def test_save_as_csv_per_slice_then_per_level(dummy_metrics, dummy_vert_level):
"""Test with and without specifying perlevel. See: https://github.com/neuropoly/spinalcordtoolbox/issues/2141"""
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(
dummy_metrics['with float'],
levels=[3, 4],
perlevel=True,
vert_level=dummy_vert_level,
group_funcs=(('WA', aggregate_slicewise.func_wa), ))
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv')
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(
dummy_metrics['with float'],
slices=[0],
group_funcs=(('WA', aggregate_slicewise.func_wa), ),
)
aggregate_slicewise.save_as_csv(agg_metric,
'tmp_file_out.csv',
append=True)
with open('tmp_file_out.csv', 'r') as csvfile:
reader = csv.DictReader(csvfile, delimiter=',')
row = next(reader)
assert row['Slice (I->S)'] == '2:3'
assert row['VertLevel'] == '3'
next(reader)
row = next(reader)
assert row['Slice (I->S)'] == '0'
assert row['VertLevel'] == ''
def test_save_as_csv_sorting(dummy_metrics):
"""Make sure slices are sorted in output csv file"""
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(dummy_metrics['with float'], perslice=True,
group_funcs=(('WA', aggregate_slicewise.func_wa),))
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv')
with open('tmp_file_out.csv', 'r') as csvfile:
spamreader = csv.DictReader(csvfile, delimiter=',')
assert [row['Slice (I->S)'] for row in spamreader] == ['0', '1', '2', '3', '4']
def test_save_as_csv_sorting(dummy_metrics):
"""Make sure slices are sorted in output csv file"""
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(dummy_metrics['with float'], perslice=True,
group_funcs=(('WA', aggregate_slicewise.func_wa),))
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv')
with open('tmp_file_out.csv', 'r') as csvfile:
spamreader = csv.DictReader(csvfile, delimiter=',')
assert [row['Slice (I->S)'] for row in spamreader] == ['0', '1', '2', '3', '4']
def test_save_as_csv_extract_metric(dummy_data_and_labels):
"""Test file output with extract_metric()"""
# With input label file
agg_metric = aggregate_slicewise.extract_metric(dummy_data_and_labels[0], labels=dummy_data_and_labels[1],
label_struc=dummy_data_and_labels[2], id_label=0,
indiv_labels_ids=[0, 1], perslice=False, method='wa')
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv')
with open('tmp_file_out.csv', 'r') as csvfile:
spamreader = csv.reader(csvfile, delimiter=',')
next(spamreader) # skip header
assert next(spamreader)[1:-1] == [sct.__version__, '', '0:4', '', 'label_0', '2.5', '38.0']
def test_save_as_csv_per_level(dummy_metrics, dummy_vert_level):
"""Make sure slices are listed in reduced form"""
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(dummy_metrics['with float'], levels=[3, 4],
perlevel=True,
vert_level=dummy_vert_level,
group_funcs=(('WA', aggregate_slicewise.func_wa),))
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv')
with open('tmp_file_out.csv', 'r') as csvfile:
reader = csv.DictReader(csvfile, delimiter=',')
row = next(reader)
assert row['Slice (I->S)'] == '2:3'
assert row['VertLevel'] == '3'
def test_save_as_csv_extract_metric(dummy_data_and_labels):
"""Test file output with extract_metric()"""
# With input label file
agg_metric = aggregate_slicewise.extract_metric(dummy_data_and_labels[0], labels=dummy_data_and_labels[1],
label_struc=dummy_data_and_labels[2], id_label=0,
indiv_labels_ids=[0, 1], perslice=False, method='wa')
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv')
with open('tmp_file_out.csv', 'r') as csvfile:
spamreader = csv.reader(csvfile, delimiter=',')
next(spamreader) # skip header
assert next(spamreader)[1:-1] == [__version__, '', '0:4', '', 'label_0', '2.5', '38.0']
def test_save_as_csv_per_level(dummy_metrics, dummy_vert_level):
"""Make sure slices are listed in reduced form"""
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(dummy_metrics['with float'], levels=[3, 4],
perlevel=True,
vert_level=dummy_vert_level,
group_funcs=(('WA', aggregate_slicewise.func_wa),))
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv')
with open('tmp_file_out.csv', 'r') as csvfile:
reader = csv.DictReader(csvfile, delimiter=',')
row = next(reader)
assert row['Slice (I->S)'] == '2:3'
assert row['VertLevel'] == '3'
def test_save_as_csv_pmj(tmp_path, dummy_metrics):
"""Test writing of output metric csv file with distance from PMJ method"""
path_out = str(tmp_path / 'tmp_file_out.csv')
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(
dummy_metrics['with float'],
slices=[2, 3, 4, 5],
distance_pmj=64.0,
perslice=False,
perlevel=False,
group_funcs=(('WA', aggregate_slicewise.func_wa), ))
aggregate_slicewise.save_as_csv(agg_metric, path_out)
with open(path_out, 'r') as csvfile:
reader = csv.DictReader(csvfile, delimiter=',')
row = next(reader)
assert row['Slice (I->S)'] == '2:5'
assert row['DistancePMJ'] == '64.0'
assert row['VertLevel'] == ''
def test_save_as_csv_per_slice_then_per_level(dummy_metrics, dummy_vert_level):
"""Test with and without specifying perlevel. See: https://github.com/neuropoly/spinalcordtoolbox/issues/2141"""
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(dummy_metrics['with float'], levels=[3, 4],
perlevel=True,
vert_level=dummy_vert_level,
group_funcs=(('WA', aggregate_slicewise.func_wa),))
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv')
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(dummy_metrics['with float'], slices=[0],
group_funcs=(('WA', aggregate_slicewise.func_wa),),)
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv', append=True)
with open('tmp_file_out.csv', 'r') as csvfile:
reader = csv.DictReader(csvfile, delimiter=',')
row = next(reader)
assert row['Slice (I->S)'] == '2:3'
assert row['VertLevel'] == '3'
next(reader)
row = next(reader)
assert row['Slice (I->S)'] == '0'
assert row['VertLevel'] == ''
def test_save_as_csv(dummy_metrics):
"""Test writing of output metric csv file"""
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(
dummy_metrics['with float'],
slices=[3, 4],
perslice=False,
group_funcs=(('WA', aggregate_slicewise.func_wa),
('STD', aggregate_slicewise.func_std)))
# standard scenario
aggregate_slicewise.save_as_csv(agg_metric,
'tmp_file_out.csv',
fname_in='FakeFile.txt')
with open('tmp_file_out.csv', 'r') as csvfile:
spamreader = csv.reader(csvfile, delimiter=',')
next(spamreader) # skip header
assert next(spamreader)[1:] == [
sct.__version__, 'FakeFile.txt', '3:4', '', '45.5', '4.5'
]
# with appending
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv')
aggregate_slicewise.save_as_csv(agg_metric,
'tmp_file_out.csv',
append=True)
with open('tmp_file_out.csv', 'r') as csvfile:
spamreader = csv.reader(csvfile, delimiter=',')
next(spamreader) # skip header
assert next(spamreader)[1:] == [
sct.__version__, '', '3:4', '', '45.5', '4.5'
]
assert next(spamreader)[1:] == [
sct.__version__, '', '3:4', '', '45.5', '4.5'
]
def test_save_as_csv(dummy_metrics):
"""Test writing of output metric csv file"""
agg_metric = aggregate_slicewise.aggregate_per_slice_or_level(dummy_metrics['with float'], slices=[3, 4],
perslice=False,
group_funcs=(('WA', aggregate_slicewise.func_wa),
('STD', aggregate_slicewise.func_std)))
# standard scenario
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv', fname_in='FakeFile.txt')
with open('tmp_file_out.csv', 'r') as csvfile:
spamreader = csv.reader(csvfile, delimiter=',')
next(spamreader) # skip header
assert next(spamreader)[1:] == [sct.__version__, 'FakeFile.txt', '3:4', '', '45.5', '4.5']
# with appending
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv')
aggregate_slicewise.save_as_csv(agg_metric, 'tmp_file_out.csv', append=True)
with open('tmp_file_out.csv', 'r') as csvfile:
spamreader = csv.reader(csvfile, delimiter=',')
next(spamreader) # skip header
assert next(spamreader)[1:] == [sct.__version__, '', '3:4', '', '45.5', '4.5']
assert next(spamreader)[1:] == [sct.__version__, '', '3:4', '', '45.5', '4.5']
def main(args):
parser = get_parser()
arguments = parser.parse(args)
# Initialization
slices = ''
group_funcs = (('MEAN', func_wa), ('STD', func_std)) # functions to perform when aggregating metrics along S-I
fname_segmentation = sct.get_absolute_path(arguments['-i'])
fname_vert_levels = ''
if '-o' in arguments:
file_out = os.path.abspath(arguments['-o'])
else:
file_out = ''
if '-append' in arguments:
append = int(arguments['-append'])
else:
append = 0
if '-vert' in arguments:
vert_levels = arguments['-vert']
else:
vert_levels = ''
if '-r' in arguments:
remove_temp_files = arguments['-r']
if '-vertfile' in arguments:
fname_vert_levels = arguments['-vertfile']
if '-perlevel' in arguments:
perlevel = arguments['-perlevel']
else:
perlevel = None
if '-z' in arguments:
slices = arguments['-z']
if '-perslice' in arguments:
perslice = arguments['-perslice']
else:
perslice = None
if '-angle-corr' in arguments:
if arguments['-angle-corr'] == '1':
angle_correction = True
elif arguments['-angle-corr'] == '0':
angle_correction = False
param_centerline = ParamCenterline(
algo_fitting=arguments['-centerline-algo'],
smooth=arguments['-centerline-smooth'],
minmax=True)
path_qc = arguments.get("-qc", None)
qc_dataset = arguments.get("-qc-dataset", None)
qc_subject = arguments.get("-qc-subject", None)
verbose = int(arguments.get('-v'))
sct.init_sct(log_level=verbose, update=True) # Update log level
# update fields
metrics_agg = {}
if not file_out:
file_out = 'csa.csv'
metrics, fit_results = process_seg.compute_shape(fname_segmentation,
angle_correction=angle_correction,
param_centerline=param_centerline,
verbose=verbose)
for key in metrics:
metrics_agg[key] = aggregate_per_slice_or_level(metrics[key], slices=parse_num_list(slices),
levels=parse_num_list(vert_levels), perslice=perslice,
perlevel=perlevel, vert_level=fname_vert_levels,
group_funcs=group_funcs)
metrics_agg_merged = _merge_dict(metrics_agg)
save_as_csv(metrics_agg_merged, file_out, fname_in=fname_segmentation, append=append)
# QC report (only show CSA for clarity)
if path_qc is not None:
generate_qc(fname_segmentation, args=args, path_qc=os.path.abspath(path_qc), dataset=qc_dataset,
subject=qc_subject, path_img=_make_figure(metrics_agg_merged, fit_results),
process='sct_process_segmentation')
sct.display_open(file_out)
def main(args):
parser = get_parser()
arguments = parser.parse(args)
param = Param()
# Initialization
slices = param.slices
group_funcs = (('MEAN', func_wa), ('STD', func_std)
) # functions to perform when aggregating metrics along S-I
fname_segmentation = sct.get_absolute_path(arguments['-i'])
fname_vert_levels = ''
if '-o' in arguments:
file_out = os.path.abspath(arguments['-o'])
else:
file_out = ''
if '-append' in arguments:
append = int(arguments['-append'])
else:
append = 0
if '-vert' in arguments:
vert_levels = arguments['-vert']
else:
vert_levels = ''
if '-r' in arguments:
remove_temp_files = arguments['-r']
if '-vertfile' in arguments:
fname_vert_levels = arguments['-vertfile']
if '-perlevel' in arguments:
perlevel = arguments['-perlevel']
else:
perlevel = Param().perlevel
if '-z' in arguments:
slices = arguments['-z']
if '-perslice' in arguments:
perslice = arguments['-perslice']
else:
perslice = Param().perslice
if '-angle-corr' in arguments:
if arguments['-angle-corr'] == '1':
angle_correction = True
elif arguments['-angle-corr'] == '0':
angle_correction = False
verbose = int(arguments.get('-v'))
sct.init_sct(log_level=verbose, update=True) # Update log level
# update fields
metrics_agg = {}
if not file_out:
file_out = 'csa.csv'
metrics = process_seg.compute_shape(fname_segmentation,
algo_fitting='bspline',
angle_correction=angle_correction,
verbose=verbose)
for key in metrics:
metrics_agg[key] = aggregate_per_slice_or_level(
metrics[key],
slices=parse_num_list(slices),
levels=parse_num_list(vert_levels),
perslice=perslice,
perlevel=perlevel,
vert_level=fname_vert_levels,
group_funcs=group_funcs)
metrics_agg_merged = _merge_dict(metrics_agg)
save_as_csv(metrics_agg_merged,
file_out,
fname_in=fname_segmentation,
append=append)
sct.display_open(file_out)
def main(argv=None):
parser = get_parser()
arguments = parser.parse_args(argv)
verbose = arguments.v
set_loglevel(verbose=verbose)
param_default = Param()
overwrite = 0 # TODO: Not used. Why?
fname_data = get_absolute_path(arguments.i)
path_label = arguments.f
method = arguments.method
fname_output = arguments.o
append_csv = arguments.append
combine_labels = arguments.combine
labels_user = arguments.l
adv_param_user = arguments.param # TODO: Not used. Why?
slices = parse_num_list(arguments.z)
levels = parse_num_list(arguments.vert)
fname_vertebral_labeling = arguments.vertfile
perslice = arguments.perslice
perlevel = arguments.perlevel
fname_normalizing_label = arguments.norm_file # TODO: Not used. Why?
normalization_method = arguments.norm_method # TODO: Not used. Why?
label_to_fix = arguments.fix_label # TODO: Not used. Why?
fname_output_metric_map = arguments.output_map # TODO: Not used. Why?
fname_mask_weight = arguments.mask_weighted # TODO: Not used. Why?
discard_negative_values = int(arguments.discard_neg_val) # TODO: Not used. Why?
# check if path_label is a file (e.g., single binary mask) instead of a folder (e.g., SCT atlas structure which
# contains info_label.txt file)
if os.path.isfile(path_label):
# Label is a single file
indiv_labels_ids = [0]
indiv_labels_files = [path_label]
combined_labels_ids = []
label_struc = {0: LabelStruc(id=0,
name=extract_fname(path_label)[1],
filename=path_label)}
# set path_label to empty string, because indiv_labels_files will replace it from now on
path_label = ''
elif os.path.isdir(path_label):
# Labels is an SCT atlas folder structure
# Parse labels according to the file info_label.txt
# Note: the "combined_labels_*" is a list of single labels that are defined in the section defined by the keyword
# "# Keyword=CombinedLabels" in info_label.txt.
# TODO: redirect to appropriate Sphinx documentation
# TODO: output Class instead of multiple variables.
# Example 1:
# label_struc[2].id = (2)
# label_struc[2].name = "left fasciculus cuneatus"
# label_struc[2].filename = "PAM50_atlas_02.nii.gz"
# Example 2:
# label_struc[51].id = (1, 2, 3, ..., 29)
# label_struc[51].name = "White Matter"
# label_struc[51].filename = "" # no name because it is combined
indiv_labels_ids, indiv_labels_names, indiv_labels_files, \
combined_labels_ids, combined_labels_names, combined_labels_id_groups, map_clusters \
= read_label_file(path_label, param_default.file_info_label)
label_struc = {}
# fill IDs for indiv labels
for i_label in range(len(indiv_labels_ids)):
label_struc[indiv_labels_ids[i_label]] = LabelStruc(id=indiv_labels_ids[i_label],
name=indiv_labels_names[i_label],
filename=indiv_labels_files[i_label],
map_cluster=[indiv_labels_ids[i_label] in map_cluster for
map_cluster in map_clusters].index(True))
# fill IDs for combined labels
# TODO: problem for defining map_cluster: if labels overlap two regions, e.g. WM and GM (e.g. id=50),
# map_cluster will take value 0, which is wrong.
for i_label in range(len(combined_labels_ids)):
label_struc[combined_labels_ids[i_label]] = LabelStruc(id=combined_labels_id_groups[i_label],
name=combined_labels_names[i_label],
map_cluster=[indiv_labels_ids[i_label] in map_cluster for
map_cluster in map_clusters].index(True))
else:
raise RuntimeError(path_label + ' does not exist')
# check syntax of labels asked by user
labels_id_user = check_labels(indiv_labels_ids + combined_labels_ids, parse_num_list(labels_user))
nb_labels = len(indiv_labels_files)
# Load data and systematically reorient to RPI because we need the 3rd dimension to be z
printv('\nLoad metric image...', verbose)
input_im = Image(fname_data).change_orientation("RPI")
data = Metric(data=input_im.data, label='')
# Load labels
labels_tmp = np.empty([nb_labels], dtype=object)
for i_label in range(nb_labels):
im_label = Image(os.path.join(path_label, indiv_labels_files[i_label])).change_orientation("RPI")
labels_tmp[i_label] = np.expand_dims(im_label.data, 3) # TODO: generalize to 2D input label
labels = np.concatenate(labels_tmp[:], 3) # labels: (x,y,z,label)
# Load vertebral levels
if not levels:
fname_vertebral_labeling = None
# Get dimensions of data and labels
nx, ny, nz = data.data.shape
nx_atlas, ny_atlas, nz_atlas, nt_atlas = labels.shape
# Check dimensions consistency between atlas and data
if (nx, ny, nz) != (nx_atlas, ny_atlas, nz_atlas):
printv('\nERROR: Metric data and labels DO NOT HAVE SAME DIMENSIONS.', 1, type='error')
# Combine individual labels for estimation
if combine_labels:
# Add entry with internal ID value (99) which corresponds to combined labels
label_struc[99] = LabelStruc(id=labels_id_user, name=','.join([str(i) for i in labels_id_user]),
map_cluster=None)
labels_id_user = [99]
for id_label in labels_id_user:
printv('Estimation for label: ' + label_struc[id_label].name, verbose)
agg_metric = extract_metric(data, labels=labels, slices=slices, levels=levels, perslice=perslice,
perlevel=perlevel, vert_level=fname_vertebral_labeling, method=method,
label_struc=label_struc, id_label=id_label, indiv_labels_ids=indiv_labels_ids)
save_as_csv(agg_metric, fname_output, fname_in=fname_data, append=append_csv)
append_csv = True # when looping across labels, need to append results in the same file
display_open(fname_output)
def main(args):
parser = get_parser()
arguments = parser.parse(args)
param = Param()
# Initialization
slices = param.slices
angle_correction = True
use_phys_coord = True
group_funcs = (('MEAN', func_wa), ('STD', func_std)) # functions to perform when aggregating metrics along S-I
fname_segmentation = sct.get_absolute_path(arguments['-i'])
name_process = arguments['-p']
fname_vert_levels = ''
if '-o' in arguments:
file_out = os.path.abspath(arguments['-o'])
else:
file_out = ''
if '-append' in arguments:
append = int(arguments['-append'])
else:
append = 0
if '-vert' in arguments:
vert_levels = arguments['-vert']
else:
vert_levels = ''
if '-r' in arguments:
remove_temp_files = arguments['-r']
if '-vertfile' in arguments:
fname_vert_levels = arguments['-vertfile']
if '-perlevel' in arguments:
perlevel = arguments['-perlevel']
else:
perlevel = Param().perlevel
if '-v' in arguments:
verbose = int(arguments['-v'])
if '-z' in arguments:
slices = arguments['-z']
if '-perslice' in arguments:
perslice = arguments['-perslice']
else:
perslice = Param().perslice
if '-a' in arguments:
param.algo_fitting = arguments['-a']
if '-no-angle' in arguments:
if arguments['-no-angle'] == '1':
angle_correction = False
elif arguments['-no-angle'] == '0':
angle_correction = True
if '-use-image-coord' in arguments:
if arguments['-use-image-coord'] == '1':
use_phys_coord = False
if arguments['-use-image-coord'] == '0':
use_phys_coord = True
# update fields
param.verbose = verbose
metrics_agg = {}
if not file_out:
file_out = name_process + '.csv'
if name_process == 'centerline':
process_seg.extract_centerline(fname_segmentation, verbose=param.verbose,
algo_fitting=param.algo_fitting, use_phys_coord=use_phys_coord,
file_out=file_out)
if name_process == 'csa':
metrics = process_seg.compute_csa(fname_segmentation, algo_fitting=param.algo_fitting,
type_window=param.type_window, window_length=param.window_length,
angle_correction=angle_correction, use_phys_coord=use_phys_coord,
remove_temp_files=remove_temp_files, verbose=verbose)
for key in metrics:
metrics_agg[key] = aggregate_per_slice_or_level(metrics[key], slices=parse_num_list(slices),
levels=parse_num_list(vert_levels), perslice=perslice,
perlevel=perlevel, vert_level=fname_vert_levels,
group_funcs=group_funcs)
metrics_agg_merged = merge_dict(metrics_agg)
save_as_csv(metrics_agg_merged, file_out, fname_in=fname_segmentation, append=append)
sct.printv('\nFile created: '+file_out, verbose=1, type='info')
if name_process == 'label-vert':
if '-discfile' in arguments:
fname_discs = arguments['-discfile']
else:
sct.printv('\nERROR: Disc label file is mandatory (flag: -discfile).\n', 1, 'error')
process_seg.label_vert(fname_segmentation, fname_discs, verbose=verbose)
if name_process == 'shape':
fname_discs = None
if '-discfile' in arguments:
fname_discs = arguments['-discfile']
metrics = process_seg.compute_shape(fname_segmentation, remove_temp_files=remove_temp_files, verbose=verbose)
for key in metrics:
metrics_agg[key] = aggregate_per_slice_or_level(metrics[key], slices=parse_num_list(slices),
levels=parse_num_list(vert_levels), perslice=perslice,
perlevel=perlevel, vert_level=fname_vert_levels,
group_funcs=group_funcs)
metrics_agg_merged = merge_dict(metrics_agg)
save_as_csv(metrics_agg_merged, file_out, fname_in=fname_segmentation, append=append)
sct.printv('\nFile created: ' + file_out, verbose=1, type='info')
def main(fname_data, path_label, method, slices, levels, fname_output, labels_user, append,
fname_normalizing_label, normalization_method, label_to_fix, adv_param_user, fname_output_metric_map,
fname_mask_weight, fname_vertebral_labeling="", perslice=1, perlevel=1, discard_negative_values=False,
verbose=1):
"""
Extract metrics from MRI data based on mask (could be single file of folder to atlas)
:param fname_data: data to extract metric from
:param path_label: mask: could be single file or folder to atlas (which contains info_label.txt)
:param method:
:param slices_of_interest. Accepted format:
"0,1,2,3": slices 0,1,2,3
"0:3": slices 0,1,2,3
:param vertebral_levels: Vertebral levels to extract metrics from. Should be associated with a template
(e.g. PAM50/template/) or a specified file: fname_vertebral_labeling. Same format as slices_of_interest.
:param fname_output:
:param labels_user:
:param overwrite:
:param fname_normalizing_label:
:param normalization_method:
:param label_to_fix:
:param adv_param_user:
:param fname_output_metric_map:
:param fname_mask_weight:
:param fname_vertebral_labeling: vertebral labeling to be used with vertebral_levels
:param perslice: if user selected several slices, then the function outputs a metric within each slice
instead of a single average output.
:param perlevel: if user selected several levels, then the function outputs a metric within each vertebral level
instead of a single average output.
