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

SPARE scores are not being calculated correctly #229

Closed ashishsingh18 closed 2 years ago

ashishsingh18 commented 2 years ago

@melhemr Can you please add steps to reproduce this issue?

melhemr commented 2 years ago

Using the following data:

data: /cbica/home/melhemr/comp_space/FTD_center/FTDcenter.pkl.gz

harm_model: /cbica/projects/ISTAGING/Pipelines/ISTAGING_Data_Consolidation_2020/v1.3/MUSE_harmonization_model.pkl

spare_model: /cbica/projects/ISTAGING/Pipelines/ISTAGING_Data_Consolidation_2020/v1.3/SPARE_model_LIN-SVM_single_MUSE_ROIs_RES.pkl.gz

1) Load data into NiBAx

2) Load harm_model into harmonization module

3) Apply harm_model to data

4) Click 'Add to DataFrame' button

5) Load spare_model in SPAREs module

6) Apply spare_model to data

7) Click 'Add to DataFrame' button

8) Check 'SPARE_BA' and 'SPARE_AD' in AgeTrends module

The trends follow no pattern based on age at all, which is not correct

AbdulkadirA commented 2 years ago

Fixed by #231 and #232, i.e. the scores were computed correctly, but assigned to the wrong row/index

melhemr commented 2 years ago

Closed by c336b630099a4a3c4edb1fbdea42dee27e4cfbdd