Motivations

A generic algorithm written to manipulate a medical image saved in nifti format can act on the image header or on the image data (or the corresponding numpy array) where is it tested.

Apply the algorithm to the image usually involves the repetitive tasks of:

1. loading the image with nibabel
2. extract the header or the data
3. apply the algorithm
4. create a new instance of the modified nifti image
5. finally save it.

LABelsToolkit is aimed at reducing these steps in a single command, allowing to have as input and output directly the path to the input and output image.

• The underpinning algorithm is written (and sometimes tested) for arrays-data structure.
• The facade access the underpinning algorithm providing directly the path to the input image.