Retinocare: A Web-Based Intelligent System for Early Detection of Diabetic Retinopathy Using CNN

DOI: https://doi.org/10.33650/jeecom.v8i1.13568
Authors

(1) * Angelia Melani Adrian   (Universitas Katolik De La Salle Manado)  
        Indonesia
(2)  Steven Pandelaki   (Universitas Katolik De La Salle Manado)  
        Indonesia
(3)  Gladys Ratuliu   (Universitas Katolik De La Salle Manado)  
        Indonesia
(4)  Jonathan Kamagi   (Universitas Katolik De La Salle Manado)  
        Indonesia
(*) Corresponding Author

Abstract


Diabetic retinopathy (DR) is a leading cause of preventable blindness worldwide and is becoming a significant public health concern in Indonesia due to the rising prevalence of diabetes. Early detection is critical, yet access to ophthalmologists and conventional fundus cameras remains limited in many primary healthcare facilities. To address these challenges, this study proposes a cost-effective, web-based intelligent system for early detection of DR using smartphone-based fundus adapters and deep learning.

A hybrid dataset was employed, combining publicly available fundus image repositories with locally collected retinal images from Indonesian healthcare facilities, annotated by ophthalmologists. Images were preprocessed through normalization, cropping, artifact removal, and augmentation to address variability, particularly from smartphone acquisitions. A DenseNet-121 convolutional neural network was fine-tuned on this hybrid dataset to classify DR into five severity levels according to the International Clinical Diabetic Retinopathy Disease Severity Scale. Model performance was evaluated using accuracy as the primary metric, with results compared against ophthalmologist annotations.

The proposed system demonstrated promising performance in classifying DR severity levels, showing that combining public and local datasets improves contextual relevance and model robustness. Furthermore, integration into a web-based platform enables healthcare workers in primary care to upload fundus images, obtain real-time classification results, and facilitate referral decisions for severe cases.

This study contributes to the development of an accessible and scalable screening tool for DR in Indonesia by integrating affordable imaging hardware, locally relevant datasets, and an AI-powered classification system. The approach has the potential to reduce reliance on expensive equipment and specialists, supporting national efforts to prevent diabetes-related blindness.

Keywords

Eearly Detection; Diabetic retinopathy; CNN; Densnet121; Web-based application



Full Text: PDF



References


REFERENCES

S. Yau, et al., “Global prevalence and major risk factors of diabetic retinopathy,” Diabetes Care, vol. 35, no. 3, pp. 556–564, 2012.

R. Klein, et al., “The epidemiology of diabetic retinopathy,” Ophthalmology, vol. 102, no. 4, pp. 516–525, 1995.

International Diabetes Federation, IDF Diabetes Atlas, 9th ed., Brussels: IDF, 2019.

Indonesian Ministry of Health, Riset Kesehatan Dasar (Riskesdas), Jakarta: MoH, 2018.

Indonesian Ministry of Health, Profil Kesehatan Indonesia 2022, Jakarta: MoH, 2023.

A. Khandekar, et al., “Screening and public health strategies for diabetic retinopathy in the Eastern Mediterranean region,” Middle East Afr. J. Ophthalmol., vol. 19, no. 2, pp. 178–184, 2012.

D. Ting, et al., “Deep learning in ophthalmology: The technical and clinical considerations,” Prog. Retin. Eye Res., vol. 72, pp. 100759, 2019.

J. Jonas, et al., “Global inequalities in eye health: The role of ophthalmologists,” Lancet Glob. Health, vol. 8, no. 5, pp. e545–e546, 2020.

M. Abràmoff, et al., “Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices,” NPJ Digit. Med., vol. 1, no. 1, p. 39, 2018.

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015.

M. Litjens, et al., “A survey on deep learning in medical image analysis,” Med. Image Anal., vol. 42, pp. 60–88, 2017.

V. Gulshan, et al., “Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs,” JAMA, vol. 316, no. 22, pp. 2402–2410, 2016.

K. Quellec, et al., “Deep image mining for diabetic retinopathy screening,” Med. Image Anal., vol. 39, pp. 178–193, 2017.

