V4Vision is an ambitious project that pushes the redefinition of the role of radiologist by training a multimodal ML model to detect deseases from medical images and write its radiologic report.
This repository contains the source code for the web app that hosts the multimodal model. The web app hosts the multimodal ml model for inference.
V4Vision utilises the following technologies:
- FastAPI (Backend)
- Qwik (Frontend)
- Docker (Container)
- GitHub Actions (Continuous Operations)
- PyTorch (ML)