Skip to content

Latest commit

 

History

History
45 lines (29 loc) · 1.98 KB

YourTransformObjectNeedsMetadata.md

File metadata and controls

45 lines (29 loc) · 1.98 KB
Raw

Back to the Tutorials List

Your Transform Object needs Metadata

Instructors

  • Hastings Greer

Tutorial Description

Downstream medical application code needs to correctly handle image spacing, image orientation, and unusual image origins correctly – in particular, landmarks, volume and size measurements, and mesh data are always in physical coordinates.

If we try to manually handle this metadata by, for each downstream task, manually scaling, transposing, and shifting deformation fields, we will make mistakes and spend a lot of time. Instead, we need to use a metadata-aware representation of image registration results at application boundaries. I propose that itk.Transform objects are the current best option.

notebook

Learning Outcomes

  1. Outcome 1. At the end of this tutorial, participants will be able to add a wrapper or interface to their registration project, that

    • Takes as input a pair of ITK images with spatial metadata
    • Outputs an ITK Transform with spatial metadata

  2. Outcome 2. Participants will be able to structure a downstream application to use this format, making switching registration libraries achievable

Approach and Materials

Background and References

https://pypi.org/project/icon-registration/ ITK