A Deep Learning Augmented System for Automated Diagnosis of Hypertensive Retinopathy using Retinal Fundus Images

International Journal of Computer Science and Engineering

© 2024 by SSRG - IJCSE Journal

Volume 11 Issue 11

Year of Publication : 2024

Authors : Sarthak Ahuja

10.14445/23488387/IJCSE-V11I11P103

How to Cite?

Sarthak Ahuja, "A Deep Learning Augmented System for Automated Diagnosis of Hypertensive Retinopathy using Retinal Fundus Images," SSRG International Journal of Computer Science and Engineering , vol. 11,  no. 11, pp. 2024, 2024. Crossref, https://doi.org/10.14445/23488387/IJCSE-V11I11P103

Abstract:

Hypertensive Retinopathy (HR) is a common, vision-threatening complication of high blood pressure. A 2023 study in India revealed a 49.33% prevalence of HR among hypertensive individuals, with 81% unaware of their condition. These figures highlight the urgent need for accessible diagnostic tools, especially since early HR signs are often invisible, making timely diagnosis difficult—particularly in resource-limited settings without specialist care. Fundus imaging is the gold standard for HR diagnosis but is often labor-intensive, inaccessible, and time-consuming. To address this, a dataset of 3,300 digitized fundus images (from both HR-diagnosed and HR-free patients) was used to train a Convolutional Neural Network (CNN) model based on YoloV8. The images were split into training (2,400), validation (450), and test (450) sets. Image processing techniques, including CLAHE and Otsu Thresholding, were applied to enhance accuracy. The CNN model achieved training, validation, and test accuracies of 95%-98%, with AUROC scores ranging from 0.96-0.99. An ML-based web app for real-time HR detection was also developed, and internal/external validation demonstrated 95%-98% accuracy. The current study demonstrated the potential of machine learning models in aiding early detection of hypertensive retinopathy in resource-limited settings, offering a valuable tool to support ophthalmologists and pathologists in clinical decision-making.

Keywords:

Hypertensive Retinopathy, Fundus images, Machine Learning (ML)-based web app, CNN model.

References:

[1] Chethana Warad et al., “Incidence and Determinants of Hypertensive Retinopathy in Hypertension Patients at a Teaching Hospital in North Western Karnataka,” Indian Journal of Clinical and Experimental Ophthalmology, vol. 9, no. 4, pp. 634-640, 2023.
[CrossRef] [Publisher Link]
[2] B.K. Triwijoyo, and Y.D. Pradipto, “Detection of Hypertension Retinopathy Using Deep Learning and Boltzmann Machines,” Journal of Physics: Conference Series, vol. 801, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Miguel Alberto Urina-Triana et al., “Machine Learning and AI Approaches for Analyzing Diabetic and Hypertensive Retinopathy in Ocular Images: A Literature Review,” IEEE Access, vol. 12, pp. 54590-54607, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Pranav Modi, and Tasneem Arsiwalla, Hypertensive Retinopathy, StatPearls - NCBI Bookshelf, 2023.
[Publisher Link]
[5] CGI-Hypertensive Retinopathy Diagnosis Challenge (CGI-HRDC2023), 2023. [Online]. Available: https://www.cgs network.org/cgi23/cgi-hrdc2023/
[6] Jyotsana, Image Augmentation Techniques, Medium, 2023. [Online]. Available: https://medium.com/@jyotsana.cg/image-augmentation techniques-798243f6afdf
[7] Avani Manesh et al., “Breast Cancer Detection Using CLAHE-CNN Architecture,” International Journal of Engineering Research & Technology (IJERT), vol. 11, no. 1, 2023.
[CrossRef] [Publisher Link]
[8] Jörg Fischer et al., “Scanning Laser ophthalmoscopy (SLO),” High Resolution Imaging in Microscopy and Ophthalmology, pp. 35–57, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Supriya Suman et al., “Automated Detection of Hypertensive Retinopathy Using Few-Shot Learning,” Biomedical Signal Processing and Control, vol. 86, 2023.
[CrossRef] [Google Scholar] [Publisher Link]