Difference between revisions of "Multi Label Segmentation"
Jump to navigation
Jump to search
MarcoNolden (talk | contribs) |
MarcoNolden (talk | contribs) |
||
| Line 1: | Line 1: | ||
__NOTOC__ | __NOTOC__ | ||
| − | <!-- #acl | + | <!-- #acl [[DanielMaleike]],[[TobiasHeimann]],[[SebastianOrdas]],[[MarcoNolden]]:read,write,revert --> |
| − | [[DanielMaleike]],[[TobiasHeimann]],[[SebastianOrdas]],[[MarcoNolden]]:read,write,revert | ||
<!-- #acl All: --> | <!-- #acl All: --> | ||
Revision as of 19:02, 25 January 2011
Using multiple segmentations with the Segmentation bundle
#!wiki caution This is really just a sketch. Move / change anything
Following a proposal of Sebastian Ordas to support multi-label segmentations, this page will be used to sketch future changes to the Segmentation bundle and the related framework.
Shortcomings of the current implementation
- 8-bit images are used for segmentations by default, wasting 7 of 8 byts, occupying far more memory than technically necessary
Wishlist
- what is not possible or cumbersome and should be changed?
- what enhancements would help in which situations?
- to support multi-label images, ITK's label object classes (http://www.insight-journal.org/browse/publication/176) could be useful
- how does I/O work?
- do we need a new data type for MITK (derived from BaseData?)
- how could these be mapped types for rendering?
Implications on the implementation
- what parts of MITK would need to be changed?
- what needs to be changed in the Segmentation view?