[1]杨得国,马兰萍,聂 毓.基于PCANet和SVM的病变眼底图像检测算法[J].江西师范大学学报(自然科学版),2022,(04):372-378.[doi:10.16357/j.cnki.issn1000-5862.2022.04.07]
　YANG Deguo,MA Lanping,NIE Yu.The Detection Algorithm of Pathological Fundus Image Based on PCANet and SVM[J].Journal of Jiangxi Normal University:Natural Science Edition,2022,(04):372-378.[doi:10.16357/j.cnki.issn1000-5862.2022.04.07]
点击复制

基于PCANet和SVM的病变眼底图像检测算法()
分享到：

《江西师范大学学报》（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2022年04期
页码:
372-378
栏目:
信息科学与技术
出版日期:
2022-07-25

文章信息/Info

Title:
The Detection Algorithm of Pathological Fundus Image Based on PCANet and SVM
文章编号:
1000-5862(2022)04-0372-07
作者:
杨得国; 马兰萍; 聂 毓
西北师范大学计算机科学与工程学院,甘肃 兰州 730070
Author(s):
YANG Deguo; MA Lanping; NIE Yu
College of Computer Science and Engineering,Northwest Normal University,Lanzhou Gansu 730070,China
关键词:
图像增强;  图像检测;  无监督;  神经网络
Keywords:
image enhancement;  image detection;  unsupervised;  the neural network
分类号:
TP 391.41
DOI:
10.16357/j.cnki.issn1000-5862.2022.04.07
文献标志码:
A
摘要:
针对眼底图像训练数据集少的问题,该文采用了无监督的主成分分析网络(principal components analysis networks,PCANet)和有监督的支持向量机(support vector mochine,SVM)相结合的算法,通过对彩色眼底图像视网膜渗出物特征的提取,检测出含渗出的糖尿病性视网膜病变眼底图像和正常眼底图像.在对眼底图像进行渗出物特征提取之前,为了减少对渗出物特征提取的干扰,首先对眼底图像进行图像预处理,包括去除冗余背景、通道分离、直方图均衡化、血管去除和视盘去除.无监督的PCANet不需要进行标签训练,与SVM结合,既节约了训练时间,又在训练数据集较小的情况下实现眼底图像的准确分类.实验结果表明:PCANet和SVM相结合的模型在准确性、灵敏度和特异值3个方面与相关方法比较都具有一定的提升.
Abstract:
To address the problem of small training data set of fundus images,the combination of unsupervised principal components analysis networks(PCANet)and supervised support vector mochine(SVM)algorithm is used to detect diabetic retinopathy fundus images containing exudates and normal fundus images by extracting retinal exudate features from color fundus images.Before performing exudate feature extraction on fundus images,image preprocessing is first performed on fundus images to reduce interference with exudate feature extraction,including redundant background removal,channel separation,histogram equalization,vessel removal,and optic disc removal.The unsupervised PCANet does not require labels for training and is combined with SVM to both save training time and achieve accurate classification of fundus images with a small training data set.The experimental results show that the PCANet+SVM model has a certain improvement in accuracy,sensitivity and specificity value compared with related methods.

参考文献/References:

[1] 张悦.基于卷积神经网络的双源遥感数据语义分割的方法研究[D].哈尔滨:哈尔滨工业大学,2018.
[2] 范丽琪,宣杰,邓小丽.92例糖尿病性视网膜病变患者术前眼底造影结果评估及护理[J].影像研究与医学应用,2019,3(16):5-6.
[3] 张皓,吴建鑫.基于深度特征的无监督图像检索研究综述[J].计算机研究与发展,2018,55(9):1829-1842.
[4] 游齐靖.机器学习在染色体和眼底图像分析中的应用[D].南京:南京航空航天大学,2020.
[5] 张翔翔.相关噪声下基于深度学习的卷积码译码器的研究[D].北京:北京邮电大学,2019.
[6] JAAFAR H F,NANDI A K,AL-NUAIMY W.Detection of exudates in retinal images using a pure splitting technique[EB/OL].[2021-10-17].https://ieeexplore.ieee.org/document/5626014/.
[7] IMANI E,POURREZA H R.A novel method for retinal exudate segmentation using signal separation algorithm[J].Computer Methods and Programs in Biomedicine,2016,133:195-205.
[8] FRAZ M M,JAHANGIR W,ZAHID S,et al.Multiscale segmentation of exudates in retinal images using contextual cues and ensemble classification[J].Biomedical Signal Processing and Control,2017,35:50-62.
[9] WELFER D,SCHARCANSKI J,MARINHO D R.A coarse-to-fine strategy for automatically detecting exudates in color eye fundus images[J].Computerized Medical Imaging and Graphics,2010,34(3):228-235.
[10] HARANGI B,HAJDU A.Automatic exudate detection by fusing multiple active contours and regionwise classification[J].Computers in Biology and Medicine,2014,54:156-171.
[11] MO Juan,ZHANG Lei,FENG Yangqin.Exudate-based diabetic macular edema recognition in retinal images using cascaded deep residual networks[J].Neurocomputing,2018,290:161-171.
[12] DAS V,PUHAN N B.Tsallis entropy and sparse reconstructive dictionary learning for exudate detection in diabetic retinopathy[J].Journal of Medical Imaging,2017,4(2):024002.
[13] LIU Qing,ZOU Beiji,CHEN Jie,et al.A location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images[J].Computerized Medical Imaging and Graphics,2017,55(S1):78-86.

备注/Memo

备注/Memo:
收稿日期:2022-02-19
基金项目:国家自然科学基金(61165002)资助项目.
作者简介:杨得国(1971—),男,甘肃民勤人,教授,主要从事网络与多媒体的研究.E-mail:gansuskl@163.com
更新日期/Last Update: 2022-07-25