Abstract
Purpose
Diabetic macular edema (DME) is a kind of hard exudates lesion seen near the diabetic macular region of the retina. DME causes visual loss and may result in complete blindness; early identification and treatment may be able to cure this. Identification of DME at an early stage is a challenging and error-prone task. To address this issue, the article presents a methodology that uses the notion of transfer learning to identify cases of DME from retinal fundus images.
Methods
A pre-trained DenseNet121 is used in this technique to extract the useful set of feature vectors from the fundus images, which are then fed into a few additional fully connected layers and then into the classification layer to classify DME instances. A total of 577 fundus training images from 3 DME classes were used to train the proposed model, and 103 fundus testing images were used to verify the proposed model for classifying them into one of the three DME cases.
Results
The suggested model is trained and tested on the Indian Diabetic Retinopathy Image Dataset (IDRiD). With the test images, the results demonstrate that the proposed model outperformed the state-of-the-art models presented in “Diabetic Retinopathy – Segmentation and Grading Challenge” held at ISBI-2018 with an accuracy of 86.4%.
Conclusion
The proposed model diagnoses DME at an early stage for timely treatment and helps to reduce the workload of ophthalmologists.
Similar content being viewed by others
Data availability
The dataset (Indian Diabetic Retinopathy Image Dataset (IDRiD)) is publicly available at https://www.kaggle.com/aaryapatel98/indian-diabetic-retinopathy-image-dataset.
Code availability
The developed code is available at https://github.com/amitbsbkumar/amitbsbkumar.
References
Acharya UR, Mookiah MR, Koh JE, Tan JH, Bhandary SV, Rao AK, Hagiwara Y, Chua CK, Laude A. Automated diabetic macular edema (DME) grading system using DWT, DCT features and maculopathy index. Comput Biol Med. 2017;1(84):59–68.
Akram MU, Tariq A, Khan SA, Javed MY. Automated detection of exudates and macula for grading of diabetic macular edema. Comput Methods Programs Biomed. 2014;114(2):141–52.
Al-Bander B, Al-Nuaimy W, Al-Taee MA, Williams BM, Zheng Y. (n.d) Diabetic macular edema grading based on deep neural networks.
Bandello F, Lanzetta P, Loewenstein A, Massin P, Menchini F, Veritti D. Diabetic macular edema. Dev Ophthalmol. 2017;28(58):102–38.
Budai A, Odstrcilik J, Kolar R, Hornegger J, Jan J, Kubena T, Michelson G. A public database for the evaluation of fundus image segmentation algorithms. Invest Ophthalmol Visual Sci. 2011;52(14):1345.
Carin L, Pencina MJ. On deep learning for medical image analysis. JAMA. 2018;320(11):1192–3.
Ciulla TA, Amador AG, Zinman B. Diabetic retinopathy and diabetic macular edema: pathophysiology, screening, and novel therapies. Diabetes Care. 2003;26(9):2653–64.
Decencière E, Zhang X, Cazuguel G, Lay B, Cochener B, Trone C, Gain P, Ordonez R, Massin P, Erginay A, Charton B. Feedback on a publicly distributed image database: the Messidor database. Image Anal Stereol. 2014;33(3):231–4.
Dutta A, Agarwal P, Mittal A, Khandelwal S. Detecting grades of diabetic retinopathy by extraction of retinal lesions using digital fundus images. Res Biomed Eng. 2021;9:1–6.
Fong DS, Aiello L, Gardner TW, King GL, Blankenship G, Cavallerano JD, Ferris FL, Klein R. Retinopathy in diabetes. Diabetes Care. 2004;27(suppl 1):s84–7.
Giancardo L, Meriaudeau F, Karnowski TP, Tobin KW, Grisan E, Favaro P, Ruggeri A, Chaum E. Textureless macula swelling detection with multiple retinal fundus images. IEEE Trans Biomed Eng. 2010;58(3):795–9.
Giancardo L, Meriaudeau F, Karnowski TP, Li Y, Tobin KW, Chaum E Automatic retina exudates segmentation without a manually labelled training set. In 2011 IEEE Int Symp Biomed Imaging From Nano to Macro 2011 (1396–1400) IEEE
Giancardo L. The Hamilton Eye Institute Macular Edema dataset (HEI-MED). GitHub https://github. com/lgiancaUTH/HEI-MED. 2012
Goldbaum M. The STARE Project, Structured Analysis of the Retina Database. Zuletzt abgerufen am 27
He J, Shen L, Ai X, et al. Diabetic retinopathy grade and macular edema risk classification using convolutional neural networks. In: 2019 IEEE Int Conference on Power, Intelligent Computing Syst (ICPICS) IEEE 2019 463-466
He K, Zhang X, Ren S, Sun J Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition 2016:770–778
Hee MR, Puliafito CA, Wong C, Duker JS, Reichel E, Rutledge B, Schuman JS, Swanson EA, Fujimoto JG. Quantitative assessment of macular edema with optical coherence tomography. Arch Ophthalmol. 1995;113(8):1019–29.
