You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
If the segmentation is too noisy the the isolate function fails as it is unable to handle the large number of connected components. ITK filter by default labels each non-zero unconnected pixel as a separate object, which is not efficient.
We need to be able to specify the minimum object size required.
# source: https://github.com/Bonelab/DECT_BoneAnalysis/blob/87ab9cad4afcc029085dc403ed212a7be39176ce/Segment_Edema.py#L110
#Component labeling to remove small clusters less than 100 voxels in size:
cc_filter = sitk.ConnectedComponentImageFilter()
cl = cc_filter.Execute(edema_masked)
cc_relabel = sitk.RelabelComponentImageFilter()
cc_relabel.SetMinimumObjectSize(100)
The text was updated successfully, but these errors were encountered:
If the segmentation is too noisy the the isolate function fails as it is unable to handle the large number of connected components. ITK filter by default labels each non-zero unconnected pixel as a separate object, which is not efficient.
We need to be able to specify the minimum object size required.
The text was updated successfully, but these errors were encountered: