Journal of Computer Science and Technology ›› 2019, Vol. 34 ›› Issue (6): 1307-1318.doi: 10.1007/s11390-019-1977-x

Special Issue: Artificial Intelligence and Pattern Recognition; Computer Graphics and Multimedia

• Computer Graphics and Multimedia • Previous Articles     Next Articles

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
  • 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.

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. Machine Learning Aided Key-Guessing Attack Paradigm Against Logic Block Encryption [J]. Journal of Computer Science and Technology, 2021, 36(5): 1102-1117.
[2] Jiachen Li, Fan Zhong, Songhua Xu, Xueying Qin. 3D Object Tracking with Adaptively Weighted Local Bundles [J]. Journal of Computer Science and Technology, 2021, 36(3): 555-571.
[3] Tie-Ke He, Hao Lian, Ze-Min Qin, Zhen-Yu Chen, Bin Luo. PTM: A Topic Model for the Inferring of the Penalty [J]. , 2018, 33(4): 756-767.
[4] Lan Yao, Feng Zeng, Dong-Hui Li, Zhi-Gang Chen. Sparse Support Vector Machine with Lp Penalty for Feature Selection [J]. , 2017, 32(1): 68-77.
[5] Mitat Poyraz, Zeynep Hilal Kilimci, and Murat Can Ganiz. Higher-Order Smoothing:A Novel Semantic Smoothing Method for Text Classification [J]. , 2014, 29(3): 376-391.
[6] Wei Wu(武威), Hang Li(李航), Member, CCF, ACM, IEEE, Yun-Hua Hu(胡云华), Member, ACM, and Rong Jin(金榕), Member, IEEE. A Kernel Approach to Multi-Task Learning with Task-Specific Kernels [J]. , 2012, 27(6): 1289-1301.
[7] 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). Diagnosing Traffic Anomalies Using a Two-Phase Model [J]. , 2012, (2): 313-327.
[8] Seyed Abolghasem Mirroshandel, Gholamreza Ghassem-Sani, and Mahdy Khayyamian. Using Syntactic-Based Kernels for Classifying Temporal Relations [J]. , 2011, 26(1): 68-80.
[9] Bin Gu(顾 彬), Jian-Dong Wang(王建东), and Tao Li(李 涛). Ordinal-Class Core Vector Machine [J]. , 2010, 25(4): 699-708.
[10] Lei Jia(贾 磊), Shi-Zhong Liao(廖士中), Member, CCF, and Li-Zhong Ding(丁立中). Learning with Uncertain Kernel Matrix Set [J]. , 2010, 25(4): 709-727.
[11] ZHANG Ling (张铃) and ZHANG Bo (张钹). Relationship Between Support Vector Set and Kernel Functions in SVM [J]. , 2002, 17(5): 0-0.
Full text



[1] Xie Li; Chen Peipei; Yang Peigen; Sun Zhongxiu;. The Design and Implementation of an OA System ZGL1[J]. , 1988, 3(1): 75 -80 .
[2] Xu Zhiming;. Discrete Interpolation Surface[J]. , 1990, 5(4): 329 -332 .
[3] Zhang Bo; Zhang Ling;. On Memory Capacity of the Probabilistic Logic Neuron Network[J]. , 1993, 8(3): 62 -66 .
[4] Zhao Zhaokeng; Dai Jun; Chen Wendan;. Automated Theorem Proving in Temporal Logic:T-Resolution[J]. , 1994, 9(1): 53 -62 .
[5] Zhong-Xuan Liu, Shi-Guo Lian, and Zhen Ren. Quaternion Diffusion for Color Image Filtering[J]. , 2006, 21(1): 126 -136 .
[6] Dinesh J. Peter, V. K. Govindan, and Abraham T. Mathew. Nonlocal-Means Image Denoising Technique Using Robust M-Estimator[J]. , 2010, 25(3): 623 -631 .
[7] Xia-Bing Zhou, Zhong-Qing Wang, Xing-Wei Liang, Min Zhang, and Guo-Dong Zhou. Neural Emotion Detection via Personal Attributes[J]. Journal of Computer Science and Technology, 0, (): 1 .
[8] Yusuf Fatihu Hamza, Hong-Wei Lin. Conjugate-Gradient Progressive-Iterative Approximation for Loop and Catmull-Clark Subdivision Surface Interpolation[J]. Journal of Computer Science and Technology, 0, (): 1 .
[9] Chuan Shi (石川), Member, CCF, IEEE, Zhen-Yu Yan (闫震宇), Member, IEEE, Xin Pan (潘欣), Ya-Nan Cai (蔡亚男), and Bin Wu (吴斌), Member, CCF. A Posteriori Approach for Community Detection[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, CCF, IEEE. Exploiting Consumer Reviews for Product Feature Ranking[J]. , 2012, 27(3): 635 -649 .

ISSN 1000-9000(Print)

CN 11-2296/TP

Editorial Board
Author Guidelines
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
  Copyright ©2015 JCST, All Rights Reserved