README.md

metadata

title: Bids Neuroimaging
emoji: 👁
colorFrom: indigo
colorTo: indigo
sdk: docker
pinned: false
license: cc-by-4.0
short_description: Visualize  Aphasia Recovery Cohort (ARC) Dataset - Mini Samp

BIDS Neuroimaging Viewer

A FastAPI-based web application for visualizing neuroimaging data in BIDS format using NiiVue.

Installation

1. Clone the repository:

git clone <your-repo-url>
cd bids-neuroimaging

2. Create a virtual environment and install dependencies:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -r requirements.txt

3. Install the custom datasets fork with BIDS loader:

pip install git+https://github.com/The-Obstacle-Is-The-Way/datasets.git@feat/bids-loader

Running the Application

Start the FastAPI server with:

fastapi dev main.py

Or using uvicorn directly:

uvicorn main:app --reload --host 0.0.0.0 --port 8000

Then open your browser and navigate to:

• Main viewer: http://localhost:8000
• Health check: http://localhost:8000/health

Features

• Interactive 3D visualization of NIfTI files using NiiVue
• Multiple viewing modes: Multiplanar + 3D, and 3D Render Only
• Next button to iterate through dataset samples (implement the /next endpoint)

Development

The main application is in main.py. To implement the "Next" functionality:

1. Modify the /next endpoint in main.py to load and return the next sample
2. The endpoint should return a JSON with the base64-encoded NIfTI data

Configuration Reference

For Hugging Face Spaces deployment, check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference