def test_getelbow_smoke():
"""A smoke test for the getelbow function."""
arr = np.random.random(100)
idx = _utils.getelbow(arr)
assert isinstance(idx, np.integer)
val = _utils.getelbow(arr, return_val=True)
assert isinstance(val, float)
# Running an empty array should raise a ValueError
arr = np.array([])
with pytest.raises(ValueError):
_utils.getelbow(arr)
# Running a 2D array should raise a ValueError
arr = np.random.random((100, 100))
with pytest.raises(ValueError):
_utils.getelbow(arr)
def kundu_tedpca(comptable, n_echos, kdaw=10., rdaw=1., stabilize=False):
"""
Select PCA components using Kundu's decision tree approach.
Parameters
----------
comptable : :obj:`pandas.DataFrame`
Component table with relevant metrics: kappa, rho, and normalized
variance explained. Component number should be the index.
n_echos : :obj:`int`
Number of echoes in dataset.
kdaw : :obj:`float`, optional
Kappa dimensionality augmentation weight. Must be a non-negative float,
or -1 (a special value). Default is 10.
rdaw : :obj:`float`, optional
Rho dimensionality augmentation weight. Must be a non-negative float,
or -1 (a special value). Default is 1.
stabilize : :obj:`bool`, optional
Whether to stabilize convergence by reducing dimensionality, for low
quality data. Default is False.
Returns
-------
comptable : :obj:`pandas.DataFrame`
Component table with components classified as 'accepted', 'rejected',
or 'ignored'.
metric_metadata : :obj:`dict`
Dictionary with metadata about calculated metrics.
Each entry corresponds to a column in ``comptable``.
"""
LGR.info('Performing PCA component selection with Kundu decision tree')
comptable['classification'] = 'accepted'
comptable['rationale'] = ''
eigenvalue_elbow = getelbow(comptable['normalized variance explained'],
return_val=True)
diff_varex_norm = np.abs(
np.diff(comptable['normalized variance explained']))
lower_diff_varex_norm = diff_varex_norm[(len(diff_varex_norm) // 2):]
varex_norm_thr = np.mean(
[lower_diff_varex_norm.max(),
diff_varex_norm.min()])
varex_norm_min = comptable['normalized variance explained'][
(len(diff_varex_norm) // 2) + np.arange(len(lower_diff_varex_norm))[
lower_diff_varex_norm >= varex_norm_thr][0] + 1]
varex_norm_cum = np.cumsum(comptable['normalized variance explained'])
fmin, fmid, fmax = getfbounds(n_echos)
if int(kdaw) == -1:
lim_idx = utils.andb(
[comptable['kappa'] < fmid, comptable['kappa'] > fmin]) == 2
kappa_lim = comptable.loc[lim_idx, 'kappa'].values
kappa_thr = kappa_lim[getelbow(kappa_lim)]
lim_idx = utils.andb(
[comptable['rho'] < fmid, comptable['rho'] > fmin]) == 2
rho_lim = comptable.loc[lim_idx, 'rho'].values
rho_thr = rho_lim[getelbow(rho_lim)]
stabilize = True
LGR.info('kdaw set to -1. Switching TEDPCA algorithm to '
'kundu-stabilize')
elif int(rdaw) == -1:
lim_idx = utils.andb(
[comptable['rho'] < fmid, comptable['rho'] > fmin]) == 2
rho_lim = comptable.loc[lim_idx, 'rho'].values
rho_thr = rho_lim[getelbow(rho_lim)]
else:
kappa_thr = np.average(sorted(
[fmin, (getelbow(comptable['kappa'], return_val=True) / 2), fmid]),
weights=[kdaw, 1, 1])
rho_thr = np.average(sorted([
fmin, (getelbow_cons(comptable['rho'], return_val=True) / 2), fmid
]),
weights=[rdaw, 1, 1])
# Reject if low Kappa, Rho, and variance explained
is_lowk = comptable['kappa'] <= kappa_thr
is_lowr = comptable['rho'] <= rho_thr
is_lowe = comptable['normalized variance explained'] <= eigenvalue_elbow
is_lowkre = is_lowk & is_lowr & is_lowe
comptable.loc[is_lowkre, 'classification'] = 'rejected'
comptable.loc[is_lowkre, 'rationale'] += 'P001;'
# Reject if low variance explained
is_lows = comptable['normalized variance explained'] <= varex_norm_min
comptable.loc[is_lows, 'classification'] = 'rejected'
comptable.loc[is_lows, 'rationale'] += 'P002;'
# Reject if Kappa over limit
is_fmax1 = comptable['kappa'] == F_MAX
comptable.loc[is_fmax1, 'classification'] = 'rejected'
comptable.loc[is_fmax1, 'rationale'] += 'P003;'
# Reject if Rho over limit
is_fmax2 = comptable['rho'] == F_MAX
comptable.loc[is_fmax2, 'classification'] = 'rejected'
comptable.loc[is_fmax2, 'rationale'] += 'P004;'
if stabilize:
temp7 = varex_norm_cum >= 0.95
comptable.loc[temp7, 'classification'] = 'rejected'
comptable.loc[temp7, 'rationale'] += 'P005;'
under_fmin1 = comptable['kappa'] <= fmin
comptable.loc[under_fmin1, 'classification'] = 'rejected'
comptable.loc[under_fmin1, 'rationale'] += 'P006;'
under_fmin2 = comptable['rho'] <= fmin
comptable.loc[under_fmin2, 'classification'] = 'rejected'
comptable.loc[under_fmin2, 'rationale'] += 'P007;'
n_components = comptable.loc[comptable['classification'] ==
'accepted'].shape[0]
LGR.info('Selected {0} components with Kappa threshold: {1:.02f}, Rho '
'threshold: {2:.02f}'.format(n_components, kappa_thr, rho_thr))
# Move decision columns to end
comptable = clean_dataframe(comptable)
metric_metadata = collect.get_metadata(comptable)
return comptable, metric_metadata
def kundu_selection_v2(comptable, n_echos, n_vols):
"""
Classify components as "accepted," "rejected," or "ignored" based on
relevant metrics.
The selection process uses previously calculated parameters listed in
comptable for each ICA component such as Kappa (a T2* weighting metric),
Rho (an S0 weighting metric), and variance explained.
See `Notes` for additional calculated metrics used to classify each
component into one of the listed groups.
Parameters
----------
comptable : (C x M) :obj:`pandas.DataFrame`
Component metric table. One row for each component, with a column for
each metric. The index should be the component number.
n_echos : :obj:`int`
Number of echos in original data
n_vols : :obj:`int`
Number of volumes in dataset
Returns
-------
comptable : :obj:`pandas.DataFrame`
Updated component table with additional metrics and with
classification (accepted, rejected, or ignored)
Notes
-----
The selection algorithm used in this function was originated in ME-ICA
by Prantik Kundu, and his original implementation is available at:
https://github.com/ME-ICA/me-ica/blob/b2781dd087ab9de99a2ec3925f04f02ce84f0adc/meica.libs/select_model.py
This component selection process uses multiple, previously calculated
metrics that include kappa, rho, variance explained, noise and spatial
frequency metrics, and measures of spatial overlap across metrics.
Prantik began to update these selection criteria to use SVMs to distinguish
components, a hypercommented version of this attempt is available at:
https://gist.github.com/emdupre/ca92d52d345d08ee85e104093b81482e
References
----------
* Kundu, P., Brenowitz, N. D., Voon, V., Worbe, Y.,
Vértes, P. E., Inati, S. J., ... & Bullmore, E. T.
(2013). Integrated strategy for improving functional
connectivity mapping using multiecho fMRI. Proceedings
of the National Academy of Sciences, 110(40),
16187-16192.
"""
LGR.info(
'Performing ICA component selection with Kundu decision tree v2.5')
RepLGR.info("Next, component selection was performed to identify "
"BOLD (TE-dependent), non-BOLD (TE-independent), and "
"uncertain (low-variance) components using the Kundu "
"decision tree (v2.5; Kundu et al., 2013).")
RefLGR.info("Kundu, P., Brenowitz, N. D., Voon, V., Worbe, Y., "
"Vértes, P. E., Inati, S. J., ... & Bullmore, E. T. "
"(2013). Integrated strategy for improving functional "
"connectivity mapping using multiecho fMRI. Proceedings "
"of the National Academy of Sciences, 110(40), "
"16187-16192.")
comptable['classification'] = 'accepted'
comptable['rationale'] = ''
# Set knobs
LOW_PERC = 25
HIGH_PERC = 90
if n_vols < 100:
EXTEND_FACTOR = 3
else:
EXTEND_FACTOR = 2
RESTRICT_FACTOR = 2
# Lists of components
all_comps = np.arange(comptable.shape[0])
# unclf is a full list that is whittled down over criteria
# since the default classification is "accepted", at the end of the tree
# the remaining elements in unclf are classified as accepted
unclf = all_comps.copy()
"""
Step 1: Reject anything that's obviously an artifact
a. Estimate a null variance
"""
# Rho is higher than Kappa
temp_rej0a = all_comps[(comptable['rho'] > comptable['kappa'])]
comptable.loc[temp_rej0a, 'classification'] = 'rejected'
comptable.loc[temp_rej0a, 'rationale'] += 'I002;'
# Number of significant voxels for S0 model is higher than number for R2
# model *and* number for R2 model is greater than zero.
temp_rej0b = all_comps[(
(comptable['countsigFS0'] > comptable['countsigFR2']) &
(comptable['countsigFR2'] > 0))]
comptable.loc[temp_rej0b, 'classification'] = 'rejected'
comptable.loc[temp_rej0b, 'rationale'] += 'I003;'
rej = np.union1d(temp_rej0a, temp_rej0b)
# Dice score for S0 maps is higher than Dice score for R2 maps and variance
# explained is higher than the median across components.
temp_rej1 = all_comps[(comptable['dice_FS0'] > comptable['dice_FR2'])
& (comptable['variance explained'] > np.median(
comptable['variance explained']))]
comptable.loc[temp_rej1, 'classification'] = 'rejected'
comptable.loc[temp_rej1, 'rationale'] += 'I004;'
rej = np.union1d(temp_rej1, rej)
# T-value is less than zero (noise has higher F-statistics than signal in
# map) and variance explained is higher than the median across components.
temp_rej2 = unclf[(comptable.loc[unclf, 'signal-noise_t'] < 0)
& (comptable.loc[unclf, 'variance explained'] >
np.median(comptable['variance explained']))]
comptable.loc[temp_rej2, 'classification'] = 'rejected'
comptable.loc[temp_rej2, 'rationale'] += 'I005;'
rej = np.union1d(temp_rej2, rej)
unclf = np.setdiff1d(unclf, rej)
# Quit early if no potentially accepted components remain
if len(unclf) == 0:
LGR.warning('No BOLD-like components detected. Ignoring all remaining '
'components.')
ign = sorted(np.setdiff1d(all_comps, rej))
comptable.loc[ign, 'classification'] = 'ignored'
comptable.loc[ign, 'rationale'] += 'I006;'
# Move decision columns to end
comptable = clean_dataframe(comptable)
return comptable
"""
Step 2: Make a guess for what the good components are, in order to
estimate good component properties
a. Not outlier variance
b. Kappa>kappa_elbow
c. Rho<Rho_elbow
d. High R2* dice compared to S0 dice
e. Gain of F_R2 in clusters vs noise
f. Estimate a low and high variance
"""
# Step 2a
# Upper limit for variance explained is median across components with high
# Kappa values. High Kappa is defined as Kappa above Kappa elbow.
varex_upper_p = np.median(comptable.loc[
comptable['kappa'] > getelbow(comptable['kappa'], return_val=True),
'variance explained'])
# Sort component table by variance explained and find outlier components by
# change in variance explained from one component to the next.
# Remove variance-explained outliers from list of components to consider
# for acceptance. These components will have another chance to be accepted
# later on.
# NOTE: We're not sure why this is done this way, nor why it's specifically
# done three times.
ncls = unclf.copy()
for i_loop in range(3):
temp_comptable = comptable.loc[ncls].sort_values(
by=['variance explained'], ascending=False)
diff_vals = temp_comptable['variance explained'].diff(-1)
diff_vals = diff_vals.fillna(0)
ncls = temp_comptable.loc[diff_vals < varex_upper_p].index.values
# Compute elbows from other elbows
f05, _, f01 = getfbounds(n_echos)
kappas_nonsig = comptable.loc[comptable['kappa'] < f01, 'kappa']
# NOTE: Would an elbow from all Kappa values *ever* be lower than one from
# a subset of lower values?
kappa_elbow = np.min((getelbow(kappas_nonsig, return_val=True),
getelbow(comptable['kappa'], return_val=True)))
rho_elbow = np.mean((getelbow(comptable.loc[ncls, 'rho'], return_val=True),
getelbow(comptable['rho'], return_val=True), f05))
# Provisionally accept components based on Kappa and Rho elbows
acc_prov = ncls[(comptable.loc[ncls, 'kappa'] >= kappa_elbow)
& (comptable.loc[ncls, 'rho'] < rho_elbow)]
# Quit early if no potentially accepted components remain
if len(acc_prov) <= 1:
LGR.warning('Too few BOLD-like components detected. '
'Ignoring all remaining.')
ign = sorted(np.setdiff1d(all_comps, rej))
comptable.loc[ign, 'classification'] = 'ignored'
comptable.loc[ign, 'rationale'] += 'I006;'
# Move decision columns to end
comptable = clean_dataframe(comptable)
return comptable
# Calculate "rate" for kappa: kappa range divided by variance explained
# range, for potentially accepted components
# NOTE: What is the logic behind this?
kappa_rate = ((np.max(comptable.loc[acc_prov, 'kappa']) -
np.min(comptable.loc[acc_prov, 'kappa'])) /
(np.max(comptable.loc[acc_prov, 'variance explained']) -
np.min(comptable.loc[acc_prov, 'variance explained'])))
comptable['kappa ratio'] = kappa_rate * comptable[
'variance explained'] / comptable['kappa']
# Calculate bounds for variance explained
varex_lower = stats.scoreatpercentile(
comptable.loc[acc_prov, 'variance explained'], LOW_PERC)
varex_upper = stats.scoreatpercentile(
comptable.loc[acc_prov, 'variance explained'], HIGH_PERC)
"""
Step 3: Get rid of midk components; i.e., those with higher than
max decision score and high variance
"""
max_good_d_score = EXTEND_FACTOR * len(acc_prov)
midk = unclf[(comptable.loc[unclf, 'd_table_score'] > max_good_d_score) & (
comptable.loc[unclf,
'variance explained'] > EXTEND_FACTOR * varex_upper)]
comptable.loc[midk, 'classification'] = 'rejected'
comptable.loc[midk, 'rationale'] += 'I007;'
unclf = np.setdiff1d(unclf, midk)
acc_prov = np.setdiff1d(acc_prov, midk)
"""
Step 4: Find components to ignore
"""
# collect high variance unclassified components
# and mix of high/low provisionally accepted
high_varex = np.union1d(
acc_prov,
unclf[comptable.loc[unclf, 'variance explained'] > varex_lower])
# ignore low variance components
ign = np.setdiff1d(unclf, high_varex)
# but only if they have bad decision scores
ign = np.setdiff1d(
ign, ign[comptable.loc[ign, 'd_table_score'] < max_good_d_score])
# and low kappa
ign = np.setdiff1d(ign, ign[comptable.loc[ign, 'kappa'] > kappa_elbow])
comptable.loc[ign, 'classification'] = 'ignored'
comptable.loc[ign, 'rationale'] += 'I008;'
unclf = np.setdiff1d(unclf, ign)
"""
Step 5: Scrub the set if there are components that haven't been rejected or
ignored, but are still not listed in the provisionally accepted group.
"""
if len(unclf) > len(acc_prov):
comptable['d_table_score_scrub'] = np.nan
# Recompute the midk steps on the limited set to clean up the tail
d_table_rank = np.vstack([
len(unclf) - stats.rankdata(comptable.loc[unclf, 'kappa']),
len(unclf) - stats.rankdata(comptable.loc[unclf, 'dice_FR2']),
len(unclf) -
stats.rankdata(comptable.loc[unclf, 'signal-noise_t']),
stats.rankdata(comptable.loc[unclf, 'countnoise']),
len(unclf) - stats.rankdata(comptable.loc[unclf, 'countsigFR2'])
]).T
comptable.loc[unclf, 'd_table_score_scrub'] = d_table_rank.mean(1)
num_acc_guess = int(
np.mean([
np.sum((comptable.loc[unclf, 'kappa'] > kappa_elbow)
& (comptable.loc[unclf, 'rho'] < rho_elbow)),
np.sum(comptable.loc[unclf, 'kappa'] > kappa_elbow)
]))
# Rejection candidate based on artifact type A: candartA
conservative_guess = num_acc_guess / RESTRICT_FACTOR
candartA = np.intersect1d(
unclf[comptable.loc[unclf,
'd_table_score_scrub'] > conservative_guess],
unclf[comptable.loc[unclf, 'kappa ratio'] > EXTEND_FACTOR * 2])
candartA = (candartA[comptable.loc[candartA, 'variance explained'] >
varex_upper * EXTEND_FACTOR])
comptable.loc[candartA, 'classification'] = 'rejected'
comptable.loc[candartA, 'rationale'] += 'I009;'
midk = np.union1d(midk, candartA)
unclf = np.setdiff1d(unclf, midk)
# Rejection candidate based on artifact type B: candartB
conservative_guess2 = num_acc_guess * HIGH_PERC / 100.
candartB = unclf[
comptable.loc[unclf, 'd_table_score_scrub'] > conservative_guess2]
candartB = (candartB[comptable.loc[candartB, 'variance explained'] >
varex_lower * EXTEND_FACTOR])
comptable.loc[candartB, 'classification'] = 'rejected'
comptable.loc[candartB, 'rationale'] += 'I010;'
midk = np.union1d(midk, candartB)
unclf = np.setdiff1d(unclf, midk)
# Find components to ignore
# Ignore high variance explained, poor decision tree scored components
new_varex_lower = stats.scoreatpercentile(
comptable.loc[unclf[:num_acc_guess], 'variance explained'],
LOW_PERC)
candart = unclf[comptable.loc[unclf,
'd_table_score_scrub'] > num_acc_guess]
ign_add0 = candart[
comptable.loc[candart, 'variance explained'] > new_varex_lower]
ign_add0 = np.setdiff1d(ign_add0, midk)
comptable.loc[ign_add0, 'classification'] = 'ignored'
comptable.loc[ign_add0, 'rationale'] += 'I011;'
ign = np.union1d(ign, ign_add0)
unclf = np.setdiff1d(unclf, ign)
# Ignore low Kappa, high variance explained components
ign_add1 = np.intersect1d(
unclf[comptable.loc[unclf, 'kappa'] <= kappa_elbow],
unclf[comptable.loc[unclf,
'variance explained'] > new_varex_lower])
ign_add1 = np.setdiff1d(ign_add1, midk)
comptable.loc[ign_add1, 'classification'] = 'ignored'
comptable.loc[ign_add1, 'rationale'] += 'I012;'
# at this point, unclf is equivalent to accepted
# Move decision columns to end
comptable = clean_dataframe(comptable)
return comptable
def tedpca(catd,
OCcatd,
combmode,
mask,
t2s,
t2sG,
stabilize,
ref_img,
tes,
kdaw,
rdaw,
ste=0,
wvpca=False):
"""
Use principal components analysis (PCA) to identify and remove thermal
noise from multi-echo data.
Parameters
----------
catd : (S x E x T) array_like
Input functional data
OCcatd : (S x T) array_like
Optimally-combined time series data
combmode : {'t2s', 'ste'} str
How optimal combination of echos should be made, where 't2s' indicates
using the method of Posse 1999 and 'ste' indicates using the method of
Poser 2006
mask : (S,) array_like
Boolean mask array
stabilize : :obj:`bool`
Whether to attempt to stabilize convergence of ICA by returning
dimensionally-reduced data from PCA and component selection.
ref_img : :obj:`str` or img_like
Reference image to dictate how outputs are saved to disk
tes : :obj:`list`
List of echo times associated with `catd`, in milliseconds
kdaw : :obj:`float`
Dimensionality augmentation weight for Kappa calculations
rdaw : :obj:`float`
Dimensionality augmentation weight for Rho calculations
ste : :obj:`int` or :obj:`list` of :obj:`int`, optional
Which echos to use in PCA. Values -1 and 0 are special, where a value
of -1 will indicate using all the echos and 0 will indicate using the
optimal combination of the echos. A list can be provided to indicate
a subset of echos. Default: 0
wvpca : :obj:`bool`, optional
Whether to apply wavelet denoising to data. Default: False
Returns
-------
n_components : :obj:`int`
Number of components retained from PCA decomposition
dd : (S x T) :obj:`numpy.ndarray`
Dimensionally reduced optimally combined functional data
Notes
-----
====================== =================================================
Notation Meaning
====================== =================================================
:math:`\\kappa` Component pseudo-F statistic for TE-dependent
(BOLD) model.
:math:`\\rho` Component pseudo-F statistic for TE-independent
(artifact) model.
:math:`v` Voxel
:math:`V` Total number of voxels in mask
:math:`\\zeta` Something
:math:`c` Component
:math:`p` Something else
====================== =================================================
Steps:
1. Variance normalize either multi-echo or optimally combined data,
depending on settings.
2. Decompose normalized data using PCA or SVD.
3. Compute :math:`{\\kappa}` and :math:`{\\rho}`:
.. math::
{\\kappa}_c = \\frac{\sum_{v}^V {\\zeta}_{c,v}^p * \
F_{c,v,R_2^*}}{\sum {\\zeta}_{c,v}^p}
{\\rho}_c = \\frac{\sum_{v}^V {\\zeta}_{c,v}^p * \
F_{c,v,S_0}}{\sum {\\zeta}_{c,v}^p}
4. Some other stuff. Something about elbows.
5. Classify components as thermal noise if they meet both of the
following criteria:
- Nonsignificant :math:`{\\kappa}` and :math:`{\\rho}`.
- Nonsignificant variance explained.
Outputs:
This function writes out several files:
====================== =================================================
Filename Content
====================== =================================================
pcastate.pkl Values from PCA results.
comp_table_pca.txt PCA component table.
mepca_mix.1D PCA mixing matrix.
====================== =================================================
"""
n_samp, n_echos, n_vols = catd.shape
ste = np.array([int(ee) for ee in str(ste).split(',')])
if len(ste) == 1 and ste[0] == -1:
LGR.info('Computing PCA of optimally combined multi-echo data')
d = OCcatd[utils.make_min_mask(OCcatd[:,
np.newaxis, :])][:,
np.newaxis, :]
elif len(ste) == 1 and ste[0] == 0:
LGR.info('Computing PCA of spatially concatenated multi-echo data')
d = catd[mask].astype('float64')
else:
LGR.info('Computing PCA of echo #%s' %
','.join([str(ee) for ee in ste]))
d = np.stack([catd[mask, ee] for ee in ste - 1],
axis=1).astype('float64')
eim = np.squeeze(eimask(d))
d = np.squeeze(d[eim])
dz = ((d.T - d.T.mean(axis=0)) / d.T.std(axis=0)).T # var normalize ts
dz = (dz - dz.mean()) / dz.std() # var normalize everything
if wvpca:
dz, cAl = dwtmat(dz)
if not op.exists('pcastate.pkl'):
voxel_comp_weights, varex, comp_ts = run_svd(dz)
# actual variance explained (normalized)
varex_norm = varex / varex.sum()
eigenvalue_elbow = getelbow(varex_norm, return_val=True)
diff_varex_norm = np.abs(np.diff(varex_norm))
lower_diff_varex_norm = diff_varex_norm[(len(diff_varex_norm) // 2):]
varex_norm_thr = np.mean(
[lower_diff_varex_norm.max(),
diff_varex_norm.min()])
varex_norm_min = varex_norm[
(len(diff_varex_norm) // 2) + np.arange(len(lower_diff_varex_norm))
[lower_diff_varex_norm >= varex_norm_thr][0] + 1]
varex_norm_cum = np.cumsum(varex_norm)
# Compute K and Rho for PCA comps
eimum = np.atleast_2d(eim)
eimum = np.transpose(eimum, np.argsort(eimum.shape)[::-1])
eimum = eimum.prod(axis=1)
o = np.zeros((mask.shape[0], *eimum.shape[1:]))
o[mask] = eimum
eimum = np.squeeze(o).astype(bool)
vTmix = comp_ts.T
vTmixN = ((vTmix.T - vTmix.T.mean(0)) / vTmix.T.std(0)).T
LGR.info('Making initial component selection guess from PCA results')
_, ct_df, betasv, v_T = model.fitmodels_direct(catd,
comp_ts.T,
eimum,
t2s,
t2sG,
tes,
combmode,
ref_img,
mmixN=vTmixN,
full_sel=False)
# varex_norm overrides normalized varex computed by fitmodels_direct
ct_df['normalized variance explained'] = varex_norm
# Save state
fname = op.abspath('pcastate.pkl')
LGR.info('Saving PCA results to: {}'.format(fname))
pcastate = {
'voxel_comp_weights': voxel_comp_weights,
'varex': varex,
'comp_ts': comp_ts,
'comptable': ct_df,
'eigenvalue_elbow': eigenvalue_elbow,
'varex_norm_min': varex_norm_min,
'varex_norm_cum': varex_norm_cum
}
try:
with open(fname, 'wb') as handle:
pickle.dump(pcastate, handle)
except TypeError:
LGR.warning('Could not save PCA solution')
else: # if loading existing state
LGR.info('Loading PCA from: pcastate.pkl')
with open('pcastate.pkl', 'rb') as handle:
pcastate = pickle.load(handle)
voxel_comp_weights, varex = pcastate['voxel_comp_weights'], pcastate[
'varex']
comp_ts = pcastate['comp_ts']
ct_df = pcastate['comptable']
eigenvalue_elbow = pcastate['eigenvalue_elbow']
varex_norm_min = pcastate['varex_norm_min']
varex_norm_cum = pcastate['varex_norm_cum']
np.savetxt('mepca_mix.1D', comp_ts.T)
# write component maps to 4D image
comp_maps = np.zeros((OCcatd.shape[0], comp_ts.shape[0]))
for i_comp in range(comp_ts.shape[0]):
temp_comp_ts = comp_ts[i_comp, :][:, None]
comp_map = utils.unmask(
model.computefeats2(OCcatd, temp_comp_ts, mask), mask)
comp_maps[:, i_comp] = np.squeeze(comp_map)
io.filewrite(comp_maps, 'mepca_OC_components.nii', ref_img)
fmin, fmid, fmax = utils.getfbounds(n_echos)
kappa_thr = np.average(sorted(
[fmin, getelbow(ct_df['kappa'], return_val=True) / 2, fmid]),
weights=[kdaw, 1, 1])
rho_thr = np.average(sorted(
[fmin, getelbow_cons(ct_df['rho'], return_val=True) / 2, fmid]),
weights=[rdaw, 1, 1])
if int(kdaw) == -1:
lim_idx = utils.andb([ct_df['kappa'] < fmid,
ct_df['kappa'] > fmin]) == 2
kappa_lim = ct_df.loc[lim_idx, 'kappa'].values
kappa_thr = kappa_lim[getelbow(kappa_lim)]
lim_idx = utils.andb([ct_df['rho'] < fmid, ct_df['rho'] > fmin]) == 2
rho_lim = ct_df.loc[lim_idx, 'rho'].values
rho_thr = rho_lim[getelbow(rho_lim)]
stabilize = True
elif int(rdaw) == -1:
lim_idx = utils.andb([ct_df['rho'] < fmid, ct_df['rho'] > fmin]) == 2
rho_lim = ct_df.loc[lim_idx, 'rho'].values
rho_thr = rho_lim[getelbow(rho_lim)]
# Add new columns to comptable for classification
ct_df['classification'] = 'accepted'
ct_df['rationale'] = ''
# Reject if low Kappa, Rho, and variance explained
is_lowk = ct_df['kappa'] <= kappa_thr
is_lowr = ct_df['rho'] <= rho_thr
is_lowe = ct_df['normalized variance explained'] <= eigenvalue_elbow
is_lowkre = is_lowk & is_lowr & is_lowe
ct_df.loc[is_lowkre, 'classification'] = 'rejected'
ct_df.loc[is_lowkre, 'rationale'] += 'low rho, kappa, and varex;'
# Reject if low variance explained
is_lows = ct_df['normalized variance explained'] <= varex_norm_min
ct_df.loc[is_lows, 'classification'] = 'rejected'
ct_df.loc[is_lows, 'rationale'] += 'low variance explained;'
# Reject if Kappa over limit
is_fmax1 = ct_df['kappa'] == F_MAX
ct_df.loc[is_fmax1, 'classification'] = 'rejected'
ct_df.loc[is_fmax1, 'rationale'] += 'kappa equals fmax;'
# Reject if Rho over limit
is_fmax2 = ct_df['rho'] == F_MAX
ct_df.loc[is_fmax2, 'classification'] = 'rejected'
ct_df.loc[is_fmax2, 'rationale'] += 'rho equals fmax;'
if stabilize:
temp7 = varex_norm_cum >= 0.95
ct_df.loc[temp7, 'classification'] = 'rejected'
ct_df.loc[temp7, 'rationale'] += 'cumulative var. explained above 95%;'
under_fmin1 = ct_df['kappa'] <= fmin
ct_df.loc[under_fmin1, 'classification'] = 'rejected'
ct_df.loc[under_fmin1, 'rationale'] += 'kappa below fmin;'
under_fmin2 = ct_df['rho'] <= fmin
ct_df.loc[under_fmin2, 'classification'] = 'rejected'
ct_df.loc[under_fmin2, 'rationale'] += 'rho below fmin;'
ct_df.to_csv('comp_table_pca.txt',
sep='\t',
index=True,
index_label='component',
float_format='%.6f')
sel_idx = ct_df['classification'] == 'accepted'
n_components = np.sum(sel_idx)
voxel_kept_comp_weighted = (voxel_comp_weights[:, sel_idx] *
varex[None, sel_idx])
kept_data = np.dot(voxel_kept_comp_weighted, comp_ts[sel_idx, :])
if wvpca:
kept_data = idwtmat(kept_data, cAl)
LGR.info('Selected {0} components with Kappa threshold: {1:.02f}, '
'Rho threshold: {2:.02f}'.format(n_components, kappa_thr,
rho_thr))
kept_data = stats.zscore(kept_data,
axis=1) # variance normalize timeseries
kept_data = stats.zscore(kept_data,
axis=None) # variance normalize everything
return n_components, kept_data
def selcomps(seldict, comptable, mmix, manacc, n_echos):
"""
Classify components in seldict as "accepted," "rejected," "midk," or "ignored."
The selection process uses previously calculated parameters listed in `seldict`
for each ICA component such as Kappa (a T2* weighting metric), Rho (an S0 weighting metric),
and variance explained. See `Notes` for additional calculated metrics used to
classify each component into one of the four listed groups.
Parameters
----------
seldict : :obj:`dict`
A dictionary with component-specific features used for classification.
As output from `fitmodels_direct`
comptable : (C x 5) :obj:`pandas.DataFrame`
Component metric table
mmix : (T x C) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the number of volumes in the original data
manacc : :obj:`list`
Comma-separated list of indices of manually accepted components
n_echos : :obj:`int`
Number of echos in original data
Returns
-------
comptable : :obj:`pandas.DataFrame`
Updated component table with additional metrics and with
classification (accepted, rejected, midk, or ignored)
Notes
-----
The selection algorithm used in this function was originated in ME-ICA
by Prantik Kundu, and his original implementation is available at:
https://github.com/ME-ICA/me-ica/blob/b2781dd087ab9de99a2ec3925f04f02ce84f0adc/meica.libs/select_model.py
This component selection process uses multiple, previously calculated metrics that include:
kappa, rho, variance explained, component spatial weighting maps, noise and spatial
frequency metrics, and measures of spatial overlap across metrics.
Prantik began to update these selection criteria to use SVMs to
distinguish components, a hypercommented version of this attempt is available at:
https://gist.github.com/emdupre/ca92d52d345d08ee85e104093b81482e
"""
cols_at_end = ['classification', 'rationale']
comptable['classification'] = 'accepted'
comptable['rationale'] = ''
Z_maps = seldict['Z_maps']
Z_clmaps = seldict['Z_clmaps']
F_R2_maps = seldict['F_R2_maps']
F_S0_clmaps = seldict['F_S0_clmaps']
F_R2_clmaps = seldict['F_R2_clmaps']
Br_S0_clmaps = seldict['Br_S0_clmaps']
Br_R2_clmaps = seldict['Br_R2_clmaps']
n_vols, n_comps = mmix.shape
# Set knobs
LOW_PERC = 25
HIGH_PERC = 90
if n_vols < 100:
EXTEND_FACTOR = 3
else:
EXTEND_FACTOR = 2
RESTRICT_FACTOR = 2
# List of components
midk = []
ign = []
all_comps = np.arange(comptable.shape[0])
acc = np.arange(comptable.shape[0])
# If user has specified
if manacc:
acc = sorted([int(vv) for vv in manacc.split(',')])
rej = sorted(np.setdiff1d(all_comps, acc))
comptable.loc[acc, 'classification'] = 'accepted'
comptable.loc[rej, 'classification'] = 'rejected'
comptable.loc[rej, 'rationale'] += 'I001;'
# Move decision columns to end
comptable = comptable[[c for c in comptable if c not in cols_at_end] +
[c for c in cols_at_end if c in comptable]]
return comptable
"""
Do some tallies for no. of significant voxels
"""
countnoise = np.zeros(n_comps)
comptable['countsigFR2'] = F_R2_clmaps.sum(axis=0)
comptable['countsigFS0'] = F_S0_clmaps.sum(axis=0)
"""
Make table of dice values
"""
comptable['dice_FR2'] = np.zeros(all_comps.shape[0])
comptable['dice_FS0'] = np.zeros(all_comps.shape[0])
for i_comp in acc:
comptable.loc[i_comp, 'dice_FR2'] = utils.dice(Br_R2_clmaps[:, i_comp],
F_R2_clmaps[:, i_comp])
comptable.loc[i_comp, 'dice_FS0'] = utils.dice(Br_S0_clmaps[:, i_comp],
F_S0_clmaps[:, i_comp])
comptable.loc[np.isnan(comptable['dice_FR2']), 'dice_FR2'] = 0
comptable.loc[np.isnan(comptable['dice_FS0']), 'dice_FS0'] = 0
"""
Make table of noise gain
"""
comptable['countnoise'] = 0
comptable['signal-noise_t'] = 0
comptable['signal-noise_p'] = 0
for i_comp in all_comps:
comp_noise_sel = ((np.abs(Z_maps[:, i_comp]) > 1.95) &
(Z_clmaps[:, i_comp] == 0))
comptable.loc[i_comp, 'countnoise'] = np.array(comp_noise_sel,
dtype=np.int).sum()
noise_FR2_Z = np.log10(np.unique(F_R2_maps[comp_noise_sel, i_comp]))
signal_FR2_Z = np.log10(
np.unique(F_R2_maps[Z_clmaps[:, i_comp] == 1, i_comp]))
(comptable.loc[i_comp, 'signal-noise_t'],
comptable.loc[i_comp,
'signal-noise_p']) = stats.ttest_ind(signal_FR2_Z,
noise_FR2_Z,
equal_var=False)
comptable.loc[np.isnan(comptable['signal-noise_t']), 'signal-noise_t'] = 0
comptable.loc[np.isnan(comptable['signal-noise_p']), 'signal-noise_p'] = 0
"""
Assemble decision table
"""
d_table_rank = np.vstack([
n_comps - stats.rankdata(comptable['kappa'], method='ordinal'),
n_comps - stats.rankdata(comptable['dice_FR2'], method='ordinal'),
n_comps -
stats.rankdata(comptable['signal-noise_t'], method='ordinal'),
stats.rankdata(countnoise, method='ordinal'),
n_comps - stats.rankdata(comptable['countsigFR2'], method='ordinal')
]).T
n_decision_metrics = d_table_rank.shape[1]
comptable['d_table_score'] = d_table_rank.sum(axis=1)
"""
Step 1: Reject anything that's obviously an artifact
a. Estimate a null variance
"""
temp_rej0 = all_comps[(comptable['rho'] > comptable['kappa']) | (
(comptable['countsigFS0'] > comptable['countsigFR2']) &
(comptable['countsigFR2'] > 0))]
comptable.loc[temp_rej0, 'classification'] = 'rejected'
comptable.loc[temp_rej0, 'rationale'] += 'I002;'
temp_rej1 = all_comps[(comptable['dice_FS0'] > comptable['dice_FR2'])
& (comptable['variance explained'] > np.median(
comptable['variance explained']))]
comptable.loc[temp_rej1, 'classification'] = 'rejected'
comptable.loc[temp_rej1, 'rationale'] += 'I003;'
rej = np.union1d(temp_rej0, temp_rej1)
temp_rej2 = acc[(comptable.loc[acc, 'signal-noise_t'] < 0)
& (comptable.loc[acc, 'variance explained'] > np.median(
comptable['variance explained']))]
comptable.loc[temp_rej2, 'classification'] = 'rejected'
comptable.loc[temp_rej2, 'rationale'] += 'I004;'
rej = np.union1d(temp_rej2, rej)
acc = np.setdiff1d(acc, rej)
"""
Step 2: Make a guess for what the good components are, in order to
estimate good component properties
a. Not outlier variance
b. Kappa>kappa_elbow
c. Rho<Rho_elbow
d. High R2* dice compared to S0 dice
e. Gain of F_R2 in clusters vs noise
f. Estimate a low and high variance
"""
# Step 2a
varex_upper_p = np.median(comptable.loc[
comptable['kappa'] > getelbow(comptable['kappa'], return_val=True),
'variance explained'])
ncls = acc.copy()
