基于Hesse矩阵和多尺度分析的视网膜动静脉血管管径测量方法

肖志涛; 崔宁; 吴骏; 耿磊; 张芳; 温佳; 童军; 刘晓婷; 杨嵩

doi:10.11999/JEIT160165

基于Hesse矩阵和多尺度分析的视网膜动静脉血管管径测量方法

doi: 10.11999/JEIT160165

肖志涛¹,
崔宁¹,
吴骏¹,
耿磊¹,
张芳¹,
温佳¹,
童军¹,
刘晓婷¹,
杨嵩¹

基金项目:

国家自然科学基金(61401439)，天津市科技支撑计划重点项目(14ZCZDGX00033)，天津市应用基础与前沿技术研究计划项目(15JCYBJC16600)，高等学校博士学科点专项科研基金(20131201110001)

计量
- 文章访问数: 1324
- HTML全文浏览量: 199
- PDF下载量: 667
- 被引次数: 0
出版历程
- 收稿日期: 2016-02-24
- 修回日期: 2016-06-22
- 刊出日期: 2016-11-19

Measurement of Retinal Diameters of Artery and Vein Based on Hesse Matrix and Multi-scale Analysis

Funds:

The National Natural Science Foundation of China (61401439), Tianjin Science and Technology Supporting Projection (14ZCZDGX00033), Tianjin Research Program of Application Foundation and Advanced Technology (15JCYBJC 16600), Specialized Research Fund for the Doctoral Program of Higher Education of China (20131201110001)

摘要

摘要: 许多全身性疾病会引起视网膜血管管径及动静脉血管比例(Arteriolar-to-Venular diameter Ratios, AVR)的变化，因此对视网膜血管管径进行准确的量化分析对病情诊断具有重要的意义。该文提出一种视网膜动静脉血管管径及AVR的自动测量方法。首先，在分割血管网络的基础上，依据Hesse矩阵检测线状结构的优势，结合多尺度分析准确定位血管方向并计算血管管径；然后利用广义回归神经网络(General Regression Neural Network, GRNN)分类器对动静脉血管骨架线上的点进行准确分类；最后计算感兴趣区域(Region Of Interest, ROI)内的AVR。对REVIEW和DRIVE数据库进行实验，验证了该文方法的有效性。
- 视网膜血管 /
- Hesse矩阵 /
- 管径测量 /
- 广义回归神经网络 /
- 视网膜血管管径与动静脉管径比
Abstract: Many systemic diseases can cause changes of the diameters of retinal vessels and Arteriolar-to-Venular diameter Ratios (AVR), so it is of great importance to make quantitative analysis of the diameter of retinal vessels accurately in the diagnosis of the disease. An automatic method measuring the diameters of the artery and the vein and the AVR is proposed. Firstly, based on the segmentation of vascular network, the diameters of retinal vessels are measured according to the advantage of Hesse matrix for detecting line-like structure, and accurate localization of vascular direction with multi-scale analysis. Secondly, a General Regression Neural Network (GRNN) classifier is used to classify the artery and the vein points. Finally, the AVR in the Region Of Interest (ROI) is calculated. The validity of the proposed method is demonstrated by testing on the DRIVE and the REVIEW database.
- Retinal vessels /
- Hesse matrix /
- Diameter measurement /
- General Regression Neural Network (GRNN) /
- Arteriolar-to-Venular diameter Ratios (AVR)

HTML全文

参考文献(17)

李春艳, 徐力. 糖尿病视网膜血管管径的研究进展[J]. 医学综述, 2015, 25(17): 3173-3176. doi: 10.3969/j.issn.1006-2084. 2015.17.038.

LI Chunyan and XU Li. Research progress of diabetic retinal vascular caliber[J], Medical Recapitulate, 2015, 25(17): 3173-3176. doi: 10.3969/j.issn.1006-2084.2015.17.038.

NIEMEIJER M, XU X, DUMITRESCU A V, et al. Automated measurement of the arteriolar-to-venular width ratio in digital color fundus photographs[J]. IEEE Transactions on Medical Imaging, 2011, 30(11): 1941-1950. doi: 10.1109/TMI.2011.2159619.

GRISAN E and RUGGERI A. A divide et impera strategy for automatic classification of retinal vessels into arteries and veins[C]. The 25th Annual International Conference of the IEEE in Medicine and Biology Society, Cancun, Mexico, 2003, 1: 890-893. doi: 10.1109/IEMBS.2003.1279908.

姚畅, 陈后金. 一种基于先验知识的视网膜血管宽度测量方法[J]. 中国科技论文在线, 2009, 4(1): 64-68. doi: 10.3969/ j.issn.2095-2783.2009.01.011.

YAO Chang and CHEN Houjin. Measurement of retinal vessel widths based on prior knowledge[J]. Sciencepaper Online, 2009, 4(1): 64-68. doi: 10.3969/j.issn.2095-2783.2009. 01.011.

LOWELL J, HUNTER A, STEEL D, et al. Quantitative measurement of retinal vessel widths from fundus images based on 2D modelling[J]. IEEE Transactions on Medical Imaging, 2004, 23(10): 1196-1204. doi: 10.1109/TMI.2004. 830524.

LUPA S CU C A, TEGOLO D, and TRUCCO E. Accurate estimation of retinal vessel width using bagged decision trees and an extended multiresolution Hermite model[J]. Medical Image Analysis, 2013, 17(8): 1164-1180. doi: 10.1016/j.media. 2013.07.006.

FRANGI A F, NIESSEN W J, VINCKEN K L, et al. Multiscale Vessel Enhancement Filtering[M]. Berlin, Germany, Medical Image Computing and Computer-Assisted Interventation, Springer, 1998: 130-137.

张新红, 张帆, 崔延斌. 基于多尺度自适应滤波的DSA血管增强[J]. 计算机工程与应用, 2015, 51(14): 179-185. doi: 10. 3778/j.issn.1002-8331.1406-0457.

ZHANG Xinhong, ZHANG Fan, and CUI Yanbin. Blood vessel enhancement algorithm for DSA images based on adaptive multi-scale filtering[J]. Computer Engineering and Applications, 2015, 51(14): 179-185. doi: 10.3778/j.issn. 1002- 8331.1406-0457.

CHEN Y, BARCELOS C A Z, and MAIR B A. Smoothing and edge detection by time-varying coupled nonlinear diffusion equations[J]. Computer Vision and Image Understanding, 2001, 82(2): 85-100. doi: 10.1006/cviu. 2001.0903.

严颂华, 吴世才, 吴雄斌. 基于神经网络的高频地波雷达目标到达角估计[J]. 电子与信息学报, 2008, 30(2): 339-342.

YAN Songhua, WU Shicai, and WU Xiongbin. DOA estimation based on neural network for HFGWR[J]. Journal of Electronics Information Technology, 2008, 30(2): 339-342.

LI X, XIAO Z, and ZHANG F, et al. Fundus optic disc localization method based on phase congruency[J]. International Journal of Digital Content Technology and Its Applications, 2013, 7(4): 726-733.

ZHANG B, ZHANG L, ZHANG L, et al. Retinal vessel extraction by matched filter with first-order derivative of Gaussian[J]. Computers in Biology and Medicine, 2010, 40(4): 438-445. doi: 10.1016/j.compbiomed.2010.02.008.

ZHAO Y Q, WANG X H, WANG X F, et al. Retinal vessels segmentation based on level set and region growing[J]. Pattern Recognition, 2014, 47(7): 2437-2446. doi: 10.1016/j. patcog.2014.01.006.

施引文献

资源附件(0)

访问统计