RetinaCare
Preserving Vision, Restoring Hope
The problem RetinaCare solves
Diabetic Retinopathy is a disease with an increasing prevalence and the main cause of blindness among working-age population. The risk of severe vision loss can be significantly reduced by timely diagnosis and treatment. Systematic screening for DR has been identified as a cost-effective way to save health services resources. Automatic retinal image analysis is emerging as an important screening tool for early DR detection, which can reduce the workload associated to manual grading as well as save diagnosis costs and time. Many research efforts in the last years have been devoted to developing automated tools to help in the detection and evaluation of DR lesions. We are interested in automating this predition using deep learning models.
Challenges we ran into
Model Training and Integration:
Training a deep learning model, such as Inception-ResNet V2, can be computationally intensive and time-consuming.
Integrating the trained model with your web application might require careful handling of dependencies, versions, and compatibility issues.
Data Collection and Quality:
Gathering a diverse and high-quality dataset for medical image analysis can be challenging.
Ensuring that the input data (eye images in this case) are clean and accurately labeled is crucial for model accuracy.
Security and Privacy:
Handling patient data and email addresses must comply with privacy and security regulations.
Securely storing and transmitting sensitive information is a top priority.
User Experience and UI Design:
Designing an intuitive user interface and optimizing the user experience can be demanding.
Ensuring that the UI works well on different devices and browsers can be challenging.
Email Integration:
Setting up an email service to send diagnostic reports requires proper configuration and handling of potential issues.
Managing email templates and personalizing reports can be complex.
Creating a seamless user experience and an attractive UI design is a significant challenge. The web application should not only provide accurate diagnostics but also offer a user-friendly interface. Ensuring compatibility across various devices and browsers adds another layer of complexity, requiring extensive testing and optimization.