Abstract
Deep convolution neural networks (CNNs) have demonstrated their capabilities in modern-day medical image classification and analysis. The vital edge of deep CNN over other techniques is their ability to train without expert knowledge. Time bound detection is very beneficial for the early cure of disease. In this paper, a deep CNN architecture is proposed to classify nondiabetic retinopathy and diabetic retinopathy fundus eye images. Kaggle 2015 diabetic retinopathy competition dataset and messier experiment dataset are used in this study. The proposed deep CNN algorithm produces significant results with 93% area under the curve (AUC) for the Kaggle dataset and 91% AUC for the Messidor dataset. The sensitivity and specificity for the Kaggle dataset are 90.22% and 85.13%, respectively; the corresponding values of the Messidor dataset are 91.07% and 80.23%, respectively. The results outperformed many existing studies. The present architecture is a promising tool for diabetic retinopathy image classification.
Acknowledgement
We would like to thank the kaggle and messidor dataset provider for providing the open access to the datasets.
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
Research funding: None declared.
Employment or leadership: None declared.
Competing interests: The funding organization(s) played no role in the study design; in the collection, analysis, and interpretation of data; in the writing of the report; or in the decision to submit the report for publication.
References
[1] Kaveeshwar SA, Cornwall J. The current state of diabetes mellitus in India. Australas Med J 2014;7:45–8.10.4066/AMJ.2014.1979Search in Google Scholar PubMed
[2] Wilkinson CP, Ferris FL 3rd, Klein RE, Lee PP, Agardh CD, Davis M, et al. Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales. Ophthalmology 2003;110:1677–82.10.1016/S0161-6420(03)00475-5Search in Google Scholar PubMed
[3] Diabetic-retinopathy. 2015. Available at: http://wjscottmd.com/wp-content/uploads/2015/11/Diabetic-Retinopathy.jpg.Search in Google Scholar
[4] Abràmoff MD, Garvin MK, Sonka M. Retinal imaging and image analysis. IEEE Rev Biomed Eng 2010;3:169–208.10.1109/RBME.2010.2084567Search in Google Scholar PubMed
[5] Patz A, Fine S, Finkelstein D, Prout T, Aiello L. Photocoagulation treatment of proliferative diabetic retinopathy: the second report of diabetic retinopathy study findings. Ophthalmology 1978;85:82–106.10.1016/S0161-6420(78)35693-1Search in Google Scholar PubMed
[6] Early photocoagulation for diabetic retinopathy: ETDRS report number 9. Ophthalmology 1991;98:766–85.10.1016/S0161-6420(13)38011-7Search in Google Scholar PubMed
[7] Quellec G, Charriere K, Boundi Y, Cochener B, Lamard M. Deep image mining for diabetic retinopathy screening. Med Image Anal 2017;39:178–93.10.1016/j.media.2017.04.012Search in Google Scholar PubMed
[8] Tufail A, Rudisill C, Egan C, Kapetanakis VV, Salas-Vega S, Owen CG, et al. Automated diabetic retinopathy image assessment software: diagnostic accuracy and cost-effectiveness compared with human graders. Ophthalmology 2017;124:343–51.10.1016/j.ophtha.2016.11.014Search in Google Scholar PubMed
[9] Prentasic P, Loncaric S. Detection of exudates in fundus photographs using deep neural networks and anatomical landmark detection fusion. Comput Methods Programs Biomed 2017;137:281–92.10.1016/j.cmpb.2016.09.018Search in Google Scholar PubMed
[10] Arenas-Cavalli JT, Rios SA, Pola M, Donoso R. A web-based platform for automated diabetic retinopathy screening. Procedia Comput Sci 2015;60:557–63.10.1016/j.procs.2015.08.179Search in Google Scholar
[11] Pratt H, Coenen F, Broadbent DM, Harding SP, Zheng Y. Convolutional neural networks for diabetic retinopathy. Procedia Comput Sci 2016;90:200–5.10.1016/j.procs.2016.07.014Search in Google Scholar
[12] Pang H, Luo C, Wang C. Improvement of the application of diabetic retinopathy detection model. Wireless Pers Commun 2018. DOI: 10.1007/s11277-018-5465-3.Search in Google Scholar
[13] Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. J Am Med Assoc 2016;316:2402–10.10.1001/jama.2016.17216Search in Google Scholar PubMed
[14] Paing MP, Choomchuay S, Yodprom MD. Detection of lesions and classification of diabetic retinopathy using fundus images. 9th Biomedical Engineering International Conference (BMEiCON), Laung Prabang; 2016.10.1109/BMEiCON.2016.7859642Search in Google Scholar
[15] Andonová M, Pavlovicˇová J, Kajan S, Oravec M, Kurilová V. Diabetic retinopathy screening based on CNN. 2017 International Symposium ELMAR, Zadar, Croatia; 2017.Search in Google Scholar
[16] Costa P, Campilho A. Convolutional bag of words for diabetic retinopathy detection from eye fundus images. IPSJ T Comput Vis Appl 2017;9:10.10.1186/s41074-017-0023-6Search in Google Scholar
[17] Kaggle diabetic retinopathy detection competition. Available at: https://www.kaggle.com/c/diabetic-retinopathy-detection. Accessed: 30 Jun 2017.Search in Google Scholar
[18] Decenciere E, Zhang X, Cazuguel G, Lay B, Cochener B, Trone C, et al. Feedback on a publicly distributed image database: the Messidor database. Image Anal Stereol 2014;33:231–4.10.5566/ias.1155Search in Google Scholar
©2018 Walter de Gruyter GmbH, Berlin/Boston
