Abstract
Purpose
Diabetic retinopathy is one of the main complications of diabetes mellitus. To assess the progression of the disease, retinal images are commonly obtained through fundus examination. However, those images may present problems such as low contrast, inadequate lighting, and unsatisfactory noise level, among other aspects that can compromise medical analysis and intervention. In this context, this work aims to apply the neural network VGG16 to classify the diabetic retinopathy in 5 categories and with an additional class (named class 5) to report low quality of digital retinal images publicly available in the DDR, EyePACS/Kaggle, and IDRiD databases.
Methods
The proposed methodology includes pre-processing of retinal images, consisting of size adequacy, data cleaning (the removal of low-quality images from other classes and inclusion of them in class 5), data augmentation and class balancing during the training phase, and hyperparameter adjustment and image classification using the VGG16 neural network.
Results
Among the tests carried out on the three databases, this proposal has been presented the best performance for DDR database regarding accuracy, precision, sensitivity, specificity, and F1-score.
Conclusion
This work contributes towards the improvement of results achieved in the state-of-the-art for DDR and IDRiD databases without DME, and the inclusion of performance metrics sensitivity, specificity, precision, and F1-score.
Similar content being viewed by others
References
Abbas Q, Fondon I, Sarmiento A, Jiménez S, Alemany P. Automatic recognition of severity level for diagnosis of diabetic retinopathy using deep visual features. Med Biol Eng Compu. 2017;55(11):1959–74. https://doi.org/10.1007/s11517-017-1638-6.
Abràmoff MD, Folk JC, Han DP, Walker JD, Williams DF, Russell SR, Massin P, Cochener B, Gain P, Tang Li, Lamard M, Moga DC, Quellec G, Niemeijer M. Automated analysis of retinal images for detection of referable diabetic retinopathy. JAMA Ophthalmol. 2013; 131(3):351–7. https://doi.org/10.1001/jamaophthalmol.2013.1743
Abràmoff MD, Garvin MK, Sonka M. Retinal imaging and image analysis. IEEE Rev Biomed Eng. 2010; 3:169–208; https://doi.org/10.1109/RBME.2010.2084567.
Al-Antary MT, Arafa Y. Multi-scale attention network for diabetic retinopathy classification. IEEE Access. 2021;9:54190–200. https://doi.org/10.1109/ACCESS.2021.3070685.
Alghadyan AA. Diabetic retinopathy — an update. Saudi J Ophthalmol. 2011;25(2):99–111. https://doi.org/10.1016/j.sjopt.2011.01.009.
Chollet F. Deep learning with Python. 1st ed. USA: Manning Publications Co.; 2017.
Cuadros J, Bresnick G. Eyepacs: An adaptable telemedicine system for diabetic retinopathy screening. J Diabetes Sci Technol. 2009;3(3):509–16. https://doi.org/10.1177/193229680900300315.
Decencière E, Zhang X, Cazuguel G, Lay B, Cochener B, Trone C, Gain P, Ordóñez-Varela J, Massin P, Erginay A, Charton B, Klein JC. Feedback on a publicly distributed image database: the Messidor database. Image Analys Stereol. 2014;2014(33):231–4. https://doi.org/10.5566/ias.1155.
ETDRS (Early Treatment Diabetic Retinopathy Study Research Group). Fundus photographic risk factors for progression of diabetic retinopathy: Etdrs report number 12. Ophthalmology. 1991; 98(5, Supplement): 823–33; https://doi.org/10.1016/S0161-6420(13)38014-2.
Gangwar AK, Ravi V. Diabetic retinopathy detection using transfer learning and deep learning. In: Bhateja V, Peng SL, Satapathy SC, Zhang YD, editors. Evolution in Computational Intelligence. Frontiers in Intelligent Computing: Theory and Applications (FICTA 2020); Singapore; 2020. pp. 679–89. https://doi.org/10.1007/978-981-15-5788-0_64.
Gargeya R, Leng T. Automated identification of diabetic retinopathy using deep learning. Ophthalmology. 2017;124(7):962–9. https://doi.org/10.1016/j.ophtha.2017.02.008.
Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, Venugopalan S, Widner K, Madams T, Cuadros J, Kim R, Raman R, Nelson PC, Mega J, Webster D. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016; 316(22):2402–10; http://jamanetwork.com/journals/jama/fullarticle/2588763.
ICO (International Council of Ophthalmology). 2017. In: ICO guidelines for diabetic eye care. http://www.icoph.org/downloads/ICOGuidelinesforDiabeticEyeCare.pdf. Accessed 19 Feb 2020.
Kar SS, Maity SP. Automatic detection of retinal lesions for screening of diabetic retinopathy. IEEE Trans Biomed Eng. 2018;65(3):608–18. https://doi.org/10.1109/TBME.2017.2707578.
Lakshminarayanan V, Kheradfallah H, Sarkar A, Jothi BJ. Automated detection and diagnosis of diabetic retinopathy: a comprehensive survey. J Imaging. 2021;7(9):165. https://doi.org/10.3390/jimaging7090165.
Leeza M, Farooq H. Detection of severity level of diabetic retinopathy using bag of features model. IET Comput Vision. 2019;13(5):523–30. https://doi.org/10.1049/iet-cvi.2018.5263.
Li T, Gao Y, Wang K, Guo S, Liu H, Kang H. Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening. Inf Sci. 2019;501:511–22; https://doi.org/10.1016/j.ins.2019.06.011.
