区域特征融合的高血压视网膜病变分类方法

doi:10.3778/j.issn.1002-8331.2010-0427

摘要/Abstract

摘要： 由于高血压性视网膜病变（hypertensive retinopathy，HR）病灶特征不明显，传统分类算法难以对其进行有效分类。针对这一问题，提出一种具有整体特征和局部特征的区域特征融合HR分类方法，即在整体HR分类模型的基础上，融合局部特征动静脉交叉压迫（arteriovenous nicking，AVN）分类模型来增强HR分类效果。在AVN分类中，提出一种新型的交叉点检测算法，该算法对分类后的动静脉进行逻辑与运算以求出交叉点位置，利用感兴趣区域提取方法从HR眼底图像中提取AVN图像块。提出的融合模型在私有数据集上进行了评估，准确率、敏感性和特异性分别为93.50%、69.83%和98.33%。在单阶段分类模型中分别与已有的方法进行对比，实验结果证明所提出模型效果较好。

关键词: 区域特征融合, 高血压性视网膜病变分类, 动静脉交叉压迫分类, 交叉点检测

Abstract: Due to the lack of distinctive clinical features of hypertensive retinopathy（HR）, it is difficult to effectively classify using conventional methods. Targeting on this problem, it proposes a regional feature fusion HR classification method with global and local characteristic, that is, based on the global model, merging its local characteristic arteriovenous nicking（AVN） classification model to enhance the HR classification effect. On AVN classification, it proposes a novel method to detect arteriovenous intersections. The proposed algorithm calculates the locations of these intersections through logical computing, AVN images are then extracted in regions of interest from HR affected rear of an eye photographs. Tested the proposed merging model with private databases, the accuracy, sensitivity and specificity are 93.5%, 69.83% and 98.33%, respectively. The experimental results show that this new model works well and gets better effect compared with the existing methods in the single-stage classification model.

Key words: regional feature fusion, hypertensive retinopathy classification, arteriovenous nicking classification, cross point detection

王伟, 浦一雯. 区域特征融合的高血压视网膜病变分类方法[J]. 计算机工程与应用, 2022, 58(8): 230-236.

WANG Wei, PU Yiwen. Classification Method of Hypertensive Retinopathy Based on Regional Feature Fusion[J]. Computer Engineering and Applications, 2022, 58(8): 230-236.

参考文献

[1] NERENBERG K A，ZARNKE K B，LEUNG A A，et al.Hypertension Canada’s 2018 guidelines for diagnosis，risk assessment，prevention，and treatment of hypertension in adults and children[J].Canadian Journal of Cardiology，2018，34（5）：506-525.
[2] WONG T，MITHCHELL P.The eye in hypertension[J].The Lancet，2007，369：425-435.
[3] WONG T Y，MITHCHELL P.Hypertensive retinopathy[J].New England Journal of Medicine，2004，351（22）：2310-2317.
[4] KIRUTHIKA M，SWAPNA T R，SANTHOS K C，et al.Artery and vein classification for hypertensive retinopathy[C]//2019 3rd International Conference on Trends in Electronics and Informatics（ICOEI），2019：244-248.
[5] KHITRAN S，AKRAM M U，USMAN A，et al.Automated system for the detection of hypertensive retinopathy[C]//2014 4th International Conference on Image Processing Theory，Tools and Applications（IPTA），2014：1-6.
[6] AHMAD F，SIAL M R K，YOUSAF A，et al.Textural and intensity feature based retinal vessels classification for the identification of hypertensive retinopathy[C]//2018 IEEE 21st International Multi-Topic Conference（INMIC），2018：1-4.
[7] KUAN K，RAVAUT M，MANEK G，et al.Deep learning for lung cancer detection：tackling the kaggle data science bowl 2017 challenge[J].arXiv：1705.09435，2017.
[8] HENDERSON A D，BRUCE B B，NEWMAN N J，et al.Hypertension-related eye abnormalities and the risk of stroke[J].Reviews in Neurological Diseases，2011，8（1/2）：1-9.
[9] ROY P K，NGUYEN U T V，BHUIYAN A，et al.An effective automated system for grading severity of retinal arteriovenous nicking in colour retinal images[C]//2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society，2014：6324-6327.
[10] NGUYEN U T V，BHUIYAN A，PARK L A F，et al.An automated method for retinal arteriovenous nicking quantification from color fundus images[J].IEEE Transactions on Biomedical Engineering，2013，60（11）：3194-3203.
[11] 马志扬.基于彩色眼底图像的视网膜血管动静脉分类研究[D].北京：北京理工大学，2015.
MA Z Y.An automatic method for the artery/vein classification in retinal images[D].Beijing：Beijing Institute of Technology，2015.
[12] 王嘉良，罗健旭，刘斌，等.基于R-FCN算法的糖尿病眼底病变自动诊断[J].计算机工程与应用，2020，56（4）：109-114.
WANG J L，LUO J X，LIU B，et al.Automatic detection of diabetic retinopathy based on R-FCN algorithm[J].Computer Engineering and Applications，2020，56（4）：109-114.
[13] DAI J，LI Y，HE K，et al.R-FCN：object detection via region-based fully convolutional networks[C]//Advances in Neural Information Processing Systems，2016：379-387.
[14] 鞠维欣，赵希梅，魏宾，等.深度学习模型GoogleNet-PNN对肝硬化的识别[J].计算机工程与应用，2019，55（5）：112-117.
JU W X，ZHAO X M，WEI B，et al.Cirrhosis recognition by deep learning model GoogleNet-PNN[J].Computer Engineering and Applications，2019，55（5）：112-117.
[15] SZEGEDY C，LIU W，JIA Y，et al.Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2015：1-9.
[16] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：91-99.
[17] LI L，VERMA M，NAKASHIMA Y，et al.Joint learning of vessel segmentation and artery/vein classification with post-processing[J].arXiv：2005.13337，2020.
[18] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[19] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv：1409.
1556，2014.
[20] GRAHAM B.Kaggle diabetic retinopathy detection competition report[Z].University of Warwick，2015.
[21] 梅旭璋，江红，孙军.基于密集注意力网络的视网膜血管图像分割[J].计算机工程，2020，46（3）：267-272.
MEI X Z，JIANG H，SUN J.Retinal vessel image segmentation based on dense attention network[J].Computer Engineering，2020，46（3）：267-272.
[22] LI L，VERMA M，NAKASHIMA Y，et al.Iternet：retinal image segmentation utilizing structural redundancy in vessel networks[C]//The IEEE Winter Conference on Applications of Computer Vision，2020：3656-3665.
[23] RONNEBERGER O，FISCHER P，BROX T.U-net：convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.Cham：Springer，2015：234-241.
[24] STAAL J，ABRAMOFF M D，NIEMEIJER M，et al.Ridge-based vessel segmentation in color images of the retina[J].IEEE Transactions on Medical Imaging，2004，23（4）：501-509.
[25] HU Q，ABRAMOFF M D，GARVIN M K.Automated separation of binary overlapping trees in low-contrast color retinal images[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.Berlin，Heidelberg：Springer，2013：436-443.
[26] ORLANDO J I，BREDA J B，VAN KEER K，et al.Towards a glaucoma risk index based on simulated hemodynamics from fundus images[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham：Springer，2018：65-73.