# NOTE: We're not sure why this is done, nor why it's specifically done
# three times. Need to look into this deeper, esp. to make sure the 3
# isn't a hard-coded reference to the number of echoes.
for nn in range(3):
ncls = comptable.loc[ncls].loc[comptable.loc[
ncls, 'variance explained'].diff() < varex_upper_p].index.values
# Compute elbows
kappas_lim = comptable.loc[
comptable['kappa'] < utils.getfbounds(n_echos)[-1], 'kappa']
kappa_elbow = np.min((getelbow(kappas_lim, return_val=True),
getelbow(comptable['kappa'], return_val=True)))
rho_elbow = np.mean(
(getelbow(comptable.loc[ncls, 'rho'], return_val=True),
getelbow(comptable['rho'],
return_val=True), utils.getfbounds(n_echos)[0]))
# Initial guess of good components based on Kappa and Rho elbows
good_guess = ncls[(comptable.loc[ncls, 'kappa'] >= kappa_elbow)
& (comptable.loc[ncls, 'rho'] < rho_elbow)]
if len(good_guess) == 0:
LGR.warning('No BOLD-like components detected')
ign = sorted(np.setdiff1d(all_comps, rej))
comptable.loc[ign, 'classification'] = 'ignored'
comptable.loc[ign, 'rationale'] += 'I005;'
# Move decision columns to end
comptable = comptable[[c for c in comptable if c not in cols_at_end] +
[c for c in cols_at_end if c in comptable]]
return comptable
kappa_rate = ((np.max(comptable.loc[good_guess, 'kappa']) -
np.min(comptable.loc[good_guess, 'kappa'])) /
(np.max(comptable.loc[good_guess, 'variance explained']) -
np.min(comptable.loc[good_guess, 'variance explained'])))
kappa_ratios = kappa_rate * comptable['variance explained'] / comptable[
'kappa']
varex_lower = stats.scoreatpercentile(
comptable.loc[good_guess, 'variance explained'], LOW_PERC)
varex_upper = stats.scoreatpercentile(
comptable.loc[good_guess, 'variance explained'], HIGH_PERC)
"""
Step 3: Get rid of midk components; i.e., those with higher than
max decision score and high variance
"""
max_good_d_score = EXTEND_FACTOR * len(good_guess) * n_decision_metrics
midk = acc[(comptable.loc[acc, 'd_table_score'] > max_good_d_score)
& (comptable.loc[acc, 'variance explained'] > EXTEND_FACTOR *
varex_upper)]
comptable.loc[midk, 'classification'] = 'rejected'
comptable.loc[midk, 'rationale'] += 'I006;'
acc = np.setdiff1d(acc, midk)
"""
Step 4: Find components to ignore
"""
good_guess = np.setdiff1d(good_guess, midk)
loaded = np.union1d(
good_guess,
acc[comptable.loc[acc, 'variance explained'] > varex_lower])
ign = np.setdiff1d(acc, loaded)
ign = np.setdiff1d(
ign, ign[comptable.loc[ign, 'd_table_score'] < max_good_d_score])
ign = np.setdiff1d(ign, ign[comptable.loc[ign, 'kappa'] > kappa_elbow])
comptable.loc[ign, 'classification'] = 'ignored'
comptable.loc[ign, 'rationale'] += 'I007;'
acc = np.setdiff1d(acc, ign)
"""
Step 5: Scrub the set
"""
if len(acc) > len(good_guess):
# Recompute the midk steps on the limited set to clean up the tail
d_table_rank = np.vstack([
len(acc) -
stats.rankdata(comptable.loc[acc, 'kappa'], method='ordinal'),
len(acc) -
stats.rankdata(comptable.loc[acc, 'dice_FR2'], method='ordinal'),
len(acc) - stats.rankdata(comptable.loc[acc, 'signal-noise_t'],
method='ordinal'),
stats.rankdata(countnoise[acc], method='ordinal'),
len(acc) -
stats.rankdata(comptable.loc[acc, 'countsigFR2'], method='ordinal')
]).T
comptable['d_table_score_scrub'] = np.nan
comptable.loc[acc, 'd_table_score_scrub'] = d_table_rank.sum(1)
num_acc_guess = int(
np.mean([
np.sum((comptable.loc[acc, 'kappa'] > kappa_elbow)
& (comptable.loc[acc, 'rho'] < rho_elbow)),
np.sum(comptable.loc[acc, 'kappa'] > kappa_elbow)
]))
conservative_guess = num_acc_guess * n_decision_metrics / RESTRICT_FACTOR
# Rejection candidate based on artifact type A: candartA
candartA = np.intersect1d(
acc[comptable.loc[acc,
'd_table_score_scrub'] > conservative_guess],
acc[kappa_ratios[acc] > EXTEND_FACTOR * 2])
candartA = np.intersect1d(
candartA,
candartA[comptable.loc[candartA,
'variance explained'] > varex_upper *
EXTEND_FACTOR])
comptable.loc[candartA, 'classification'] = 'rejected'
comptable.loc[candartA, 'rationale'] += 'I008;'
midk = np.union1d(midk, candartA)
# Rejection candidate based on artifact type B: candartB
candartB = comptable.loc[acc].loc[
comptable.loc[acc, 'd_table_score_scrub'] > num_acc_guess *
n_decision_metrics * HIGH_PERC / 100.].index.values
candartB = np.intersect1d(
candartB,
candartB[comptable.loc[candartB,
'variance explained'] > varex_lower *
EXTEND_FACTOR])
midk = np.union1d(midk, candartB)
comptable.loc[candartB, 'classification'] = 'rejected'
comptable.loc[candartB, 'rationale'] += 'I009;'
# Find comps to ignore
new_varex_lower = stats.scoreatpercentile(
comptable.loc[acc[:num_acc_guess], 'variance explained'], LOW_PERC)
candart = comptable.loc[acc].loc[
comptable.loc[acc, 'd_table_score'] > num_acc_guess *
n_decision_metrics].index.values
ign_add0 = np.intersect1d(
candart[comptable.loc[candart,
'variance explained'] > new_varex_lower],
candart)
ign_add0 = np.setdiff1d(ign_add0, midk)
comptable.loc[ign_add0, 'classification'] = 'ignored'
comptable.loc[ign_add0, 'rationale'] += 'I010;'
ign = np.union1d(ign, ign_add0)
ign_add1 = np.intersect1d(
acc[comptable.loc[acc, 'kappa'] <= kappa_elbow],
acc[comptable.loc[acc, 'variance explained'] > new_varex_lower])
ign_add1 = np.setdiff1d(ign_add1, midk)
comptable.loc[ign_add1, 'classification'] = 'ignored'
comptable.loc[ign_add1, 'rationale'] += 'I011;'
ign = np.union1d(ign, ign_add1)
acc = np.setdiff1d(acc, np.union1d(midk, ign))
# Move decision columns to end
comptable = comptable[[c for c in comptable if c not in cols_at_end] +
[c for c in cols_at_end if c in comptable]]
return comptable
def selcomps(seldict, comptable, mmix, manacc, n_echos):
"""
Classify components in seldict as "accepted," "rejected," or "ignored."
The selection process uses previously calculated parameters listed in `seldict`
for each ICA component such as Kappa (a T2* weighting metric), Rho (an S0 weighting metric),
and variance explained. See `Notes` for additional calculated metrics used to
classify each component into one of the four listed groups.
Parameters
----------
seldict : :obj:`dict`
A dictionary with component-specific features used for classification.
As output from `fitmodels_direct`
comptable : (C x X) :obj:`pandas.DataFrame`
Component metric table. One row for each component, with a column for
each metric. The index should be the component number.
mmix : (T x C) array_like
Mixing matrix for converting input data to component space, where `C`
is components and `T` is the number of volumes in the original data
manacc : :obj:`list`
Comma-separated list of indices of manually accepted components
n_echos : :obj:`int`
Number of echos in original data
Returns
-------
comptable : :obj:`pandas.DataFrame`
Updated component table with additional metrics and with
classification (accepted, rejected, or ignored)
Notes
-----
The selection algorithm used in this function was originated in ME-ICA
by Prantik Kundu, and his original implementation is available at:
https://github.com/ME-ICA/me-ica/blob/b2781dd087ab9de99a2ec3925f04f02ce84f0adc/meica.libs/select_model.py
This component selection process uses multiple, previously calculated metrics that include:
kappa, rho, variance explained, component spatial weighting maps, noise and spatial
frequency metrics, and measures of spatial overlap across metrics.
