计算机科学技术学报 ›› 2019,Vol. 34 ›› Issue (6): 1307-1318.doi: 10.1007/s11390-019-1977-x

所属专题: Artificial Intelligence and Pattern Recognition Computer Graphics and Multimedia

• Computer Graphics and Multimedia • 上一篇    下一篇

基于图像与病灶融合特征的自动糖网病筛查级联框架

Cheng-Zhang Zhu1,2, Member, CCF, IEEE, Rong Hu2,3, Bei-Ji Zou2,3, Member, CCF, Rong-Chang Zhao2,3, Member, CCF, ACM, Chang-Long Chen2,3, Ya-Long Xiao1,2,*, Member, CCF   

  1. 1 College of Literature and Journalism, Central South University, Changsha 410083, China;
    2 Hunan Province Engineering Technology Research Center of Computer Vision and Intelligent Medical Treatment Changsha 410083, China;
    3 School of Computer Science and Engineering, Central South University, Changsha 410083, China
  • 收稿日期:2019-04-04 修回日期:2019-08-30 出版日期:2019-11-16 发布日期:2019-11-16
  • 通讯作者: Ya-Long Xiao E-mail:xiaoyalong2006@163.com
  • 作者简介:Cheng-Zhang Zhu received her M.E. degree in computer application from Huazhong University of Science and Technology, Wuhan, in 2006, and her Ph.D. degree in control science and engineering from School of Information Science and Engineering, Central South University, Changsha, in 2016. Currently, she is an associate professor of the College of Literature and Journalism, Central South University, Changsha. Her research interests include medical image processing, computer vision, and pattern recognition.
  • 基金资助:
    This work was supported by the National Natural Science Foundation of China under Grant Nos. 61573380 and 61702559, the Planned Science and Technology Project of Hunan Province of China under Grant No. 2017WK2074, and the Natural Science Foundation of Hunan Province of China under Grant No. 2018JJ3686.

Automatic Diabetic Retinopathy Screening via Cascaded Framework Based on Image- and Lesion-Level Features Fusion

Cheng-Zhang Zhu1,2, Member, CCF, IEEE, Rong Hu2,3, Bei-Ji Zou2,3, Member, CCF, Rong-Chang Zhao2,3, Member, CCF, ACM, Chang-Long Chen2,3, Ya-Long Xiao1,2,*, Member, CCF   

  1. 1 College of Literature and Journalism, Central South University, Changsha 410083, China;
    2 Hunan Province Engineering Technology Research Center of Computer Vision and Intelligent Medical Treatment Changsha 410083, China;
    3 School of Computer Science and Engineering, Central South University, Changsha 410083, China
  • Received:2019-04-04 Revised:2019-08-30 Online:2019-11-16 Published:2019-11-16
  • Contact: Ya-Long Xiao E-mail:xiaoyalong2006@163.com
  • About author:Cheng-Zhang Zhu received her M.E. degree in computer application from Huazhong University of Science and Technology, Wuhan, in 2006, and her Ph.D. degree in control science and engineering from School of Information Science and Engineering, Central South University, Changsha, in 2016. Currently, she is an associate professor of the College of Literature and Journalism, Central South University, Changsha. Her research interests include medical image processing, computer vision, and pattern recognition.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China under Grant Nos. 61573380 and 61702559, the Planned Science and Technology Project of Hunan Province of China under Grant No. 2017WK2074, and the Natural Science Foundation of Hunan Province of China under Grant No. 2018JJ3686.

糖尿病视网膜病变(糖网病)的早期检测对于预防失明至关重要。然而,目前医学图像数量急剧增加,临床医生手动分析眼底图像耗时长。在本文中,我们提出了一种使用彩色眼底图像的自动糖网病筛查方法。我们的方法包括三个主要组成部分:边缘引导的候选微动脉瘤检测,使用混合特征的候选区域分类,以及使用图像水平和病病灶水平的融合特征预测糖网病。我们将筛选任务划分为两个子分类任务:1)通过朴素贝叶斯分类器筛选候选微动脉瘤;2)使用支持向量机分类器预测糖网病。我们的方法可以有效地缓解不平衡的样本分布问题。我们在两个公共数据库上评估我们的方法:Lariboisière数据库和Messidor数据库。我们的方法在Lariboisière数据库上的曲线下面积为0.908,在Messidor数据库上的曲线下面积为0.832,这体现了我们的方法优于现有方法。

关键词: 糖尿病性视网膜病变, 特征融合, 微动脉瘤, 朴素贝叶斯, 支持向量机

Abstract: The early detection of diabetic retinopathy is crucial for preventing blindness. However, it is time-consuming to analyze fundus images manually, especially considering the increasing amount of medical images. In this paper, we propose an automatic diabetic retinopathy screening method using color fundus images. Our approach consists of three main components:edge-guided candidate microaneurysms detection, candidates classification using mixed features, and diabetic retinopathy prediction using fused features of image level and lesion level. We divide a screening task into two sub-classification tasks:1) verifying candidate microaneurysms by a naive Bayes classifier; 2) predicting diabetic retinopathy using a support vector machine classifier. Our approach can effectively alleviate the imbalanced class distribution problem. We evaluate our method on two public databases:Lariboisière and Messidor, resulting in an area under the curve of 0.908 on Lariboisière and 0.832 on Messidor. These scores demonstrate the advantages of our approach over the existing methods.

Key words: diabetic retinopathy, feature fusion, microaneurysm, naive Bayes, support vector machine

[1] Pires R, de Avila S, Jelinek H F, Wainer J, Valle E, Rocha A. Beyond lesion-based diabetic retinopathy:A direct approach for referral. IEEE Journal of Biomedical and Health Informatics, 2017, 21(1):193-200.
[2] Omar Z A, Hanafi M, Mashohor S, Mahfudz N F M, Muna'im M. Automatic diabetic retinopathy detection and classification system. In Proc. the 7th IEEE International Conference on System Engineering and Technology, October 2017, pp.162-166.
[3] Kar S S, Maity S P. Automatic detection of retinal lesions for screening of diabetic retinopathy. IEEE Transactions on Biomedical Engineering, 2018, 65(3):608-618.
[4] Srivastava R, Duan L, Wong D W, Liu J, Wong T Y. Detecting retinal microaneurysms and hemorrhages with robustness to the presence of blood vessels. IEEE Computer Methods and Programs in Biomedicine, 2017, 138:83-91.
[5] Seoud L, Hurtut T, Chelbi J, Cheriet F, Langlois J P. Red lesion detection using dynamic shape features for diabetic retinopathy screening. IEEE Transactions on Medical Imaging, 2016, 35(4):1116-1126.
[6] Pereira C, Veiga D, Mahdjoub J, Guessoum Z, Gonçalves L, Ferreira M, Monteiro J. Using a multi-agent system approach for microaneurysm detection in fundus images. Artificial Intelligence in Medicine, 2014, 60(3):179-188.
[7] Wan S, Liang Y, Zhang Y. Deep convolutional neural networks for diabetic retinopathy detection by image classification. Computers and Electrical Engineering, 2018, 72:274-282.
[8] Mansour R F. Evolutionary computing enriched computeraided diagnosis system for diabetic retinopathy:A survey. IEEE Reviews in Biomedical Engineering, 2017, 10:334-349.
[9] Morales S, Engan K, Naranjo V, Colomer A. Retinal disease screening through local binary patterns. IEEE Journal of Biomedical and Health Informatics, 2017, 21(1):184-192.
[10] Giancardo L, Karnowski T P, Tobin K W, Meriaudeau F, Chaum E. Validation of microaneurysm-based diabetic retinopathy screening across retina fundus datasets. In Proc. the 26th IEEE International Symposium on Computer-Based Medical Systems, June 2013, pp.125-130.
[11] Rahim S S, Palade V, Shuttleworth J, Jayne C, Omar R N R. Automatic detection of microaneurysms for diabetic retinopathy screening using fuzzy image processing. In Proc. the 16th IEEE International Conference on Engineering Applications of Neural Networks, September 2015, pp.69-79.
[12] Dashtbozorg B, Zhang J, Huang F, Romeny B M. Retinal microaneurysms detection using local convergence index features. IEEE Transactions on Image Processing, 2018, 27(7):3300-3315.
[13] Niemeijer M, van Ginneken B, Cree M J et al. Retinopathy online challenge:Automatic detection of microaneurysms in digital color fundus photographs. IEEE Transactions on Medical Imaging, 2010, 29(1):185-195.
[14] Chudzik P, Majumdar S, Calivá F, Al-Diri B, Hunter A. Microaneurysm detection using fully convolutional neural networks. Computer Methods and Programs in Biomedicine, 2018, 158:185-192.
[15] Costa P, Galdran A, Smailagic A, Campilho A. A weaklysupervised framework for interpretable diabetic retinopathy detection on retinal images. IEEE Access, 2018, 6:18747-18758.
[16] Dai L, Fang R, Li H, Hou X, Sheng B, Wu Q, Jia W. Clinical report guided retinal microaneurysm detection with multisieving deep learning. IEEE Transactions on Medical Imaging, 2018, 37(5):1149-1161.
[17] Wang Z, Yin Y, Shi J, Fang W, Li H, Wang X. Zoom-in-net:Deep mining lesions for diabetic retinopathy detection. In Proc. the 20th International Conference on Medical Image Computing and Computer Assisted Intervention, September 2017, pp.267-275.
[18] Lin Z, Guo R, Wang Y, Wu B, Chen T, Wang W, Chen D, Wu J. A framework for identifying diabetic retinopathy based on anti-noise detection and attention-based fusion. In Proc. the 21st International Conference on Medical Image Computing and Computer Assisted Intervention, September 2018, pp.74-82.
[19] Frazao L B, Theera-Umpon N, Auephanwiriyakul S. Diagnosis of diabetic retinopathy based on holistic texture and local retinal features. Information Sciences, 2019, 475:44-66.
[20] Fleming A D, Philip S, Goatman K A, Williams G J, Olson J A, Sharp P F. Automated detection of exudates for diabetic retinopathy screening. Physics in Medicine and Biology, 2007, 52(24):7385-7396.
[21] Yao L, Zeng F, Li D H, Chen Z G. Sparse support vector machine with L p penalty for feature selection. Journal of Computer Science and Technology, 2017, 32(1):68-77.
[22] Carrera E V, González A, Carrera R. Automated detection of diabetic retinopathy using SVM. In Proc. the IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing, August 2017, Article No. 58.
[23] Canny J. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6):679-698.
[24] Raman V, Then P, Sumari P. Proposed retinal abnormality detection and classification approach:Computer aided detection for diabetic retinopathy by machine learning approaches. In Proc. the 8th IEEE International Conference on Communication Software and Networks, June 2016, pp.636-641.
[25] Decenciere E, Zhang X, Cazuguel G, Lay B, Cochener B, Trone C, Gain P, Ordonez R, Massin P, Erginay A, Charton B, Klein, J. Feedback on a publicly distributed image database:The Messidor database. Image Analysis and Stereology, 2014, 33(3):231-234.
[26] Agurto C, Murray V, Barriga E, Murillo S, Pattichis M, Davis H, Russell S, Abràmoff M, Soliz P. Multiscale AM-FM methods for diabetic retinopathy lesion detection. IEEE Transactions on Medical Imaging, 2010, 29(2):502-512.
