Data

Tools

Indexes

Applications

Experiments

Open Source Science

lung-treatment-response

Machine learning model for lung treatment response after SBRT

https://github.com/plbenveniste/lung-treatment-response

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.6%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Machine learning model for lung treatment response after SBRT

Basic Info
  • Host: GitHub
  • Owner: plbenveniste
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 115 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 7
  • Releases: 2
Created about 2 years ago · Last pushed 11 months ago
Metadata Files
Readme License Citation

README.md

Lung Treatment response

Machine learning model to investigate lung cancer response after SBRT (radiotherapy treatment).

We investigated the clinical and radiomics data regarding lung cancer response after SBRT for the following predictions: - survival - local relapse - remote relapse

We also investigated feature removal, data-preprocessing and prediction timeframe.

Authors: Camille Invernizzi, Pierre-Louis Benveniste

1. Instructions to install everything

Create a new environment

console conda create -n venv_lung_response python=3.9

Activate it console conda activate venv_lung_response

Then install all required libraries console pip install -r requirements.txt

2. Code in this repository

The code is divided in two folders: - data_preprocessing: here we investigate the data for data preprocessing, dataset merging, dataset statistics and feature elimination. - model training: here we investigate the training of model prediction for survival, local relapse and final relapse.

NB: the investigations are detailed in the issues.

3. Performing a prediction

After doing the steps in installation section (section 1) and downloading the model from the release, you can run an inference using the file predict3yearsurvival.py. Use the following command:

console python predict_3year_survival.py --model-path PATH/TO/MODEL --sex X --BMI X --score_charlson X --smoke_cessation X --dose_tot X --BED_10 X --MeanIntensity X --IntensitySkewness X --IntensityKurtosis X --AreaUnderCurveCIVH X --RootMeanSquareIntensity X --IntensityHistogramMean X --IntensityHistogramVariance X --NGTDM_Strength X

Owner

  • Name: PL Benveniste
  • Login: plbenveniste
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - family-names: Benveniste
    given-names: Pierre-Louis
    orcid: https://orcid.org/0009-0003-3122-1957
title: "Predictive model for response to lung stereotactic body radiation therapy"
version: 2.0.4
identifiers:
  - type: doi
    value: 10.5281/zenodo.12628523
date-released: 2024-07-02

GitHub Events

Total
  • Release event: 1
  • Issue comment event: 1
  • Push event: 10
  • Pull request event: 3
  • Create event: 3
Last Year
  • Release event: 1
  • Issue comment event: 1
  • Push event: 10
  • Pull request event: 3
  • Create event: 3