search

rpomponio / neuroHarmonize

Harmonization tools for multi-site neuroimaging analysis. Implemented as a python package. Harmonization of MRI, sMRI, dMRI, fMRI variables with support for NIFTI images. Complements the work in Neuroimage by Pomponio et al. (2019).
https://pypi.org/project/neuroHarmonize/
MIT License
82 stars 28 forks source link

Output nifti preview after harmonizing #40

Closed hajerkr closed 9 months ago

hajerkr commented 11 months ago

Hello @rpomponio @vnckppl @AbdulkadirA

Is the rim around normal after harmonizing? There's strange black halo around the brain.

Before (original nifti):

image

After (after harmonizing)

image

Tailrach is failing on all harmonized images. Any input would be appreciated thank you

AbdulkadirA commented 11 months ago

@hajerkr Thanks for reporting the issue and demonstrating it with data. The method is intended for co-registered images of "quantitative" (as in tissue probability or RAVENS maps). It is not intended for T1 images where there is no voxel-to-voxel correspondence across images. No amount of co-registration will make the method viable for harmonizing the raw data.

rpomponio commented 9 months ago

Agreed with @AbdulkadirA. Harmonization on NIFTI images only supported for RAVENS maps or other template-space maps. Closing the issue.