Abstract
Diabetes is considered to be the foundation of a slew of other health issues and late consequences, according to medical experts. The rise in diabetes-related illnesses has presented a challenge to the healthcare industry. Diabetic neuropathy, diabetic nephropathy, and diabetic retinopathy are just a few complications that can arise from diabetes. Diabetic Retinopathy is characterized by red lesions, bright lesions, and neovascularization. Bright lesions (exudates) are the second clinically visible lesions that appear after red lesions. The present challenge in DR detection is to make early diagnosis of DR disease more accessible by minimizing the cost and personnel requirements while preserving or enhancing DR detection quality. The challenge can be solved by using automated or computer-assisted DR detection in retinal images. The precise location and shape of blood vessels and the optic disc play critical roles in accurately diagnosing and classifying dark and bright lesions for the early detection of DR. The primary aim of the proposed model is to create an automated model for identifying bright lesions for non-proliferative stage diabetic retinopathy screening using deep learning architecture. It presents algorithms for removing the background of the images, eliminating the optic disc (OD), and the segmentation of candidate lesions. The model was trained and evaluated using MESSIDOR and e-ophtha Ex public datasets and obtained maximum accuracy, sensitivity, specificity, and F1-score of 97.54%, 90.34%, 98.24%, 93.28% and 96.32%, 95.73%, 97.12%, 96.74% respectively.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fig3_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fig4_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fig5_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Figc_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Figd_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fige_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17462-8/MediaObjects/11042_2023_17462_Fig10_HTML.png)
Similar content being viewed by others
References
Wan S, Liang Y, Zhang Y (2018) Deep convolutional Neural Networks for Diabetic Retinopathy Detection by Image Classification. Comput Electr Eng 72:274–282
Wang L, Chen Z, Wang M, Wang T, Zhu W, Chen X (2021) “Cycle Adaptive Multi-Target Weighting Network for Automated Diabetic Retinopathy Segmentation,” IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1141–1144, 2021
Vashist P, Singh S, Gupta N, Saxena R (2011) Role of early screening for diabetic retinopathy in patients with diabetes mellitus: An overview. Indian J Commun Med Off Publication Indian Assoc. Prevent Soc Med 36(4):247
Valverde C, Garcia M, Hornero R, Lopez-Galvez MI (2016) Automated detection of diabetic retinopathy in retinal images. Indian J Ophthalmol. 64(1):26–32
Nirmala S. Guptha, Thanuja K (2014) “Wireless Technology to Monitor Remote Patients-A Survey,” International Journal of Computer Networking. Wireless Mobile Commun (IJCNWMC) 4:65–76
Ahmed, Syed Thouheed S, Thanuja, Guptha NS, Narasimha S (2016) "Telemedicine approach for remote patient monitoring system using smart phones with an economical hardware kit." In 2016 international conference on computing technologies and intelligent data engineering (ICCTIDE'16), 1–4
Guptha NS (2018) KK Patil,"Detection of macro and micro nodule using online region based-active contour model in histopathological liver cirrhosis”. Int J Intell Eng Syst 11(2):256–265
Esmaeili M, Rabbani H, Dehnavi AM, Dehghani A (2012) Automatic detection of Exudates and optic disk in retinal images using curvelet transform. IET Image Proc 6(7):1005–1013
Guo X, Lu X, Liu Q, Che X (2019) EMFN: Enhanced Multi-Feature Fusion Network for Hard Exudate Detection in Fundus Images. IEEE Access 7:176912–176920
Wisaeng K, Sa-Ngiamvibool W (2019) Exudates Detection using Morphology Mean Shift Algorithm in Retinal Images. IEEE Access 7:11946–11958
Zhou W, Wu C, Yi Y, Du W (2017) Automatic Detection of Exudates in Digital Color Fundus Images using Superpixel Multi-Feature Classification. IEEE Access 5:17077–17088
Wang H, Yuan G, Zhao X, Peng L, Wang Z, He Y, Qu C, Peng Z (2020) Hard Exudate Detection Based on Deep Model Learned Information and Multi-Feature Joint Representation for Diabetic Retinopathy Screening. Computer Methods and Programs in Biomedicine 191
