def _extract_warped_image_landmarks(self, record):
""" get registration results - warped registered images and landmarks
:param record: {str: value}, dictionary with registration params
:return (str, str, str, str): paths to
"""
logging.debug('.. warp the registered image and get landmarks')
path_dir = self._get_path_reg_dir(record)
path_im_ref, path_im_move, _, path_lnds_move = self._get_paths(record)
path_log = os.path.join(path_dir, NAME_LOG_REGISTRATION)
# warp moving landmarks to reference frame
path_regist = os.path.join(path_dir, os.path.basename(path_im_move))
dict_params = {
'path_fiji': self.params['path_fiji'],
'path_bsh': PATH_SCRIPT_WARP_LANDMARKS,
'source': path_im_move, 'target': path_im_ref,
'output': path_dir, 'warp': path_regist}
# export source points to TXT
pts_source = load_landmarks(path_lnds_move)
save_landmarks(os.path.join(path_dir, NAME_LANDMARKS), pts_source)
# execute transformation
exec_commands(COMMAND_WARP_LANDMARKS % dict_params, path_logger=path_log)
# load warped landmarks from TXT
path_lnds = os.path.join(path_dir, NAME_LANDMARKS_WARPED)
if os.path.isfile(path_lnds):
points_warp = load_landmarks(path_lnds)
path_lnds = os.path.join(path_dir, os.path.basename(path_lnds_move))
save_landmarks(path_lnds, points_warp)
else:
path_lnds = None
return None, path_regist, None, path_lnds
def filter_paired_landmarks(item, path_dataset, path_reference, col_source,
col_target):
""" filter all relevant landmarks which were used and copy them to experiment
The case is that in certain challenge stage users had provided just a subset
of all image landmarks which could be laos shuffled. The idea is to filter identify
all user used (provided in dataset) landmarks and filter them from temporary
reference dataset.
:param dict|Series item: experiment DataFrame
:param str path_dataset: path to provided landmarks
:param str path_reference: path to the complete landmark collection
:param str col_source: column name of landmarks to be transformed
:param str col_target: column name of landmarks to be compared
:return tuple(float,ndarray,ndarray): match ratio, filtered ref and move landmarks
>>> p_data = update_path('data-images')
>>> p_csv = os.path.join(p_data, 'pairs-imgs-lnds_histol.csv')
>>> df = pd.read_csv(p_csv)
>>> ratio, lnds_ref, lnds_move = filter_paired_landmarks(dict(df.iloc[0]), p_data, p_data,
... ImRegBenchmark.COL_POINTS_MOVE, ImRegBenchmark.COL_POINTS_REF)
>>> ratio
1.0
>>> lnds_ref.shape == lnds_move.shape
True
"""
path_ref = update_path(item[col_source], pre_path=path_reference)
if not os.path.isfile(path_ref):
raise FileNotFoundError('missing landmarks: %s' % path_ref)
path_load = update_path(item[col_source], pre_path=path_dataset)
if not os.path.isfile(path_load):
raise FileNotFoundError('missing landmarks: %s' % path_load)
pairs = common_landmarks(load_landmarks(path_ref),
load_landmarks(path_load),
threshold=1)
if not pairs.size:
logging.warning(
'there is not pairing between landmarks or dataset and user reference'
)
return 0., np.empty([0]), np.empty([0])
pairs = sorted(pairs.tolist(), key=lambda p: p[1])
ind_ref = np.asarray(pairs)[:, 0]
nb_common = min([
len(load_landmarks(update_path(item[col], pre_path=path_reference)))
for col in (col_target, col_source)
])
ind_ref = ind_ref[ind_ref < nb_common]
path_lnd_ref = update_path(item[col_target], pre_path=path_reference)
lnds_filter_ref = load_landmarks(path_lnd_ref)[ind_ref]
path_lnd_move = update_path(item[col_source], pre_path=path_reference)
lnds_filter_move = load_landmarks(path_lnd_move)[ind_ref]
ratio_matches = len(ind_ref) / float(nb_common)
if ratio_matches > 1:
raise ValueError(
'suspicious ratio for %i paired and %i common landmarks' %
(len(pairs), nb_common))
return ratio_matches, lnds_filter_ref, lnds_filter_move
def filter_landmarks(idx_row, path_output, path_dataset, path_reference):
""" filter all relevant landmarks which were used and copy them to experiment
:param (idx, {}|Series) idx_row: experiment DataFrame
:param str path_output: path to output folder
:param str path_dataset: path to provided landmarks
:param str path_reference: path to the complete landmark collection
