DiaCure - Prediction of Diabetics through Retinal Images

Early detection of Diabetic retinopathy using advanced neural networks predicts diabetes, allowing timely intervention.

The Problem

Understanding Diabetic Retinopathy and its impact on vision

Diabetic Retinopathy

Diabetic retinopathy is an eye condition that can cause vision loss and blindness in people who have diabetes. It affects blood vessels in the retina (the light-sensitive layer of tissue in the back of your eye).

Symptoms

Blood vessels in the retina start to bleed into the vitreous (gel-like fluid that fills your eye) and dark, floating spots or streaks that look like cobwebs can be seen.

Complications

Diabetic retinopathy can lead to other serious eye conditions such as Diabetic macular edema (DME) and Neovascular glaucoma which can cause vision loss and blindness.

Our Solution

How we're solving the problem with advanced technology

1

Data Collection and Diversity

Gathering a diverse dataset of retinal images, encompassing both diabetic and non-diabetic cases, ensuring comprehensive representation for accurate model training.

2

Neural Network Architecture

Designing an efficient neural network architecture specifically tailored for image classification tasks, optimized for retinal image analysis.

3

Optimization Techniques

Using nature-inspired algorithms to optimize the performance of the neural network, enhancing accuracy and efficiency in diabetic retinopathy detection.

4

Training Procedure

Training the model with the ResNet18 architecture to achieve maximum accuracy and minimum loss through rigorous validation processes.

5

Performance Evaluation

Evaluating the model's performance using appropriate metrics such as accuracy, precision, recall, and F1 score to ensure reliable results.

Our Team

Meet the talented individuals behind DiaCure

Abhishek V K

Team Member

Suhas S

Team Member

Sai Kruthik Reddy N S

Team Member

Sanchit Vijay

Team Member

Future Scope

Expanding the capabilities of DiaCure

Mobile Application

Developing a user-friendly mobile application for easier access and real-time diabetic retinopathy detection.

Clinical Integration

Integrating the system with hospital management systems for seamless diagnosis and patient tracking.

Advanced AI Models

Implementing more sophisticated AI models for higher accuracy and detection of additional eye conditions.