def parcellate_voronoi_vol(mask, nb_parcels, seeds=None):
"""
Produce a parcellation from a Voronoi diagram built on random seeds.
The number of seeds is equal to the nb of parcels.
Seed are randomly placed within the mask, expect on edge positions
Args:
- mask (numpy.ndarray): binary 3D array of valid position to parcellate
- nb_parcels (int): the required number of parcels
- seeds: TODO
Return:
- the parcellation (numpy.ndarray): a 3D array of integers
-
"""
parcellation = np.zeros(mask.shape, dtype=int)
nvox = (mask !=0).sum()
for cc_mask in mg.split_mask_into_cc_iter(mask!=0):
# compute the required number of parcels within the current CC:
size_cc = cc_mask.sum()
cc_np = max(int(np.round(nb_parcels * size_cc / (nvox*1.))), 1)
pyhrf.verbose(2, 'Treating a connected component (CC) of %d positions' \
%cc_mask.sum())
if cc_mask.sum() < 6:
continue
if seeds is None:
# perform voronoi on random seeds
eroded_mask = peelVolume3D(cc_mask)
eroded_mask_size = eroded_mask.sum()
if eroded_mask_size < nb_parcels: #do no erode, mask too small
eroded_mask_size = nvox
eroded_mask = mask.copy()
cc_seeds = np.random.randint(0,eroded_mask_size, cc_np)
mask_for_seed = np.zeros(eroded_mask_size, dtype=int)
mask_for_seed[cc_seeds] = 1
mask_for_seed = expand_array_in_mask(mask_for_seed, eroded_mask)
else:
mask_for_seed = seeds * cc_mask
pyhrf.verbose(2, 'Nb of seeds in current CC: %d' \
%mask_for_seed.sum())
cc_parcellation = voronoi(np.vstack(np.where(cc_mask)).T,
np.vstack(np.where(mask_for_seed)).T) + 1
pyhrf.verbose(3, 'CC parcellation labels: %s' \
%str(np.unique(cc_parcellation)))
maxp = parcellation.max()
parcellation += expand_array_in_mask(cc_parcellation + maxp, cc_mask)
pyhrf.verbose(3, 'Current parcellation labels: %s' \
%str(np.unique(parcellation)))
pyhrf.verbose(1, 'voronoi parcellation: %s, %s' \
%(str(parcellation.shape), str(parcellation.dtype)))
return parcellation
def parcellate_voronoi_vol(mask, nb_parcels, seeds=None):
"""
Produce a parcellation from a Voronoi diagram built on random seeds.
The number of seeds is equal to the nb of parcels.
Seed are randomly placed within the mask, expect on edge positions
Args:
- mask (numpy.ndarray): binary 3D array of valid position to parcellate
- nb_parcels (int): the required number of parcels
- seeds: TODO
Return:
- the parcellation (numpy.ndarray): a 3D array of integers
-
"""
parcellation = np.zeros(mask.shape, dtype=int)
nvox = (mask != 0).sum()
for cc_mask in mg.split_mask_into_cc_iter(mask != 0):
# compute the required number of parcels within the current CC:
size_cc = cc_mask.sum()
cc_np = max(int(np.round(nb_parcels * size_cc / (nvox * 1.))), 1)
logger.info('Treating a connected component (CC) of %d positions',
cc_mask.sum())
if cc_mask.sum() < 6:
continue
if seeds is None:
# perform voronoi on random seeds
eroded_mask = peelVolume3D(cc_mask)
eroded_mask_size = eroded_mask.sum()
if eroded_mask_size < nb_parcels: # do no erode, mask too small
eroded_mask_size = nvox
eroded_mask = mask.copy()
cc_seeds = np.random.randint(0, eroded_mask_size, cc_np)
mask_for_seed = np.zeros(eroded_mask_size, dtype=int)
mask_for_seed[cc_seeds] = 1
mask_for_seed = expand_array_in_mask(mask_for_seed, eroded_mask)
else:
mask_for_seed = seeds * cc_mask
logger.info('Nb of seeds in current CC: %d', mask_for_seed.sum())
cc_parcellation = voronoi(
np.vstack(np.where(cc_mask)).T,
np.vstack(np.where(mask_for_seed)).T) + 1
logger.info('CC parcellation labels: %s',
str(np.unique(cc_parcellation)))
maxp = parcellation.max()
parcellation += expand_array_in_mask(cc_parcellation + maxp, cc_mask)
logger.info('Current parcellation labels: %s',
str(np.unique(parcellation)))
logger.info('voronoi parcellation: %s, %s', str(parcellation.shape),
str(parcellation.dtype))
return parcellation
def perm_prfx(domain, graphs, features, nb_parcel, ldata, initial_mask=None,
