def test_csd_xval():
# First, let's see that it works with some data:
data = nib.load(fdata).get_data()[1:3, 1:3, 1:3] # Make it *small*
gtab = gt.gradient_table(fbval, fbvec)
S0 = np.mean(data[..., gtab.b0s_mask])
response = ([0.0015, 0.0003, 0.0001], S0)
csdm = csd.ConstrainedSphericalDeconvModel(gtab, response)
kf_xval = xval.kfold_xval(csdm, data, 2, response, sh_order=2)
# In simulation, it should work rather well (high COD):
psphere = dpd.get_sphere('symmetric362')
bvecs = np.concatenate(([[0, 0, 0]], psphere.vertices))
bvals = np.zeros(len(bvecs)) + 1000
bvals[0] = 0
gtab = gt.gradient_table(bvals, bvecs)
mevals = np.array(([0.0015, 0.0003, 0.0001], [0.0015, 0.0003, 0.0003]))
mevecs = [
np.array([[1, 0, 0], [0, 1, 0], [0, 0, 1]]),
np.array([[0, 0, 1], [0, 1, 0], [1, 0, 0]])
]
S0 = 100
S = sims.single_tensor(gtab, S0, mevals[0], mevecs[0], snr=None)
sm = csd.ConstrainedSphericalDeconvModel(gtab, response)
smfit = sm.fit(S)
np.random.seed(12345)
response = ([0.0015, 0.0003, 0.0001], S0)
kf_xval = xval.kfold_xval(sm, S, 2, response, sh_order=2)
# Because of the regularization, COD is not going to be perfect here:
cod = xval.coeff_of_determination(S, kf_xval)
# We'll just test for regressions:
csd_cod = 97 # pre-computed by hand for this random seed
# We're going to be really lenient here:
npt.assert_array_almost_equal(np.round(cod), csd_cod)
def _fit(gtab, data, mask, response=None, sh_order=None, lambda_=1, tau=0.1):
"""
Helper function that does the core of fitting a model to data.
"""
if sh_order is None:
ndata = np.sum(~gtab.b0s_mask)
# See dipy.reconst.shm.calculate_max_order
L1 = (-3 + np.sqrt(1 + 8 * ndata)) / 2.0
sh_order = int(L1)
if np.mod(sh_order, 2) != 0:
sh_order = sh_order - 1
if sh_order > 8:
sh_order = 8
if response is None:
response, ratio = csd.auto_response(gtab,
data,
roi_radius=10,
fa_thr=0.7)
csdmodel = csd.ConstrainedSphericalDeconvModel(gtab,
response,
sh_order=sh_order)
csdfit = csdmodel.fit(data, mask=mask)
return csdfit
def fit_csd(data_files,
bval_files,
bvec_files,
mask=None,
response=None,
sh_order=8,
lambda_=1,
tau=0.1,
out_dir=None):
"""
Fit the CSD model and save file with SH coefficients.
Parameters
----------
data_files : str or list
Files containing DWI data. If this is a str, that's the full path to a
single file. If it's a list, each entry is a full path.
bval_files : str or list
Equivalent to `data_files`.
bvec_files : str or list
Equivalent to `data_files`.
mask : ndarray, optional
Binary mask, set to True or 1 in voxels to be processed.
Default: Process all voxels.
out_dir : str, optional
A full path to a directory to store the maps that get computed.
Default: file with coefficients gets stored in the same directory as
the first DWI file in `data_files`.
Returns
-------
fname : the full path to the file containing the SH coefficients.
"""
img, data, gtab, mask = ut.prepare_data(data_files, bval_files, bvec_files)
if response is None:
response, ratio = csd.auto_response(gtab,
data,
roi_radius=10,
fa_thr=0.7)
csdmodel = csd.ConstrainedSphericalDeconvModel(gtab,
response,
sh_order=sh_order)
csdfit = csdmodel.fit(data, mask=mask)
if out_dir is None:
out_dir = op.join(op.split(data_files)[0], 'dki')
if not op.exists(out_dir):
os.makedirs(out_dir)
aff = img.affine
fname = op.join(out_dir, 'csd_sh_coeff.nii.gz')
nib.save(nib.Nifti1Image(csdfit.shm_coeff, aff), fname)
return fname
def test_csd_xval():
# First, let's see that it works with some data:
data = load_nifti_data(fdata)[1:3, 1:3, 1:3] # Make it *small*
gtab = gt.gradient_table(fbval, fbvec)
S0 = np.mean(data[..., gtab.b0s_mask])
response = ([0.0015, 0.0003, 0.0001], S0)
# In simulation, it should work rather well (high COD):
psphere = dpd.get_sphere('symmetric362')
bvecs = np.concatenate(([[0, 0, 0]], psphere.vertices))
bvals = np.zeros(len(bvecs)) + 1000
bvals[0] = 0
gtab = gt.gradient_table(bvals, bvecs)
mevals = np.array(([0.0015, 0.0003, 0.0001], [0.0015, 0.0003, 0.0003]))
mevecs = [
np.array([[1, 0, 0], [0, 1, 0], [0, 0, 1]]),
np.array([[0, 0, 1], [0, 1, 0], [1, 0, 0]])
]
S0 = 100
S = sims.single_tensor(gtab, S0, mevals[0], mevecs[0], snr=None)
with warnings.catch_warnings():
warnings.filterwarnings("ignore",
message=descoteaux07_legacy_msg,
category=PendingDeprecationWarning)
sm = csd.ConstrainedSphericalDeconvModel(gtab, response)
np.random.seed(12345)
response = ([0.0015, 0.0003, 0.0001], S0)
with warnings.catch_warnings():
warnings.filterwarnings("ignore",
message=descoteaux07_legacy_msg,
category=PendingDeprecationWarning)
kf_xval = xval.kfold_xval(sm, S, 2, response, sh_order=2)
# Because of the regularization, COD is not going to be perfect here:
cod = xval.coeff_of_determination(S, kf_xval)
# We'll just test for regressions:
csd_cod = 97 # pre-computed by hand for this random seed
# We're going to be really lenient here:
npt.assert_array_almost_equal(np.round(cod), csd_cod)
# Test for sD data with more than one voxel for use of a mask:
S = np.array([[S, S], [S, S]])
mask = np.ones(S.shape[:-1], dtype=bool)
mask[1, 1] = 0
with warnings.catch_warnings():
warnings.filterwarnings("ignore",
message=descoteaux07_legacy_msg,
category=PendingDeprecationWarning)
kf_xval = xval.kfold_xval(sm, S, 2, response, sh_order=2, mask=mask)
cod = xval.coeff_of_determination(S, kf_xval)
npt.assert_array_almost_equal(np.round(cod[0]), csd_cod)
def _fit(gtab, data, mask, response=None, sh_order=8,
lambda_=1, tau=0.1):
"""
Helper function that does the core of fitting a model to data.
"""
if response is None:
response, ratio = csd.auto_response(gtab, data, roi_radius=10,
fa_thr=0.7)
csdmodel = csd.ConstrainedSphericalDeconvModel(gtab, response,
sh_order=sh_order)
csdfit = csdmodel.fit(data, mask=mask)
return csdfit
dpd.fetch_stanford_hardi() img, gtab = dpd.read_stanford_hardi() data = img.get_data() cc_vox = data[40, 70, 38] cso_vox = data[30, 76, 38] """ We initialize each kind of model: """ dti_model = dti.TensorModel(gtab) response, ratio = csd.auto_response(gtab, data, roi_radius=10, fa_thr=0.7) csd_model = csd.ConstrainedSphericalDeconvModel(gtab, response) """ Next, we perform cross-validation for each kind of model, comparing model predictions to the diffusion MRI data in each one of these voxels. Note that we use 2-fold cross-validation, which means that in each iteration, the model will be fit to half of the data, and used to predict the other half. """ dti_cc = xval.kfold_xval(dti_model, cc_vox, 2) csd_cc = xval.kfold_xval(csd_model, cc_vox, 2, response) dti_cso = xval.kfold_xval(dti_model, cso_vox, 2) csd_cso = xval.kfold_xval(csd_model, cso_vox, 2, response) """