def main(argv=None):
"""
Main function
:param argv:
:return:
"""
parser = get_parser()
arguments = parser.parse_args(argv)
verbose = arguments.v
set_global_loglevel(verbose=verbose)
dim_list = ['x', 'y', 'z', 't']
fname_in = arguments.i
fname_out = arguments.o
output_type = arguments.type
# Open file(s)
im = Image(fname_in)
data = im.data # 3d or 4d numpy array
dim = im.dim
# run command
if arguments.otsu is not None:
param = arguments.otsu
data_out = sct_math.otsu(data, param)
elif arguments.adap is not None:
param = arguments.adap
data_out = sct_math.adap(data, param[0], param[1])
elif arguments.otsu_median is not None:
param = arguments.otsu_median
data_out = sct_math.otsu_median(data, param[0], param[1])
elif arguments.thr is not None:
param = arguments.thr
data_out = sct_math.threshold(data, param)
elif arguments.percent is not None:
param = arguments.percent
data_out = sct_math.perc(data, param)
elif arguments.bin is not None:
bin_thr = arguments.bin
data_out = sct_math.binarize(data, bin_thr=bin_thr)
elif arguments.add is not None:
data2 = get_data_or_scalar(arguments.add, data)
data_concat = sct_math.concatenate_along_4th_dimension(data, data2)
data_out = np.sum(data_concat, axis=3)
elif arguments.sub is not None:
data2 = get_data_or_scalar(arguments.sub, data)
data_out = data - data2
elif arguments.laplacian is not None:
sigmas = arguments.laplacian
if len(sigmas) == 1:
sigmas = [sigmas for i in range(len(data.shape))]
elif len(sigmas) != len(data.shape):
printv(
parser.error(
'ERROR: -laplacian need the same number of inputs as the number of image dimension OR only one input'
))
# adjust sigma based on voxel size
sigmas = [sigmas[i] / dim[i + 4] for i in range(3)]
# smooth data
data_out = sct_math.laplacian(data, sigmas)
elif arguments.mul is not None:
data2 = get_data_or_scalar(arguments.mul, data)
data_concat = sct_math.concatenate_along_4th_dimension(data, data2)
data_out = np.prod(data_concat, axis=3)
elif arguments.div is not None:
data2 = get_data_or_scalar(arguments.div, data)
data_out = np.divide(data, data2)
elif arguments.mean is not None:
dim = dim_list.index(arguments.mean)
if dim + 1 > len(
np.shape(data)): # in case input volume is 3d and dim=t
data = data[..., np.newaxis]
data_out = np.mean(data, dim)
elif arguments.rms is not None:
dim = dim_list.index(arguments.rms)
if dim + 1 > len(
np.shape(data)): # in case input volume is 3d and dim=t
data = data[..., np.newaxis]
data_out = np.sqrt(np.mean(np.square(data.astype(float)), dim))
elif arguments.std is not None:
dim = dim_list.index(arguments.std)
if dim + 1 > len(
np.shape(data)): # in case input volume is 3d and dim=t
data = data[..., np.newaxis]
data_out = np.std(data, dim, ddof=1)
elif arguments.smooth is not None:
sigmas = arguments.smooth
if len(sigmas) == 1:
sigmas = [sigmas[0] for i in range(len(data.shape))]
elif len(sigmas) != len(data.shape):
printv(
parser.error(
'ERROR: -smooth need the same number of inputs as the number of image dimension OR only one input'
))
# adjust sigma based on voxel size
sigmas = [sigmas[i] / dim[i + 4] for i in range(3)]
# smooth data
data_out = sct_math.smooth(data, sigmas)
elif arguments.dilate is not None:
if arguments.shape in ['disk', 'square'] and arguments.dim is None:
printv(
parser.error(
'ERROR: -dim is required for -dilate with 2D morphological kernel'
))
data_out = sct_math.dilate(data,
size=arguments.dilate,
shape=arguments.shape,
dim=arguments.dim)
elif arguments.erode is not None:
if arguments.shape in ['disk', 'square'] and arguments.dim is None:
printv(
parser.error(
'ERROR: -dim is required for -erode with 2D morphological kernel'
))
data_out = sct_math.erode(data,
size=arguments.erode,
shape=arguments.shape,
dim=arguments.dim)
elif arguments.denoise is not None:
# parse denoising arguments
p, b = 1, 5 # default arguments
list_denoise = (arguments.denoise).split(",")
for i in list_denoise:
if 'p' in i:
p = int(i.split('=')[1])
if 'b' in i:
b = int(i.split('=')[1])
data_out = sct_math.denoise_nlmeans(data,
patch_radius=p,
block_radius=b)
elif arguments.symmetrize is not None:
data_out = (data + data[list(range(data.shape[0] -
1, -1, -1)), :, :]) / float(2)
elif arguments.mi is not None:
# input 1 = from flag -i --> im
# input 2 = from flag -mi
im_2 = Image(arguments.mi)
compute_similarity(im,
im_2,
fname_out,
metric='mi',
metric_full='Mutual information',
verbose=verbose)
data_out = None
elif arguments.minorm is not None:
im_2 = Image(arguments.minorm)
compute_similarity(im,
im_2,
fname_out,
metric='minorm',
metric_full='Normalized Mutual information',
verbose=verbose)
data_out = None
elif arguments.corr is not None:
# input 1 = from flag -i --> im
# input 2 = from flag -mi
im_2 = Image(arguments.corr)
compute_similarity(im,
im_2,
fname_out,
metric='corr',
metric_full='Pearson correlation coefficient',
verbose=verbose)
data_out = None
# if no flag is set
else:
data_out = None
printv(
parser.error(
'ERROR: you need to specify an operation to do on the input image'
))
if data_out is not None:
# Write output
nii_out = Image(fname_in) # use header of input file
nii_out.data = data_out
nii_out.save(fname_out, dtype=output_type)
# TODO: case of multiple outputs
# assert len(data_out) == n_out
# if n_in == n_out:
# for im_in, d_out, fn_out in zip(nii, data_out, fname_out):
# im_in.data = d_out
# im_in.absolutepath = fn_out
# if arguments.w is not None:
# im_in.hdr.set_intent('vector', (), '')
# im_in.save()
# elif n_out == 1:
# nii[0].data = data_out[0]
# nii[0].absolutepath = fname_out[0]
# if arguments.w is not None:
# nii[0].hdr.set_intent('vector', (), '')
# nii[0].save()
# elif n_out > n_in:
# for dat_out, name_out in zip(data_out, fname_out):
# im_out = nii[0].copy()
# im_out.data = dat_out
# im_out.absolutepath = name_out
# if arguments.w is not None:
# im_out.hdr.set_intent('vector', (), '')
# im_out.save()
# else:
# printv(parser.usage.generate(error='ERROR: not the correct numbers of inputs and outputs'))
# display message
if data_out is not None:
display_viewer_syntax([fname_out], verbose=verbose)
else:
printv('\nDone! File created: ' + fname_out, verbose, 'info')
def main(argv=None):
parser = get_parser()
arguments = parser.parse_args(argv)
verbose = arguments.v
set_global_loglevel(verbose=verbose)
# initializations
initz = ''
initcenter = ''
fname_initlabel = ''
file_labelz = 'labelz.nii.gz'
param = Param()
fname_in = os.path.abspath(arguments.i)
fname_seg = os.path.abspath(arguments.s)
contrast = arguments.c
path_template = os.path.abspath(arguments.t)
scale_dist = arguments.scale_dist
path_output = arguments.ofolder
param.path_qc = arguments.qc
if arguments.discfile is not None:
fname_disc = os.path.abspath(arguments.discfile)
else:
fname_disc = None
if arguments.initz is not None:
initz = arguments.initz
if len(initz) != 2:
raise ValueError('--initz takes two arguments: position in superior-inferior direction, label value')
if arguments.initcenter is not None:
initcenter = arguments.initcenter
# if user provided text file, parse and overwrite arguments
if arguments.initfile is not None:
file = open(arguments.initfile, 'r')
initfile = ' ' + file.read().replace('\n', '')
arg_initfile = initfile.split(' ')
for idx_arg, arg in enumerate(arg_initfile):
if arg == '-initz':
initz = [int(x) for x in arg_initfile[idx_arg + 1].split(',')]
if len(initz) != 2:
raise ValueError('--initz takes two arguments: position in superior-inferior direction, label value')
if arg == '-initcenter':
initcenter = int(arg_initfile[idx_arg + 1])
if arguments.initlabel is not None:
# get absolute path of label
fname_initlabel = os.path.abspath(arguments.initlabel)
if arguments.param is not None:
param.update(arguments.param[0])
remove_temp_files = arguments.r
clean_labels = arguments.clean_labels
laplacian = arguments.laplacian
path_tmp = tmp_create(basename="label_vertebrae")
# Copying input data to tmp folder
printv('\nCopying input data to tmp folder...', verbose)
Image(fname_in).save(os.path.join(path_tmp, "data.nii"))
Image(fname_seg).save(os.path.join(path_tmp, "segmentation.nii"))
# Go go temp folder
curdir = os.getcwd()
os.chdir(path_tmp)
# Straighten spinal cord
printv('\nStraighten spinal cord...', verbose)
# check if warp_curve2straight and warp_straight2curve already exist (i.e. no need to do it another time)
cache_sig = cache_signature(
input_files=[fname_in, fname_seg],
)
cachefile = os.path.join(curdir, "straightening.cache")
if cache_valid(cachefile, cache_sig) and os.path.isfile(os.path.join(curdir, "warp_curve2straight.nii.gz")) and os.path.isfile(os.path.join(curdir, "warp_straight2curve.nii.gz")) and os.path.isfile(os.path.join(curdir, "straight_ref.nii.gz")):
# if they exist, copy them into current folder
printv('Reusing existing warping field which seems to be valid', verbose, 'warning')
copy(os.path.join(curdir, "warp_curve2straight.nii.gz"), 'warp_curve2straight.nii.gz')
copy(os.path.join(curdir, "warp_straight2curve.nii.gz"), 'warp_straight2curve.nii.gz')
copy(os.path.join(curdir, "straight_ref.nii.gz"), 'straight_ref.nii.gz')
# apply straightening
s, o = run_proc(['sct_apply_transfo', '-i', 'data.nii', '-w', 'warp_curve2straight.nii.gz', '-d', 'straight_ref.nii.gz', '-o', 'data_straight.nii'])
else:
sct_straighten_spinalcord.main(argv=[
'-i', 'data.nii',
'-s', 'segmentation.nii',
'-r', str(remove_temp_files),
'-v', '0',
])
cache_save(cachefile, cache_sig)
# resample to 0.5mm isotropic to match template resolution
printv('\nResample to 0.5mm isotropic...', verbose)
s, o = run_proc(['sct_resample', '-i', 'data_straight.nii', '-mm', '0.5x0.5x0.5', '-x', 'linear', '-o', 'data_straightr.nii'], verbose=verbose)
# Apply straightening to segmentation
# N.B. Output is RPI
printv('\nApply straightening to segmentation...', verbose)
sct_apply_transfo.main(['-i', 'segmentation.nii',
'-d', 'data_straightr.nii',
'-w', 'warp_curve2straight.nii.gz',
'-o', 'segmentation_straight.nii',
'-x', 'linear',
'-v', '0'])
# Threshold segmentation at 0.5
img = Image('segmentation_straight.nii')
img.data = threshold(img.data, 0.5)
img.save()
# If disc label file is provided, label vertebrae using that file instead of automatically
if fname_disc:
# Apply straightening to disc-label
printv('\nApply straightening to disc labels...', verbose)
run_proc('sct_apply_transfo -i %s -d %s -w %s -o %s -x %s' %
(fname_disc,
'data_straightr.nii',
'warp_curve2straight.nii.gz',
'labeldisc_straight.nii.gz',
'label'),
verbose=verbose
)
label_vert('segmentation_straight.nii', 'labeldisc_straight.nii.gz', verbose=1)
else:
# create label to identify disc
printv('\nCreate label to identify disc...', verbose)
fname_labelz = os.path.join(path_tmp, file_labelz)
if initz or initcenter:
if initcenter:
# find z centered in FOV
nii = Image('segmentation.nii').change_orientation("RPI")
nx, ny, nz, nt, px, py, pz, pt = nii.dim # Get dimensions
z_center = int(np.round(nz / 2)) # get z_center
initz = [z_center, initcenter]
im_label = create_labels_along_segmentation(Image('segmentation.nii'), [(initz[0], initz[1])])
im_label.data = dilate(im_label.data, 3, 'ball')
im_label.save(fname_labelz)
elif fname_initlabel:
Image(fname_initlabel).save(fname_labelz)
else:
# automatically finds C2-C3 disc
im_data = Image('data.nii')
im_seg = Image('segmentation.nii')
if not remove_temp_files: # because verbose is here also used for keeping temp files
verbose_detect_c2c3 = 2
else:
verbose_detect_c2c3 = 0
im_label_c2c3 = detect_c2c3(im_data, im_seg, contrast, verbose=verbose_detect_c2c3)
ind_label = np.where(im_label_c2c3.data)
if not np.size(ind_label) == 0:
im_label_c2c3.data[ind_label] = 3