:param discard_negative_values: Bool: Discard negative voxels when computing metrics statistics
:param verbose
:return:
"""
# check if path_label is a file (e.g., single binary mask) instead of a folder (e.g., SCT atlas structure which
# contains info_label.txt file)
if os.path.isfile(path_label):
# Label is a single file
indiv_labels_ids = [0]
indiv_labels_names = [path_label]
indiv_labels_files = [path_label]
combined_labels_ids = []
combined_labels_names = []
combined_labels_id_groups = []
map_clusters = []
label_struc = {0: LabelStruc(id=0,
name=sct.extract_fname(path_label)[1],
filename=path_label)}
# set path_label to empty string, because indiv_labels_files will replace it from now on
path_label = ''
elif os.path.isdir(path_label):
# Labels is an SCT atlas folder structure
# Parse labels according to the file info_label.txt
# Note: the "combined_labels_*" is a list of single labels that are defined in the section defined by the keyword
# "# Keyword=CombinedLabels" in info_label.txt.
# TODO: redirect to appropriate Sphinx documentation
# TODO: output Class instead of multiple variables.
# Example 1:
# label_struc[2].id = (2)
# label_struc[2].name = "left fasciculus cuneatus"
# label_struc[2].filename = "PAM50_atlas_02.nii.gz"
# Example 2:
# label_struc[51].id = (1, 2, 3, ..., 29)
# label_struc[51].name = "White Matter"
# label_struc[51].filename = "" # no name because it is combined
indiv_labels_ids, indiv_labels_names, indiv_labels_files, \
combined_labels_ids, combined_labels_names, combined_labels_id_groups, map_clusters \
= read_label_file(path_label, param_default.file_info_label)
label_struc = {}
# fill IDs for indiv labels
for i_label in range(len(indiv_labels_ids)):
label_struc[indiv_labels_ids[i_label]] = LabelStruc(id=indiv_labels_ids[i_label],
name=indiv_labels_names[i_label],
filename=indiv_labels_files[i_label],
map_cluster=[indiv_labels_ids[i_label] in map_cluster for
map_cluster in map_clusters].index(True))
# fill IDs for combined labels
for i_label in range(len(combined_labels_ids)):
label_struc[combined_labels_ids[i_label]] = LabelStruc(id=combined_labels_id_groups[i_label],
name=combined_labels_names[i_label],
map_cluster=[indiv_labels_ids[i_label] in map_cluster for
map_cluster in map_clusters].index(True))
else:
sct.printv('\nERROR: ' + path_label + ' does not exist.', 1, 'error')
# check syntax of labels asked by user
labels_id_user = check_labels(indiv_labels_ids + combined_labels_ids, parse_num_list(labels_user))
nb_labels = len(indiv_labels_files)
# Load data and systematically reorient to RPI because we need the 3rd dimension to be z
sct.printv('\nLoad metric image...', verbose)
input_im = Image(fname_data).change_orientation("RPI")
data = Metric(data=input_im.data, label='')
# Load labels
labels_tmp = np.empty([nb_labels], dtype=object)
for i_label in range(nb_labels):
im_label = Image(os.path.join(path_label, indiv_labels_files[i_label])).change_orientation("RPI")
labels_tmp[i_label] = np.expand_dims(im_label.data, 3) # TODO: generalize to 2D input label
labels = np.concatenate(labels_tmp[:], 3) # labels: (x,y,z,label)
# Load vertebral levels
if vertebral_levels:
im_vertebral_labeling = Image(fname_vertebral_labeling).change_orientation("RPI")
else:
im_vertebral_labeling = None
# Get dimensions of data and labels
nx, ny, nz = data.data.shape
nx_atlas, ny_atlas, nz_atlas, nt_atlas = labels.shape
# Check dimensions consistency between atlas and data
if (nx, ny, nz) != (nx_atlas, ny_atlas, nz_atlas):
sct.printv('\nERROR: Metric data and labels DO NOT HAVE SAME DIMENSIONS.', 1, type='error')
for id_label in labels_id_user:
sct.printv('Estimation for label: '+label_struc[id_label].name, verbose)
agg_metric = extract_metric(data, labels=labels, slices=slices, levels=levels, perslice=perslice,
perlevel=perlevel, vert_level=im_vertebral_labeling, method=method,
label_struc=label_struc, id_label=id_label, indiv_labels_ids=indiv_labels_ids)
save_as_csv(agg_metric, fname_output, fname_in=fname_data, append=append)
append = True # when looping across labels, need to append results in the same file
sct.display_open(fname_output)
def main(fname_data,
path_label,
method,
slices,
levels,
fname_output,
labels_user,
append_csv,
fname_vertebral_labeling="",
perslice=1,
perlevel=1,
verbose=1,
combine_labels=True):
"""
Extract metrics from MRI data based on mask (could be single file of folder to atlas)
:param fname_data: data to extract metric from
:param path_label: mask: could be single file or folder to atlas (which contains info_label.txt)
:param method {'wa', 'bin', 'ml', 'map'}
:param slices. Slices of interest. Accepted format:
"0,1,2,3": slices 0,1,2,3
"0:3": slices 0,1,2,3
:param levels: Vertebral levels to extract metrics from. Should be associated with a template
(e.g. PAM50/template/) or a specified file: fname_vertebral_labeling. Same format as slices_of_interest.
:param fname_output:
:param labels_user:
:param append_csv: Append to csv file
:param fname_normalizing_label:
:param fname_vertebral_labeling: vertebral labeling to be used with vertebral_levels
:param perslice: if user selected several slices, then the function outputs a metric within each slice
instead of a single average output.
