search

CBICA / niCHART

The neuro-imaging brain aging chart [niCHART] is a comprehensive solution to analyze standard structural and functional brain MRI data across studies. [niCHART] and the associated pre-processing tools implement computational morphometry, functional signal analysis, quality control, statistical harmonization, data standardization, interactive visual
https://cbica.github.io/niCHART/
Other
13 stars 8 forks source link

Dealing with derived volumes in harmonization #189

Closed melhemr closed 2 years ago

melhemr commented 2 years ago

This PR handles cases in which DERIVED ROI volumes are included in the harmonization model. It also fixes a bug that has to do with age limits in harmonization

melhemr commented 2 years ago

@AbdulkadirA I included the dataset/model used to make checks on this PR. The model, in particular, is useful because it includes derived harmonized volumes in the key model['ROIs']. I have saved them to my comp_space found here:

/cbica/home/melhemr/comp_space/Mathilde/

data_for_harmonization1994_good.pkl is the data phenom_hc_harmonize_iStaging_modelTEST.pkl is the model

melhemr commented 2 years ago

@AbdulkadirA also, make sure any istaging dataset you match with phenom_hc_harmonize_iStaging_modelTEST.pkl includes a 'UseForComBatGAMHarmonization' column so that harmonized volumes will be calculated out-of-model

AbdulkadirA commented 2 years ago

The issue with overstepping bounds is resolved.