E. Pratt, et al., “Convolutional neural networks for diabetic retinopathy,” Procedia Comput. Sci., vol. 90, pp. 200–205, 2016.

G. Huang, Z. Liu, L. van der Maaten, and K. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2017, pp. 4700–4708.

S. Khan, et al., “A survey of the recent architectures of deep convolutional neural networks,” arXiv preprint arXiv:1901.06032, 2019.

X. Li, et al., “Automated detection of diabetic retinopathy using deep learning,” Ophthalmology, vol. 125, no. 7, pp. 1048–1054, 2018.

D. Lin, et al., “Application of DenseNet for diabetic retinopathy classification,” Comput. Methods Programs Biomed., vol. 198, p. 105112, 2021.

Y. Wu, et al., “Comparison of deep learning architectures for diabetic retinopathy classification,” IEEE Access, vol. 8, pp. 103373–103383, 2020.

L. Wang, et al., “Attention guided CNN for early diabetic retinopathy detection,” IEEE Trans. Med. Imaging, vol. 39, no. 5, pp. 1438–1450, 2020.

P. Bastawrous, et al., “Clinical validation of a smartphone-based adapter for ocular fundus photography,” JAMA Ophthalmol., vol. 134, no. 2, pp. 151–158, 2016.

T. Rani, et al., “Smartphone-based fundus imaging systems: A review,” Indian J. Ophthalmol., vol. 67, no. 7, pp. 974–981, 2019.

L. Russo, et al., “Comparative study between smartphone-based and conventional fundus photography for diabetic retinopathy screening,” Eye, vol. 34, no. 6, pp. 1010–1016, 2020.

A. Malan, et al., “Field evaluation of smartphone fundus photography for diabetic retinopathy screening in rural clinics,” BMJ Open Ophthalmol., vol. 3, no. 1, e000123, 2018.

P. Bastawrous, et al., “Teleophthalmology with portable fundus cameras and mobile phones in Kenya,” Middle East Afr. J. Ophthalmol., vol. 19, no. 3, pp. 220–224, 2012.

R. Nderitu, et al., “Challenges of smartphone fundus photography for diabetic retinopathy detection,” Afr. Vis. Eye Health, vol. 79, no. 1, a535, 2020.

C. Shorten and T. Khoshgoftaar, “A survey on image data augmentation for deep learning,” J. Big Data, vol. 6, no. 1, pp. 1–48, 2019.

R. Gupta, et al., “Illumination correction methods for fundus images: A comparative study,” Biocybern. Biomed. Eng., vol. 38, no. 4, pp. 773–784, 2018.

J. Budai, et al., “Robust vessel segmentation in fundus images,” Int. J. Biomed. Imaging, vol. 2013, pp. 1–11, 2013.

Y. Perez and J. Wang, “Data augmentation for improving deep learning in image classification,” arXiv preprint arXiv:1712.04621, 2017.

D. Ting, et al., “Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multi-ethnic populations with diabetes,” JAMA, vol. 318, no. 22, pp. 2211–2223, 2017.

J. Cohen, “Weighted kappa statistics for reliability tests of clinical classification,” Stat. Med., vol. 29, no. 3, pp. 421–433, 2010.

D. Davis, et al., “External validation of deep learning algorithms for diabetic retinopathy,” Diabetes Care, vol. 43, no. 8, pp. e108–e109, 2020.

Z. He, et al., “Domain adaptation for medical image analysis: A survey,” IEEE Trans. Med. Imaging, vol. 39, no. 11, pp. 3615–3635, 2020.

Q. Yang, et al., “Federated learning for medical imaging: A survey,” arXiv preprint arXiv:2002.09346, 2020.


Dimensions, PlumX, and Google Scholar Metrics

10.33650/jeecom.v8i1.13568


Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Angelia Melani Adrian

 
This work is licensed under a Creative Commons Attribution License (CC BY-SA 4.0)

Journal of Electrical Engineering and Computer (JEECOM)
Published by LP3M Nurul Jadid University, Indonesia, Probolinggo, East Java, Indonesia.