:param perlevel: if user selected several levels, then the function outputs a metric within each vertebral level
instead of a single average output.
:param verbose
:param combine_labels: bool: Combine labels into a single value
:return:
"""
# check if path_label is a file (e.g., single binary mask) instead of a folder (e.g., SCT atlas structure which
# contains info_label.txt file)
if os.path.isfile(path_label):
# Label is a single file
indiv_labels_ids = [0]
indiv_labels_files = [path_label]
combined_labels_ids = []
label_struc = {
0:
LabelStruc(id=0,
name=extract_fname(path_label)[1],
filename=path_label)
}
# set path_label to empty string, because indiv_labels_files will replace it from now on
path_label = ''
elif os.path.isdir(path_label):
# Labels is an SCT atlas folder structure
# Parse labels according to the file info_label.txt
# Note: the "combined_labels_*" is a list of single labels that are defined in the section defined by the keyword
# "# Keyword=CombinedLabels" in info_label.txt.
# TODO: redirect to appropriate Sphinx documentation
# TODO: output Class instead of multiple variables.
# Example 1:
# label_struc[2].id = (2)
# label_struc[2].name = "left fasciculus cuneatus"
# label_struc[2].filename = "PAM50_atlas_02.nii.gz"
# Example 2:
# label_struc[51].id = (1, 2, 3, ..., 29)
# label_struc[51].name = "White Matter"
# label_struc[51].filename = "" # no name because it is combined
indiv_labels_ids, indiv_labels_names, indiv_labels_files, \
combined_labels_ids, combined_labels_names, combined_labels_id_groups, map_clusters \
= read_label_file(path_label, param_default.file_info_label)
label_struc = {}
# fill IDs for indiv labels
for i_label in range(len(indiv_labels_ids)):
label_struc[indiv_labels_ids[i_label]] = LabelStruc(
id=indiv_labels_ids[i_label],
name=indiv_labels_names[i_label],
filename=indiv_labels_files[i_label],
map_cluster=[
indiv_labels_ids[i_label] in map_cluster
for map_cluster in map_clusters
].index(True))
# fill IDs for combined labels
# TODO: problem for defining map_cluster: if labels overlap two regions, e.g. WM and GM (e.g. id=50),
# map_cluster will take value 0, which is wrong.
for i_label in range(len(combined_labels_ids)):
label_struc[combined_labels_ids[i_label]] = LabelStruc(
id=combined_labels_id_groups[i_label],
name=combined_labels_names[i_label],
map_cluster=[
indiv_labels_ids[i_label] in map_cluster
for map_cluster in map_clusters
].index(True))
else:
raise RuntimeError(path_label + ' does not exist')
# check syntax of labels asked by user
labels_id_user = check_labels(indiv_labels_ids + combined_labels_ids,
parse_num_list(labels_user))
nb_labels = len(indiv_labels_files)
# Load data and systematically reorient to RPI because we need the 3rd dimension to be z
printv('\nLoad metric image...', verbose)
input_im = Image(fname_data).change_orientation("RPI")
data = Metric(data=input_im.data, label='')
# Load labels
labels_tmp = np.empty([nb_labels], dtype=object)
for i_label in range(nb_labels):
im_label = Image(os.path.join(
path_label, indiv_labels_files[i_label])).change_orientation("RPI")
labels_tmp[i_label] = np.expand_dims(
im_label.data, 3) # TODO: generalize to 2D input label
labels = np.concatenate(labels_tmp[:], 3) # labels: (x,y,z,label)
# Load vertebral levels
if vertebral_levels:
im_vertebral_labeling = Image(
fname_vertebral_labeling).change_orientation("RPI")
else:
im_vertebral_labeling = None
# Get dimensions of data and labels
nx, ny, nz = data.data.shape
nx_atlas, ny_atlas, nz_atlas, nt_atlas = labels.shape
# Check dimensions consistency between atlas and data
if (nx, ny, nz) != (nx_atlas, ny_atlas, nz_atlas):
printv('\nERROR: Metric data and labels DO NOT HAVE SAME DIMENSIONS.',
1,
type='error')
# Combine individual labels for estimation
if combine_labels:
# Add entry with internal ID value (99) which corresponds to combined labels
label_struc[99] = LabelStruc(id=labels_id_user,
name=','.join(
[str(i) for i in labels_id_user]),
map_cluster=None)
labels_id_user = [99]
for id_label in labels_id_user:
printv('Estimation for label: ' + label_struc[id_label].name, verbose)
agg_metric = extract_metric(data,
labels=labels,
slices=slices,
levels=levels,
perslice=perslice,
perlevel=perlevel,
vert_level=im_vertebral_labeling,
method=method,
label_struc=label_struc,
id_label=id_label,
indiv_labels_ids=indiv_labels_ids)
save_as_csv(agg_metric,
fname_output,
fname_in=fname_data,
append=append_csv)