nb_perm=100, niter=5, dmax=10., lamb=100.0, chunksize=1.e5,
verbose=1):
"""
caveat: assumes that the functional dimension is 1
"""
from ..utils.reproducibility_measures import ttest
# permutations for the assesment of the results
prfx0 = []
adim = domain.coord.shape[1]
nb_subj = len(ldata)
for q in range(nb_perm):
feature = []
sldata = []
for s in range(nb_subj):
lf = features[s].copy()
swap = (rand() > 0.5) * 2 - 1
lf[:, 0:-adim] = swap * lf[:, 0:-adim]
sldata.append(swap * ldata[s])
feature.append(lf)
# optimization part
all_labels, proto_anat = _optim_hparcel(
feature, domain, graphs, nb_parcel, lamb, dmax, niter,
initial_mask, chunksize=chunksize)
labels = - np.ones((domain.size, nb_subj)).astype(np.int)
for s in range(nb_subj):
labels[initial_mask[:, s] > -1, s] = all_labels[s]
# compute the group-level labels
template_labels = voronoi(domain.coord, proto_anat)
# create the parcellation
pcl = MultiSubjectParcellation(domain, individual_labels=labels,
template_labels=template_labels)
pdata = pcl.make_feature('functional',
np.rollaxis(np.array(ldata), 1, 0))
prfx = ttest(np.squeeze(pdata))
if verbose:
print q, prfx.max(0)
prfx0.append(prfx.max(0))
return prfx0
def hparcel(domain, ldata, nb_parcel, nb_perm=0, niter=5, mu=10., dmax=10.,
lamb=100.0, chunksize=1.e5, verbose=0, initial_mask=None):
"""
Function that performs the parcellation by optimizing the
inter-subject similarity while retaining the connectedness
within subject and some consistency across subjects.
Parameters
----------
domain: discrete_domain.DiscreteDomain instance,
yields all the spatial information on the parcelled domain
ldata: list of (n_subj) arrays of shape (domain.size, dim)
the feature data used to inform the parcellation
nb_parcel: int,
the number of parcels
nb_perm: int, optional,
the number of times the parcellation and prfx
computation is performed on sign-swaped data
niter: int, optional,
number of iterations to obtain the convergence of the method
information in the clustering algorithm
mu: float, optional,
relative weight of anatomical information
dmax: float optional,
radius of allowed deformations
lamb: float optional
parameter to control the relative importance of space vs function
chunksize; int, optional
number of points used in internal sub-sampling
verbose: bool, optional,
verbosity mode
initial_mask: array of shape (domain.size, nb_subj), optional
initial subject-depedent masking of the domain
Results
-------
Pa: the resulting parcellation structure appended with the labelling
"""
# a various parameters
nbvox = domain.size
nb_subj = len(ldata)
if initial_mask is None:
initial_mask = np.ones((nbvox, nb_subj), np.int)
graphs = []
feature = []
for s in range(nb_subj):
# build subject-specific models of the data
lnvox = np.sum(initial_mask[:, s] > - 1)
lac = domain.coord[initial_mask[:, s] > - 1]
beta = np.reshape(ldata[s], (lnvox, ldata[s].shape[1]))
lf = np.hstack((beta, mu * lac / (1.e-15 + np.std(domain.coord, 0))))
feature.append(lf)
g = wgraph_from_coo_matrix(domain.topology)
g.remove_trivial_edges()
graphs.append(g)
# main function
all_labels, proto_anat = _optim_hparcel(
feature, domain, graphs, nb_parcel, lamb, dmax, niter, initial_mask,
chunksize=chunksize, verbose=verbose)
# write the individual labelling
labels = - np.ones((nbvox, nb_subj)).astype(np.int)
for s in range(nb_subj):
labels[initial_mask[:, s] > -1, s] = all_labels[s]
# compute the group-level labels
template_labels = voronoi(domain.coord, proto_anat)
# create the parcellation
pcl = MultiSubjectParcellation(domain, individual_labels=labels,
template_labels=template_labels,
nb_parcel=nb_parcel)
pcl.make_feature('functional', np.rollaxis(np.array(ldata), 1, 0))
if nb_perm > 0:
prfx0 = perm_prfx(domain, graphs, feature, nb_parcel, ldata,
initial_mask, nb_perm, niter, dmax, lamb, chunksize)
return pcl, prfx0
else:
return pcl