Real-Time Detection of Diabetic Retinopathy Using Deep Learning Techniques
Journal Title: International Journal of Innovations in Science and Technology - Year 2024, Vol 6, Issue 4
Abstract
Diabetic retinopathy is a prevalent disease which is a medical condition frequently caused due to high sugar levels in the blood. It deteriorates the optic nerve as it compresses and blurs the vision, which is used to detect white light and transmit signals to your cerebrum using a nerve. There has been a massive increase in the statistics having diabetic retinopathy which causes the loss of sight in any age group with no treatment Every diabetic patient is required to visit their ophthalmologist every two weeks or mandatorily in a month. Moreover, a bi-annual inspection is required to notice the amount of vision to see the objects. For this reason, Pakistan lacks ophthalmologists who are experts in their domain. Mostly, they are not available around the clock, especially in less privileged areas. Therefore, we have developed a smartphonebased handheld AI-integrated product that is cost-effective and portable which detects visual Impairment and produces reports of the concerned patient with a minor intervention on the same day by an eye specialist. This research project focuses on diabetic retinopathy detection by utilizing a 20D (20 Diopter) Lens and camera of any random smartphone that captures fundus images which are further spitted and compared against various models of deep learning. In this research, VGG-15, ResNet50, and Custom CNN were undertaken. As a result, VGG16 outperformed other models by obtaining the highest validation accuracy which is 74.53% as well as the lowest validation loss of 55.94%. Moreover, ResNet50 yielded 74.08% validation accuracy and a computing validation loss of 58.72%. Consequently, the custom CNN Model achieves 57.26% validation accuracy and 57.26% validation loss. Thus, VGG16 performed best on the dataset provided and is deployed in the smartphone application which is a portable and costeffective method for Diabetic Retinopathy screening in less privileged areas. This project aims to target three Sustainable Development Goals including Affordable and clean energy, good health and well-being, and Industry Innovation and Infrastructure respectively.
Authors and Affiliations
Irfan Ali Bhacho, Hina Lilaram, Sarmad Talpur, Madeha Memon, Nouman Qadeer Soomro
Keywords
Related Articles
- EP ID EP760574
- DOI -
- Views 9
- Downloads 0
Identification of Fake Contents Using Text-mining Techniques
In recent years, social media users have become increasingly concerned about sharing content that may be unpleasant or harmful. The widespread use of platforms like Facebook and Twitter has contributed significantly to...
Gemstones Supply Chain Management throughBlockchain Mechanism
T provenance of gemstones significantly enhances their value. However, both conventional supply chain management and digital systems are susceptible to counterfeiting, loss, and theft. Blockchain has emerged as a suita...
Analysis of MLP, CNN,and Transfer Learning Using VGG-16 for CIFAR-10 Dataset
Artificial Neural Networks (ANN) are becoming the core domain of Artificial Intelligence. Generally, Machine learning and specifically, deep learning gained popularity in problemsolving by virtue of Multi-Layer Perceptr...
AI-Powered Detection: Implementing Deep Learning for Breast Cancer Prediction
Breast cancer remains a critical global health issue, affecting millions of women worldwide. According to the World Health Organization (WHO), there were 2.3 million new cases and 685,000 deaths from breast cancer in 2...
Spatial Investigation of Soil Erosion Risk in the High Rainfall Zone of Pakistan by Using Rusle Model
The degradation of soil quality and agricultural sustainability is threatened by soil erosion, which poses a serious threat to livelihoods and food security. Maintaining soil fertility and reducing the danger of erosio...