1. Description of the platform/product:
  2. name and version of the software: MITK Workbench 2016.11 (not yet released)
  3. free? yes -
  4. commercial? no
  5. open source? yes -
  6. what DICOM library do you use? DCMTK, GDCM, DCMQI
  7. Description of the relevant features of the platform:
  8. are both single and multiple segments supported? yes
  9. how are the overlapping segments handled? With semi-transparent color overlay and the active label is contoured (see screenshots)


  • do you support both BINARY and FRACTIONAL segmentation types?
  • do you render the segment using the color specified in the DICOM object? yes
  • how do you communicate segment semantics to the user? semantic codes are stored as property for each label, so the user can not easily get the information
  • how do you support the user in defining the semantics of the object at the time segmentation is created? The user can select from a pre-defined list of organs, structures,... when adding a new label to the segmentation. The selection is mapped to segmentation category/type and color internally

  • Read task: load each of the DICOM SEG datasets that accompany the imaging series into your platform

Test dataset #1

Test dataset Result of rendering
3D Slicer

Test dataset #2

Test dataset Result of rendering
3D Slicer

Test dataset #3

Test dataset Result of rendering
3D Slicer

Test dataset #4


Test dataset Result of rendering
3D Slicer
  1. Write task
  2. segment the lung lesion using any method available in your platform; save the result as DICOM SEG; please include in the series description the name of your tool to simplify comparison tasks!
  3. results are uploaded
  4. run dciodvfy DICOM validator; iterate on resolving the identified issues as necessary
  5. no errors, only warnings from dciodvfy