-anchor frame network

Application of SENet generative adversarial network in image semantics description

Underwater image enhancement based on color balance and multi-scale fusion

Related Author

LIU Jing

LI Yang

LIU Yi

LIU Yingxu

PU Chunyu

XU Diankun

YANG Yichuan

HUANG Hong

Related Institution

School of Electronic Engineering， Xidian University

School of Electronic Engineering， Xi’an University of Posts and Telecommunications

Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China， Chongqing University

Measurement and Control Technology and Instrument major， College of Optoelectronic Engineering， Chongqing University

School of Electrical Engineering， XinJiang University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