def find_bad_nrigh(name, score):
test_data = np.load(os.path.join('..', 'cci_clean_data', name))
data_evl = test_data['arr_0']
key = os.path.splitext(name)[0]
cci_score = cci_dict[key]
cci_score = np.array(cci_score)
streamlines_evl = Streamlines()
for i in range(np.shape(data_evl)[0]):
tmp = data_evl[i]
tmp = zero_remove(tmp)
#tmp = tmp[~np.all(tmp == 0, axis=-1)]
#tmp = np.around(tmp, decimals=0)
streamlines_evl.append(tmp)
lengths = np.array(list(length(streamlines_evl)))
neighb = np.zeros((np.shape(data_evl)[0]))
subsamp_sls = set_number_of_points(streamlines_evl, 64)
for i in range(len(streamlines_evl)):
mdf_mx = bundles_distances_mdf([subsamp_sls[i]], subsamp_sls)
if (score[i] == 0): # bad fiber
thre = np.percentile(mdf_mx, 4)
len_bad = lengths[i]
bound = len_bad * 0.1
len_limt = 1 * ((lengths > len_bad - bound) &
(lengths < len_bad + bound))
label = 1 * (mdf_mx < thre).flatten() # bad neighbour
neighb = neighb + label * (cci_score < 10)
return data_evl, neighb
def cal_cov_sub(fiber_sub):
streamlines_evl = Streamlines()
for i in range(np.shape(fiber_sub)[0]):
tmp = fiber_sub[i]
tmp = zero_remove(tmp)
streamlines_evl.append(tmp)
#==============
fiber_one = fiber_sub[0].transpose()
fiber_one_std = preprocessing.scale(fiber_one)
covarience = np.cov(fiber_one_std)
result = np.array([
covarience[0, 0], covarience[1, 1], covarience[2, 2], covarience[0, 1],
covarience[0, 2], covarience[1, 2]
]).transpose()
for i in range(1, np.shape(fiber_sub)[0]):
fiber_one = fiber_sub[i].transpose()
fiber_one_std = preprocessing.scale(fiber_one)
covarience = np.cov(fiber_one_std)
#tmp = np.array( [covarience[0,0], covarience[1,1], covarience[2,2]]).transpose()
tmp = np.array([
covarience[0, 0], covarience[1, 1], covarience[2, 2],
covarience[0, 1], covarience[0, 2], covarience[1, 2]
]).transpose()
result = np.vstack((result, tmp))
return result
def remove_clusters_by_size(clusters, min_size=0):
ob = filter(lambda c: len(c) >= min_size, clusters)
centroids = Streamlines()
for cluster in ob:
centroids.append(cluster.centroid)
return centroids
def remove_clusters_by_size(clusters, min_size=0):
ob = filter(lambda c: len(c) >= min_size, clusters)
centroids = Streamlines()
for cluster in ob:
centroids.append(cluster.centroid)
return centroids
def remove_cci_outliers(streamlines):
s = Streamlines(streamlines)
cci = cluster_confidence(s,subsample=7)
keep_streamlines = Streamlines()
keep_streamlines_idx = list()
for i, sl in enumerate(s):
if cci[i] >= 1:
keep_streamlines.append(sl)
keep_streamlines_idx.append(i)
return keep_streamlines,keep_streamlines_idx
def test_horizon():
s1 = 10 * np.array([[0, 0, 0], [1, 0, 0], [2, 0, 0], [3, 0, 0], [4, 0, 0]],
dtype='f8')
s2 = 10 * np.array([[0, 0, 0], [0, 1, 0], [0, 2, 0], [0, 3, 0], [0, 4, 0]],
dtype='f8')
s3 = 10 * np.array(
[[0, 0, 0], [1, 0.2, 0], [2, 0.2, 0], [3, 0.2, 0], [4, 0.2, 0]],
dtype='f8')
print(s1.shape)
print(s2.shape)
print(s3.shape)
streamlines = Streamlines()
streamlines.append(s1)
streamlines.append(s2)
streamlines.append(s3)
tractograms = [streamlines]
images = None
horizon(tractograms,
images=images,
cluster=True,
cluster_thr=5,
random_colors=False,
length_lt=np.inf,
length_gt=0,
clusters_lt=np.inf,
clusters_gt=0,
world_coords=False,
interactive=False)
affine = np.diag([2., 1, 1, 1]).astype('f8')
data = 255 * np.random.rand(150, 150, 150)
images = [(data, affine)]
horizon(tractograms,
images=images,
cluster=True,
cluster_thr=5,
random_colors=False,
length_lt=np.inf,
length_gt=0,
clusters_lt=np.inf,
clusters_gt=0,
world_coords=True,
interactive=False)
def test_horizon():
s1 = 10 * np.array([[0, 0, 0],
[1, 0, 0],
[2, 0, 0],
[3, 0, 0],
[4, 0, 0]], dtype='f8')
s2 = 10 * np.array([[0, 0, 0],
[0, 1, 0],
[0, 2, 0],
[0, 3, 0],
[0, 4, 0]], dtype='f8')
s3 = 10 * np.array([[0, 0, 0],
[1, 0.2, 0],
[2, 0.2, 0],
[3, 0.2, 0],
[4, 0.2, 0]], dtype='f8')
print(s1.shape)
print(s2.shape)
print(s3.shape)
streamlines = Streamlines()
streamlines.append(s1)
streamlines.append(s2)
streamlines.append(s3)
tractograms = [streamlines]
images = None
horizon(tractograms, images=images, cluster=True, cluster_thr=5,
random_colors=False, length_lt=np.inf, length_gt=0,
clusters_lt=np.inf, clusters_gt=0,
world_coords=False, interactive=False)
affine = np.diag([2., 1, 1, 1]).astype('f8')
data = 255 * np.random.rand(150, 150, 150)
images = [(data, affine)]
horizon(tractograms, images=images, cluster=True, cluster_thr=5,
random_colors=False, length_lt=np.inf, length_gt=0,
clusters_lt=np.inf, clusters_gt=0,
world_coords=True, interactive=False)
tractograms = []
horizon(tractograms, images=images, cluster=True, cluster_thr=5,
random_colors=False, length_lt=np.inf, length_gt=0,
clusters_lt=np.inf, clusters_gt=0,
world_coords=True, interactive=False)
def test_streamlines_generator():
# Test generator
streamlines_generator = Streamlines(generate_sl(streamlines))
npt.assert_equal(len(streamlines_generator), len(streamlines))
# Nothing should change
streamlines_generator.append(np.array([]))
npt.assert_equal(len(streamlines_generator), len(streamlines))
# Test append error
npt.assert_raises(ValueError, streamlines_generator.append, streamlines)
# Test empty streamlines
streamlines_generator = Streamlines(np.array([]))
npt.assert_equal(len(streamlines_generator), 0)
def test_streamlines_generator():
# Test generator
streamlines_generator = Streamlines(generate_sl(streamlines))
npt.assert_equal(len(streamlines_generator), len(streamlines))
# Nothing should change
streamlines_generator.append(np.array([]))
npt.assert_equal(len(streamlines_generator), len(streamlines))
# Test append error
npt.assert_raises(ValueError, streamlines_generator.append, streamlines)
# Test empty streamlines
streamlines_generator = Streamlines(np.array([]))
npt.assert_equal(len(streamlines_generator), 0)
def visualize_streamline(darray,
score,
save_able=False,
save_name='default.png',
control_par=1,
hue=[0.5, 1]):
data_evl = darray
streamlines_evl = Streamlines()
for i in range(np.shape(data_evl)[0]):
tmp = data_evl[i]
tmp = zero_remove(tmp)
#tmp = tmp[~np.all(tmp == 0, axis=-1)]
#tmp = np.around(tmp, decimals=0)
streamlines_evl.append(tmp)
mse_nor = score
# Visualize the streamlines, colored by cci
ren = window.Scene()
saturation = [0.0, 1.0]
lut_cmap = actor.colormap_lookup_table(
scale_range=(min(mse_nor), max(mse_nor) / control_par),
hue_range=hue,
saturation_range=saturation)
bar3 = actor.scalar_bar(lut_cmap)
ren.add(bar3)
stream_actor = actor.line(streamlines_evl,
mse_nor,
linewidth=0.1,
lookup_colormap=lut_cmap)
ren.add(stream_actor)
if not save_able:
interactive = True
if interactive:
window.show(ren)
if save_able:
window.record(ren, n_frames=1, out_path=save_name, size=(800, 800))
def clean_subject(ndata):
cci = []
streamlines_evl = Streamlines()
for j in range(np.shape(ndata)[0]):
tmp = ndata[j]
tmp = zero_remove(tmp)
streamlines_evl.append(tmp)
lengths = list(utils.length(streamlines_evl))
long_streamlines_evl = Streamlines()
for i, sl in enumerate(streamlines_evl):
if lengths[i] > 40:
long_streamlines_evl.append(sl)
streamlines_test = remove_indentical(10, long_streamlines_evl)
cci_idv = cluster_confidence(streamlines_test, subsample=64)
cci.append(cci_idv)
return gen_array(streamlines_test), np.array(cci[0])
def cal_cci(name_list, text):
cci = []
for i in range(len(name_list)):
path = os.path.join('np_data', name_list[i])
sample_data = np.load(path)
ndata = sample_data['arr_0']
streamlines_evl = Streamlines()
for j in range(np.shape(ndata)[0]):
tmp = ndata[j]
tmp = zero_remove(tmp)
streamlines_evl.append(tmp)
streamlines_test = remove_indentical(10, streamlines_evl)
cci_idv = cluster_confidence(streamlines_test, subsample=64)
cci.append(cci_idv)
print('the ' + str(i + 1) + ' finished')
path_save = os.path.join('data_4_model', text)
np.save(path_save, cci)
return cci
def remove_indentical(n, streamlines_ori):
for i in range(n):
error_index = []
subsamp_sls = set_number_of_points(streamlines_ori, 64)
mdf1 = np.zeros((1, len(subsamp_sls)))
for i, sl in enumerate(subsamp_sls):
mdf_mx = bundles_distances_mdf([subsamp_sls[i]], subsamp_sls)
mdf1 = np.vstack((mdf1, mdf_mx))
if (mdf_mx == 0).sum() > 1:
if i - 1 not in error_index:
error_index.append(i)
if error_index == []:
return streamlines_ori
print('number of detecting iteration is ' + str(2 * i + 1))
break
streamlines_evl_final1 = Streamlines()
for i, sl in enumerate(streamlines_ori):
if i not in error_index:
streamlines_evl_final1.append(sl)
error_index = []
subsamp_sls = set_number_of_points(streamlines_evl_final1, 64)
mdf1 = np.zeros((1, len(subsamp_sls)))
for i, sl in enumerate(subsamp_sls):
mdf_mx = bundles_distances_mdf([subsamp_sls[i]], subsamp_sls)
mdf1 = np.vstack((mdf1, mdf_mx))
if (mdf_mx == 0).sum() > 1:
if i - 1 not in error_index:
error_index.append(i)
if error_index == []:
return streamlines_evl_final1
print('number of detecting iteration is ' + str(2 * i + 2))
break
streamlines_ori = Streamlines()
for i, sl in enumerate(streamlines_evl_final1):
if i not in error_index:
streamlines_ori.append(sl)
def cal_cov_sub(sub_name):
fiber_sub = np.load(os.path.join('..', 'cci_clean_data', sub_name))
fiber_sub = fiber_sub['arr_0']
cci = cci_dict[os.path.splitext(sub_name)[0]]
mask_score = mask_score_dict[os.path.splitext(sub_name)[0]]
streamlines_evl = Streamlines()
for i in range(np.shape(fiber_sub)[0]):
tmp = fiber_sub[i]
tmp = zero_remove(tmp)
streamlines_evl.append(tmp)
lengths = np.array(list(length(streamlines_evl)))
#==============
fiber_one = fiber_sub[0].transpose()
fiber_one_std = preprocessing.scale(fiber_one)
covarience = np.cov(fiber_one_std)
result = np.array([
mask_score[0], cci[0], lengths[0], covarience[0, 0], covarience[1, 1],
covarience[2, 2], covarience[0, 1], covarience[0, 2], covarience[1, 2]
]).transpose()
for i in range(1, np.shape(fiber_sub)[0]):
fiber_one = fiber_sub[i].transpose()
fiber_one_std = preprocessing.scale(fiber_one)
covarience = np.cov(fiber_one_std)
#tmp = np.array( [covarience[0,0], covarience[1,1], covarience[2,2]]).transpose()
tmp = np.array([
mask_score[i], cci[i], lengths[i], covarience[0, 0],
covarience[1, 1], covarience[2, 2], covarience[0, 1],
covarience[0, 2], covarience[1, 2]
]).transpose()
result = np.vstack((result, tmp))
return result
def gen_short_data(name_list):
for i in range(len(name_list)):
name = name_list[i]
path = os.path.join('..', 'cci_clean_data', name)
sample_data = np.load(path)
ndata = sample_data['arr_0']
streamlines_evl = Streamlines()
for j in range(np.shape(ndata)[0]):
tmp = ndata[j]
tmp = zero_remove(tmp)
streamlines_evl.append(tmp)
subsamp_sls = set_number_of_points(streamlines_evl, sub_len)
tt = np.array(subsamp_sls)
path = os.path.join('..', 'subsample-data', str(sub_len))
if not os.path.exists(path):
os.makedirs(path)
name_save = os.path.join(path, os.path.splitext(name)[0])
np.savez_compressed(name_save, tt)
print(str(i + 1) + '/141 finished')
def test_cluster_confidence():
mysl = np.array([np.arange(10)] * 3, 'float').T
# a short streamline (<20 mm) should raise an error unless override=True
test_streamlines = Streamlines()
test_streamlines.append(mysl)
assert_raises(ValueError, cluster_confidence, test_streamlines)
cci = cluster_confidence(test_streamlines, override=True)
# two identical streamlines should raise an error
test_streamlines = Streamlines()
test_streamlines.append(mysl, cache_build=True)
test_streamlines.append(mysl)
test_streamlines.finalize_append()
assert_raises(ValueError, cluster_confidence, test_streamlines)
# 3 offset collinear streamlines
test_streamlines = Streamlines()
test_streamlines.append(mysl, cache_build=True)
test_streamlines.append(mysl + 1)
test_streamlines.append(mysl + 2)
test_streamlines.finalize_append()
cci = cluster_confidence(test_streamlines, override=True)
assert_equal(cci[0], cci[2])
assert_true(cci[1] > cci[0])
# 3 parallel streamlines
mysl = np.zeros([10, 3])
mysl[:, 0] = np.arange(10)
mysl2 = mysl.copy()
mysl2[:, 1] = 1
mysl3 = mysl.copy()
mysl3[:, 1] = 2
mysl4 = mysl.copy()
mysl4[:, 1] = 4
mysl5 = mysl.copy()
mysl5[:, 1] = 5000
test_streamlines_p1 = Streamlines()
test_streamlines_p1.append(mysl, cache_build=True)
test_streamlines_p1.append(mysl2)
test_streamlines_p1.append(mysl3)
test_streamlines_p1.finalize_append()
test_streamlines_p2 = Streamlines()
test_streamlines_p2.append(mysl, cache_build=True)
test_streamlines_p2.append(mysl3)
test_streamlines_p2.append(mysl4)
test_streamlines_p2.finalize_append()
test_streamlines_p3 = Streamlines()
test_streamlines_p3.append(mysl, cache_build=True)
test_streamlines_p3.append(mysl2)
test_streamlines_p3.append(mysl3)
test_streamlines_p3.append(mysl5)
test_streamlines_p3.finalize_append()
cci_p1 = cluster_confidence(test_streamlines_p1, override=True)
cci_p2 = cluster_confidence(test_streamlines_p2, override=True)
# test relative distance
assert_array_equal(cci_p1, cci_p2 * 2)
# test simple cci calculation
expected_p1 = np.array([1. / 1 + 1. / 2, 1. / 1 + 1. / 1, 1. / 1 + 1. / 2])
expected_p2 = np.array([1. / 2 + 1. / 4, 1. / 2 + 1. / 2, 1. / 2 + 1. / 4])
assert_array_equal(expected_p1, cci_p1)
assert_array_equal(expected_p2, cci_p2)
# test power variable calculation (dropoff with distance)
cci_p1_pow2 = cluster_confidence(test_streamlines_p1,
power=2,
override=True)
expected_p1_pow2 = np.array([
np.power(1. / 1, 2) + np.power(1. / 2, 2),
np.power(1. / 1, 2) + np.power(1. / 1, 2),
np.power(1. / 1, 2) + np.power(1. / 2, 2)
])
assert_array_equal(cci_p1_pow2, expected_p1_pow2)
# test max distance (ignore distant sls)
cci_dist = cluster_confidence(test_streamlines_p3,
max_mdf=5,
override=True)
expected_cci_dist = np.concatenate([cci_p1, np.zeros(1)])
assert_array_equal(cci_dist, expected_cci_dist)
cc_uniques = np.unique(cc_int, axis=0)
score_tmp = cal_dist_score(avg_dist, cc_uniques)
scores.append(score_tmp)
return np.array(scores)
result_dis = cal_score_subject(bundle)
#%%
streamlines_evl = Streamlines()
for j in range(np.shape(bundle)[0]):
tmp = bundle[j]
tmp = zero_remove(tmp)
streamlines_evl.append(tmp)
result_cci = cluster_confidence(streamlines_evl, subsample=64)
#%%
preds_cci = 1 * (result_cci > results.cci_thre)
preds_dis = 1 * (result_dis < results.dis_thre)
pred_if = 1 * (pred_if > 0)
pred_1 = 1 * ((preds_cci + preds_dis + pred_if) > 2)
bundle_str = Streamlines()
for i in range(np.shape(bundle)[0]):
tmp = bundle[i]
denoise = model(bundle)
denoise = denoise.numpy()
mse_idv = cal_mse(bundle, denoise)
thre = np.percentile(mse_idv,thre_con)
pred_1 = 1*(mse_idv<thre)
bundle_str = Streamlines()
for i in range(np.shape(bundle)[0]):
tmp = bundle[i]
tmp = zero_remove(tmp)
#tmp = tmp[~np.all(tmp == 0, axis=-1)]
#tmp = np.around(tmp, decimals=0)
bundle_str.append(tmp)
lengths = length(bundle_str)
len_thre = results.len_con
pred_2 = 1*(lengths > len_thre)
pred = 1*((pred_1 + pred_2)>1)
op_path = 'result'
if not os.path.exists(op_path):
os.mkdir(op_path)
save_path = os.path.join(op_path,'Detection'+name.split('_')[0]+'_m'+str(results.model_type))
np.save(save_path,pred)
def test_horizon_flow():
s1 = 10 * np.array([[0, 0, 0], [1, 0, 0], [2, 0, 0], [3, 0, 0], [4, 0, 0]],
dtype='f8')
s2 = 10 * np.array([[0, 0, 0], [0, 1, 0], [0, 2, 0], [0, 3, 0], [0, 4, 0]],
dtype='f8')
s3 = 10 * np.array(
[[0, 0, 0], [1, 0.2, 0], [2, 0.2, 0], [3, 0.2, 0], [4, 0.2, 0]],
dtype='f8')
affine = np.array([[1., 0., 0., -98.], [0., 1., 0., -134.],
[0., 0., 1., -72.], [0., 0., 0., 1.]])
data = 255 * np.random.rand(197, 233, 189)
vox_size = (1., 1., 1.)
streamlines = Streamlines()
streamlines.append(s1)
streamlines.append(s2)
streamlines.append(s3)
header = create_nifti_header(affine, data.shape, vox_size)
sft = StatefulTractogram(streamlines, header, Space.RASMM)
tractograms = [sft]
images = None
horizon(tractograms,
images=images,
cluster=True,
cluster_thr=5,
random_colors=False,
length_lt=np.inf,
length_gt=0,
clusters_lt=np.inf,
clusters_gt=0,
world_coords=True,
interactive=False)
buan_colors = np.ones(streamlines.get_data().shape)
horizon(tractograms,
buan=True,
buan_colors=buan_colors,
world_coords=True,
interactive=False)
data = 255 * np.random.rand(197, 233, 189)
images = [(data, affine)]
horizon(tractograms,
images=images,
cluster=True,
cluster_thr=5,
random_colors=False,
length_lt=np.inf,
length_gt=0,
clusters_lt=np.inf,
clusters_gt=0,
world_coords=True,
interactive=False)
with TemporaryDirectory() as out_dir:
fimg = os.path.join(out_dir, 'test.nii.gz')
ftrk = os.path.join(out_dir, 'test.trk')
fnpy = os.path.join(out_dir, 'test.npy')
save_nifti(fimg, data, affine)
dimensions = data.shape
nii_header = create_nifti_header(affine, dimensions, vox_size)
sft = StatefulTractogram(streamlines, nii_header, space=Space.RASMM)
save_tractogram(sft, ftrk, bbox_valid_check=False)
pvalues = np.random.uniform(low=0, high=1, size=(10, ))
np.save(fnpy, pvalues)
input_files = [ftrk, fimg]
npt.assert_equal(len(input_files), 2)
hz_flow = HorizonFlow()
hz_flow.run(input_files=input_files,
stealth=True,
out_dir=out_dir,
out_stealth_png='tmp_x.png')
npt.assert_equal(os.path.exists(os.path.join(out_dir, 'tmp_x.png')),
True)
npt.assert_raises(ValueError,
hz_flow.run,
input_files=input_files,
bg_color=(0.2, 0.2))
hz_flow.run(input_files=input_files,
stealth=True,
bg_color=[
0.5,
],
out_dir=out_dir,
out_stealth_png='tmp_x.png')
npt.assert_equal(os.path.exists(os.path.join(out_dir, 'tmp_x.png')),
True)
input_files = [ftrk, fnpy]
npt.assert_equal(len(input_files), 2)
hz_flow.run(input_files=input_files,
stealth=True,
bg_color=[
0.5,
],
buan=True,
buan_thr=0.5,
buan_highlight=(1, 1, 0),
out_dir=out_dir,
out_stealth_png='tmp_x.png')
npt.assert_equal(os.path.exists(os.path.join(out_dir, 'tmp_x.png')),
True)
npt.assert_raises(ValueError,
hz_flow.run,
input_files=input_files,
roi_colors=(0.2, 0.2))
hz_flow.run(input_files=input_files,
stealth=True,
roi_colors=[
0.5,
],
out_dir=out_dir,
out_stealth_png='tmp_x.png')
npt.assert_equal(os.path.exists(os.path.join(out_dir, 'tmp_x.png')),
True)
mse_idv = cal_mse(bundle, denoise)
#%%
thre = np.percentile(mse_idv,85)
pred_1 = 1*(mse_idv<thre)
bundle_str = Streamlines()
for i in range(np.shape(bundle)[0]):
tmp = bundle[i]
tmp = zero_remove(tmp)
#tmp = tmp[~np.all(tmp == 0, axis=-1)]
#tmp = np.around(tmp, decimals=0)
bundle_str.append(tmp)
lengths = length(bundle_str)
len_thre = 40
pred_2 = 1*(lengths > len_thre)
pred = 1*((pred_1 + pred_2)>1)
data_new = np.delete(bundle, np.where(pred == 0), axis=0)
npz2ply_cleaned(data_new,name)
#%%
import sys
all_sl = Streamlines(all_sl)
lengths = list(length(all_sl))
print('Removing small streamlines, DIPY. Number of streamlines: ' +
str(len(lengths)))
t1 = time.time()
long_sl = Streamlines()
#n_long= 0
c_long = 0
for i, sl in enumerate(all_sl):
if i % 10000 == 0:
print(i)
if lengths[i] > min_stream_length:
long_sl.append(sl)
#n_long+= sl.shape[0]
c_long += 1
print(
'Finished removing small streamlines, DIPY, time elapsed (minutes): '
+ str(int((time.time() - t1) / 60)) +
'. Percentage of streamlines kept: ' +
str(int(100 * c_long / len(lengths))))
sft = StatefulTractogram(long_sl, FA_img_nii, Space.RASMM)
save_trk(
sft, dav_dir + "tractogram_dipy_deterministic_long_" +
str(min_stream_length) + ".trk")
####################################################
def test_horizon_flow():
s1 = 10 * np.array([[0, 0, 0], [1, 0, 0], [2, 0, 0], [3, 0, 0], [4, 0, 0]],
dtype='f8')
s2 = 10 * np.array([[0, 0, 0], [0, 1, 0], [0, 2, 0], [0, 3, 0], [0, 4, 0]],
dtype='f8')
s3 = 10 * np.array(
[[0, 0, 0], [1, 0.2, 0], [2, 0.2, 0], [3, 0.2, 0], [4, 0.2, 0]],
dtype='f8')
print(s1.shape)
print(s2.shape)
print(s3.shape)
streamlines = Streamlines()
streamlines.append(s1)
streamlines.append(s2)
streamlines.append(s3)
tractograms = [streamlines]
images = None
horizon(tractograms,
images=images,
cluster=True,
cluster_thr=5,
random_colors=False,
length_lt=np.inf,
length_gt=0,
clusters_lt=np.inf,
clusters_gt=0,
world_coords=False,
interactive=False)
#
affine = np.diag([2., 1, 1, 1]).astype('f8')
#
data = 255 * np.random.rand(150, 150, 150)
#
images = [(data, affine)]
horizon(tractograms,
images=images,
cluster=True,
cluster_thr=5,
random_colors=False,
length_lt=np.inf,
length_gt=0,
clusters_lt=np.inf,
clusters_gt=0,
world_coords=True,
interactive=False)
with TemporaryDirectory() as out_dir:
fimg = os.path.join(out_dir, 'test.nii.gz')
ftrk = os.path.join(out_dir, 'test.trk')
save_nifti(fimg, data, affine)
dimensions = data.shape
voxel_sizes = np.array([2, 1.0, 1.0])
nii_header = create_nifti_header(affine, dimensions, voxel_sizes)
sft = StatefulTractogram(streamlines, nii_header, space=Space.RASMM)
save_tractogram(sft, ftrk, bbox_valid_check=False)
input_files = [ftrk, fimg]
npt.assert_equal(len(input_files), 2)
hz_flow = HorizonFlow()
hz_flow.run(input_files=input_files,
stealth=True,
out_dir=out_dir,
out_stealth_png='tmp_x.png')
npt.assert_equal(os.path.exists(os.path.join(out_dir, 'tmp_x.png')),
True)
# Make a streamline bundle model of the corpus callosum ROI connectivity
streamlines = LocalTracking(csa_peaks, classifier, seeds, affine,
step_size=2)
streamlines = Streamlines(streamlines)
"""
We do not want our results inflated by short streamlines, so we remove
streamlines shorter than 40mm prior to calculating the CCI.
"""
lengths = list(length(streamlines))
long_streamlines = Streamlines()
for i, sl in enumerate(streamlines):
if lengths[i] > 40:
long_streamlines.append(sl)
"""
Now we calculate the Cluster Confidence Index using the corpus callosum
streamline bundle and visualize them.
"""
cci = cluster_confidence(long_streamlines)
# Visualize the streamlines, colored by cci
ren = window.Renderer()
hue = [0.5, 1]
saturation = [0.0, 1.0]
def test_horizon():
s1 = 10 * np.array([[0, 0, 0],
[1, 0, 0],
[2, 0, 0],
[3, 0, 0],
[4, 0, 0]], dtype='f8')
s2 = 10 * np.array([[0, 0, 0],
[0, 1, 0],
[0, 2, 0],
[0, 3, 0],
[0, 4, 0]], dtype='f8')
s3 = 10 * np.array([[0, 0, 0],
[1, 0.2, 0],
[2, 0.2, 0],
[3, 0.2, 0],
[4, 0.2, 0]], dtype='f8')
streamlines = Streamlines()
streamlines.append(s1)
streamlines.append(s2)
streamlines.append(s3)
affine = np.array([[1., 0., 0., -98.],
[0., 1., 0., -134.],
[0., 0., 1., -72.],
[0., 0., 0., 1.]])
data = 255 * np.random.rand(197, 233, 189)
vox_size = (1., 1., 1.)
streamlines._data += np.array([-98., -134., -72.])
header = create_nifti_header(affine, data.shape, vox_size)
sft = StatefulTractogram(streamlines, header, Space.RASMM)
# only tractograms
tractograms = [sft]
images = None
horizon(tractograms, images=images, cluster=True, cluster_thr=5,
random_colors=False, length_lt=np.inf, length_gt=0,
clusters_lt=np.inf, clusters_gt=0,
world_coords=True, interactive=False)
images = [(data, affine)]
# tractograms in native coords (not supported for now)
with npt.assert_raises(ValueError) as ve:
horizon(tractograms, images=images, cluster=True, cluster_thr=5,
random_colors=False, length_lt=np.inf, length_gt=0,
clusters_lt=np.inf, clusters_gt=0,
world_coords=False, interactive=False)
msg = 'Currently native coordinates are not supported for streamlines'
npt.assert_(msg in str(ve.exception))
# only images
tractograms = None
horizon(tractograms, images=images, cluster=True, cluster_thr=5,
random_colors=False, length_lt=np.inf, length_gt=0,
clusters_lt=np.inf, clusters_gt=0,
world_coords=True, interactive=False)
# no clustering tractograms and images
horizon(tractograms, images=images, cluster=False, cluster_thr=5,
random_colors=False, length_lt=np.inf, length_gt=0,
clusters_lt=np.inf, clusters_gt=0,
world_coords=True, interactive=False)
streamlines = LocalTracking(csa_peaks,
stopping_criterion,
seeds,
affine,
step_size=2)
streamlines = Streamlines(streamlines)
"""
We do not want our results inflated by short streamlines, so we remove
streamlines shorter than 40mm prior to calculating the CCI.
"""
lengths = list(length(streamlines))
long_streamlines = Streamlines()
for i, sl in enumerate(streamlines):
if lengths[i] > 40:
long_streamlines.append(sl)
"""
Now we calculate the Cluster Confidence Index using the corpus callosum
streamline bundle and visualize them.
"""
cci = cluster_confidence(long_streamlines)
# Visualize the streamlines, colored by cci
ren = window.Renderer()
hue = [0.5, 1]
saturation = [0.0, 1.0]
lut_cmap = actor.colormap_lookup_table(scale_range=(cci.min(), cci.max() / 4),
hue_range=hue,
def test_horizon_flow():
s1 = 10 * np.array([[0, 0, 0],
[1, 0, 0],
[2, 0, 0],
[3, 0, 0],
[4, 0, 0]], dtype='f8')
s2 = 10 * np.array([[0, 0, 0],
[0, 1, 0],
[0, 2, 0],
[0, 3, 0],
[0, 4, 0]], dtype='f8')
s3 = 10 * np.array([[0, 0, 0],
[1, 0.2, 0],
[2, 0.2, 0],
[3, 0.2, 0],
[4, 0.2, 0]], dtype='f8')
print(s1.shape)
print(s2.shape)
print(s3.shape)
streamlines = Streamlines()
streamlines.append(s1)
streamlines.append(s2)
streamlines.append(s3)
tractograms = [streamlines]
images = None
horizon(tractograms, images=images, cluster=True, cluster_thr=5,
random_colors=False, length_lt=np.inf, length_gt=0,
clusters_lt=np.inf, clusters_gt=0,
world_coords=False, interactive=False)
#
affine = np.diag([2., 1, 1, 1]).astype('f8')
#
data = 255 * np.random.rand(150, 150, 150)
#
images = [(data, affine)]
horizon(tractograms, images=images, cluster=True, cluster_thr=5,
random_colors=False, length_lt=np.inf, length_gt=0,
clusters_lt=np.inf, clusters_gt=0,
world_coords=True, interactive=False)
with TemporaryDirectory() as out_dir:
fimg = os.path.join(out_dir, 'test.nii.gz')
ftrk = os.path.join(out_dir, 'test.trk')
save_nifti(fimg, data, affine)
save_tractogram(ftrk, streamlines, affine)
input_files = [ftrk, fimg]
npt.assert_equal(len(input_files), 2)
hz_flow = HorizonFlow()
hz_flow.run(input_files=input_files, stealth=True,
out_dir=out_dir, out_stealth_png='tmp_x.png')
npt.assert_equal(os.path.exists(os.path.join(out_dir, 'tmp_x.png')),
True)
