Skip to content

farhat-lab/tbp-severity-scoring

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

47 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

tbp-severity-scoring

Part 2: CNN

This repository contains the code and sample data used for the research work titled "Percent lung involved with tuberculosis on chest X-ray predicts unfavorable treatment outcome and is accurately predicted with artificial intelligence". More information on the raw data used for this research work is present in the TB-Portals website (https://tbportals.niaid.nih.gov).

Repository Structure

  • data/: Contains the example data files used for the analysis.
  • models/: Ensemble model weights.
  • notebooks/: Jupyter notebooks for cohort selection, quality checking and data exploration.
  • scripts/: Python scripts for regression and classification tasks.
  • requirements.txt: Python dependencies required to run the scripts.
  • LICENSE: License information.

Getting Started

Prerequisites

  • Python 3.7 or higher
  • Git
  • Virtual environment tools (optional)

Installation

  1. Clone the repository:
git clone https://github.com/farhat-lab/tbp-severity-scoring.git
cd tbp-severity-scoring
  1. Create and activate a virtual environment (optional but recommended):
python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`
  1. Install the required dependencies:
pip install -r requirements.txt

Usage

To test the PLI regression model on your image samples:

python scripts/test.py

License Notice

The model weights are deposited for peer-review purposes only. See LICENSE file for more details.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors