def main(args=None):
args = arg_parser().parse_args(args)
if args.verbosity == 1:
level = logging.getLevelName('INFO')
elif args.verbosity >= 2:
level = logging.getLevelName('DEBUG')
else:
level = logging.getLevelName('WARNING')
logging.basicConfig(
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
level=level)
logger = logging.getLogger(__name__)
try:
if not os.path.isdir(args.img_dir):
raise ValueError(
'(-i / --img-dir) argument needs to be a directory of NIfTI images.'
)
if args.mask_dir is not None:
if not os.path.isdir(args.mask_dir):
raise ValueError(
'(-m / --mask-dir) argument needs to be a directory of NIfTI images.'
)
ax = all_hists(args.img_dir,
args.mask_dir,
alpha=args.alpha,
figsize=args.figsize,
lw=args.linewidth)
if args.plot_title is not None:
ax.set_title(args.plot_title)
plt.savefig(args.out_name)
return 0
except Exception as e:
logger.exception(e)
return 1
def main(args=None):
args = arg_parser().parse_args(args)
if args.verbosity == 1:
level = logging.getLevelName('INFO')
elif args.verbosity >= 2:
level = logging.getLevelName('DEBUG')
else:
level = logging.getLevelName('WARNING')
logging.basicConfig(format='%(asctime)s - %(name)s - %(levelname)s - %(message)s', level=level)
logger = logging.getLogger(__name__)
try:
if not os.path.isdir(args.img_dir):
raise ValueError('(-i / --img-dir) argument needs to be a directory of NIfTI images.')
if args.mask_dir is not None:
if not os.path.isdir(args.mask_dir):
raise ValueError('(-m / --mask-dir) argument needs to be a directory of NIfTI images.')
_ = lsq.lsq_normalize(args.img_dir, args.mask_dir, args.output_dir)
if args.plot_hist:
with warnings.catch_warnings():
warnings.filterwarnings('ignore', category=FutureWarning)
from intensity_normalization.plot.hist import all_hists
import matplotlib.pyplot as plt
ax = all_hists(args.output_dir, args.mask_dir)
ax.set_title('Least Squares')
plt.savefig(os.path.join(args.output_dir, 'hist.png'))
return 0
except Exception as e:
logger.exception(e)
return 1
def main(args=None):
args = arg_parser().parse_args(args)
if args.verbosity == 1:
level = logging.getLevelName('INFO')
elif args.verbosity >= 2:
level = logging.getLevelName('DEBUG')
else:
level = logging.getLevelName('WARNING')
logging.basicConfig(
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
level=level)
logger = logging.getLogger(__name__)
try:
ax = all_hists(args.img_dir,
args.mask_dir,
alpha=args.alpha,
figsize=args.figsize,
lw=args.linewidth)
if args.plot_title is not None:
ax.set_title(args.plot_title)
plt.savefig(args.out_name)
return 0
except Exception as e:
logger.exception(e)
return 1
def main(args=None):
args = arg_parser().parse_args(args)
if args.verbosity == 1:
level = logging.getLevelName('INFO')
elif args.verbosity >= 2:
level = logging.getLevelName('DEBUG')
else:
level = logging.getLevelName('WARNING')
logging.basicConfig(
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
level=level)
logger = logging.getLogger(__name__)
try:
_ = hm.hm_normalize(args.img_dir, args.mask_dir, args.output_dir)
if args.plot_hist:
with warnings.catch_warnings():
warnings.filterwarnings('ignore', category=FutureWarning)
from intensity_normalization.plot.hist import all_hists
import matplotlib.pyplot as plt
ax = all_hists(args.output_dir, args.mask_dir)
ax.set_title('Histogram Matching')
plt.savefig(os.path.join(args.output_dir, 'hist.png'))
return 0
except Exception as e:
logger.exception(e)
return 1
def main(args=None):
args = arg_parser().parse_args(args)
if args.verbosity == 1:
level = logging.getLevelName('INFO')
elif args.verbosity >= 2:
level = logging.getLevelName('DEBUG')
else:
level = logging.getLevelName('WARNING')
logging.basicConfig(
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
level=level)
logger = logging.getLogger(__name__)
try:
if not args.single_img:
if not os.path.isdir(args.image) or not os.path.isdir(
args.brain_mask):
raise NormalizationError(
'if single-img option off, then image and brain-mask must be directories'
)
img_fns = io.glob_nii(args.image)
mask_fns = io.glob_nii(args.brain_mask)
if len(img_fns) != len(mask_fns) and len(img_fns) > 0:
raise NormalizationError(
'input images and masks must be in correspondence and greater than zero '
'({:d} != {:d})'.format(len(img_fns), len(mask_fns)))
for i, (img, mask) in enumerate(zip(img_fns, mask_fns), 1):
_, base, _ = io.split_filename(img)
logger.info('Normalizing image {} ({:d}/{:d})'.format(
img, i, len(img_fns)))
process(img, mask, args, logger)
else:
if not os.path.isfile(args.image) or not os.path.isfile(
args.brain_mask):
raise NormalizationError(
'if single-img option on, then image and brain-mask must be files'
)
process(args.image, args.brain_mask, args, logger)
if args.plot_hist:
with warnings.catch_warnings():
warnings.filterwarnings('ignore', category=FutureWarning)
from intensity_normalization.plot.hist import all_hists
import matplotlib.pyplot as plt
ax = all_hists(args.output_dir, args.brain_mask)
ax.set_title('GMM')
plt.savefig(os.path.join(args.output_dir, 'hist.png'))
return 0
except Exception as e:
logger.exception(e)
return 1
def main(args=None):
args = arg_parser().parse_args(args)
if not (args.brain_mask is None) ^ (args.tissue_mask is None):
raise NormalizationError(
'Only one of {brain mask, tissue mask} should be given')
if args.verbosity == 1:
level = logging.getLevelName('INFO')
elif args.verbosity >= 2:
level = logging.getLevelName('DEBUG')
else:
level = logging.getLevelName('WARNING')
logging.basicConfig(
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
level=level)
logger = logging.getLogger(__name__)
try:
if not args.single_img:
if not os.path.isdir(
args.image) or (False if args.brain_mask is None else
not os.path.isdir(args.brain_mask)):
raise NormalizationError(
'if single-img option off, then image and brain-mask must be directories'
)
img_fns = io.glob_nii(args.image)
mask_fns = io.glob_nii(
args.brain_mask
) if args.brain_mask is not None else [None] * len(img_fns)
if len(img_fns) != len(mask_fns) and len(img_fns) > 0:
raise NormalizationError(
'input images and masks must be in correspondence and greater than zero '
'({:d} != {:d})'.format(len(img_fns), len(mask_fns)))
args.output_dir = args.output_dir or 'fcm'
output_dir_base = os.path.abspath(
os.path.join(args.output_dir, '..'))
if args.contrast.lower() == 't1' and args.tissue_mask is None:
tissue_mask_dir = os.path.join(output_dir_base, 'tissue_masks')
if os.path.exists(tissue_mask_dir):
logger.warning(
'Tissue mask directory already exists, may overwrite existing tissue masks!'
)
else:
logger.info('Creating tissue mask directory: {}'.format(
tissue_mask_dir))
os.mkdir(tissue_mask_dir)
for i, (img, mask) in enumerate(zip(img_fns, mask_fns), 1):
_, base, _ = io.split_filename(img)
_, mask_base, _ = io.split_filename(mask)
logger.info(
'Creating tissue mask for {} ({:d}/{:d})'.format(
base, i, len(img_fns)))
logger.debug('Tissue mask {} ({:d}/{:d})'.format(
mask_base, i, len(img_fns)))
process(img, mask, None, tissue_mask_dir, args, logger)
elif os.path.exists(args.tissue_mask):
tissue_mask_dir = args.tissue_mask
else:
raise NormalizationError(
'If contrast is not t1, then tissue mask directory ({}) '
'must already be created!'.format(args.tissue_mask))
tissue_masks = io.glob_nii(tissue_mask_dir)
for i, (img, tissue_mask) in enumerate(zip(img_fns, tissue_masks),
1):
dirname, base, _ = io.split_filename(img)
_, tissue_base, _ = io.split_filename(tissue_mask)
logger.info('Normalizing image {} ({:d}/{:d})'.format(
base, i, len(img_fns)))
logger.debug('Tissue mask {} ({:d}/{:d})'.format(
tissue_base, i, len(img_fns)))
if args.output_dir is not None:
dirname = args.output_dir
process(img, None, tissue_mask, dirname, args, logger)
else:
if not os.path.isfile(args.image):
raise NormalizationError(
'if single-img option on, then image must be a file')
if args.tissue_mask is None and args.contrast.lower() == 't1':
logger.info('Creating tissue mask for {}'.format(args.image))
process(args.image, args.brain_mask, None, args.output_dir,
args, logger)
elif os.path.isfile(args.tissue_mask):
pass
else:
raise NormalizationError(
'If contrast is not t1, then tissue mask must be provided!'
)
logger.info('Normalizing image {}'.format(args.image))
dirname, base, _ = io.split_filename(args.image)
dirname = args.output_dir or dirname
if args.tissue_mask is None:
tissue_mask = os.path.join(
dirname, base + '_{}_mask.nii.gz'.format(args.tissue_type))
else:
tissue_mask = args.tissue_mask
process(args.image, args.brain_mask, tissue_mask, dirname, args,
logger)
if args.plot_hist:
with warnings.catch_warnings():
warnings.filterwarnings('ignore', category=FutureWarning)
from intensity_normalization.plot.hist import all_hists
import matplotlib.pyplot as plt
ax = all_hists(args.output_dir, args.brain_mask)
ax.set_title('Fuzzy C-Means')
plt.savefig(os.path.join(args.output_dir, 'hist.png'))
return 0
except Exception as e:
logger.exception(e)
return 1
def main(args=None):
args = arg_parser().parse_args(args)
if args.verbosity == 1:
level = logging.getLevelName('INFO')
elif args.verbosity >= 2:
level = logging.getLevelName('DEBUG')
else:
level = logging.getLevelName('WARNING')
logging.basicConfig(
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
level=level)
logger = logging.getLogger(__name__)
try:
img_fns = io.glob_nii(args.img_dir)
mask_fns = io.glob_nii(args.mask_dir)
if len(img_fns) != len(mask_fns) or len(img_fns) == 0:
raise NormalizationError(
'Image directory ({}) and mask directory ({}) must contain the same '
'(positive) number of images!'.format(args.img_dir,
args.mask_dir))
logger.info('Normalizing the images according to RAVEL')
Z, _ = ravel.ravel_normalize(
args.img_dir,
args.mask_dir,
args.contrast,
do_whitestripe=args.no_whitestripe,
b=args.num_unwanted_factors,
membership_thresh=args.control_membership_threshold,
do_registration=args.no_registration,
segmentation_smoothness=args.segmentation_smoothness,
use_fcm=not args.use_atropos,
sparse_svd=args.sparse_svd,
csf_masks=args.csf_masks)
V = ravel.image_matrix(img_fns, args.contrast, masks=mask_fns)
V_norm = ravel.ravel_correction(V, Z)
normalized = ravel.image_matrix_to_images(V_norm, img_fns)
# save the normalized images to disk
output_dir = os.getcwd(
) if args.output_dir is None else args.output_dir
out_fns = []
for fn in img_fns:
_, base, ext = io.split_filename(fn)
out_fns.append(os.path.join(output_dir, base + '_ravel' + ext))
if not os.path.exists(output_dir):
os.mkdir(output_dir)
for norm, out_fn in zip(normalized, out_fns):
norm.to_filename(out_fn)
if args.plot_hist:
with warnings.catch_warnings():
warnings.filterwarnings('ignore', category=FutureWarning)
from intensity_normalization.plot.hist import all_hists
import matplotlib.pyplot as plt
ax = all_hists(output_dir, args.mask_dir)
ax.set_title('RAVEL')
plt.savefig(os.path.join(output_dir, 'hist.png'))
return 0
except Exception as e:
logger.exception(e)
return 1
def test_all_hist(self):
from intensity_normalization.plot.hist import all_hists
_ = all_hists(self.data_dir, self.mask_dir)
def test_all_hist(self):
_ = all_hists(self.data_dir, self.mask_dir)
