Apppublic

uten4211/T1_T2_FLAIR_MRI

sourceHugging Faceupdated 4mo agoView on Hugging Face

0likes

App README

🧠 MRI Simulator: T1-Weighted, T2-Weighted & FLAIR

A simple interactive MRI simulation app built with Streamlit. It loads a high-resolution brain phantom (.mat file) from Google Drive and lets you explore how MRI parameters affect image contrast for three common sequences: T1w, T2w, and FLAIR.

📋 Requirements

—Python 3.10 or higher
—Internet connection (to auto-download the brain phantom on first run)

🚀 Getting Started

1. Clone or download this project

bash

git clone <your-repo-url>
cd <project-folder>

2. (Optional) Create a virtual environment

bash

python -m venv venv
source venv/bin/activate        # macOS / Linux
venv\Scripts\activate           # Windows

3. Install dependencies

bash

pip install -r requirements.txt

4. ⚠️ Create Streamlit configuration file (Required)

bash

mkdir -p .streamlit

Then create .streamlit/config.toml:

toml

[server]
headless = true
port = 8501
enableCORS = false
enableXsrfProtection = false

[theme]
base = "light"

5. Run the app

bash

streamlit run app.py

The app will open at http://localhost:8501.

Note: On first run, BrainHighResolution.mat (~50 MB) will be downloaded automatically from Google Drive. This only happens once.

📁 Project Structure

project/
├── .streamlit/
│   └── config.toml         ← required to avoid configuration error
├── app.py
├── requirements.txt
├── .gitattributes          ← Git LFS tracking for large files
└── README.md

🕹️ How to Use

Use the sidebar sliders to adjust MRI parameters:

Parameter	Description	Affects
TR (ms)	Repetition Time	T2-Weighted, FLAIR
TE (ms)	Echo Time	T2-Weighted, FLAIR
TI (ms)	Inversion Time	FLAIR only

—T1-Weighted — fixed at TR = 600 ms, TE = 15 ms
—T2-Weighted — responds to TR and TE sliders
—FLAIR — responds to TR, TE, and TI sliders (set TI ≈ 2500 ms to null CSF)

🔬 MRI Sequences Explained

T1-Weighted

Short TR + Short TE → highlights fat/white matter, CSF appears dark.

T2-Weighted

Long TR + Long TE → highlights fluid/CSF (bright), white matter appears darker.

FLAIR

Inversion Recovery that suppresses CSF signal — making periventricular lesions more visible.

🌐 Deploy on Hugging Face Spaces

1.Create a new Space at huggingface.co/spaces with Streamlit SDK
2.Push all files including .streamlit/config.toml and .gitattributes
3.The YAML header in this README is automatically read by Hugging Face to configure the Space

bash

git lfs install
git add .
git commit -m "Initial commit"
git push

🛠️ Troubleshooting

Problem	Solution
`Configuration error` on startup	Ensure the YAML front matter at the top of README.md is present and valid
`.streamlit/config.toml` missing	Create it manually as shown in Step 4 above
App not loading data	Check internet connection — `.mat` file downloads on first run
Port already in use	Change `port = 8501` in `config.toml` to e.g. `8502`
Large file push rejected	Run `git lfs install` and ensure `.gitattributes` is committed

📚 Data Source

Brain phantom data: BrainHighResolution.mat — loaded from Google Drive (file ID: 1vdV5xDNfAiHvmKuH5DPi1YJ5Ptl927nk).

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference