def get_data(download_folder):
"""get_data
:param download_folder: download destination folder for nifti gz files
:returns brainmaps: list of nii gz images
"""
all_collections = api.get_collections()
collections_with_dois = all_collections[np.logical_not(all_collections.DOI.isnull())]
group_collections = collections_with_dois[collections_with_dois.group_comparison != True]
images = api.get_images(collection_pks=list(group_collections.collection_id))
images = api.filter(df=images, column_name="is_thresholded", field_value=False)
images = api.filter(df=images, column_name="not_mni", field_value=False)
images = api.filter(df=images, column_name="modality", field_value="fMRI-BOLD")
api.download_images(dest_dir=download_folder, images_df=images, resample=False)
return glob("%s/original/*.nii.gz" % (download_folder))
def get_data(download_folder):
'''get_data
:param download_folder: download destination folder for nifti gz files
:returns brainmaps: list of nii gz images
'''
all_collections = api.get_collections()
collections_with_dois = all_collections[np.logical_not(
all_collections.DOI.isnull())]
group_collections = collections_with_dois[
collections_with_dois.group_comparison != True]
images = api.get_images(
collection_pks=list(group_collections.collection_id))
images = api.filter(df=images,
column_name="is_thresholded",
field_value=False)
images = api.filter(df=images, column_name="not_mni", field_value=False)
images = api.filter(df=images,
column_name="modality",
field_value="fMRI-BOLD")
api.download_images(dest_dir=download_folder,
images_df=images,
resample=False)
return glob("%s/original/*.nii.gz" % (download_folder))
images.cognitive_paradigm_cogatlas.isin(["None / Other", "rest eyes closed", "rest eyes open"]) == False
]
# Limit to Z and T maps (all are Z and T)
z = images[images.map_type == "Z map"]
t = images[images.map_type == "T map"]
# Remove tmaps that do not have # subjects defined
t_collections = collections[collections.collection_id.isin([int(x) for x in t.collection_id])]
to_keep = t_collections.collection_id[t_collections.number_of_subjects.isnull() == False]
t = t[t.collection_id.isin(to_keep)]
images = z.append(t)
# Download images
standard = os.path.abspath("mr/MNI152_T1_2mm_brain.nii.gz")
api.download_images(dest_dir=data, images_df=images, target=standard)
# For T images, convert to Z
tmaps = ["%s/resampled/%06d.nii.gz" % (data, x) for x in t.image_id.tolist()]
# Look up number of subjects, and calculate dofs
dofs = []
for row in t.iterrows():
dof = collections.number_of_subjects[collections.collection_id == int(row[1].collection_id)].tolist()[0] - 2
dofs.append(dof)
outfolder_z = "%s/resampled_z" % (data)
if not os.path.exists(outfolder_z):
os.mkdir(outfolder_z)
for tt in range(0, len(tmaps)):
from pyneurovault import api import numpy as np all_collections = api.get_collections() collections_with_dois = all_collections[np.logical_not(all_collections.DOI.isnull())] images = api.get_images(collection_pks=list(collections_with_dois.collection_id)) # Remove images that are thresholded images = api.filter(df=images,column_name="is_thresholded",field_value=False) # Not in MNI images = api.filter(df=images,column_name="not_mni",field_value=False) # Just fMRI bold images = api.filter(df=images,column_name="modality",field_value="fMRI-BOLD") # Download all images to file, resample to target outfolder = "/home/vanessa/Documents/Work/NEUROVAULT/mosaic" # If you don't want to resample api.download_images(dest_dir = outfolder,images_df=images,resample=False)
from pyneurovault import api
import pandas as pd
from nilearn.image import resample_img, smooth_img
import nibabel as nb
import numpy as np
from scipy.ndimage import binary_fill_holes
from scipy import stats
from scipy.ndimage.measurements import labeled_comprehension
import sys
atlas_id = sys.argv[2]
data_location = sys.argv[1]
atlases = api.get_images(pks=[atlas_id])
api.download_images(data_location + "/atlases", atlases, resample=False)
standard = "/usr/share/fsl/data/standard/MNI152_T1_2mm_brain.nii.gz"
get_ipython().system('mkdir -p ' + data_location + '/atlases/resampled')
fname = atlas_id + ".nii.gz"
print "resampling " + fname
nii = nb.load(data_location + "atlases/original/" + fname)
target_nii = nb.load(standard)
resampled_nii = resample_img(nii,
target_affine=target_nii.get_affine(),
target_shape=target_nii.shape,
interpolation='nearest')
resampled_nii.to_filename(data_location + "atlases/resampled/" + fname)
# We can't use Rest or other/none
images = images[images.cognitive_paradigm_cogatlas_id.isnull() == False]
images = images[images.cognitive_paradigm_cogatlas.isin(
["None / Other", "rest eyes closed", "rest eyes open"]) == False]
# Limit to Z and T maps (all are Z and T)
z = images[images.map_type == "Z map"]
t = images[images.map_type == "T map"]
# Remove tmaps that do not have # subjects defined
t = t[t.number_of_subjects.isnull() == False]
images = z.append(t)
# Download images
standard = os.path.abspath("%s/mr/MNI152_T1_2mm_brain.nii.gz" % (here))
api.download_images(dest_dir=data_directory, images_df=images, target=standard)
# For T images, convert to Z. NeuroVault outputs two folders - original and resampled
resampled_dir = "%s/resampled" % (data_directory)
# We need to select a subset of the images, just the T Maps from the set
tmaps = ["%s/%06d.nii.gz" % (resampled_dir, x) for x in t.image_id.tolist()]
# We need degrees of freedom to convert properly to Zstat maps.
dofs = []
for row in t.iterrows():
dof = row[1].number_of_subjects - 2
dofs.append(dof)
# We will move converted Z maps, and as is Z maps, to a common folder
outfolder_z = "%s/resampled_z" % (data_directory)
def download_combined_database(out_dir, overwrite=False):
"""
Download coordinates/annotations from brainspell and images/annotations
from Neurovault.
Currently, the largest barrier is the lack of links between experiments
(tables) in brainspell/NeuroSynth and those in NeuroVault. The closest we
have is overall papers, via DOIs.
Additional problems:
- Does NeuroVault have standard error maps?
- If so, I doubt there's any way to associate a given SE map and beta
map within a collection.
- How should space be handled?
- Should everything be resliced and transformed to the same space at
this stage or later on?
- How can we link a target template (for images) to a target space
(for coordinates)?
- Should we even allow custom targets? Maybe we just limit it to 2mm
and 1mm MNI templates.
Parameters
----------
out_dir : :obj:`str`
Folder in which to write out Dataset object and subfolders containing
images.
overwrite: :obj:`bool`, optional
Whether to overwrite existing database, if one exists in `out_dir`.
Defaults to False.
"""
# Download collections metadata from Neurovault
collections_file = op.join(out_dir, 'neurovault_collections.csv')
if overwrite or not op.isfile(collections_file):
colls_df = api.get_collections()
colls_df.to_csv(collections_file, index=False, encoding='utf-8')
else:
colls_df = pd.read_csv(collections_file, encoding='utf-8')
# Only include collections from published papers (or preprints)
papers_file = op.join(out_dir, 'neurovault_papers.csv')
if overwrite or not op.isfile(papers_file):
paper_df = colls_df.dropna(subset=['DOI'])
paper_df.to_csv(papers_file, index=False, encoding='utf-8')
else:
paper_df = pd.read_csv(papers_file, encoding='utf-8')
# Get metadata for individual images from valid collections
papers_metadata_file = op.join(out_dir, 'neurovault_papers_metadata.csv')
if overwrite or not op.isfile(papers_metadata_file):
valid_collections = sorted(paper_df['collection_id'].tolist())
# Sleep between get_images calls to avoid spamming Neurovault
image_dfs = []
for chunk in to_chunks(valid_collections, 500):
image_dfs.append(api.get_images(collection_pks=chunk))
time.sleep(10)
image_df = pd.concat(image_dfs)
image_df.to_csv(papers_metadata_file, index=False, encoding='utf-8')
else:
image_df = pd.read_csv(papers_metadata_file, encoding='utf-8')
# Reduce images database according to additional criteria
# Only keep unthresholded, MNI, group level fMRI maps
red_df = image_df.loc[image_df['modality'] == 'fMRI-BOLD']
red_df = red_df.loc[red_df['image_type'] == 'statistic_map']
red_df = red_df.loc[red_df['analysis_level'] == 'group']
red_df = red_df.loc[red_df['is_thresholded'] is False]
red_df = red_df.loc[red_df['not_mni'] is False]
# Look for relevant metadata
red_df = red_df.dropna(subset=['cognitive_paradigm_cogatlas'])
## MFX/FFX GLMs need contrast (beta) + standard error
mffx_df = red_df.loc[red_df['map_type'] == 'univariate-beta map']
## RFX GLMs need contrast (beta)
rfx_df = red_df.loc[red_df['map_type'] == 'univariate-beta map']
## Stouffer's, Stouffer's RFX, and Fisher's IBMAs can use Z maps.
# T and F maps can be transformed into Z maps, but T maps need sample size.
# Only keep test statistic maps
acc_map_types = ['Z map', 'T map', 'F map']
st_df = red_df.loc[red_df['map_type'].isin(acc_map_types)]
keep_idx = st_df['map_type'].isin(['Z map', 'F map'])
keep_idx2 = (st_df['map_type'] == 'T map') & ~pd.isnull(st_df['number_of_subjects'])
keep_idx = keep_idx | keep_idx2
st_df = st_df.loc[keep_idx]
## Weighted Stouffer's IBMAs need Z + sample size.
st_df['id_str'] = st_df['image_id'].astype(str).str.zfill(6)
if not op.isdir(out_dir):
mkdir(out_dir)
api.download_images(out_dir, red_df, target=None, resample=False)
elif overwrite:
# clear out out_dir
raise Exception('Currently not prepared to overwrite database.')
api.download_images(out_dir, red_df, target=None, resample=False)
from pyneurovault import api
import pandas as pd
from nilearn.image import resample_img, smooth_img
import nibabel as nb
import numpy as np
from scipy.ndimage import binary_fill_holes
from scipy import stats
from scipy.ndimage.measurements import labeled_comprehension
import sys
atlas_id = sys.argv[2]
data_location = sys.argv[1]
atlases = api.get_images(pks=[atlas_id])
api.download_images(data_location + "/atlases", atlases, resample=False)
standard = "/usr/share/fsl/data/standard/MNI152_T1_2mm_brain.nii.gz"
get_ipython().system('mkdir -p '+data_location+'/atlases/resampled')
fname = atlas_id+".nii.gz"
print "resampling " + fname
nii = nb.load(data_location+"atlases/original/" + fname)
target_nii = nb.load(standard)
resampled_nii = resample_img(nii,target_affine=target_nii.get_affine(),
target_shape=target_nii.shape, interpolation='nearest')
resampled_nii.to_filename(data_location+"atlases/resampled/" + fname)
def score_map(map_filename, atlas_data, labels):
map_data = nb.load(map_filename).get_data()
# Get a collection
collection = api.get_collections(pks=457)
# collection.collection_id is 457
# Get all images
images = api.get_images()
# Get all images meta data for a collection
images = api.get_images(collection_pks=457)
# Remove images that are thresholded
images = api.filter(df=images,column_name="is_thresholded",field_value=False)
# Not in MNI
images = api.filter(df=images,column_name="not_mni",field_value=False)
# Just fMRI bold
images = api.filter(df=images,column_name="modality",field_value="fMRI-BOLD")
# Download images, collections, or both
api.export_images_tsv("/home/vanessa/Desktop/images.tsv",images)
api.export_collections_tsv("/home/vanessa/Desktop/collections.tsv",collection)
# Download all images to file, resample to target
outfolder = "/home/vanessa/Desktop"
standard = "/usr/share/fsl/data/standard/MNI152_T1_2mm_brain.nii.gz"
api.download_images(dest_dir = outfolder,images_df=images,target=standard)
# If you don't want to resample
api.download_images(dest_dir = outfolder,images_df=images,resample=False)