else:
printv('Automatic C2-C3 detection failed. Please provide manual label with sct_label_utils', 1, 'error')
sys.exit()
im_label_c2c3.save(fname_labelz)
# dilate label so it is not lost when applying warping
dilate(Image(fname_labelz), 3, 'ball').save(fname_labelz)
# Apply straightening to z-label
printv('\nAnd apply straightening to label...', verbose)
sct_apply_transfo.main(['-i', file_labelz,
'-d', 'data_straightr.nii',
'-w', 'warp_curve2straight.nii.gz',
'-o', 'labelz_straight.nii.gz',
'-x', 'nn',
'-v', '0'])
# get z value and disk value to initialize labeling
printv('\nGet z and disc values from straight label...', verbose)
init_disc = get_z_and_disc_values_from_label('labelz_straight.nii.gz')
printv('.. ' + str(init_disc), verbose)
# apply laplacian filtering
if laplacian:
printv('\nApply Laplacian filter...', verbose)
img = Image("data_straightr.nii")
# apply std dev to each axis of the image
sigmas = [1 for i in range(len(img.data.shape))]
# adjust sigma based on voxel size
sigmas = [sigmas[i] / img.dim[i + 4] for i in range(3)]
# smooth data
img.data = laplacian(img.data, sigmas)
img.save()
# detect vertebral levels on straight spinal cord
init_disc[1] = init_disc[1] - 1
vertebral_detection('data_straightr.nii', 'segmentation_straight.nii', contrast, param, init_disc=init_disc,
verbose=verbose, path_template=path_template, path_output=path_output, scale_dist=scale_dist)
# un-straighten labeled spinal cord
printv('\nUn-straighten labeling...', verbose)
sct_apply_transfo.main(['-i', 'segmentation_straight_labeled.nii',
'-d', 'segmentation.nii',
'-w', 'warp_straight2curve.nii.gz',
'-o', 'segmentation_labeled.nii',
'-x', 'nn',
'-v', '0'])
if clean_labels:
# Clean labeled segmentation
printv('\nClean labeled segmentation (correct interpolation errors)...', verbose)
clean_labeled_segmentation('segmentation_labeled.nii', 'segmentation.nii', 'segmentation_labeled.nii')
# label discs
printv('\nLabel discs...', verbose)
printv('\nUn-straighten labeled discs...', verbose)
run_proc('sct_apply_transfo -i %s -d %s -w %s -o %s -x %s' %
('segmentation_straight_labeled_disc.nii',
'segmentation.nii',
'warp_straight2curve.nii.gz',
'segmentation_labeled_disc.nii',
'label'),
verbose=verbose,
is_sct_binary=True,
)
# come back
os.chdir(curdir)
# Generate output files
path_seg, file_seg, ext_seg = extract_fname(fname_seg)
fname_seg_labeled = os.path.join(path_output, file_seg + '_labeled' + ext_seg)
printv('\nGenerate output files...', verbose)
generate_output_file(os.path.join(path_tmp, "segmentation_labeled.nii"), fname_seg_labeled)
generate_output_file(os.path.join(path_tmp, "segmentation_labeled_disc.nii"), os.path.join(path_output, file_seg + '_labeled_discs' + ext_seg))
# copy straightening files in case subsequent SCT functions need them
generate_output_file(os.path.join(path_tmp, "warp_curve2straight.nii.gz"), os.path.join(path_output, "warp_curve2straight.nii.gz"), verbose=verbose)
generate_output_file(os.path.join(path_tmp, "warp_straight2curve.nii.gz"), os.path.join(path_output, "warp_straight2curve.nii.gz"), verbose=verbose)
generate_output_file(os.path.join(path_tmp, "straight_ref.nii.gz"), os.path.join(path_output, "straight_ref.nii.gz"), verbose=verbose)
# Remove temporary files
if remove_temp_files == 1:
printv('\nRemove temporary files...', verbose)
rmtree(path_tmp)
# Generate QC report
if param.path_qc is not None:
path_qc = os.path.abspath(arguments.qc)
qc_dataset = arguments.qc_dataset
qc_subject = arguments.qc_subject
labeled_seg_file = os.path.join(path_output, file_seg + '_labeled' + ext_seg)
generate_qc(fname_in, fname_seg=labeled_seg_file, args=argv, path_qc=os.path.abspath(path_qc),
dataset=qc_dataset, subject=qc_subject, process='sct_label_vertebrae')
display_viewer_syntax([fname_in, fname_seg_labeled], colormaps=['', 'subcortical'], opacities=['1', '0.5'])