Infrastructure for Medical Imaging Research

Overview of the image analysis infrastructure. On the left side are the centers where the data is acquired and anonymized. In the center is the XNAT archive, the StudyManager and a TaskManager. On the top are the study database and the viewing/annotation applications for manual annotations. On the bottom is fastr and a compute cluster/cloud for automated analysis. Finally all derived data is collected and exported in a format the study desires. The different components interface with each other through REST APIs.

Large scale medical studies pose technical and administrative challenges. We created an infrastructure to conduct reproducible medical imaging research.

What is our goal?

Our infrastructure was originally devloped for the Rotterdam Scan Study, where we tried to implement a continous flow from acquisition to processing, to analyses, to quantitative imaging biomakers.

Our infrastructure can greatly benefit personalized medicine by making pipelines for imaging biomarker extraction available to researchers and clinicians. Additionally, we create a reference database for different imaging biomarkers, which can be used to compare an individual against the general population. This will enable im- proved re-use of imaging data for diagnostics and prognostics.

Our infrastructure:

  • Improves robustness
  • Increases reproducibility
  • Increases data consistency
  • Is automated where possible
  • Consists of modular building blocks

Succes Stories:

  • Incidental finding and QC on ~ 2000 RSS subjects
  • Mark and outline Infarcts on 500+ CVON HBC subjects
  • Tongue Tumor segmentations for 50 subjects.
  • Inspection tasks for more than 50000 clinical scans.

Meet our software components