Processing DICOM Files With Spark on CDP Hybrid Cloud

Processing DICOM Files With Spark on CDP Hybrid Cloud

Oct 7, 2021

In this video, you will see how you can use PySpark to process medical images from an MRI and convert them from DICOM format to PNG. The data is read from and written to AWS S3 and we leverage numpy and the pydicom libraries to do the data transformation. We are using data from the "RSNA-MICCAI Brain Tumor Radiogenomic Classification" Kaggle competition but this approach can be used for general purpose DICOM processing.

Link to Related Tutorial:
https://www.cloudera.com/tutorials/processing-dicom-files-with-spark-on-cde.html

Link to Related Meetup:
https://www.meetup.com/futureofdata-nova/events/281278346/

Cloudera User's Page:
https://www.cloudera.com/users

Cloudera Community:
https://community.cloudera.com