Mookiah MRK, Acharya UR, Chua CK, Lim CM, Ng EYK, Laude A. Computer-aided diagnosis of diabetic retinopathy: a review. Comput Biol Med. 2013;43(12):2136–55. https://doi.org/10.1016/j.compbiomed.2013.10.007.
Nage P, Shitole S. A survey on automatic diabetic retinopathy screening. SN Computer Science. 2021;2:439. https://doi.org/10.1007/s42979-021-00833-z.
Navarro JC, Peña CB, Escorcia-Gutierrez J. Una revisión de los métodos de deep learning aplicados a la detección automatizada de la retinopatía diabética. Revista Sextante. 2020;23:12–27.
Porwal P, Pachade S, Kokare M, Deshmukh G, Son J, Bae W, Liu L, Wang J, Liu X, Gao L, Wu T, Xiao J, Wang F, Yin B, Wang Y, Danala G, He L, Choi LH, Lee YC, Jung SH, Li Z, Sui X, Wu J, Li X, Zhou T, Toth J, Baran A, Kori A, Chennamsetty SS, Safwan M, Alex V, Lyu X, Cheng L, Chu Q, Li P, Ji X, Zhang S, Shen Y, Dai L, Saha O, Sathish T, Melo T, Araújo T, Harangi B, Sheng B, Fang R, Sheet D, Hajdu A, Zheng Y, Mendonça AM, Zhang S, Campilho A, Zheng B, Shen D, Giancardo L, Quellec G, Mériaudeau F. Idrid: Diabetic retinopathy — segmentation and grading challenge. Med Image Anal. 2020; 59:10156. https://doi.org/10.1016/j.media.2019.101561.
Pratt H, Coenen F, Broadbent DM, Harding SP, Zheng Y. Convolutional neural networks for diabetic retinopathy. Procedia Computer Science. In: 20th Conference on Medical Image Understanding and Analysis (MIUA); 2016 July 6–8; Loughborough, UK. 2016;90:200–5; https://doi.org/10.1016/j.procs.2016.07.014.
Quellec G, Charrière K, Boudi Y, Cochener B, Lamard M. Deep image mining for diabetic retinopathy screening. Medical Image Analysis. 2017;39:178–93; https://doi.org/10.1016/j.media.2017.04.012.
Riaz H, Park J, Choi H, Kim H, Kim J. Deep and densely connected networks for classification of diabetic retinopathy. Diagnostics. 2020;10(1):24. https://doi.org/10.3390/diagnostics10010024.
Rocha DA, Barbosa ABL, Guimarães DS, Gregório LM, Gomes LHN, Amorim LS, Peixoto ZMA. An unsupervised approach to improve contrast and segmentation of blood vessels in retinal images using CLAHE, 2D Gabor wavelet, and morphological operations. Res Biomed Eng. 2020;36:67–75; https://doi.org/10.1007/s42600-019-00032-z.
Salamat N, Missen MMS, Rashid A. Diabetic retinopathy techniques in retinal images: a review. Artif Intell Med. 2019;97:168–88. https://doi.org/10.1016/j.artmed.2018.10.009.
Shanthi T, Sabeenian RS. Modified AlexNet architecture for classification of diabetic retinopathy images. Comput Electric Eng. 2019;76:56–64; https://doi.org/10.1016/j.compeleceng.2019.03.004.
Sikder N, Masud M, Bairagi AK, Arif ASM, Nahid A-A, Alhumyani HA. Severity classification of diabetic retinopathy using an ensemble learning algorithm through analyzing retinal images. Symmetry. 2021;13(4):670. https://doi.org/10.3390/sym13040670.
Silva Amorim L, Ferreira FMF, Guimarães JR, Peixoto ZMA. Automatic segmentation of blood vessels in retinal images using 2D Gabor wavelet and sub-image thresholding resulting from image partition. Res Biomed Eng. 2019;35:241–9; https://doi.org/10.1007/s42600-019-00028-9.
Simonyan K and Zisserman A. Very deep convolutional networks for large-scale image recognition; 2014; arXiv preprint arXiv:1409.1556.
Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks. Inf Process Manage. 2009;45(4):427–37. https://doi.org/10.1016/j.ipm.2009.03.002.
Wan S, Liang Y, Zhang Y. Deep convolutional neural networks for diabetic retinopathy detection by image classification. Comput Electric Eng. 2018;72:274–82 https://doi.org/10.1016/j.compeleceng.2018.07.042.
Wang R, Chen B, Meng D, Wang L. Weakly supervised lesion detection from fundus images. IEEE Trans Med Imaging. 2019;38(6):1501–12. https://doi.org/10.1109/TMI.2018.2885376.
WHO (World Health Organization). In: Global report on diabetes. World Health Organization. 2014. https://apps.who.int/iris/handle/10665/204871. Accessed 22 Feb 2020.
Zhang W, Zhong J, Yang S, Gao Z, Hu J, Chen Y, Yi Z. Automated identification and grading system of diabetic retinopathy using deep neural networks. Knowledge-Based Syst. 2019;175:12–25; https://doi.org/10.1016/j.knosys.2019.03.016.
Funding
This study was financed in part by CAPES—Coordenação de Aperfeiçoamento de Pessoal de Nível Superior — Brasil — Finance Code 001.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
da Rocha, D.A., Ferreira, F.M.F. & Peixoto, Z.M.A. Diabetic retinopathy classification using VGG16 neural network. Res. Biomed. Eng. 38, 761–772 (2022). https://doi.org/10.1007/s42600-022-00200-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42600-022-00200-8