ML Medical Image Classification · November 2022
physicAIn
An end-to-end ML-powered system integrating an Android client with a cloud inference API for near real-time diagnostic predictions.
10,000 images
Training set
95%
Accuracy
MLH 3rd Place
Award
What it does
- Trained a deep-learning model on 10,000 images, achieving 95% accuracy.
- Deployed a Flask-based microservice on a Google Cloud VPS.
- Enabled near real-time diagnostic predictions.
- MLH 3rd Place Overall at BCHACKS 4.0; Best Use of GitHub Award recipient.