8.3. Computer Parcel Aggregation.

This example uses a ParcelAggregation marker to compute the mean of each parcel using the Schaefer parcellations (100 rois, 7 Yeo networks) for both a 3D and 4D nifti

Authors: Federico Raimondo

License: BSD 3 clause

import nilearn

from junifer.markers.parcel_aggregation import ParcelAggregation
from junifer.utils import configure_logging

Set the logging level to info to see extra information

configure_logging(level="INFO")

2023-10-17 10:30:52,423 - JUNIFER - INFO - ===== Lib Versions =====
2023-10-17 10:30:52,423 - JUNIFER - INFO - numpy: 1.25.2
2023-10-17 10:30:52,423 - JUNIFER - INFO - scipy: 1.11.3
2023-10-17 10:30:52,423 - JUNIFER - INFO - pandas: 2.0.3
2023-10-17 10:30:52,423 - JUNIFER - INFO - nilearn: 0.10.2
2023-10-17 10:30:52,423 - JUNIFER - INFO - nibabel: 5.1.0
2023-10-17 10:30:52,423 - JUNIFER - INFO - junifer: 0.0.4.dev96
2023-10-17 10:30:52,423 - JUNIFER - INFO - ========================

Load the VBM GM data (3d): - Fetch the Oasis dataset

oasis_dataset = nilearn.datasets.fetch_oasis_vbm(n_subjects=1)
vbm_fname = oasis_dataset.gray_matter_maps[0]
vbm_img = nilearn.image.load_img(vbm_fname)

Dataset created in /home/runner/nilearn_data/oasis1

Downloading data from https://www.nitrc.org/frs/download.php/6364/archive_dartel.tgz ...

Downloaded 53739520 of 905208634 bytes (5.9%,   15.9s remaining)
Downloaded 139264000 of 905208634 bytes (15.4%,   11.0s remaining)
Downloaded 223109120 of 905208634 bytes (24.6%,    9.2s remaining)
Downloaded 305127424 of 905208634 bytes (33.7%,    7.9s remaining)
Downloaded 389144576 of 905208634 bytes (43.0%,    6.6s remaining)
Downloaded 473464832 of 905208634 bytes (52.3%,    5.5s remaining)
Downloaded 557449216 of 905208634 bytes (61.6%,    4.4s remaining)
Downloaded 640221184 of 905208634 bytes (70.7%,    3.3s remaining)
Downloaded 722305024 of 905208634 bytes (79.8%,    2.3s remaining)
Downloaded 802594816 of 905208634 bytes (88.7%,    1.3s remaining)
Downloaded 886128640 of 905208634 bytes (97.9%,    0.2s remaining) ...done. (12 seconds, 0 min)
Extracting data from /home/runner/nilearn_data/oasis1/6d19418bccb98b1333309bd8baa05152/archive_dartel.tgz..... done.
/opt/hostedtoolcache/Python/3.10.13/x64/lib/python3.10/site-packages/nilearn/datasets/struct.py:852: UserWarning: `legacy_format` will default to `False` in release 0.11. Dataset fetchers will then return pandas dataframes by default instead of recarrays.
  warnings.warn(_LEGACY_FORMAT_MSG)

Load the functional data (4d): - Fetch the SPM auditory dataset - Concatenate the functional data into one 4D image

s_func_data = nilearn.datasets.fetch_spm_auditory()
fmri_img = nilearn.image.concat_imgs(s_func_data.func)

Dataset created in /home/runner/nilearn_data/spm_auditory

Data absent, downloading...
Downloading data from https://www.fil.ion.ucl.ac.uk/spm/download/data/MoAEpilot/MoAEpilot.zip ...

Downloaded 2719744 of 34212021 bytes (7.9%,   12.0s remaining)
Downloaded 6430720 of 34212021 bytes (18.8%,    8.8s remaining)
Downloaded 9306112 of 34212021 bytes (27.2%,    8.2s remaining)
Downloaded 12378112 of 34212021 bytes (36.2%,    7.2s remaining)
Downloaded 15548416 of 34212021 bytes (45.4%,    6.1s remaining)
Downloaded 18743296 of 34212021 bytes (54.8%,    5.1s remaining)
Downloaded 21938176 of 34212021 bytes (64.1%,    4.0s remaining)
Downloaded 25141248 of 34212021 bytes (73.5%,    3.0s remaining)
Downloaded 27959296 of 34212021 bytes (81.7%,    2.1s remaining)
Downloaded 30580736 of 34212021 bytes (89.4%,    1.2s remaining)
Downloaded 33439744 of 34212021 bytes (97.7%,    0.3s remaining) ...done. (13 seconds, 0 min)
Extracting data from /home/runner/nilearn_data/spm_auditory/sub001/MoAEpilot.zip..... done.

Define the marker

marker = ParcelAggregation(parcellation="Schaefer100x7", method="mean")

Prepare the input

input = {
    "BOLD": {"data": fmri_img, "meta": {"element": "subject1"}},
    "VBM_GM": {"data": vbm_img, "meta": {"element": "subject1"}},
}

Fit transform the data

out = marker.fit_transform(input)

2023-10-17 10:31:26,562 - JUNIFER - INFO - Computing BOLD
2023-10-17 10:31:26,562 - JUNIFER - INFO - Fetching one of Schaefer parcellations.
2023-10-17 10:31:26,562 - JUNIFER - INFO - Parcellation parameters:
2023-10-17 10:31:26,562 - JUNIFER - INFO -      resolution: 3.0
2023-10-17 10:31:26,562 - JUNIFER - INFO -      n_rois: 100
2023-10-17 10:31:26,563 - JUNIFER - INFO -      yeo_networks: 7
2023-10-17 10:31:26,563 - JUNIFER - INFO - At least one of the parcellation files are missing. Fetching using nilearn.

Dataset created in /home/runner/junifer/data/parcellations/schaefer_2018

Downloading data from https://raw.githubusercontent.com/ThomasYeoLab/CBIG/v0.14.3-Update_Yeo2011_Schaefer2018_labelname/stable_projects/brain_parcellation/Schaefer2018_LocalGlobal/Parcellations/MNI/Schaefer2018_100Parcels_7Networks_order.txt ...
 ...done. (0 seconds, 0 min)
Downloading data from https://raw.githubusercontent.com/ThomasYeoLab/CBIG/v0.14.3-Update_Yeo2011_Schaefer2018_labelname/stable_projects/brain_parcellation/Schaefer2018_LocalGlobal/Parcellations/MNI/Schaefer2018_100Parcels_7Networks_order_FSLMNI152_2mm.nii.gz ...
 ...done. (0 seconds, 0 min)
2023-10-17 10:31:26,824 - JUNIFER - INFO - Loading parcellation /home/runner/junifer/data/parcellations/schaefer_2018/Schaefer2018_100Parcels_7Networks_order_FSLMNI152_2mm.nii.gz
2023-10-17 10:31:28,465 - JUNIFER - INFO - No storage specified, returning dictionary
2023-10-17 10:31:28,465 - JUNIFER - INFO - Computing VBM_GM
2023-10-17 10:31:28,465 - JUNIFER - INFO - Fetching one of Schaefer parcellations.
2023-10-17 10:31:28,465 - JUNIFER - INFO - Parcellation parameters:
2023-10-17 10:31:28,465 - JUNIFER - INFO -      resolution: 2.0
2023-10-17 10:31:28,465 - JUNIFER - INFO -      n_rois: 100
2023-10-17 10:31:28,465 - JUNIFER - INFO -      yeo_networks: 7
2023-10-17 10:31:28,468 - JUNIFER - INFO - Loading parcellation /home/runner/junifer/data/parcellations/schaefer_2018/Schaefer2018_100Parcels_7Networks_order_FSLMNI152_2mm.nii.gz
2023-10-17 10:31:29,151 - JUNIFER - INFO - No storage specified, returning dictionary

Check the results

print(out.keys())
print(out["VBM_GM"]["data"].shape)  # Shape is (1 x parcels)

print(out.keys())
print(out["BOLD"]["data"].shape)  # Shape is (timepoints x parcels)

dict_keys(['BOLD', 'VBM_GM'])
(1, 100)
dict_keys(['BOLD', 'VBM_GM'])
(96, 100)