Introduction

nextPyrad is a bioinformatics best-practice analysis pipeline designed for processing CT scans and extracting Radiomics features from medical images. Utilizing Pyradiomics, an open-source Python package, this pipeline automates the extraction of Radiomics features, making it a valuable tool for medical imaging research.

The pipeline is built using Nextflow, a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. The Nextflow DSL2 implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from nf-core/modules in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community!

Pipeline summary

• Input: Read folder with medical images and corresponding masks in NIfTI format.
• Processing: Utilize (PyRadiomics) to extract Radiomics features.
• Output: Merge all the individual Radiomics feature patient's file in a unified final CSV file Radiomics_features_results.csv

Quick Start

1. Install Nextflow (>=22.10.1)

2. Download the pipeline by cloning the repository

   git clone git@github.com:sandrocarollo/nextPyrad.git
   cd nextPyrad

3. Create and activate conda environment

   conda env create -f environment.yml
   conda activate nextpyrad

4. Run the pipeline:

   nextflow run main.nf 

5. Start running your own analysis!

   In order to do so you should keep your data in a certain folder structure like this one:

      Data
      ├── Sample_1
      │   ├── sample1_image.nrrd
      │   └── sample1_seg.nrrd
      ├── ...
      ├── Sample_N
      │   ├── sampleN_image.nrrd
      │   └── sampleN_seg.nrrd
      └── ...

   Note that the predifined pattern to access all the Images and the respective Masks is *_{image,seg}.n*, meaning that the image file should have "_image" and the mask "_seg" as a suffix.

   Use:

   nextflow run main.nf --input_img_mask = "./data/Test" --pattern = "*_{image,seg}.n*" --outdir = './results'

   where the flags --input_img_mask and --pattern replace the predefined values.

Acknowledgments

nextPyrad was originally written by Sandro Carollo.

Citations

If you use nextPyrad for your research, please cite its use in your publications.