Adem K (2018) Exudate detection for diabetic retinopathy with circular Hough transformation and convolutional neural networks. Expert Syst Appl 114:289–295
Prentasic P, Loncaric S (2016) Detection of Exudates in Fundus Photographs using Deep Neural Networks and Anatomical Landmark Detection Fusion. Comput Methods Programs Biomed 137:281–292
Auccahuasi W, Flores E, Sernaque F, Cueva J, Diaz M et al (2020) Recognition of Hard Exudates using Deep Learning. Procedia Computer Science 167:2343–2353
Rajkumar RS, Selvarani AG (2022) Diabetic Retinopathy Diagnosis using ResNet with Fuzzy Rough C-Means Clustering. Comput Syst Sci Eng 42(2):509–521
SowmyaSundari K, Guptha LK, Shruthi NS, Thanuja G, Anitha K (2019) Detection of liver lesion using ROBUST machine learning technique. Int J Eng Adv Technol (IJEAT) 8(5):214–219
Ahmed ST, SK S, Guptha NS, Lavanya NL, Basha SM, Fathima AS (2022) “Improving Medical Image Pixel Quality Using Micq Unsupervised Machine Learning Technique.” Malaysian J Comput Sci 53–64
Sudha S, Srinivasan A, Devi TG (2022) Detection and Classification of Diabetic Retinopathy using DCNN and BSN Models. CMC-Comput Mater Cont 72(1):597–609
Rawat W, Wang Z (2017) Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput 29(9):2352–2449
Yadav SS, Jadhav SM (2019) Deep convolutional neural network based medical image classification for disease diagnosis. J Big Data 6(113):1–18
Decenciere E, Zhang, Xiwei, Cazuguel G, Lay B, Cochener et al (2014) “Feedback on a Publicly Distributed Image Database: The Messidor database.” Image Anal Stereol
Decenciere E, Cazuguel G, Zhang X, Thibault G, Klein et al (2013) Teleophta: Machine Learning and Image Processing Methods for Teleophthalmology. IRBM 34:196–203
Bannigidad P, Deshpande A (2019) “Exudates Detection from Digital Fundus Images using GLCM Features with Decision Tree Classifier”. Recent Trends in Image Processing and Pattern Recognition, RTIP2R 2018. Communications in Computer and Information Science, Springer, Singapore 1036:245–257
Megantara RA, Abdussalam Purwanto, Fanani AZ, Andono PN et al (2020) Exudates Detection for Multiclass Diabetic Retinopathy Grade Detection using Ensemble. Technol Reports Kansai Univ 62(3):807–820
Bilal A, Zhu L, Deng A, Lu H, Wu N (2022) AI-Based Automatic Detection and Classification of Diabetic Retinopathy Using U-Net and Deep Learning. Symmetry 14(7):1427
Usman TM, Saheed YK, Ignace D, Nsang A (2023) Diabetic retinopathy detection using principal component analysis multi-label feature extraction and classification. Int J Cogn Comput Eng 4:78–88
Joshi S, Karule PT (2018) Detection of Hard exudates Based on Morphological Feature Extraction. Biomed Pharmacol J 11(1):215–225
Long Shengchun, Huang Xiaoxiao, Chen Zhiqing, Pardhan Shahina, Zheng Dingchang (2019) Automatic Detection of Hard Exudates in Color Retinal Images using Dynamic Threshold and SVM Classification: Algorithm Development and Evaluation. BioMed Res Int 2019:1–13
Colomer A, Igual J, Naranjo V (2020) Detection of Early Signs of Diabetic Retinopathy Based on Textural and Morphological Information in Fundus Images. Sensors 20(4):1005
Chen PN, Lee CC, Liang CM et al (2021) General deep learning model for detecting diabetic retinopathy. BMC Bioinformatics 22(5):84
Asiri NM, Hussain M, Adel FA, Aboalsamh (2022) “A Deep Learning-Based Unified Framework for Red Lesions Detection on Retinal Fundus Images.” ArXiv,1–18
Malhi A, Grewal R, Pannu HS (2023) Detection and diabetic retinopathy grading using digital retinal images. Int J Intell Robot Appl 7:426–458
Acknowledgements
The authors would like to thank the SRM Institute of Science and Technology, Department of Computing Technologies for providing an excellent atmosphere for researching on this topic.
Funding
The authors received no specific funding for this research.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Conflict of interest
The Authors declare that there is no conflict of interest.
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 (e.g. a society or other partner) 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
Saranya, P., Umamaheswari, K.M. Detection of exudates from retinal images for non-proliferative diabetic retinopathy detection using deep learning model. Multimed Tools Appl 83, 52253–52273 (2024). https://doi.org/10.1007/s11042-023-17462-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-17462-8