Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks. Support: https://discourse.slicer.org/c/community/radiomics
The marching cubes algoritm is performed to obtain the surface mesh.
PCA is performed on the resulting mesh to get λmajor, λminor and λleast.
but I can't find information on the PCA is really doing.
Is it just taking of the ROI across slices and then doing PCA to find the longest lengths?
OR
is it comparing length between different combinations of triangles?
The reason I'm asking that ml indicates the minor-axis length differs between my target groups but the orientation of the roi between these groups may differ (unavoidable due to the nature of the work). A slice of an offset ROI is shown below compared the correct orientation of the roi (as a 3d render).
Hi,
This is more to double check some results.
My understanding is that:
but I can't find information on the PCA is really doing.
Is it just taking of the ROI across slices and then doing PCA to find the longest lengths? OR is it comparing length between different combinations of triangles?
The reason I'm asking that ml indicates the minor-axis length differs between my target groups but the orientation of the roi between these groups may differ (unavoidable due to the nature of the work). A slice of an offset ROI is shown below compared the correct orientation of the roi (as a 3d render).