Prantik began to update these selection criteria to use SVMs to
distinguish components, a hypercommented version of this attempt is available at:
https://gist.github.com/emdupre/ca92d52d345d08ee85e104093b81482e
"""
cols_at_end = ['classification', 'rationale']
# Lists of components
all_comps = np.arange(comptable.shape[0])
# unclf is a full list that is whittled down over criteria
# since the default classification is "accepted", at the end of the tree
# the remaining elements in unclf are classified as accepted
unclf = all_comps.copy()
# If user has specified
if manacc:
LGR.info('Performing manual ICA component selection')
if ('classification' in comptable.columns and
'original_classification' not in comptable.columns):
comptable['original_classification'] = comptable['classification']
comptable['original_rationale'] = comptable['rationale']
comptable['classification'] = 'accepted'
comptable['rationale'] = ''
acc = [int(comp) for comp in manacc]
rej = sorted(np.setdiff1d(all_comps, acc))
comptable.loc[acc, 'classification'] = 'accepted'
comptable.loc[rej, 'classification'] = 'rejected'
comptable.loc[rej, 'rationale'] += 'I001;'
# Move decision columns to end
comptable = comptable[[c for c in comptable if c not in cols_at_end] +
[c for c in cols_at_end if c in comptable]]
comptable['rationale'] = comptable['rationale'].str.rstrip(';')
return comptable
comptable['classification'] = 'accepted'
comptable['rationale'] = ''
Z_maps = seldict['Z_maps']
Z_clmaps = seldict['Z_clmaps']
F_R2_maps = seldict['F_R2_maps']
F_S0_clmaps = seldict['F_S0_clmaps']
F_R2_clmaps = seldict['F_R2_clmaps']
Br_S0_clmaps = seldict['Br_S0_clmaps']
Br_R2_clmaps = seldict['Br_R2_clmaps']
# Set knobs
n_vols, n_comps = mmix.shape
LOW_PERC = 25
HIGH_PERC = 90
if n_vols < 100:
EXTEND_FACTOR = 3
else:
EXTEND_FACTOR = 2
RESTRICT_FACTOR = 2
"""
Tally number of significant voxels for cluster-extent thresholded R2 and S0
model F-statistic maps.
"""
comptable['countsigFR2'] = F_R2_clmaps.sum(axis=0)
comptable['countsigFS0'] = F_S0_clmaps.sum(axis=0)
"""
Generate Dice values for R2 and S0 models
- dice_FR2: Dice value of cluster-extent thresholded maps of R2-model betas
and F-statistics.
- dice_FS0: Dice value of cluster-extent thresholded maps of S0-model betas
and F-statistics.
"""
comptable['dice_FR2'] = np.zeros(all_comps.shape[0])
comptable['dice_FS0'] = np.zeros(all_comps.shape[0])
for i_comp in all_comps:
comptable.loc[i_comp, 'dice_FR2'] = utils.dice(Br_R2_clmaps[:, i_comp],
F_R2_clmaps[:, i_comp])
comptable.loc[i_comp, 'dice_FS0'] = utils.dice(Br_S0_clmaps[:, i_comp],
F_S0_clmaps[:, i_comp])
comptable.loc[np.isnan(comptable['dice_FR2']), 'dice_FR2'] = 0
comptable.loc[np.isnan(comptable['dice_FS0']), 'dice_FS0'] = 0
"""
Generate three metrics of component noise:
- countnoise: Number of "noise" voxels (voxels highly weighted for
component, but not from clusters)
- signal-noise_t: T-statistic for two-sample t-test of F-statistics from
"signal" voxels (voxels in clusters) against "noise" voxels (voxels not
in clusters) for R2 model.
- signal-noise_p: P-value from t-test.
"""
comptable['countnoise'] = 0
comptable['signal-noise_t'] = 0
comptable['signal-noise_p'] = 0
for i_comp in all_comps:
# index voxels significantly loading on component but not from clusters
comp_noise_sel = ((np.abs(Z_maps[:, i_comp]) > 1.95) &
(Z_clmaps[:, i_comp] == 0))
comptable.loc[i_comp, 'countnoise'] = np.array(
comp_noise_sel, dtype=np.int).sum()
# NOTE: Why only compare distributions of *unique* F-statistics?
noise_FR2_Z = np.log10(np.unique(F_R2_maps[comp_noise_sel, i_comp]))
signal_FR2_Z = np.log10(np.unique(
F_R2_maps[Z_clmaps[:, i_comp] == 1, i_comp]))
(comptable.loc[i_comp, 'signal-noise_t'],
comptable.loc[i_comp, 'signal-noise_p']) = stats.ttest_ind(
signal_FR2_Z, noise_FR2_Z, equal_var=False)
comptable.loc[np.isnan(comptable['signal-noise_t']), 'signal-noise_t'] = 0
comptable.loc[np.isnan(comptable['signal-noise_p']), 'signal-noise_p'] = 0
"""
Assemble decision table with five metrics:
- Kappa values ranked from largest to smallest
- R2-model F-score map/beta map Dice scores ranked from largest to smallest
- Signal F > Noise F t-statistics ranked from largest to smallest
- Number of "noise" voxels (voxels highly weighted for component, but not
from clusters) ranked from smallest to largest
- Number of voxels with significant R2-model F-scores within clusters
ranked from largest to smallest
Smaller values (i.e., higher ranks) across metrics indicate more BOLD
dependence and less noise.
"""
d_table_rank = np.vstack([
n_comps - stats.rankdata(comptable['kappa']),
n_comps - stats.rankdata(comptable['dice_FR2']),
n_comps - stats.rankdata(comptable['signal-noise_t']),
stats.rankdata(comptable['countnoise']),
n_comps - stats.rankdata(comptable['countsigFR2'])]).T
comptable['d_table_score'] = d_table_rank.mean(axis=1)
"""
Step 1: Reject anything that's obviously an artifact
a. Estimate a null variance
"""
# Rho is higher than Kappa
temp_rej0a = all_comps[(comptable['rho'] > comptable['kappa'])]
comptable.loc[temp_rej0a, 'classification'] = 'rejected'
comptable.loc[temp_rej0a, 'rationale'] += 'I002;'
# Number of significant voxels for S0 model is higher than number for R2
# model *and* number for R2 model is greater than zero.
temp_rej0b = all_comps[((comptable['countsigFS0'] > comptable['countsigFR2']) &
(comptable['countsigFR2'] > 0))]
comptable.loc[temp_rej0b, 'classification'] = 'rejected'
comptable.loc[temp_rej0b, 'rationale'] += 'I003;'
rej = np.union1d(temp_rej0a, temp_rej0b)
# Dice score for S0 maps is higher than Dice score for R2 maps and variance
# explained is higher than the median across components.
temp_rej1 = all_comps[(comptable['dice_FS0'] > comptable['dice_FR2']) &
(comptable['variance explained'] >
np.median(comptable['variance explained']))]
comptable.loc[temp_rej1, 'classification'] = 'rejected'
comptable.loc[temp_rej1, 'rationale'] += 'I004;'
rej = np.union1d(temp_rej1, rej)
# T-value is less than zero (noise has higher F-statistics than signal in
# map) and variance explained is higher than the median across components.
temp_rej2 = unclf[(comptable.loc[unclf, 'signal-noise_t'] < 0) &
(comptable.loc[unclf, 'variance explained'] >
np.median(comptable['variance explained']))]
comptable.loc[temp_rej2, 'classification'] = 'rejected'
comptable.loc[temp_rej2, 'rationale'] += 'I005;'
rej = np.union1d(temp_rej2, rej)
unclf = np.setdiff1d(unclf, rej)
"""
Step 2: Make a guess for what the good components are, in order to
estimate good component properties
a. Not outlier variance
b. Kappa>kappa_elbow
c. Rho<Rho_elbow
d. High R2* dice compared to S0 dice
e. Gain of F_R2 in clusters vs noise
f. Estimate a low and high variance
"""
# Step 2a
# Upper limit for variance explained is median across components with high
# Kappa values. High Kappa is defined as Kappa above Kappa elbow.
varex_upper_p = np.median(
comptable.loc[comptable['kappa'] > getelbow(comptable['kappa'], return_val=True),
'variance explained'])
ncls = unclf.copy()
# NOTE: We're not sure why this is done, nor why it's specifically done
# three times. Need to look into this deeper, esp. to make sure the 3
# isn't a hard-coded reference to the number of echoes.
# Reduce components to investigate as "good" to ones in which change in
# variance explained is less than the limit defined above.... What?
for i_loop in range(3):
ncls = comptable.loc[ncls].loc[
comptable.loc[
ncls, 'variance explained'].diff() < varex_upper_p].index.values
# Compute elbows from other elbows
f05, _, f01 = utils.getfbounds(n_echos)
kappas_nonsig = comptable.loc[comptable['kappa'] < f01, 'kappa']
# NOTE: Would an elbow from all Kappa values *ever* be lower than one from
# a subset of lower values?
kappa_elbow = np.min((getelbow(kappas_nonsig, return_val=True),
getelbow(comptable['kappa'], return_val=True)))
rho_elbow = np.mean((getelbow(comptable.loc[ncls, 'rho'], return_val=True),
getelbow(comptable['rho'], return_val=True),
f05))
# Provisionally accept components based on Kappa and Rho elbows
acc_prov = ncls[(comptable.loc[ncls, 'kappa'] >= kappa_elbow) &
(comptable.loc[ncls, 'rho'] < rho_elbow)]
if len(acc_prov) == 0:
LGR.warning('No BOLD-like components detected')
ign = sorted(np.setdiff1d(all_comps, rej))
comptable.loc[ign, 'classification'] = 'ignored'
comptable.loc[ign, 'rationale'] += 'I006;'
# Move decision columns to end
comptable = comptable[[c for c in comptable if c not in cols_at_end] +
[c for c in cols_at_end if c in comptable]]
comptable['rationale'] = comptable['rationale'].str.rstrip(';')
return comptable
# Calculate "rate" for kappa: kappa range divided by variance explained
# range, for potentially accepted components
# NOTE: What is the logic behind this?
kappa_rate = ((np.max(comptable.loc[acc_prov, 'kappa']) -
np.min(comptable.loc[acc_prov, 'kappa'])) /
(np.max(comptable.loc[acc_prov, 'variance explained']) -
np.min(comptable.loc[acc_prov, 'variance explained'])))
comptable['kappa ratio'] = kappa_rate * comptable['variance explained'] / comptable['kappa']
varex_lower = stats.scoreatpercentile(
comptable.loc[acc_prov, 'variance explained'], LOW_PERC)
varex_upper = stats.scoreatpercentile(
comptable.loc[acc_prov, 'variance explained'], HIGH_PERC)
"""
Step 3: Get rid of midk components; i.e., those with higher than
max decision score and high variance
"""
max_good_d_score = EXTEND_FACTOR * len(acc_prov)
midk = unclf[(comptable.loc[unclf, 'd_table_score'] > max_good_d_score) &
(comptable.loc[unclf, 'variance explained'] > EXTEND_FACTOR * varex_upper)]
comptable.loc[midk, 'classification'] = 'rejected'
comptable.loc[midk, 'rationale'] += 'I007;'
unclf = np.setdiff1d(unclf, midk)
acc_prov = np.setdiff1d(acc_prov, midk)
"""
Step 4: Find components to ignore
"""
# collect high variance unclassified components
# and mix of high/low provisionally accepted
high_varex = np.union1d(
acc_prov,
unclf[comptable.loc[unclf, 'variance explained'] > varex_lower])
# ignore low variance components
ign = np.setdiff1d(unclf, high_varex)
# but only if they have bad decision scores
ign = np.setdiff1d(
ign, ign[comptable.loc[ign, 'd_table_score'] < max_good_d_score])
# and low kappa
ign = np.setdiff1d(ign, ign[comptable.loc[ign, 'kappa'] > kappa_elbow])
comptable.loc[ign, 'classification'] = 'ignored'
comptable.loc[ign, 'rationale'] += 'I008;'
unclf = np.setdiff1d(unclf, ign)
"""
Step 5: Scrub the set if there are components that haven't been rejected or
ignored, but are still not listed in the provisionally accepted group.
"""
if len(unclf) > len(acc_prov):
comptable['d_table_score_scrub'] = np.nan
# Recompute the midk steps on the limited set to clean up the tail
d_table_rank = np.vstack([
len(unclf) - stats.rankdata(comptable.loc[unclf, 'kappa']),
len(unclf) - stats.rankdata(comptable.loc[unclf, 'dice_FR2']),
len(unclf) - stats.rankdata(comptable.loc[unclf, 'signal-noise_t']),
stats.rankdata(comptable.loc[unclf, 'countnoise']),
len(unclf) - stats.rankdata(comptable.loc[unclf, 'countsigFR2'])]).T
comptable.loc[unclf, 'd_table_score_scrub'] = d_table_rank.mean(1)
num_acc_guess = int(np.mean([
np.sum((comptable.loc[unclf, 'kappa'] > kappa_elbow) &
(comptable.loc[unclf, 'rho'] < rho_elbow)),
np.sum(comptable.loc[unclf, 'kappa'] > kappa_elbow)]))
# Rejection candidate based on artifact type A: candartA
conservative_guess = num_acc_guess / RESTRICT_FACTOR
candartA = np.intersect1d(
unclf[comptable.loc[unclf, 'd_table_score_scrub'] > conservative_guess],
unclf[comptable.loc[unclf, 'kappa ratio'] > EXTEND_FACTOR * 2])
candartA = (candartA[comptable.loc[candartA, 'variance explained'] >
varex_upper * EXTEND_FACTOR])
comptable.loc[candartA, 'classification'] = 'rejected'
comptable.loc[candartA, 'rationale'] += 'I009;'
midk = np.union1d(midk, candartA)
unclf = np.setdiff1d(unclf, midk)
# Rejection candidate based on artifact type B: candartB
conservative_guess2 = num_acc_guess * HIGH_PERC / 100.
candartB = unclf[comptable.loc[unclf, 'd_table_score_scrub'] > conservative_guess2]
candartB = (candartB[comptable.loc[candartB, 'variance explained'] >
varex_lower * EXTEND_FACTOR])
comptable.loc[candartB, 'classification'] = 'rejected'
comptable.loc[candartB, 'rationale'] += 'I010;'
midk = np.union1d(midk, candartB)
unclf = np.setdiff1d(unclf, midk)
# Find components to ignore
# Ignore high variance explained, poor decision tree scored components
new_varex_lower = stats.scoreatpercentile(
comptable.loc[unclf[:num_acc_guess], 'variance explained'],
LOW_PERC)
candart = unclf[comptable.loc[unclf, 'd_table_score_scrub'] > num_acc_guess]
ign_add0 = candart[comptable.loc[candart, 'variance explained'] > new_varex_lower]
ign_add0 = np.setdiff1d(ign_add0, midk)
comptable.loc[ign_add0, 'classification'] = 'ignored'
comptable.loc[ign_add0, 'rationale'] += 'I011;'
ign = np.union1d(ign, ign_add0)
unclf = np.setdiff1d(unclf, ign)
# Ignore low Kappa, high variance explained components
ign_add1 = np.intersect1d(
unclf[comptable.loc[unclf, 'kappa'] <= kappa_elbow],
unclf[comptable.loc[unclf, 'variance explained'] > new_varex_lower])
ign_add1 = np.setdiff1d(ign_add1, midk)
comptable.loc[ign_add1, 'classification'] = 'ignored'
comptable.loc[ign_add1, 'rationale'] += 'I012;'
# at this point, unclf is equivalent to accepted
# Move decision columns to end
comptable = comptable[[c for c in comptable if c not in cols_at_end] +
[c for c in cols_at_end if c in comptable]]
comptable['rationale'] = comptable['rationale'].str.rstrip(';')
return comptable