[27] Quellec G, Lamard M, Abràmoff M D, Decencière E, Lay B, Erginay A, Cochener B, Cazuguel G. A multiple-instance learning framework for diabetic retinopathy screening. Medical Image Analysis, 2012, 16(6):1228-1240.
[28] Sánchez C I, Niemeijer M, Dumitrescu A V, SuttorpSchulten M S, Abràmoff M D, Ginneken B V. Evaluation of a computer-aided diagnosis system for diabetic retinopathy screening on public data. Investigative Ophthalmology and Visual Science, 2011, 52(7):4866-4871.
[29] Cao P, Ren F, Wan C, Yang J, Zaïane O. Efficient multikernel multi-instance learning using weakly supervised and imbalanced data for diabetic retinopathy diagnosis. Computerized Medical Imaging and Graphics, 2018, 69:112-124.
[30] Zhang X J, Lu Y F, Zhang S H. Multi-task learning for food identification and analysis with deep convolutional neural networks. Journal of Computer Science and Technology, 2016, 31(3):489-500.
[31] Deng J, Dong W, Socher R, Li L, Li K, Li F F. ImageNet:A large-scale hierarchical image database. In Proc. the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 2009, pp.248-255.
[32] Abràmoff M, Reinhardt J, Russell S, Folk J, Mahajan V, Niemeijer M, Quellec G. Automated early detection of diabetic retinopathy. Ophthalmology, 2010, 117(6):1147-1154.
[1] Yi Zhong, Jian-Hua Feng, Xiao-Xin Cui, Xiao-Le Cui. 机器学习辅助的抗逻辑块加密密钥猜测攻击范式[J]. 计算机科学技术学报, 2021, 36(5): 1102-1117.
[2] Jiachen Li, Fan Zhong, Songhua Xu, Xueying Qin. 基于自适应加权局部集束结构的三维物体跟踪[J]. 计算机科学技术学报, 2021, 36(3): 555-571.
[3] Tie-Ke He, Hao Lian, Ze-Min Qin, Zhen-Yu Chen, Bin Luo. 一种用于罚金判定的主题模型[J]. , 2018, 33(4): 756-767.
[4] Lan Yao, Feng Zeng, Dong-Hui Li, Zhi-Gang Chen. 基于Lp正则化的稀疏支持向量机特征选择算法[J]. , 2017, 32(1): 68-77.
[5] Qiaohong Li, Yu-Ming Fang, Jing-Tao Xu. 一种新的用于图像质量评价的空域池化方法[J]. , 2016, 31(2): 225-234.
[6] Xiong Lv, Shu-Qiang Jiang, Luis Herranz, Shuang Wang . 基于异构特征融合的RGB-D手持物体识别[J]. , 2015, 30(2): 340-352.
[7] Mitat Poyraz, Zeynep Hilal Kilimci, and Murat Can Ganiz. 高阶平滑:一种新的用于文本分类的语义平滑方法[J]. , 2014, 29(3): 376-391.
[8] Chong-Jia Ni1 (倪崇嘉), Ai-Ying Zhang1 (张爱英), Wen-Ju Liu2 (刘文举), and Bo Xu2 (徐波). 自动韵律间断检测和特征分析[J]. , 2012, 27(6): 1184-1196.
[9] Wei Wu1,2 (武威), Hang Li3 (李航), Member, CCF, ACM, IEEE, Yun-Hua Hu4 (胡云华), Member, ACM, and Rong Jin5 (金榕), Member, IEEE. 任务特定核下基于核方法的多任务学习[J]. , 2012, 27(6): 1289-1301.
[10] Bin Zhang (张宾), Jia-Hai Yang (杨家海), Member, CCF, ACM, IEEE Jian-Ping Wu (吴建平), Fellow, IEEE, Member, CCF, ACM, and Ying-Wu Zhu (朱应武). 一个两阶段诊断网络异常的模型[J]. , 2012, (2): 313-327.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 谢立; 陈珮珮; 杨培根; 孙钟秀;. The Design and Implementation of an OA System ZGL1[J]. , 1988, 3(1): 75 -80 .
[2] 许志明;. Discrete Interpolation Surface[J]. , 1990, 5(4): 329 -332 .
[3] 张钹; 张铃;. On Memory Capacity of the Probabilistic Logic Neuron Network[J]. , 1993, 8(3): 62 -66 .
[4] 招兆铿; 戴军; 陈文丹;. Automated Theorem Proving in Temporal Logic:T-Resolution[J]. , 1994, 9(1): 53 -62 .
[5] . 颜色图像滤波的四元数扩散方法[J]. , 2006, 21(1): 126 -136 .
[6] Dinesh J. Peter, V. K. Govindan, Abraham T. Mathew. [J]. , 2010, 25(3): 623 -631 .
[7] . [J]. 计算机科学技术学报, 0, (): 1 .
[8] . [J]. 计算机科学技术学报, 0, (): 1 .
[9] Chuan Shi (石川), Member, CCF, IEEE, Zhen-Yu Yan (闫震宇), Member, IEEE. 一种基于事后决策的社团发现算法[J]. , 2011, 26(5): 792 -805 .
[10] Su-Ke Li (李素科), Zhi Guan (关志), Li-Yong Tang (唐礼勇), and Zhong Chen (陈钟), Member, . 利用消费者评论对产品特征排序[J]. , 2012, 27(3): 635 -649 .
版权所有 © 《计算机科学技术学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn
总访问量: