Note

Click here to download the full example code or to run this example in your browser via Binder

9.3.9. Decoding of a dataset after GLM fit for signal extraction

Full step-by-step example of fitting a GLM to perform a decoding experiment. We use the data from one subject of the Haxby dataset.

More specifically:

  1. Download the Haxby dataset.

  2. Extract the information to generate a glm representing the blocks of stimuli.

  3. Analyze the decoding performance using a classifier.

To run this example, you must launch IPython via ipython --matplotlib in a terminal, or use the Jupyter notebook.

9.3.9.1. Fetch example Haxby dataset

We download the Haxby dataset This is a study of visual object category representation

# By default 2nd subject will be fetched
import numpy as np
import pandas as pd
from nilearn import datasets
haxby_dataset = datasets.fetch_haxby()

# repetition has to be known
TR = 2.5

9.3.9.2. Load the behavioral data

# Load target information as string and give a numerical identifier to each
behavioral = pd.read_csv(haxby_dataset.session_target[0], sep=' ')
conditions = behavioral['labels'].values

# Record these as an array of sessions
sessions = behavioral['chunks'].values
unique_sessions = behavioral['chunks'].unique()

# fMRI data: a unique file for each session
func_filename = haxby_dataset.func[0]

9.3.9.3. Build a proper event structure for each session

events = {}
# events will take  the form of a dictionary of Dataframes, one per session
for session in unique_sessions:
    # get the condition label per session
    conditions_session = conditions[sessions == session]
    # get the number of scans per session, then the corresponding
    # vector of frame times
    n_scans = len(conditions_session)
    frame_times = TR * np.arange(n_scans)
    # each event last the full TR
    duration = TR * np.ones(n_scans)
    # Define the events object
    events_ = pd.DataFrame(
        {'onset': frame_times, 'trial_type': conditions_session, 'duration': duration})
    # remove the rest condition and insert into the dictionary
    events[session] = events_[events_.trial_type != 'rest']

9.3.9.4. Instantiate and run FirstLevelModel

We generate a list of z-maps together with their session and condition index

z_maps = []
conditions_label = []
session_label = []

# Instantiate the glm
from nilearn.glm.first_level import FirstLevelModel
glm = FirstLevelModel(t_r=TR,
                      mask_img=haxby_dataset.mask,
                      high_pass=.008,
                      smoothing_fwhm=4,
                      memory='nilearn_cache')

9.3.9.5. Run the glm on data from each session

events[session].trial_type.unique()
from nilearn.image import index_img
for session in unique_sessions:
    # grab the fmri data for that particular session
    fmri_session = index_img(func_filename, sessions == session)

    # fit the glm
    glm.fit(fmri_session, events=events[session])

    # set up contrasts: one per condition
    conditions = events[session].trial_type.unique()
    for condition_ in conditions:
        z_maps.append(glm.compute_contrast(condition_))
        conditions_label.append(condition_)
        session_label.append(session)

Out:

________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef63913d0>, <nibabel.nifti1.Nifti1Image object at 0x7fbef8f5bd00>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.0s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[-0.114769, ..., -2.149296],
       ...,
       [ 2.367151, ...,  0.779998]], dtype=float32),
array([[0., ..., 1.],
       ...,
       [0., ..., 1.]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.2s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.256013, ...,  0.308334]), <nibabel.nifti1.Nifti1Image object at 0x7fbef8f5bd00>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.038572, ...,  0.855077]), <nibabel.nifti1.Nifti1Image object at 0x7fbef8f5bd00>)
___________________________________________________________unmask - 0.2s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.070285, ..., -1.222001]), <nibabel.nifti1.Nifti1Image object at 0x7fbef8f5bd00>)
___________________________________________________________unmask - 0.2s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.1724  , ...,  0.033508]), <nibabel.nifti1.Nifti1Image object at 0x7fbef8f5bd00>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-2.96724 , ..., -1.474856]), <nibabel.nifti1.Nifti1Image object at 0x7fbef8f5bd00>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.432136, ..., -1.197805]), <nibabel.nifti1.Nifti1Image object at 0x7fbef8f5bd00>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.420626, ..., -0.443207]), <nibabel.nifti1.Nifti1Image object at 0x7fbef8f5bd00>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([1.310409, ..., 0.196496]), <nibabel.nifti1.Nifti1Image object at 0x7fbef8f5bd00>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef4d22ac0>, <nibabel.nifti1.Nifti1Image object at 0x7fbef63913d0>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[ 12.660587, ..., -13.536042],
       ...,
       [ -3.254408, ..., -33.842804]], dtype=float32),
array([[0., ..., 1.],
       ...,
       [0., ..., 1.]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.2s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.705774, ..., -0.934083]), <nibabel.nifti1.Nifti1Image object at 0x7fbef63913d0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.476069, ..., -1.29404 ]), <nibabel.nifti1.Nifti1Image object at 0x7fbef63913d0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.210752, ..., -1.441079]), <nibabel.nifti1.Nifti1Image object at 0x7fbef63913d0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-2.341707, ...,  2.094528]), <nibabel.nifti1.Nifti1Image object at 0x7fbef63913d0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.097247, ..., -0.496306]), <nibabel.nifti1.Nifti1Image object at 0x7fbef63913d0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.118812, ...,  1.58503 ]), <nibabel.nifti1.Nifti1Image object at 0x7fbef63913d0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.801345, ..., -1.648133]), <nibabel.nifti1.Nifti1Image object at 0x7fbef63913d0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.621172, ..., -0.678871]), <nibabel.nifti1.Nifti1Image object at 0x7fbef63913d0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef6905160>, <nibabel.nifti1.Nifti1Image object at 0x7fbef68ea550>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.0s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[ 5.205584, ..., 26.587189],
       ...,
       [-6.836576, ..., 10.676956]], dtype=float32),
array([[0., ..., 1.],
       ...,
       [0., ..., 1.]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.3s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 1.733742, ..., -0.435687]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68ea550>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([1.502666, ..., 1.789333]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68ea550>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.690828, ...,  0.731519]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68ea550>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-2.403789, ...,  0.257657]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68ea550>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.472767, ..., -1.160892]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68ea550>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-2.07507 , ..., -2.203006]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68ea550>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.445359, ..., -0.36161 ]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68ea550>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.034083, ..., 0.35299 ]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68ea550>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef68f6be0>, <nibabel.nifti1.Nifti1Image object at 0x7fbef11a7bb0>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[-2.026206, ...,  5.974948],
       ...,
       [ 2.616334, ...,  0.104535]], dtype=float32),
array([[0., ..., 1.],
       ...,
       [0., ..., 1.]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.3s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.596132, ..., -1.910225]), <nibabel.nifti1.Nifti1Image object at 0x7fbef11a7bb0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.217544, ..., -0.003551]), <nibabel.nifti1.Nifti1Image object at 0x7fbef11a7bb0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.337751, ..., 0.789979]), <nibabel.nifti1.Nifti1Image object at 0x7fbef11a7bb0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.161412, ..., -0.265537]), <nibabel.nifti1.Nifti1Image object at 0x7fbef11a7bb0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 1.538844, ..., -0.797649]), <nibabel.nifti1.Nifti1Image object at 0x7fbef11a7bb0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.589617, ..., -0.790328]), <nibabel.nifti1.Nifti1Image object at 0x7fbef11a7bb0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.306331, ..., -0.003053]), <nibabel.nifti1.Nifti1Image object at 0x7fbef11a7bb0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.20477 , ..., -0.804061]), <nibabel.nifti1.Nifti1Image object at 0x7fbef11a7bb0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef4f466d0>, <nibabel.nifti1.Nifti1Image object at 0x7fbef473df40>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[ 53.033577, ..., -55.45955 ],
       ...,
       [-51.57195 , ..., -55.994713]], dtype=float32),
array([[0., ..., 1.],
       ...,
       [0., ..., 1.]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.2s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.161983, ..., -0.068078]), <nibabel.nifti1.Nifti1Image object at 0x7fbef473df40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.467058, ..., -0.494102]), <nibabel.nifti1.Nifti1Image object at 0x7fbef473df40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.008358, ..., 0.250096]), <nibabel.nifti1.Nifti1Image object at 0x7fbef473df40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 1.127065, ..., -0.241985]), <nibabel.nifti1.Nifti1Image object at 0x7fbef473df40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.066426, ..., 0.493324]), <nibabel.nifti1.Nifti1Image object at 0x7fbef473df40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.049242, ..., -1.008997]), <nibabel.nifti1.Nifti1Image object at 0x7fbef473df40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.336253, ..., -0.596381]), <nibabel.nifti1.Nifti1Image object at 0x7fbef473df40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.707037, ..., 1.358865]), <nibabel.nifti1.Nifti1Image object at 0x7fbef473df40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef4f3cbe0>, <nibabel.nifti1.Nifti1Image object at 0x7fbef68d47f0>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[-27.150482, ...,  -5.81308 ],
       ...,
       [-30.204891, ...,   7.417917]], dtype=float32),
array([[0., ..., 1.],
       ...,
       [0., ..., 1.]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.2s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.197916, ...,  1.581644]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68d47f0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-2.576467, ...,  0.392603]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68d47f0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.969252, ...,  1.15444 ]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68d47f0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.716041, ...,  1.094486]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68d47f0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.280537, ...,  0.542739]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68d47f0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.331329, ..., -0.019244]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68d47f0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.298501, ..., -0.355821]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68d47f0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.232015, ..., -0.420629]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68d47f0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef2590340>, <nibabel.nifti1.Nifti1Image object at 0x7fbef4720be0>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[129.51173 , ..., -15.279282],
       ...,
       [-18.911755, ...,  21.839058]], dtype=float32),
array([[0., ..., 1.],
       ...,
       [0., ..., 1.]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.2s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.490124, ..., -0.665442]), <nibabel.nifti1.Nifti1Image object at 0x7fbef4720be0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.374685, ..., -0.980248]), <nibabel.nifti1.Nifti1Image object at 0x7fbef4720be0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 1.654133, ..., -0.288692]), <nibabel.nifti1.Nifti1Image object at 0x7fbef4720be0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 1.244312, ..., -1.462072]), <nibabel.nifti1.Nifti1Image object at 0x7fbef4720be0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.665202, ...,  1.793466]), <nibabel.nifti1.Nifti1Image object at 0x7fbef4720be0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.036326, ..., 0.693956]), <nibabel.nifti1.Nifti1Image object at 0x7fbef4720be0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.672634, ..., -0.24818 ]), <nibabel.nifti1.Nifti1Image object at 0x7fbef4720be0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.099764, ..., -1.722951]), <nibabel.nifti1.Nifti1Image object at 0x7fbef4720be0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef4f3b2b0>, <nibabel.nifti1.Nifti1Image object at 0x7fbef94f0f40>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[-15.915996, ...,  22.07737 ],
       ...,
       [-16.981215, ...,   3.372383]], dtype=float32),
array([[ 0.      , ...,  1.      ],
       ...,
       [-0.259023, ...,  1.      ]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.2s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.033872, ..., -0.317176]), <nibabel.nifti1.Nifti1Image object at 0x7fbef94f0f40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.98478 , ..., -0.770334]), <nibabel.nifti1.Nifti1Image object at 0x7fbef94f0f40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([1.127461, ..., 0.929068]), <nibabel.nifti1.Nifti1Image object at 0x7fbef94f0f40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.489347, ..., -0.230229]), <nibabel.nifti1.Nifti1Image object at 0x7fbef94f0f40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.673052, ...,  0.6757  ]), <nibabel.nifti1.Nifti1Image object at 0x7fbef94f0f40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.260282, ..., -0.346342]), <nibabel.nifti1.Nifti1Image object at 0x7fbef94f0f40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([1.775541, ..., 1.603123]), <nibabel.nifti1.Nifti1Image object at 0x7fbef94f0f40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([3.391727, ..., 0.653312]), <nibabel.nifti1.Nifti1Image object at 0x7fbef94f0f40>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef638eee0>, <nibabel.nifti1.Nifti1Image object at 0x7fbef47176a0>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[-0.292987, ..., 18.392956],
       ...,
       [-3.935719, ...,  0.602484]], dtype=float32),
array([[ 0.      , ...,  1.      ],
       ...,
       [-0.259023, ...,  1.      ]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.4s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.620911, ...,  2.309993]), <nibabel.nifti1.Nifti1Image object at 0x7fbef47176a0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.44548 , ..., 0.576334]), <nibabel.nifti1.Nifti1Image object at 0x7fbef47176a0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.483355, ..., -0.068969]), <nibabel.nifti1.Nifti1Image object at 0x7fbef47176a0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.166576, ..., 0.713549]), <nibabel.nifti1.Nifti1Image object at 0x7fbef47176a0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.612744, ..., 1.441012]), <nibabel.nifti1.Nifti1Image object at 0x7fbef47176a0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.254934, ..., -1.288018]), <nibabel.nifti1.Nifti1Image object at 0x7fbef47176a0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.134169, ..., -0.621367]), <nibabel.nifti1.Nifti1Image object at 0x7fbef47176a0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.234171, ..., -1.497943]), <nibabel.nifti1.Nifti1Image object at 0x7fbef47176a0>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef8fda730>, <nibabel.nifti1.Nifti1Image object at 0x7fbef2590e50>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[-5.223948, ..., -5.959582],
       ...,
       [-7.677519, ..., 16.024363]], dtype=float32),
array([[0., ..., 1.],
       ...,
       [0., ..., 1.]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.3s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.01344 , ...,  1.283233]), <nibabel.nifti1.Nifti1Image object at 0x7fbef2590e50>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([1.79114 , ..., 1.031069]), <nibabel.nifti1.Nifti1Image object at 0x7fbef2590e50>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([1.583575, ..., 0.488828]), <nibabel.nifti1.Nifti1Image object at 0x7fbef2590e50>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.265741, ..., -0.623721]), <nibabel.nifti1.Nifti1Image object at 0x7fbef2590e50>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.20672, ...,  1.09668]), <nibabel.nifti1.Nifti1Image object at 0x7fbef2590e50>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-2.045178, ...,  0.822339]), <nibabel.nifti1.Nifti1Image object at 0x7fbef2590e50>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-2.463833, ..., -0.151504]), <nibabel.nifti1.Nifti1Image object at 0x7fbef2590e50>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.230311, ...,  0.198537]), <nibabel.nifti1.Nifti1Image object at 0x7fbef2590e50>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef3c8c280>, <nibabel.nifti1.Nifti1Image object at 0x7fbef82ad700>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[-19.66533 , ...,  -6.299562],
       ...,
       [-24.647343, ...,   2.331865]], dtype=float32),
array([[0., ..., 1.],
       ...,
       [0., ..., 1.]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.3s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.080165, ..., -3.497239]), <nibabel.nifti1.Nifti1Image object at 0x7fbef82ad700>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-3.083184, ..., -3.071235]), <nibabel.nifti1.Nifti1Image object at 0x7fbef82ad700>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.724401, ..., -2.892927]), <nibabel.nifti1.Nifti1Image object at 0x7fbef82ad700>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.044506, ..., 0.285176]), <nibabel.nifti1.Nifti1Image object at 0x7fbef82ad700>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([1.257372, ..., 1.802962]), <nibabel.nifti1.Nifti1Image object at 0x7fbef82ad700>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.485481, ...,  0.284696]), <nibabel.nifti1.Nifti1Image object at 0x7fbef82ad700>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.032135, ..., -1.290339]), <nibabel.nifti1.Nifti1Image object at 0x7fbef82ad700>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.417132, ..., -1.258094]), <nibabel.nifti1.Nifti1Image object at 0x7fbef82ad700>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.input_data.nifti_masker.filter_and_mask...
filter_and_mask(<nibabel.nifti1.Nifti1Image object at 0x7fbef4d30460>, <nibabel.nifti1.Nifti1Image object at 0x7fbef68e1070>, { 'detrend': False,
  'dtype': None,
  'high_pass': None,
  'high_variance_confounds': False,
  'low_pass': None,
  'reports': True,
  'runs': None,
  'smoothing_fwhm': 4,
  'standardize': False,
  'standardize_confounds': True,
  't_r': 2.5,
  'target_affine': None,
  'target_shape': None}, memory_level=1, memory=Memory(location=nilearn_cache/joblib), verbose=0, confounds=None, sample_mask=None, copy=True, dtype=None)
__________________________________________________filter_and_mask - 1.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.glm.first_level.first_level.run_glm...
run_glm(array([[-1.095605, ..., 16.449202],
       ...,
       [ 2.59974 , ..., -2.179998]], dtype=float32),
array([[0., ..., 1.],
       ...,
       [0., ..., 1.]]), noise_model='ar1', bins=100, n_jobs=1)
__________________________________________________________run_glm - 1.2s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.545625, ..., -1.041515]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68e1070>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.152042, ..., 1.145641]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68e1070>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([1.55236 , ..., 0.696758]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68e1070>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.684509, ...,  0.226524]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68e1070>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([ 0.423531, ..., -0.641954]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68e1070>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([0.726779, ..., 0.687642]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68e1070>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-0.809306, ...,  0.496974]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68e1070>)
___________________________________________________________unmask - 0.1s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.masking.unmask...
unmask(array([-1.116436, ..., -0.811166]), <nibabel.nifti1.Nifti1Image object at 0x7fbef68e1070>)
___________________________________________________________unmask - 0.1s, 0.0min

9.3.9.6. Generating a report

Since we have already computed the FirstLevelModel and have the contrast, we can quickly create a summary report.

from nilearn.image import mean_img
from nilearn.reporting import make_glm_report
mean_img_ = mean_img(func_filename)
report = make_glm_report(glm,
                         contrasts=conditions,
                         bg_img=mean_img_,
                         )

report  # This report can be viewed in a notebook

Statistical Report for bottle, cat, chair, face, house, scissors, scrambledpix, shoe

First Level Model

Model details:

drift_modelcosine
drift_order1
fir_delays[0]
high_pass (Hz)0.008
hrf_modelglover
noise_modelar1
scaling_axis0
signal_scalingTrue
slice_time_ref0
smoothing_fwhm4
standardizeFalse
subject_labelNone
t_r (s)2.5
target_affineNone
target_shapeNone

Design Matrix:

Plot of Design Matrix used in Session 1.

Contrasts

Plot of the contrast: bottle.Plot of the contrast: house.Plot of the contrast: chair.Plot of the contrast: scrambledpix.Plot of the contrast: face.Plot of the contrast: shoe.Plot of the contrast: cat.Plot of the contrast: scissors.

Mask

Model did not supply a mask image.

Stat Maps with Cluster Tables

bottle

Stat map plot for the contrast: bottle
Contrast Plot Plot of the contrast: bottle.

Cluster Table
Height controlfpr
α0.001
Threshold (computed)3.3
Cluster size threshold (voxels)0
Minimum distance (mm)8

Cluster IDXYZPeak StatCluster Size (mm3)
1-36.75-46.88-46.886.61147
2-54.2513.125.626.4798
3-1.75-39.3813.126.45196
4-57.75-39.389.386.17246
5-40.25-35.62-35.626.12393
633.25-43.12-43.126.111722
6a22.75-35.62-43.125.78
6b15.75-46.88-39.384.33
6c12.25-46.88-46.884.11
7-19.25-24.38-43.125.99492
7a-19.25-31.88-39.385.47
829.75-20.62-24.385.98393
9-43.7528.12-9.385.96196
108.75-50.62-35.625.88492
1119.25-54.38-43.125.781476
11a12.25-58.12-28.125.44
11b8.75-58.12-39.384.44
1240.2516.88-20.625.7349
1322.75-46.88-61.885.70492
13a22.75-58.12-61.885.38
1426.25-46.88-46.885.69147
15-1.75-50.62-39.385.66147
16-26.25-16.88-24.385.64147
1712.25-28.12-73.125.60246
18-50.7535.62-16.885.58246
19-33.25-73.1231.885.5649
20-15.75-28.12-43.125.5549
2119.25-76.88-13.125.50492
22-12.25-24.38-76.885.46196
23-47.25-13.1213.125.4298
2426.25-20.62-13.125.41344
25-29.759.38-28.125.38246
26-57.75-16.881.885.3498
2722.75-43.129.385.33246
28-47.25-61.88-5.625.2998
29-40.25-39.3831.885.27344
29a-29.75-39.3831.884.36
30-19.25-50.62-39.385.26147
31-12.255.62-16.885.2549
32-29.75-43.12-50.625.24393
338.75-91.885.625.2449
341.7550.62-16.885.19344
35-50.75-50.6220.625.17147
3643.75-50.62-5.625.17935
36a47.25-43.12-1.884.41
36b50.75-50.62-5.624.15
3726.259.38-16.885.16196
385.25-76.8824.385.1549
39-29.75-84.381.885.1449
4026.25-69.38-16.885.14246
41-54.25-31.88-13.125.1449
42-47.25-9.385.625.10295
4333.255.62-13.125.10246
44-40.2524.38-9.385.0849
4512.25-84.38-28.125.0798
46-29.75-80.62-24.385.0549
47-54.25-46.88-5.625.0298
4826.2531.88-31.885.02147
4912.25-13.12-28.125.0298
5029.751.88-9.385.0198
51-47.25-39.38-20.625.01885
51a-50.75-39.38-9.384.50
52-19.25-58.12-9.385.00196
5333.2520.62-20.625.0098
545.25-61.88-20.624.97295
55-33.2513.1228.124.93246
56-47.25-28.1213.124.90147
571.75-43.12-1.884.9049
58-22.75-58.12-46.884.89147
59-15.75-76.8828.124.88196
6033.259.38-24.384.8898
61-61.25-5.6220.624.87147
62-40.25-20.62-31.884.8749
63-50.7516.88-1.884.86147
64-15.75-50.62-1.884.8649
6540.25-35.62-24.384.862067
65a43.75-28.12-9.384.70
65b40.25-20.62-13.124.57
65c47.25-35.62-20.624.13
6622.75-20.62-35.624.8498
6736.7528.12-35.624.8449
68-15.7516.8843.124.82147
69-43.7550.6216.884.8249
7012.25-65.62-24.384.81246
71-47.25-28.125.624.8198
721.75-58.12-24.384.8098
7329.75-50.62-50.624.77196
7419.25-43.12-20.624.7598
7536.75-65.62-13.124.75344
76-1.75-58.12-54.384.7349
7719.2535.6228.124.7249
78-40.25-61.88-16.884.70295
79-22.751.88-1.884.6949
8022.75-16.88-9.384.6998
8133.2531.88-9.384.6998
82-8.75-46.88-65.624.68246
835.25-73.1216.884.67344
83a-1.75-65.6216.883.95
8422.75-20.62-28.124.67295
84a12.25-20.62-31.884.46
85-15.75-1.88-69.384.6549
86-47.2535.6216.884.65196
8712.2520.6235.624.6449
88-26.25-20.62-13.124.6498
89-29.7513.12-13.124.63147
90-15.75-31.88-61.884.6349
91-47.25-54.38-9.384.62344
9250.7543.12-5.624.6149
9340.2531.8813.124.5949
9412.25-54.38-46.884.5998
95-15.75-39.38-50.624.5849
96-5.25-31.8858.124.5749
97-1.7558.1213.124.5749
9822.75-35.6254.384.57246
99-12.25-58.12-16.884.5649
100-12.25-13.12-46.884.55246
101-19.25-76.88-28.124.55147
1028.75-20.62-13.124.55147
1031.75-76.8835.624.5549
104-36.75-76.881.884.55246
105-61.25-20.6213.124.5449
106-1.75-9.38-20.624.5449
107-5.25-13.12-69.384.5349
108-57.75-9.389.384.53295
108a-61.25-1.889.384.20
109-47.25-28.1243.124.5249
110-47.2516.885.624.5298
1118.75-16.8846.884.5249
112-12.25-58.12-46.884.5249
113-36.7543.1224.384.5198
114-22.75-76.88-16.884.5149
115-29.75-58.12-9.384.5149
1161.7513.129.384.5049
11715.75-1.88-16.884.50196
11833.25-9.38-58.124.5098
11950.75-5.625.624.4949
12033.25-50.62-20.624.49246
121-50.759.38-16.884.48196
12240.2535.62-1.884.4849
1238.75-50.62-20.624.4849
124-1.75-46.881.884.4698
125-47.2520.62-13.124.4649
12615.759.3843.124.4698
127-40.25-65.62-5.624.4549
128-15.759.38-20.624.4598
12912.25-9.3813.124.4549
13050.751.8843.124.4498
131-26.25-54.3846.884.4398
132-15.75-76.8820.624.4349
133-50.75-16.8824.384.4249
134-50.75-5.62-5.624.4249
13540.255.62-24.384.4249
136-50.759.389.384.4149
137-50.7516.88-13.124.41147
138-40.259.38-28.124.41147
13919.25-1.8828.124.3849
14033.2524.3839.384.3849
141-15.7524.38-9.384.3849
14222.75-61.88-46.884.38147
143-40.25-46.881.884.38147
144-12.2554.38-9.384.3798
14526.2528.12-20.624.3798
14657.7535.6228.124.3798
1475.25-88.12-1.884.3749
148-15.7513.1250.624.3698
149-36.7528.1231.884.36246
15068.25-13.12-9.384.36246
150a68.25-1.88-9.384.29
1511.75-5.62-13.124.3549
152-47.25-24.38-16.884.3598
153-26.2513.1246.884.3549
1545.25-35.62-58.124.3598
15536.75-73.125.624.3498
156-33.25-9.38-13.124.34344
157-15.75-9.3828.124.34295
158-19.25-54.38-61.884.33196
159-8.755.62-24.384.3349
16019.25-35.6269.384.3249
161-29.75-80.62-9.384.3249
16219.25-9.3820.624.3249
163-1.75-1.881.884.32196
164-15.75-54.3843.124.3149
165-40.25-28.12-20.624.3149
16619.25-31.8816.884.3149
16715.75-1.88-1.884.3149
168-15.75-16.8824.384.3098
169-36.7558.1235.624.2949
17012.25-80.6213.124.29147
171-1.75-24.389.384.2949
172-1.75-54.38-9.384.2898
173-43.7543.12-28.124.2898
1745.25-58.12-54.384.2849
17554.25-24.38-5.624.28344
176-57.75-31.88-5.624.2849
17715.7550.6258.124.2798
17836.75-61.88-5.624.2749
17933.25-50.62-28.124.2749
180-5.2531.88-20.624.26147
18115.75-35.6231.884.2698
182-47.25-65.621.884.26196
183-54.25-20.62-24.384.2549
18426.25-80.62-9.384.2549
18522.7516.885.624.24147
1865.25-65.62-13.124.23196
187-47.2524.3820.624.2398
188-47.25-58.1213.124.2398
18940.259.38-20.624.2398
19019.2528.1231.884.2349
19112.2550.62-1.884.2398
19247.25-54.38-16.884.2349
19312.2561.885.624.2249
19419.25-9.385.624.2249
195-57.75-31.8824.384.2298
196-19.25-20.62-35.624.2198
19719.25-84.38-20.624.2149
19812.2543.12-16.884.2149
199-1.75-9.38-46.884.2149
20015.75-24.38-35.624.21246
201-5.25-24.38-20.624.20147
202-1.75-50.62-1.884.2049
20315.75-73.12-31.884.2049
204-47.25-28.1228.124.2049
20536.75-31.88-9.384.20246
20612.255.6243.124.1949
207-1.7576.885.624.1949
208-29.7520.62-24.384.1849
20947.25-54.38-1.884.1849
2101.75-5.62-54.384.1849
21140.25-58.125.624.1798
21226.255.6216.884.17246
21319.25-5.6243.124.1798
214-22.75-69.38-13.124.16196
215-1.75-58.12-28.124.1698
21619.2565.629.384.1698
217-61.25-16.889.384.1649
21836.7543.12-28.124.1549
219-1.75-39.381.884.1598
22012.251.8828.124.15147
221-15.75-20.62-58.124.1549
22229.75-28.12-24.384.1549
22319.2516.8828.124.1549
22440.25-35.62-43.124.1549
225-22.75-50.6254.384.1549
226-22.7516.885.624.1549
2275.25-80.62-1.884.1449
228-36.7520.6235.624.14246
229-26.25-73.12-35.624.1498
230-43.7524.38-1.884.1498
231-8.759.3824.384.13196
2328.7520.62-24.384.13147
233-57.755.6213.124.1398
23426.25-5.62-1.884.1249
235-54.251.8813.124.1249
236-33.25-31.88-65.624.1298
237-8.75-46.88-31.884.1249
238-1.75-50.62-24.384.12147
239-12.2554.3854.384.1198
240-47.2546.8820.624.1149
241-15.75-1.8816.884.1049
242-29.7524.3813.124.1098
243-57.75-46.88-1.884.10246
244-50.75-20.629.384.1098
24519.25-13.1228.124.1049
24622.7546.88-16.884.1049
24719.25-39.38-13.124.0949
248-19.2565.6239.384.0949
249-1.75-9.38-5.624.0949
250-8.75-39.38-31.884.0849
251-40.25-16.88-50.624.0849
252-43.75-39.38-16.884.07147
25319.2513.12-1.884.0798
25422.755.62-1.884.0749
255-8.75-39.38-39.384.06442
255a-12.25-46.88-43.123.77
256-19.2561.885.624.0649
25754.25-20.6239.384.0649
25854.25-9.3820.624.06147
25922.75-69.381.884.06147
260-19.25-5.62-24.384.04393
261-1.751.8813.124.0449
262-40.2516.8824.384.0398
26333.255.6228.124.0349
264-36.7543.121.884.02147
26519.25-69.38-13.124.0249
26612.25-9.385.624.0249
26712.25-88.125.624.0298
268-26.25-76.8835.624.0249
269-47.25-43.129.384.02147
270-50.7539.389.384.0249
27133.25-24.38-13.124.0149
27240.25-43.12-28.124.0149
27329.75-24.38-16.884.0149
27426.25-20.62-65.624.0098
275-43.7520.6220.624.0049
276-15.75-73.12-13.124.0049
277-1.7513.12-20.623.9998
27857.75-39.385.623.9949
279-29.75-65.62-20.623.9949
280-19.25-50.6216.883.9949
2815.25-61.88-46.883.9849
28222.7531.889.383.9849
283-19.25-65.62-20.623.9849
28415.75-16.88-58.123.9849
28519.25-13.12-28.123.9898
286-47.25-13.12-54.383.9798
287-47.25-39.3816.883.9749
2881.75-1.8831.883.9798
28936.75-39.38-69.383.9749
290-1.75-35.62-61.883.9698
291-8.7539.385.623.9649
29226.2520.62-24.383.9698
293-5.25-84.38-20.623.9649
2948.7576.8835.623.95147
295-22.7531.88-24.383.9549
296-26.2546.885.623.95147
297-22.75-9.3813.123.9549
298-33.2513.1213.123.9498
2995.25-43.12-9.383.9449
300-47.25-13.1235.623.9349
301-68.25-24.381.883.93147
302-8.75-54.38-31.883.9349
303-54.25-28.12-16.883.9249
30450.75-54.38-9.383.9249
30568.25-31.889.383.91196
30612.25-1.88-69.383.9198
30719.2516.8816.883.91147
308-33.25-16.88-5.623.9149
3095.25-28.12-9.383.9149
310-5.2546.8854.383.9098
311-43.7516.8858.123.9049
312-33.251.88-16.883.90147
31315.7588.129.383.9098
3145.25-65.6254.383.90147
315-64.75-13.12-24.383.9049
31629.75-43.12-58.123.9049
3171.75-43.12-16.883.90295
317a12.25-39.38-13.123.81
318-47.25-58.12-28.123.9049
31933.255.6235.623.8998
32050.75-13.125.623.8949
32119.25-24.3816.883.8949
322-33.25-69.3839.383.8949
32315.75-73.12-20.623.8949
32464.75-43.125.623.8949
32515.75-46.8820.623.8849
326-36.75-31.88-46.883.8849
327-12.25-20.62-61.883.8849
328-15.75-73.1239.383.8898
329-43.7550.6228.123.8749
33012.25-13.1231.883.8798
33119.25-84.3824.383.8749
332-5.25-46.88-16.883.87147
333-8.75-65.62-43.123.8749
3341.75-58.129.383.8749
335-47.251.88-28.123.8749
3368.7546.88-5.623.8749
33726.25-80.621.883.8749
338-33.2535.62-24.383.8698
339-19.25-13.1261.883.8649
34012.25-35.6273.123.8698
34143.7531.885.623.8649
342-57.751.88-13.123.8698
3438.7513.1250.623.8598
344-26.255.62-13.123.8549
3458.75-24.389.383.8549
346-12.25-20.62-46.883.8549
347-26.251.8843.123.8598
34812.2524.3861.883.8549
349-47.25-61.8820.623.8549
35019.25-58.12-13.123.8549
351-22.75-5.62-1.883.8549
35226.25-61.8831.883.8549
353-29.7535.62-9.383.8549
35447.2513.12-20.623.8549
3551.75-9.38-50.623.8549
356-15.75-50.62-31.883.84196
357-12.25-31.88-50.623.84196
35850.7550.62-1.883.8449
35929.75-50.6254.383.83147
36061.251.8824.383.8349
3611.75-31.881.883.8249
36236.75-54.38-20.623.8249
36326.25-16.88-58.123.8249
364-15.75-46.88-5.623.8149
36547.2520.625.623.8149
36622.75-28.1269.383.8198
36740.25-20.6220.623.8149
368-43.75-65.6224.383.8149
369-19.25-61.8820.623.8149
37015.7516.88-16.883.8049
37129.75-31.8839.383.80147
372-12.2546.8828.123.8049
37312.2569.385.623.8049
37415.75-20.62-20.623.8049
37522.75-24.381.883.7949
376-29.75-20.62-69.383.7949
377-47.25-1.88-20.623.7949
37843.75-69.38-1.883.7949
3795.25-28.1273.123.7949
38019.2535.621.883.7898
38147.2513.125.623.7898
382-15.75-5.6261.883.7898
383-8.7584.3820.623.77147
38426.2524.3813.123.7798
38519.25-9.38-5.623.7749
38615.75-16.885.623.7749
387-1.75-28.1258.123.7649
388-29.75-1.88-1.883.7549
38926.251.8813.123.7549
39029.75-58.12-46.883.7449
391-40.2535.6231.883.7449
39236.7550.621.883.7498
393-1.7580.621.883.7449
394-57.75-9.3816.883.74147
39540.25-9.38-31.883.7449
3961.7524.3831.883.7349
39733.2543.1235.623.7349
39843.759.38-39.383.7349
39926.2513.129.383.7349
40033.25-9.38-9.383.7349
40140.25-28.12-1.883.7349
40222.75-76.88-35.623.7398
403-8.75-46.88-24.383.7349
4041.75-20.62-35.623.7349
40519.2554.381.883.7349
406-26.25-31.8816.883.7249
40747.2531.88-24.383.7249
408-54.2513.1220.623.72147
409-33.25-43.12-61.883.7249
41019.25-16.8816.883.7249
411-19.25-84.381.883.7249
41247.2516.88-39.383.7249
41340.25-31.8854.383.7198
41461.25-31.8839.383.7149
415-54.25-24.38-39.383.7149
41626.25-20.6265.623.7149
41736.75-73.12-9.383.7149
41829.75-1.88-20.623.7149
41915.75-31.88-50.623.7149
420-15.755.6265.623.7149
4211.759.38-16.883.7049
422-22.75-20.62-31.883.7049
4238.75-73.1235.623.7049
42436.75-54.38-28.123.7049
42543.75-39.38-1.883.7049
426-33.25-35.62-9.383.7049
427-50.7528.1246.883.6949
428-15.75-43.121.883.6949
429-1.75-43.12-31.883.6998
43050.75-16.8828.123.6849
431-15.7520.62-43.123.6898
43243.75-5.62-13.123.6849
43329.75-16.88-61.883.6849
43457.75-20.6228.123.6849
435-47.2546.8828.123.6849
43615.75-20.6273.123.6849
4371.7565.62-16.883.6898
438-22.7513.12-24.383.6749
439-33.2516.8850.623.6798
440-15.75-43.12-43.123.6798
441-12.25-9.38-24.383.6749
442-1.7520.62-16.883.6798
443-26.25-28.12-31.883.6749
444-15.75-69.3828.123.6649
445-47.259.38-9.383.6649
446-15.75-1.88-31.883.6649
447-29.75-1.88-24.383.6698
44826.251.88-13.123.6649
44933.25-24.38-58.123.6649
450-40.25-58.129.383.6698
4511.7520.62-39.383.6598
45247.2516.8839.383.6549
453-26.25-35.6254.383.6549
45422.75-16.8843.123.6549
45512.2524.38-39.383.6549
456-1.75-16.88-28.123.6449
45733.25-39.38-58.123.6449
45826.25-20.6220.623.6449
45919.255.62-13.123.6449
46033.2543.1224.383.6349
46119.25-9.3835.623.6349
462-54.25-20.62-9.383.6349
463-5.25-39.385.623.6349
46422.75-54.3861.883.6249
46519.25-35.62-20.623.62147
466-22.75-80.621.883.6249
46740.25-35.6250.623.6249
46822.75-1.885.623.6249
46943.75-69.389.383.6198
47033.25-58.12-16.883.6149
4718.75-65.6220.623.6149
47226.25-9.3813.123.6198
4731.7565.62-9.383.6149
474-12.2588.1216.883.6149
475-47.2561.881.883.6149
476-26.2513.1213.123.6149
477-33.25-1.8813.123.6149
478-8.75-61.88-46.883.6149
47940.2528.12-39.383.6149
48043.7524.38-5.623.6149
481-50.75-58.121.883.6149
48226.25-76.88-16.883.6049
483-1.75-9.38-28.123.6049
484-5.25-54.38-54.383.6049
485-47.25-9.3843.123.6049
486-22.7543.12-28.123.5949
487-36.75-16.88-46.883.5949
48819.25-31.88-16.883.5849
48947.2539.3813.123.5898
49029.7516.8835.623.5849
49122.7546.8813.123.5849
492-29.75-80.6220.623.5849
49368.25-28.1216.883.5749
494-19.2543.12-1.883.5749
49519.25-24.38-39.383.5749
496-8.75-9.38-20.623.5749
49726.25-80.62-28.123.5749
49815.7520.6243.123.5649
49919.25-46.8831.883.5649
50022.7573.125.623.5649
50150.75-43.129.383.5649
502-57.75-24.385.623.5649
503-1.75-9.3831.883.5649
504-15.75-50.6239.383.5649
505-57.7539.3816.883.5698
50612.25-9.3850.623.5649
507-12.25-13.12-73.123.5598
508-26.25-61.8831.883.5549
509-33.2539.3854.383.5549
51054.251.8835.623.5549
51129.75-31.88-31.883.5549
512-33.2565.6220.623.5549
513-54.25-9.38-5.623.5498
51436.7550.62-16.883.5449
51515.7528.12-39.383.5449
5161.75-1.88-20.623.5349
51712.25-65.621.883.5349
51829.7565.6243.123.5349
51947.25-35.6216.883.5349
520-40.25-50.6228.123.5349
52133.25-28.1265.623.5349
5225.255.62-69.383.5349
52326.25-58.12-13.123.5349
524-1.75-1.88-5.623.5249
525-1.75-46.88-65.623.5249
52612.25-54.38-54.383.5249
527-5.2543.12-16.883.5249
52812.25-9.38-24.383.5249
529-50.75-1.8816.883.5249
53012.25-35.629.383.5249
53136.7535.6216.883.52147
53219.2520.6220.623.5249
533-15.75-69.38-43.123.5249
534-33.25-58.12-1.883.5249
535-40.25-69.3831.883.5249
536-54.25-13.1213.123.5198
5378.7528.12-24.383.5149
53836.75-24.38-31.883.5049
539-36.75-13.129.383.5049
540-54.25-20.62-50.623.5049
54136.7520.6231.883.5049
5428.75-76.889.383.5049
543-47.25-24.38-5.623.4949
544-5.25-61.8820.623.4949
545-36.7561.889.383.4949
54615.7576.8835.623.4949
547-50.75-16.88-13.123.4998
5485.25-73.12-16.883.4949
54915.7528.12-5.623.4949
55019.25-28.12-24.383.4949
55119.25-50.62-73.123.4949
552-36.7535.62-13.123.4949
5531.75-16.88-24.383.4949
554-29.7535.62-1.883.4849
55512.25-84.38-5.623.4849
55633.25-35.62-5.623.4849
55750.7539.38-9.383.4849
55822.75-5.6220.623.4849
559-50.7546.889.383.4898
56054.251.88-31.883.4849
56122.75-9.38-50.623.4849
56240.25-31.88-58.123.4849
56340.25-76.88-9.383.4749
564-36.75-31.8820.623.4749
56536.751.8820.623.4749
56640.25-9.381.883.4749
56722.7513.1235.623.4798
56833.255.6250.623.4749
569-50.755.62-9.383.4749
57040.25-35.62-1.883.4749
571-50.75-9.38-13.123.4649
572-29.7524.385.623.4649
573-26.25-35.62-9.383.4649
574-15.75-16.88-28.123.4698
575-47.25-50.625.623.4649
576-36.75-69.385.623.4649
57726.25-65.6246.883.4549
57822.755.625.623.4598
57919.25-5.6213.123.4549
580-5.259.389.383.4598
581-33.251.8831.883.4549
582-19.25-50.62-46.883.4549
583-1.75-16.88-58.123.4549
58436.7524.38-13.123.4549
585-1.75-35.62-13.123.4549
586-15.759.3835.623.45147
587-43.75-35.62-9.383.4549
58822.75-9.3843.123.4549
58933.2550.6224.383.4549
5901.75-65.62-43.123.4549
591-29.7516.88-5.623.4449
59243.75-31.88-39.383.4449
59326.259.3824.383.4449
594-54.2524.3824.383.4449
59543.751.88-1.883.4449
59629.75-16.8858.123.4449
59754.25-16.881.883.4498
598-36.75-69.3813.123.4449
599-5.25-43.1269.383.4449
60015.75-50.629.383.4349
601-26.25-31.88-58.123.4349
60215.751.8835.623.4349
603-29.75-43.1258.123.4349
604-1.7543.12-20.623.4349
605-19.25-65.629.383.4349
60612.25-35.62-61.883.4349
607-33.25-9.38-46.883.4349
608-1.75-16.8824.383.4349
60947.2528.12-39.383.4349
610-36.7516.881.883.4349
61147.25-9.385.623.4249
612-19.251.8858.123.4249
613-26.25-24.38-5.623.4249
61436.75-31.8813.123.4249
61512.2550.629.383.4249
6168.75-50.62-5.623.4149
617-33.25-35.6246.883.4149
61819.2543.12-5.623.4149
61912.25-1.8824.383.4149
62022.7539.3820.623.4049
621-1.75-39.38-16.883.4049
622-15.75-1.881.883.4049
623-54.25-16.88-5.623.4049
6241.75-84.38-16.883.4049
625-47.2543.129.383.4049
6265.25-9.38-20.623.4049
627-57.751.8820.623.4049
628-43.7513.1216.883.4098
6295.2580.6231.883.4049
630-64.75-35.62-1.883.4049
631-1.75-43.12-9.383.4049
632-54.25-9.3820.623.4049
6331.75-69.3846.883.4049
634-12.25-5.62-20.623.3949
635-8.7543.1224.383.3949
63612.25-9.3843.123.3949
63712.25-35.62-16.883.3949
63850.75-16.8835.623.3949
639-5.251.88-58.123.3949
64012.25-35.6265.623.3949
64133.25-13.1265.623.3849
64219.25-69.3820.623.3849
64319.25-31.88-54.383.3849
64429.75-39.38-54.383.3849
645-54.25-35.62-5.623.3749
646-47.25-16.88-24.383.3749
647-36.759.3854.383.3749
64850.75-50.629.383.3749
649-26.25-5.6265.623.3749
650-33.25-39.38-28.123.3649
65133.2543.12-16.883.3649
65243.75-58.12-1.883.3649
653-47.2516.88-24.383.3649
654-19.2558.1239.383.3649
655-40.25-5.6235.623.3649
656-36.7561.8816.883.3649
657-1.75-28.1220.623.3598
658-8.75-54.389.383.3549
65912.25-69.385.623.3549
660-19.25-43.1231.883.3598
661-1.75-76.881.883.3549
66233.25-20.62-9.383.3549
663-12.2520.6273.123.3549
664-8.7513.12-13.123.3549
66561.25-35.6235.623.3549
66643.75-9.3846.883.3449
6671.7528.12-5.623.3449
66847.255.62-1.883.3498
66915.75-5.6228.123.3449
67015.75-13.12-73.123.3449
67154.251.889.383.3449
67222.759.3846.883.3449
67340.25-5.62-9.383.3349
67461.255.6231.883.3349
67529.75-1.88-54.383.3349
6761.75-9.38-16.883.3349
67719.25-13.1273.123.3349
678-12.2516.8820.623.3349
67915.7546.8846.883.3349
680-43.75-61.889.383.3349
68147.25-20.6220.623.3349
682-5.25-61.8854.383.3349
683-1.75-69.38-13.123.3249
68450.75-20.62-43.123.3249
68554.25-39.38-24.383.3249
68629.75-43.12-20.623.3249
687-12.25-76.88-9.383.3249
688-15.7520.6220.623.3249
689-33.259.3816.883.3249
690-29.759.3861.883.3149
69140.2513.12-46.883.3149
6921.75-58.12-13.123.3149
6931.751.88-16.883.3149
69412.25-50.6239.383.3149
695-36.755.62-9.383.3149
69626.2516.88-20.623.3149
69712.25-61.8816.883.3149
69822.75-50.6235.623.3149
69919.25-46.88-5.623.3149
70012.25-50.62-1.883.3049
701-12.25-16.88-65.623.3049
702-19.2524.3831.883.3049
70347.255.6231.883.3049
7045.2546.8813.123.3049
705-22.75-28.1231.883.3049
70633.25-76.88-28.123.3049
70722.7520.6216.883.2949
7085.25-16.88-20.623.2949
709-54.25-46.8813.123.2949

house

Stat map plot for the contrast: house
Contrast Plot Plot of the contrast: house.

Cluster Table
Height controlfpr
α0.001
Threshold (computed)3.3
Cluster size threshold (voxels)0
Minimum distance (mm)8

Cluster IDXYZPeak StatCluster Size (mm3)
122.7520.629.385.62639
2-22.7524.3813.125.01147
347.25-54.38-16.885.0098
422.75-5.6220.624.9949
522.7513.1220.624.8898
6-15.7524.389.384.79639
733.2528.1228.124.6498
8-22.75-39.38-1.884.59246
8a-22.75-28.12-1.884.38
912.2524.3820.624.57147
10-29.7528.125.624.5649
11-22.7516.885.624.3998
121.7531.88-13.124.3349
13-22.755.6224.384.29147
1419.25-16.8824.384.2898
15-15.75-35.62-1.884.2598
1619.255.6243.124.2598
17-12.25-43.12-50.624.2549
188.75-24.3824.384.2149
19-50.759.38-28.124.2049
20-33.25-24.3835.624.1949
21-12.25-16.88-20.624.1849
22-8.7535.6243.124.1649
23-22.7539.3846.884.15147
2426.25-24.38-69.384.1449
251.7513.12-16.884.1449
2650.7550.62-1.884.1449
2722.75-31.881.884.1149
28-12.2513.121.884.1198
29-15.7520.6220.624.1049
308.75-9.3831.884.0998
31-12.25-28.12-76.884.0949
32-15.75-46.8820.624.0898
3326.25-61.8831.884.0549
3436.75-54.38-20.624.0149
3515.75-54.385.624.0049
36-12.251.88-61.884.0098
37-33.25-58.1235.623.9949
38-54.25-20.62-9.383.9749
39-26.259.3820.623.9798
40-15.7520.621.883.9649
4115.75-28.1224.383.9249
4215.75-39.3813.123.9249
4322.75-16.8816.883.9149
4422.7516.885.623.9049
4533.25-43.12-35.623.8949
46-29.7516.889.383.8949
478.75-16.8831.883.8949
48-40.25-58.1228.123.8949
4926.259.38-31.883.8749
5043.75-1.8820.623.8649
5122.75-43.12-31.883.8449
52-22.7520.6220.623.8398
5322.75-43.129.383.8349
54-15.7531.885.623.8349
5536.75-13.12-31.883.8349
56-54.25-13.12-1.883.8249
575.25-20.62-13.123.8249
58-29.75-31.8835.623.8149
5926.2513.1213.123.7949
60-26.2513.1216.883.7849
6133.255.62-39.383.7549
625.25-65.6254.383.7349
63-15.75-20.62-28.123.7349
6426.25-1.8813.123.7249
65-15.7558.125.623.7249
6626.255.629.383.7249
67-15.75-50.6224.383.7149
6840.2531.88-24.383.7149
6950.75-31.88-50.623.7049
70-8.751.8828.123.6898
7133.2554.3828.123.6749
72-47.25-76.889.383.6749
7333.2513.12-5.623.6649
748.7520.6220.623.6549
75-33.25-73.12-31.883.6498
7612.25-31.88-73.123.6349
775.2531.8850.623.6349
78-12.25-39.3846.883.6349
79-19.2561.8820.623.6249
8040.25-39.3813.123.6249
8140.25-13.12-43.123.6249
82-22.75-24.3846.883.6149
83-33.259.385.623.6149
8433.25-76.88-24.383.6049
8529.75-50.62-39.383.6049
86-19.2531.8820.623.6049
87-1.75-61.88-39.383.6049
8815.75-1.88-16.883.5949
89-33.2513.12-1.883.5849
9026.259.38-24.383.5749
91-36.75-39.38-46.883.5749
928.7543.12-5.623.5649
938.75-61.88-50.623.5649
94-5.2539.38-20.623.5698
9522.75-13.1220.623.5649
9640.25-50.62-54.383.5698
97-1.75-58.12-28.123.5549
98-43.75-9.3839.383.5549
9933.2528.12-46.883.5449
100-15.7531.8824.383.5449
10157.75-54.381.883.5349
102-40.25-1.8824.383.5249
10333.259.381.883.5249
1041.75-46.88-5.623.5249
10522.75-39.3846.883.5249
106-26.251.8813.123.5149
107-12.25-5.62-13.123.5198
108-36.75-65.62-16.883.5149
109-26.25-50.62-46.883.5149
11026.25-73.1231.883.5049
11126.25-13.1254.383.5049
11215.75-50.629.383.5049
113-36.7524.3813.123.5049
114-33.2561.8839.383.5049
11519.25-73.12-16.883.4998
116-40.25-69.3820.623.4949
117-12.25-43.12-16.883.4849
11864.751.8835.623.4849
11922.75-76.8820.623.4749
120-22.75-9.38-65.623.4749
121-50.7531.889.383.4749
122-8.75-24.381.883.4449
12319.25-58.1220.623.4449
12450.7513.129.383.4349
12557.75-16.8816.883.4349
126-64.75-5.6228.123.4349
127-15.75-24.38-9.383.4349
12843.7520.6216.883.4349
129-64.75-24.38-20.623.4249
1305.25-43.12-1.883.4249
1311.7554.38-9.383.4249
132-8.75-46.88-31.883.4249
133-8.75-28.125.623.4249
134-15.75-61.8843.123.4249
13529.751.8813.123.4249
13636.7528.1239.383.4149
13750.75-43.12-1.883.4149
13829.75-65.62-24.383.4149
13922.75-9.3813.123.4149
14036.75-50.62-24.383.4049
14136.75-61.88-13.123.4049
142-15.75-31.88-50.623.4049
143-40.25-28.12-24.383.4049
144-40.25-46.8839.383.4049
14522.75-73.12-13.123.3949
14622.75-9.3835.623.3949
14722.75-65.6220.623.3949
14829.75-16.8846.883.3949
149-26.2520.62-1.883.3849
15015.75-1.8869.383.3849
151-22.75-58.1224.383.3749
15257.7516.88-1.883.3749
153-40.2524.3835.623.3749
15426.255.62-28.123.3649
155-15.7516.8813.123.3549
15612.251.8828.123.3549
157-5.2528.1213.123.3549
15815.7524.38-13.123.3449
159-8.7528.1228.123.3449
160-12.25-58.12-46.883.3449
161-12.25-65.62-39.383.3449
16219.2524.385.623.3449
163-22.75-16.8824.383.3349
164-12.2543.1246.883.3349
165-15.75-69.3846.883.3349
16626.25-16.88-9.383.3249
167-26.25-31.88-69.383.3249
16826.25-50.62-35.623.3249
169-36.75-24.381.883.3249
17019.25-35.621.883.3249
17136.7520.62-13.123.3149
1728.75-80.62-5.623.3149
17312.25-5.62-5.623.3049
174-40.2550.621.883.3049
175-15.75-28.12-5.623.2949
17629.75-54.38-24.383.2949

chair

Stat map plot for the contrast: chair
Contrast Plot Plot of the contrast: chair.

Cluster Table
Height controlfpr
α0.001
Threshold (computed)3.3
Cluster size threshold (voxels)0
Minimum distance (mm)8

Cluster IDXYZPeak StatCluster Size (mm3)
140.25-46.8813.124.86147
2-36.75-76.881.884.2349
312.2535.62-5.624.2049
4-50.7539.3816.884.1749
5-50.75-39.38-1.883.94147
6-54.25-43.1246.883.9049
733.25-58.12-1.883.8949
8-29.75-43.12-58.123.8849
9-36.75-61.8843.123.8449
1019.2520.6220.623.8149
1112.255.62-24.383.7798
1222.7524.3816.883.7649
1333.2543.12-16.883.7549
1426.25-46.88-35.623.7549
1526.2516.8816.883.7349
16-15.75-1.88-16.883.7049
17-5.2543.1250.623.6749
1833.2513.12-1.883.6649
19-57.75-9.38-1.883.6249
20-22.75-31.88-69.383.6149
21-22.7524.3813.123.5749
22-57.7513.121.883.5249
2333.25-58.12-16.883.5049
24-29.7520.6246.883.4849
2512.2516.88-20.623.4449
2633.2528.12-31.883.4349
2736.75-24.3820.623.4349
2843.75-28.12-13.123.4049
2929.7513.12-43.123.3949
3012.2528.12-16.883.3849
31-22.75-43.12-31.883.3749
32-1.755.6231.883.3749
3333.259.38-13.123.3649
3433.25-20.62-58.123.3549
35-15.75-35.62-24.383.3449
3629.75-43.12-35.623.3449
37-22.759.3824.383.3449
38-36.75-46.88-54.383.3349
391.7528.12-35.623.3249
4036.75-28.12-9.383.2949

scrambledpix

Stat map plot for the contrast: scrambledpix
Contrast Plot Plot of the contrast: scrambledpix.

Cluster Table
Height controlfpr
α0.001
Threshold (computed)3.3
Cluster size threshold (voxels)0
Minimum distance (mm)8

Cluster IDXYZPeak StatCluster Size (mm3)
11.7524.38-13.125.7449
2-22.75-46.8843.124.8298
3-15.7561.88-9.384.79147
4-29.75-61.88-31.884.6549
550.7516.88-28.124.14147
6-22.75-54.38-9.383.9449
75.2543.12-28.123.9249
8-22.75-9.3820.623.8249
940.25-16.88-39.383.8049
10-64.75-31.8839.383.7849
11-26.25-69.3839.383.5949
1222.75-24.3846.883.5649
1322.7546.88-5.623.5449
14-1.755.6231.883.5349
15-40.25-16.88-54.383.4649
1633.2535.62-28.123.4449
17-15.75-43.12-16.883.4149
1826.25-24.38-69.383.4049
191.7513.1231.883.3449
2033.25-20.6243.123.3349

face

Stat map plot for the contrast: face
Contrast Plot Plot of the contrast: face.

Cluster Table
Height controlfpr
α0.001
Threshold (computed)3.3
Cluster size threshold (voxels)0
Minimum distance (mm)8

Cluster IDXYZPeak StatCluster Size (mm3)
11.7524.38-13.125.1798
2-50.75-50.6213.125.09196
2a-47.25-58.1213.123.37
3-47.25-43.12-35.624.7449
468.25-13.12-9.384.74147
5-47.25-39.3816.884.4798
629.75-46.8835.624.4049
729.75-54.3846.884.3849
8-33.2550.6216.884.37147
9-57.75-16.881.884.37147
10-36.7531.8816.884.2298
11-12.25-58.12-16.884.2249
12-26.2524.38-13.124.16147
13-40.2546.8813.124.1498
1422.75-50.62-24.384.1149
15-22.7539.3813.124.0949
1640.2528.1239.383.9898
17-15.7513.1273.123.9798
185.2520.6265.623.9549
195.25-24.38-20.623.9349
20-47.25-50.6220.623.8849
2143.7535.6235.623.8398
22-47.25-28.1228.123.80147
23-1.7531.8861.883.7998
24-54.25-43.1220.623.7749
25-8.7513.1265.623.7749
261.75-43.12-1.883.7549
27-8.75-46.88-31.883.7349
28-47.25-61.88-5.623.7249
29-19.25-73.1239.383.7249
30-26.25-88.12-9.383.7198
3112.2528.1261.883.7149
32-50.75-35.6243.123.7049
33-36.75-43.1239.383.70147
34-47.2524.3820.623.6949
35-36.75-31.88-46.883.6949
36-47.25-54.38-9.383.6949
3740.2543.1216.883.6949
38-57.75-9.38-1.883.6749
39-57.7531.8831.883.6749
405.25-58.12-24.383.6698
41-36.7531.8835.623.65147
4233.25-46.88-39.383.6449
43-43.75-31.8835.623.6249
44-40.25-43.12-16.883.6049
45-12.25-76.8828.123.6049
46-8.75-28.1261.883.5849
4719.25-16.8839.383.5649
4826.25-43.1235.623.5649
4943.75-54.389.383.5349
5019.25-46.88-20.623.5349
51-29.7531.88-9.383.5249
5240.25-39.38-24.383.5149
5336.7561.8828.123.5149
54-15.75-73.1216.883.5049
558.75-1.889.383.5049
56-47.25-46.8816.883.4949
57-22.75-46.88-50.623.4949
5822.7531.8828.123.4949
5912.25-58.12-20.623.4849
605.25-65.6213.123.4849
61-47.25-16.88-35.623.4849
62-19.25-61.88-9.383.4749
63-15.75-13.1224.383.4798
64-26.25-43.12-43.123.4749
65-12.25-39.3858.123.4649
66-1.7539.38-20.623.4649
6726.25-43.12-31.883.4649
6833.25-61.88-13.123.4549
695.2531.88-35.623.4549
70-40.2550.6220.623.4349
71-40.25-35.62-35.623.4349
72-50.75-28.1235.623.4249
7315.75-54.38-20.623.4149
7436.75-43.125.623.4049
75-33.2539.3854.383.3949
76-15.75-54.3850.623.3849
7729.75-35.6235.623.3849
78-43.75-39.38-9.383.3649
79-29.7528.1213.123.3549
80-1.75-20.6224.383.3549
81-40.2520.6254.383.3549
8233.25-58.12-16.883.3449
83-47.25-31.885.623.3449
8457.75-35.6243.123.3349
85-29.7528.1239.383.3249
86-47.25-46.88-31.883.3249
8726.25-54.38-20.623.3249
88-33.2531.8846.883.3249
89-8.75-58.12-43.123.3049
90-33.25-58.1220.623.2949

shoe

Stat map plot for the contrast: shoe
Contrast Plot Plot of the contrast: shoe.

Cluster Table
Height controlfpr
α0.001
Threshold (computed)3.3
Cluster size threshold (voxels)0
Minimum distance (mm)8

Cluster IDXYZPeak StatCluster Size (mm3)
122.75-9.3835.624.7449
261.2524.3831.884.22147
336.7546.88-16.883.9549
450.75-35.62-35.623.8349
522.75-69.38-28.123.8249
619.25-20.62-28.123.8149
719.2573.1220.623.7649
8-54.25-65.6216.883.7049
9-19.2520.6243.123.6949
10-47.25-16.88-24.383.6649
11-1.75-28.12-73.123.6549
1219.25-28.12-54.383.5949
1315.75-24.38-73.123.5749
14-68.25-20.6224.383.5649
15-68.25-9.389.383.5349
1626.25-46.88-24.383.5249
17-1.75-20.6224.383.5249
1815.7516.8858.123.4549
1936.7528.1239.383.4549
2033.259.3861.883.4349
21-12.251.88-69.383.3749
2226.25-61.8813.123.3649
23-29.759.3835.623.3649
241.75-24.38-39.383.3649
25-12.2539.3865.623.3649
2612.255.6231.883.3349
2764.75-1.8831.883.3249
2826.2535.6228.123.3049

cat

Stat map plot for the contrast: cat
Contrast Plot Plot of the contrast: cat.

Cluster Table
Height controlfpr
α0.001
Threshold (computed)3.3
Cluster size threshold (voxels)0
Minimum distance (mm)8

Cluster IDXYZPeak StatCluster Size (mm3)
1-12.25-76.8831.884.6898
243.75-5.6216.884.53196
3-15.75-20.62-58.124.4598
4-40.25-65.6213.124.3649
51.7535.62-13.124.2949
6-12.25-58.12-16.884.2749
75.25-61.88-24.384.2798
843.755.621.884.26344
9-1.7550.62-9.384.25246
105.25-24.38-73.124.2249
1122.75-61.88-54.384.0449
1215.75-16.8846.884.0249
1336.759.38-35.623.9949
1419.25-31.88-69.383.9849
1522.75-24.38-58.123.9849
16-64.75-9.38-24.383.9849
1736.7569.385.623.9198
1812.25-61.88-31.883.8698
191.7528.12-35.623.8549
2047.251.88-46.883.8249
218.75-65.62-24.383.8249
22-29.7539.3854.383.8149
2315.75-31.88-61.883.7649
245.25-80.629.383.7549
2543.7524.389.383.7249
2640.25-5.62-5.623.7049
2750.7528.1224.383.7049
2822.75-58.12-61.883.7049
29-40.25-46.8816.883.6649
305.2543.1250.623.6349
31-12.25-73.12-31.883.6249
32-26.25-80.6213.123.5798
3350.751.88-24.383.5749
34-54.25-46.885.623.5798
35-40.25-69.3835.623.5349
3636.7528.12-20.623.5349
378.7516.88-16.883.5349
385.2520.6250.623.5349
39-47.25-31.88-43.123.5249
40-40.25-5.6250.623.5049
41-5.25-50.62-13.123.5049
42-29.75-46.885.623.4849
4329.751.88-31.883.4749
44-8.75-35.62-24.383.4449
4561.25-31.8843.123.4449
465.25-31.88-69.383.4349
47-22.7565.6239.383.4298
4836.7528.1243.123.38147
49-8.75-46.88-28.123.3649
5012.25-39.38-31.883.3649
51-8.75-28.12-61.883.3549
5261.25-31.8820.623.3549
53-40.25-31.88-58.123.3449
5440.25-20.62-39.383.3249
555.25-73.12-20.623.3249
56-29.75-20.62-35.623.3249
5715.7539.38-20.623.3149
58-36.75-50.62-39.383.3149
59-47.25-43.1243.123.3149
6026.25-65.6213.123.3049

scissors

Stat map plot for the contrast: scissors
Contrast Plot Plot of the contrast: scissors.

Cluster Table
Height controlfpr
α0.001
Threshold (computed)3.3
Cluster size threshold (voxels)0
Minimum distance (mm)8

Cluster IDXYZPeak StatCluster Size (mm3)
1-50.7520.62-24.386.551132
2-19.2584.3820.626.201476
2a-26.2580.6216.884.90
2b-15.7576.8831.884.42
3-26.2524.3828.125.83147
436.7520.62-31.885.58246
529.755.62-5.625.3298
6-12.2520.62-46.885.25344
712.25-35.62-69.385.1498
815.7576.8828.125.0549
95.2524.38-46.885.04393
10-12.2576.8820.625.02935
10a-5.2584.381.884.38
10b-5.2584.3820.624.38
10c-5.2580.6213.124.22
11-1.751.88-61.885.02295
12-19.2561.8850.625.0049
1312.2513.12-43.124.9849
1433.255.62-46.884.9249
151.75-28.12-61.884.8849
16-54.25-39.38-31.884.7949
17-22.75-54.38-50.624.66295
1812.25-61.88-46.884.5649
1912.2580.62-5.624.4949
2036.7528.12-35.624.46295
21-26.25-13.121.884.4549
22-15.75-43.12-46.884.4298
23-29.7520.62-46.884.4198
24-12.259.38-58.124.4198
2526.25-46.881.884.3649
26-5.2580.6231.884.32196
2715.75-35.62-73.124.3249
2850.7524.38-35.624.3098
2940.25-58.12-5.624.2698
30-19.2531.88-35.624.26147
3112.2513.12-50.624.26344
32-40.2569.3813.124.2549
3347.2524.38-1.884.2349
341.751.8831.884.22147
351.7513.12-16.884.2049
361.75-1.88-76.884.2098
37-40.25-9.38-5.624.1749
3815.7588.1216.884.16147
39-12.251.88-28.124.1549
4015.75-16.8846.884.1549
4147.2524.389.384.1449
42-5.25-9.3831.884.1349
4340.2528.12-43.124.1249
441.7576.8816.884.11196
4550.7531.88-31.884.1049
461.75-5.62-80.624.0898
471.75-28.12-76.884.0749
48-54.259.38-16.884.0549
4950.7520.62-1.884.0549
50-40.2561.885.624.0549
51-26.25-24.3820.624.0449
52-47.25-5.62-28.124.0349
53-50.75-9.38-20.624.03196
54-22.75-5.62-20.624.0149
55-5.25-28.12-76.884.0149
5654.255.6250.624.0198
5740.255.6231.884.0049
5829.7576.8813.123.9849
5922.75-54.38-43.123.9849
60-26.25-1.88-9.383.9698
6150.7550.6220.623.9349
62-12.2588.129.383.9149
63-36.75-1.88-20.623.91147
64-29.75-69.389.383.9198
6547.25-1.8820.623.90147
6619.25-16.88-54.383.9049
6757.75-24.385.623.8949
68-19.2550.6213.123.8849
6933.2524.38-43.123.8898
7012.2580.6235.623.8798
71-26.25-80.62-5.623.8649
72-26.2531.88-39.383.8649
73-68.25-5.625.623.8698
74-36.7565.6220.623.8598
75-40.25-16.88-65.623.8549
7622.75-58.12-50.623.8549
7719.2580.621.883.8598
78-5.251.88-76.883.8549
7912.25-61.889.383.8449
80-36.7569.3816.883.8349
8115.7550.62-9.383.8349
8233.25-35.62-35.623.8349
8322.75-1.889.383.8349
84-5.255.62-69.383.8249
855.2513.1231.883.8298
86-33.25-65.62-16.883.8249
87-5.25-16.88-39.383.8049
8822.7543.12-9.383.8049
89-50.75-13.125.623.8049
9043.75-61.885.623.7849
9119.25-1.88-1.883.7649
9222.75-35.62-9.383.7549
9312.2524.38-35.623.7598
94-8.7524.38-35.623.7449
95-40.2543.12-31.883.7449
9640.25-24.38-35.623.7349
97-8.7516.88-43.123.7249
9815.7588.129.383.7298
9929.75-1.8824.383.7249
10054.251.8843.123.7049
1011.7565.6246.883.7049
10222.75-20.62-5.623.7049
10329.7558.12-16.883.6949
104-1.7573.1235.623.6949
10540.25-39.3858.123.6849
10626.25-50.62-54.383.6849
107-8.7528.1254.383.68196
108-22.75-39.38-54.383.6749
109-1.75-35.62-65.623.6698
1101.7539.38-16.883.6549
1118.75-9.38-76.883.6549
11233.25-5.62-1.883.6498
113-1.7528.12-39.383.6449
1141.7580.6224.383.6298
11519.25-46.88-35.623.6249
1161.75-9.381.883.6149
117-47.2524.3820.623.6149
11836.7524.38-28.123.6049
11922.75-43.12-61.883.5949
120-22.7558.12-20.623.5998
12143.75-31.88-13.123.5749
122-22.7554.38-13.123.5549
1231.75-5.62-20.623.5449
124-22.7539.3831.883.5449
125-29.7531.88-9.383.5349
12657.7516.8816.883.5349
12715.75-76.88-16.883.5249
12815.7546.88-20.623.5249
12933.25-39.3824.383.5249
130-43.75-24.3835.623.5249
131-12.2565.62-9.383.5249
132-33.2539.3854.383.5149
133-26.2516.8828.123.5149
13429.75-1.8813.123.5049
13512.251.88-69.383.5049
13619.2554.3850.623.4949
1378.7576.8816.883.4949
138-26.25-28.1231.883.4949
13929.75-9.389.383.4849
14022.7558.12-5.623.4849
141-19.25-20.62-1.883.4849
142-12.25-43.12-13.123.4849
143-26.2565.6235.623.4849
14415.7576.8820.623.4798
145-5.25-1.88-28.123.4749
146-33.2569.3824.383.4698
147-19.25-5.6216.883.4649
148-26.2561.88-5.623.4649
149-22.7569.3835.623.4649
15029.75-46.88-61.883.4649
151-8.7520.6231.883.4549
15233.2524.3861.883.4549
15340.25-1.8861.883.4498
154-33.2543.12-13.123.4449
15554.2535.6235.623.4449
15622.75-20.6220.623.4449
157-19.2531.88-28.123.4349
158-61.25-46.889.383.4349
15919.2516.88-46.883.4349
160-1.75-46.88-1.883.4349
16143.75-9.38-16.883.4349
16257.75-31.8846.883.4249
163-19.25-1.88-35.623.4249
16422.7520.6224.383.4249
165-19.259.38-35.623.4249
166-22.7520.62-46.883.4149
167-57.75-5.62-1.883.4149
168-5.2539.3858.123.4049
169-47.25-16.88-13.123.4049
170-29.75-13.12-35.623.4049
17133.25-39.38-43.123.4049
1721.7535.62-24.383.4049
17329.759.3816.883.3949
17415.75-28.12-54.383.3849
17522.75-39.3813.123.3849
17629.75-20.62-5.623.3849
17740.25-43.12-5.623.3749
17833.25-39.38-20.623.3749
179-26.259.3820.623.3749
18050.75-16.88-13.123.3649
181-26.2543.12-28.123.3649
18215.75-39.3824.383.3649
183-12.251.889.383.3549
18426.25-16.88-35.623.3549
18533.255.6216.883.3549
186-19.25-1.88-9.383.3549
18715.75-50.6246.883.3549
188-57.75-9.38-13.123.3549
189-15.75-65.625.623.3549
19015.755.629.383.3549
19129.75-1.881.883.3549
1928.751.8824.383.3549
193-33.2528.12-39.383.3449
19426.251.8824.383.3449
195-22.75-88.12-1.883.3449
196-29.75-16.88-1.883.3449
19733.25-31.88-43.123.3449
198-1.75-13.1231.883.3349
19940.2513.12-39.383.3349
20033.25-20.6243.123.3349
20122.75-9.38-5.623.3249
20229.75-1.8850.623.3249
2035.25-1.885.623.3249
204-12.25-50.62-50.623.3149
205-15.751.8828.123.3149
206-33.2573.129.383.3149
2071.75-1.88-24.383.3149
20829.75-50.62-50.623.3049
2098.7516.88-39.383.3049
210-19.25-20.62-20.623.3049
21126.2513.12-39.383.3049
21250.75-16.8846.883.3049
21329.7554.38-5.623.2949

Built using Nilearn. Source code on GitHub. File bugs & feature requests here.


In a jupyter notebook, the report will be automatically inserted, as above. We have several other ways to access the report:

# report.save_as_html('report.html')
# report.open_in_browser()

9.3.9.7. Build the decoding pipeline

To define the decoding pipeline we use Decoder object, we choose :

  • a prediction model, here a Support Vector Classifier, with a linear kernel

  • the mask to use, here a ventral temporal ROI in the visual cortex

  • although it usually helps to decode better, z-maps time series don’t need to be rescaled to a 0 mean, variance of 1 so we use standardize=False.

  • we use univariate feature selection to reduce the dimension of the problem keeping only 5% of voxels which are most informative.

  • a cross-validation scheme, here we use LeaveOneGroupOut cross-validation on the sessions which corresponds to a leave-one-session-out

We fit directly this pipeline on the Niimgs outputs of the GLM, with corresponding conditions labels and session labels (for the cross validation).

from nilearn.decoding import Decoder
from sklearn.model_selection import LeaveOneGroupOut
decoder = Decoder(estimator='svc', mask=haxby_dataset.mask, standardize=False,
                  screening_percentile=5, cv=LeaveOneGroupOut())
decoder.fit(z_maps, conditions_label, groups=session_label)

# Return the corresponding mean prediction accuracy compared to chance

classification_accuracy = np.mean(list(decoder.cv_scores_.values()))
chance_level = 1. / len(np.unique(conditions))
print('Classification accuracy: {:.4f} / Chance level: {}'.format(
    classification_accuracy, chance_level))

Out:

Classification accuracy: 0.6890 / Chance level: 0.125

Total running time of the script: ( 2 minutes 38.379 seconds)

Gallery generated by Sphinx-Gallery