souravs17031999/Retinal_blindness_detection_Pytorch

AI-driven initiative to assist hospitals and rural clinics in early detection of Diabetic Retinopathy, supporting accessible eye care for all through open healthcare innovation.

40
/ 100
Emerging

# Technical Summary Uses ResNet152 transfer learning in PyTorch to classify retinal fundus images into five DR severity levels (0–4), with a Tkinter GUI frontend and MySQL backend for patient record management. Integrates Twilio SMS notifications for patient outreach and supports the APTOS Kaggle blindness dataset, enabling hospitals to automate DR screening workflows with minimal manual annotation. The architecture prioritizes accessibility for under-resourced clinics while establishing foundations for privacy-preserving deployment through federated learning and differential privacy techniques.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 21 / 25

How are scores calculated?

Stars

98

Forks

40

Language

Jupyter Notebook

License

Last pushed

Oct 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/souravs17031999/Retinal_blindness_detection_Pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.