Back
Year
2025
Tech & Technique
Python, Flask, Deep Learning, CNN, CLAHE, OpenCV, Pandas, NumPy
Description
An advanced AI-powered medical diagnostic application engineered to automate the detection and grading of diabetic retinopathy from retinal fundus images. By automating severity classification, the system streamlines screening workflows to support ophthalmologists in clinical decision-making.
Key Features:
Key Features:
- 👁️ Severity Grading: Convolutional Neural Network (CNN) model trained to categorize DR stages.
- 🧪 Advanced Preprocessing: Customized image pipelines leveraging CLAHE, resizing, and normalization to enhance feature resolution.
- 🖥️ Diagnostic Dashboard: A clean, intuitive web portal for uploading retinal images and displaying immediate model predictions.
My Role
AI & Full Stack Developer
Engineered the neural network pipelines, image preprocessing algorithms, and web interface:
Engineered the neural network pipelines, image preprocessing algorithms, and web interface:
- 🧠 Model Training: Designed and trained CNN models for high-accuracy retinal classification.
- ⚙️ Preprocessing: Built customized CLAHE and noise-filtering algorithms to optimize retinal vessel contrast.
- 🌐 Web Application: Developed the full web service backend using Python and Flask to deliver model inferences.