Annotate and Adapt Medical Imaging Models with MONAI (Latest Version)

Step #2: Download Data

For each dataset a user elects to use, the user is responsible for checking if the dataset license is fit for their intended purpose.

To use the 2021 dataset on Launchpad, you will need to sign up for the challenge, get the Synapse ID of the zipped training dataset and obtain a personal access token for the Synapse platform.

  1. Register for Brain Tumor Segmentation Challenge Task 1 by creating an account on the Synapse platform

  2. Follow the instructions in Access the Training Data section of the site

    1. Click Register for challenge

    2. Fill out the google form for registration

      • Put n/a for not applicable questions such as challenge team name, research group and principal investigator

    3. Join the BraTS Challenge Participants team on Synapse to get access to the Synapse data from the email invitation

      • Check your junk mail if it has not been receieved

  3. You should now have access to the Synapse data here

    step-02-image-01.png

  4. Find the Synapse ID for the training data (syn25956772)

  5. Go to your account settings → personal access tokens

  6. Create and save a new access token with permission to view and download the data

    step-02-image-02.png

Save the Synapse ID and API key in a notepad. It will be used later in this step.

Important

This part of the lab will need to be completed using the desktop that is accessible from the left-hand navigation pane.

  1. Log into NVIDIA NGC by visiting https://ngc.nvidia.com/signin

  2. Expand the Base Command section by clicking the downward facing chevron and select Dashboard

    base-command-007.png

  3. Click Create Job.

    base-command-011.png

  4. Select your Accelerated Computing Environment (ACE)

    base-command-012.png

  5. Set the instance size to dgxa100.80g.1.norm

    base-command-013.png

  6. Select the Workspaces tab, select the workspace you created in step 1, and set the mount point to /mount/workspace

    step-02-image-03.png

  7. Set the result mountpoint to /results

    base-command-015.png

  8. Select the nv-launchpad-bc:brats-monai-lab container from the dropdown and the 1.0 tag

    step-02-image-04.png

  9. Enter the command below in Run Command to start up JupyterLab

    Copy
    Copied!
                

    jupyter lab --ip=0.0.0.0 --allow-root --no-browser --NotebookApp.token='' --notebook-dir=/ --NotebookApp.allow_origin='*'

    step-02-image-05.png

  10. Adding ports here exposes them and automatically maps them to a URL provided once the container starts running. To access the JupyerLab enter 8888 and click Add

    step-02-image-06.png

  11. Rename the job to download-brats-2021-dataset.

    step-02-image-07.png

    Note

    Once you have filled in all the required fields, you can copy the command at the bottom of the Create Job page and paste it into your terminal to run the job via the NGC CLI tool.


  12. Once your job has entered the Running state, you should see a green link in the overview section

    step-02-image-08.png

  13. Click the link to open the JupyterLab

    base-command-023.png

  14. Open the terminal on the Jupyter Notebook

    base-command-024.png

  15. Run the commands below in the terminal to download synapse into your workspace

    Copy
    Copied!
                

    cd /mount/workspace; pip3 install synapseclient -t /mount/workspace; export PYTHONPATH=/mount/workspace;


  16. Run the following command in the terminal updating <username>, <api key>, and <synapse id> with your appropriate values.

    Copy
    Copied!
                

    /mount/workspace/bin/synapse -u <username> -p <apikey> get -r <synapse id>;


  17. Run the following commands to unzip the dataset and create the dataset.json needed for integration with the MONAI dataset class

    Copy
    Copied!
                

    unzip RSNA_ASNR_MICCAI_BraTS2021_TrainingData_16July2021.zip -d /mount/workspace; mv RSNA_ASNR_MICCAI_BraTS2021_TrainingData_16July2021 /mount/workspace/brats2021; python3 /workspace/brats-monai-curated-lab/generate_dataset_json.py


  18. Once the commands have finished running, go back to the job

© Copyright 2022-2023, NVIDIA. Last updated on Jan 10, 2023.