IDC User Guide
  • Welcome!
  • 🚀Getting started
  • Core functions
  • Frequently asked questions
  • Support
  • Key pointers
  • Publications
  • IDC team
  • Acknowledgments
  • Jobs
  • Data
    • Introduction
    • Data model
    • Data versioning
    • Organization of data
      • Files and metadata
      • Resolving CRDC Globally Unique Identifiers (GUIDs)
      • Clinical data
      • Organization of data, v2 through V13 (deprecated)
        • Files and metadata
        • Resolving CRDC Globally Unique Identifiers (GUIDs)
        • Clinical data
      • Organization of data in v1 (deprecated)
    • Downloading data
      • Downloading data with s5cmd
      • Directly loading DICOM objects from Google Cloud or AWS in Python
    • Data release notes
    • Data known issues
  • Tutorials
    • Portal tutorial
    • Python notebook tutorials
    • Slide microscopy
      • Using QuPath for visualization
  • DICOM
    • Introduction to DICOM
    • DICOM data model
    • Original objects
    • Derived objects
      • DICOM Segmentations
      • DICOM Radiotherapy Structure Sets
      • DICOM Structured Reports
    • Coding schemes
    • DICOM-TIFF dual personality files
    • IDC DICOM white papers
  • Portal
    • Getting started
    • Exploring and subsetting data
      • Configuring your search
      • Exploring search results
      • Data selection and download
    • Visualizing images
    • Proxy policy
    • Viewer release notes
    • Portal release notes
  • API
    • Getting Started
    • IDC API Concepts
    • Manifests
    • Accessing the API
    • Endpoint Details
    • V1 API
      • Getting Started
      • IDC Data Model Concepts
      • Accessing the API
      • Endpoint Details
      • Release Notes
  • Cookbook
    • Colab notebooks
    • BigQuery
    • Looker dashboards
      • Dashboard for your cohort
      • More dashboard examples
    • ACCESS allocations
    • Compute engine
      • 3D Slicer desktop VM
      • Using a BQ Manifest to Load DICOM Files onto a VM
      • Using VS Code with GCP VMs
      • Security considerations
    • NCI Cloud Resources
Powered by GitBook
On this page
  • IDC maintained notebooks
  • Community-contributed notebooks
  • Relevant resources

Was this helpful?

Edit on GitHub
Export as PDF
  1. Cookbook

Colab notebooks

This section contains various pointers that may be helpful when working with Google Colab.

Google Colaboratory, or “Colab” for short, is a product from Google Research. Colab allows anybody to write and execute arbitrary python code through the browser, and is especially well suited to machine learning, data analysis and education. More technically, Colab is a hosted Jupyter notebook service that requires no setup to use, while providing free access to computing resources including GPUs.

If you would like to share an interesting notebook that uses IDC/cloud for imaging research, please let us know and we would be happy to review and reference it here!

IDC maintained notebooks

IDC Colab example notebooks are maintained in this repository: https://github.com/ImagingDataCommons/IDC-Tutorials/tree/master/notebooks

Notebook demonstrating deployment and application of abdominal structures segmentation tool to IDC data, developed for the 2021 RSNA Deep Learning Lab course: https://tinyurl.com/RSNA21-IDC-TCIA

Community-contributed notebooks

  • Deep-learning Nodule Segmentation using LIDC dataset on Google Cloud Platform, contributed by Kuan (Kevin) Zhang, Mayo Clinic

  • 3D Brain MRI Classification Using Imaging Data Commons, Google Cloud, and NIFTI files, contributed by Pouria Rouzokh, Mayo Clinic

  • Notebooks contributed by Fabian Seidl, ISB-CGC, demonstrating the utility of BigQuery in correlative analysis of radiomics and genomics data:

    • How to compare tumor features with gene expression data

    • How to compare tumor features with mutation data

Relevant resources

  • Colab limitations: https://research.google.com/colaboratory/faq.html

  • Transferring data between Colab and Google Drive: https://gist.github.com/yt114/dc5d2fd4437f858bb73e38f0aba362c7

  • Potentially interesting sources of example notebooks:

    • SimpleITK notebooks

    • https://github.com/mdai/ml-lessons/

    • http://uwmsk.org/jupyter/

    • https://github.com/JoaoSantinha/Medical_Image_Analysis_Workshop

  • Google Colab Tips for Power Users: https://amitness.com/2020/06/google-colaboratory-tips/

  • Mounting GCS bucket using gcsfuse: https://pub.towardsai.net/connect-colab-to-gcs-bucket-using-gcsfuse-29f4f844d074

  • Almost-free Jupyter Notebooks on Google Cloud: https://www.tensorops.ai/post/almost-free-jupyter-notebooks-on-google-cloud

PreviousRelease NotesNextBigQuery

Last updated 2 years ago

Was this helpful?