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition 2017:4700–4708
Iandola F, Moskewicz M, Karayev S, Girshick R, Darrell T, Keutzer K. Densenet: implementing efficient convnet descriptor pyramids. arXiv preprint http://arxiv.org/abs/1404.1869
Kandhasamy JP, Balamurali S, Kadry S, Ramasamy LK. Diagnosis of diabetic retinopathy using multi level set segmentation algorithm with feature extraction using SVM with selective features. Multimedia Tools App. 2020;79(15):10581–96.
Kauppi T, Kalesnykiene V, Kamarainen JK, Lensu L, Sorri I, Pietila J, Kalviainen H, Uusitalo H. DIARETDB1-standard diabetic retino-pathy database. IMAGERET-Optimal Detect Decis Diagnosis Diabet Retin 2007:15
Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25:1097–105.
Math L, Fatima R. Adaptive machine learning classification for diabetic retinopathy. Multimedia Tools App. 2021;80(4):5173–86.
de Moura J, Novo J, Ortega M. Deep feature analysis in a transfer learning-based approach for the automatic identification of diabetic macular edema. In2019 Int Joint Conference Neural Net (IJCNN) 2019:1–8 IEEE
Murugan R, Roy P, Singh U. An abnormality detection of retinal fundus images by deep convolutional neural networks. Multimedia Tools App. 2020;79(33):24949–67.
Nair LR. RetoNet: a deep learning architecture for automated retinal ailment detection. Multimedia Tools App. 2020;79(21):15319–28.
Niemeijer M, Staal J, van Ginneken B, Loog M, Abramoff MD. Comparative study of retinal vessel segmentation methods on a new publicly available database. In Medical imaging 2004: image processing. Int Soc Optics Photonics. 2004;5370:648–56.
Patil SB, Patil BP. Automated macula proximity diagnosis for early finding of diabetic macular edema. Res Biomed Eng. 2020;36:249–65.
Porwal P, Pachade S, Kamble R, Kokare M, Deshmukh G, Sahasrabuddhe V, Meriaudeau F. Indian Diabetic Retinopathy Image Dataset (IDRiD): a database for diabetic retinopathy screening research. Data. 2018;3(3):25.
Porwal P, Pachade S, Kokare M, Deshmukh G, Son J, Bae W, Liu L, Wang J, Liu X, Gao L, Wu T. Idrid: Diabetic retinopathy–segmentation and grading challenge. Med Image Anal. 2020;1(59):101561.
Raja H, Akram MU, Khawaja SG, Arslan M, Ramzan A, Nazir N. Data on OCT and fundus images for the detection of glaucoma. Data Brief. 2020;1(29):105342.
Ren F, Cao P, Zhao D, Wan C. Diabetic macular edema grading in retinal images using vector quantization and semi-supervised learning. Technol Health Care. 2018;26(S1):389–97.
da Rocha DA, Barbosa AB, Guimarães DS, Gregório LM, Gomes LH, da Silva AL, Peixoto ZM. 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(1):67–75.
Saman G, Gohar N, Noor S, Shahnaz A, Idress S, Jehan N, Rashid R, Khattak SS. Automatic detection and severity classification of diabetic retinopathy. Multimedia Tools App. 2020;79(43):31803–17.
dos Santos JC, Carrijo GA, dos Santos Cardoso CD, Ferreira JC, Sousa PM, Patrocínio AC. Fundus image quality enhancement for blood vessel detection via a neural network using CLAHE and Wiener filter. Res Biomed Eng. 2020;11:1–3.
Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, Yao J, Mollura D, Summers RM. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging. 2016;35(5):1285–98.
da Silva AL, Ferreira FM, Guimarães JR, Peixoto ZM. 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(3):241–9.
Simonyan K, Zisserman A. 2014 Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Syed AM, Akram MU, Akram T, Muzammal M, Khalid S, Khan MA. Fundus images-based detection and grading of macular edema using robust macula localization. IEEE Access. 2018;15(6):58784–93.
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition 2015:1–9
Yu F, Wang D, Shelhamer E, Darrell T. Deep layer aggregation. In Proceedings of the IEEE conference on computer vision and pattern recognition 2018:2403–2412
Zhou W, Wu C, Chen D, Yi Y, Du W. Automatic microaneurysm detection using the sparse principal component analysis-based unsupervised classification method. IEEE Access. 2017;20(5):2563–72.
Author information
Authors and Affiliations
Contributions
The first author (Amit Kumar) developed the research objective in consultation with the second author, implemented it, and evaluated the results. He also developed the first draft of the article.
The second author (Anand Shanker Tewari) helped in experiments and corrected the initial draft.
The third author (Jyoti Prakash Singh) helped in shaping the research objectives, correcting, and finalizing the article.
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
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
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kumar, A., Tewari, A.S. & Singh, J.P. Classification of diabetic macular edema severity using deep learning technique. Res. Biomed. Eng. 38, 977–987 (2022). https://doi.org/10.1007/s42600-022-00233-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42600-022-00233-z