append_csv = True # when looping across labels, need to append results in the same file
display_open(fname_output)
def main(args=None):
parser = get_parser()
if args:
arguments = parser.parse_args(args)
else:
arguments = parser.parse_args(
args=None if sys.argv[1:] else ['--help'])
# Initialization
slices = ''
group_funcs = (('MEAN', func_wa), ('STD', func_std)
) # functions to perform when aggregating metrics along S-I
fname_segmentation = get_absolute_path(arguments.i)
fname_vert_levels = ''
if arguments.o is not None:
file_out = os.path.abspath(arguments.o)
else:
file_out = ''
if arguments.append is not None:
append = arguments.append
else:
append = 0
if arguments.vert is not None:
vert_levels = arguments.vert
else:
vert_levels = ''
remove_temp_files = arguments.r
if arguments.vertfile is not None:
fname_vert_levels = arguments.vertfile
if arguments.perlevel is not None:
perlevel = arguments.perlevel
else:
perlevel = None
if arguments.z is not None:
slices = arguments.z
if arguments.perslice is not None:
perslice = arguments.perslice
else:
perslice = None
angle_correction = arguments.angle_corr
param_centerline = ParamCenterline(algo_fitting=arguments.centerline_algo,
smooth=arguments.centerline_smooth,
minmax=True)
path_qc = arguments.qc
qc_dataset = arguments.qc_dataset
qc_subject = arguments.qc_subject
verbose = int(arguments.v)
init_sct(log_level=verbose, update=True) # Update log level
# update fields
metrics_agg = {}
if not file_out:
file_out = 'csa.csv'
metrics, fit_results = compute_shape(fname_segmentation,
angle_correction=angle_correction,
param_centerline=param_centerline,
verbose=verbose)
for key in metrics:
if key == 'length':
# For computing cord length, slice-wise length needs to be summed across slices
metrics_agg[key] = aggregate_per_slice_or_level(
metrics[key],
slices=parse_num_list(slices),
levels=parse_num_list(vert_levels),
perslice=perslice,
perlevel=perlevel,
vert_level=fname_vert_levels,
group_funcs=(('SUM', func_sum), ))
else:
# For other metrics, we compute the average and standard deviation across slices
metrics_agg[key] = aggregate_per_slice_or_level(
metrics[key],
slices=parse_num_list(slices),
levels=parse_num_list(vert_levels),
perslice=perslice,
perlevel=perlevel,
vert_level=fname_vert_levels,
group_funcs=group_funcs)
metrics_agg_merged = merge_dict(metrics_agg)
save_as_csv(metrics_agg_merged,
file_out,
fname_in=fname_segmentation,
append=append)
# QC report (only show CSA for clarity)
if path_qc is not None:
generate_qc(fname_segmentation,
args=args,
path_qc=os.path.abspath(path_qc),
dataset=qc_dataset,
subject=qc_subject,
path_img=_make_figure(metrics_agg_merged, fit_results),
process='sct_process_segmentation')
display_open(file_out)
def main(args):
parser = get_parser()
arguments = parser.parse(args)
param = Param()
# Initialization
slices = param.slices
group_funcs = (('MEAN', func_wa), ('STD', func_std)) # functions to perform when aggregating metrics along S-I
fname_segmentation = sct.get_absolute_path(arguments['-i'])
fname_vert_levels = ''
if '-o' in arguments:
file_out = os.path.abspath(arguments['-o'])
else:
file_out = ''
if '-append' in arguments:
append = int(arguments['-append'])
else:
append = 0
if '-vert' in arguments:
vert_levels = arguments['-vert']
else:
vert_levels = ''
if '-r' in arguments:
remove_temp_files = arguments['-r']
if '-vertfile' in arguments:
fname_vert_levels = arguments['-vertfile']
if '-perlevel' in arguments:
perlevel = arguments['-perlevel']
else:
perlevel = Param().perlevel
if '-z' in arguments:
slices = arguments['-z']
if '-perslice' in arguments:
perslice = arguments['-perslice']
else:
perslice = Param().perslice
if '-angle-corr' in arguments:
if arguments['-angle-corr'] == '1':
angle_correction = True
elif arguments['-angle-corr'] == '0':
angle_correction = False
verbose = int(arguments.get('-v'))
sct.init_sct(log_level=verbose, update=True) # Update log level
# update fields
metrics_agg = {}
if not file_out:
file_out = 'csa.csv'
metrics = process_seg.compute_shape(fname_segmentation,
algo_fitting='bspline',
angle_correction=angle_correction,
verbose=verbose)
for key in metrics:
metrics_agg[key] = aggregate_per_slice_or_level(metrics[key], slices=parse_num_list(slices),
levels=parse_num_list(vert_levels), perslice=perslice,
perlevel=perlevel, vert_level=fname_vert_levels,
group_funcs=group_funcs)
metrics_agg_merged = _merge_dict(metrics_agg)
save_as_csv(metrics_agg_merged, file_out, fname_in=fname_segmentation, append=append)
sct.display_open(file_out)