:return (idx, float): record index and match ratio
"""
idx, row = idx_row
path_ref = update_path_(row[COL_POINTS_MOVE], path_reference)
path_load = update_path_(row[COL_POINTS_MOVE], path_dataset)
pairs = common_landmarks(load_landmarks(path_ref),
load_landmarks(path_load),
threshold=1)
pairs = sorted(pairs.tolist(), key=lambda p: p[1])
ind_ref = np.asarray(pairs)[:, 0]
# moving and reference landmarks
for col in [COL_POINTS_REF, COL_POINTS_MOVE]:
path_in = update_path_(row[col], path_reference)
path_out = update_path_(row[col], path_output)
create_folder(os.path.dirname(path_out), ok_existing=True)
save_landmarks(path_out, load_landmarks(path_in)[ind_ref])
# save ratio of found landmarks
len_lnds_ref = len(
load_landmarks(update_path_(row[COL_POINTS_REF], path_reference)))
ratio_matches = len(pairs) / float(len_lnds_ref)
return idx, ratio_matches
def _extract_warped_image_landmarks(self, item):
""" get registration results - warped registered images and landmarks
:param dict item: dictionary with registration params
:return dict: paths to warped images/landmarks
"""
logging.debug('.. warp the registered image and get landmarks')
path_dir = self._get_path_reg_dir(item)
path_im_ref, path_im_move, _, path_lnds_move = self._get_paths(
item, prefer_pproc=False)
path_log = os.path.join(path_dir, self.NAME_LOG_REGISTRATION)
# warp moving landmarks to reference frame
path_dir_out = os.path.join(path_dir, self.DIR_OUTPUTS)
# name_ref, _ = os.path.splitext(os.path.basename(path_im_ref))
name_move, _ = os.path.splitext(os.path.basename(path_im_move))
path_img_warp = os.path.join(path_dir, os.path.basename(path_im_move))
dict_params = {
'exec_Fiji': self.params['exec_Fiji'],
'path_bsh': self.PATH_SCRIPT_WARP_LANDMARKS,
'source': path_im_move,
'target': path_im_ref,
'output': path_dir,
# 'transf': os.path.join(path_dir_out, name_ref + '.xml'),
'transf': os.path.join(path_dir_out, name_move + '.xml'),
'warp': path_img_warp,
}
# export source points to TXT
pts_source = load_landmarks(path_lnds_move)
save_landmarks(os.path.join(path_dir, BmUnwarpJ.NAME_LANDMARKS),
pts_source)
# execute transformation
exec_commands(self.COMMAND_WARP_LANDMARKS % dict_params,
path_logger=path_log,
timeout=self.EXECUTE_TIMEOUT)
# load warped landmarks from TXT
path_lnds_warp = os.path.join(path_dir,
BmUnwarpJ.NAME_LANDMARKS_WARPED)
if os.path.isfile(path_lnds_warp):
points_warp = load_landmarks(path_lnds_warp)
path_lnds_warp = os.path.join(path_dir,
os.path.basename(path_lnds_move))
save_landmarks(path_lnds_warp, points_warp)
else:
path_lnds_warp = None
# return results
return {
self.COL_IMAGE_MOVE_WARP: path_img_warp,
self.COL_POINTS_MOVE_WARP: path_lnds_warp
}
def _extract_warped_image_landmarks(self, item):
""" get registration results - warped registered images and landmarks
:param dict item: dictionary with registration params
:return dict: paths to warped images/landmarks
"""
logging.debug('.. warp the registered image and get landmarks')
path_dir = self._get_path_reg_dir(item)
_, path_img_move, _, path_lnds_move = self._get_paths(item)
path_lnds_warp, path_img_warp = None, None
# load warped landmarks from TXT
path_lnds = os.path.join(path_dir, self.NAME_FILE_LANDMARKS)
if os.path.isfile(path_lnds):
points_warp = load_landmarks(path_lnds)
path_lnds_warp = os.path.join(path_dir, os.path.basename(path_lnds_move))
save_landmarks(path_lnds_warp, points_warp)
os.remove(path_lnds)
path_regist = os.path.join(path_dir, self.NAME_FILE_IMAGE)
if os.path.isfile(path_regist):
name_img_move, _ = os.path.splitext(os.path.basename(path_img_move))
_, ext_img_warp = os.path.splitext(self.NAME_FILE_IMAGE)
path_img_warp = os.path.join(path_dir, name_img_move + ext_img_warp)
os.rename(path_regist, path_img_warp)
return {self.COL_IMAGE_MOVE_WARP: path_img_warp,
self.COL_POINTS_MOVE_WARP: path_lnds_warp}
def _visual_image_ref_warp_lnds_move_warp(record, path_dataset=None,
path_experiment=None):
""" visualise the case with warped reference landmarks to the move frame
:param {} record: row with the experiment
:param str|None path_dataset: path to the dataset folder
:param str|None path_experiment: path to the experiment folder
:return obj|None:
"""
assert COL_POINTS_REF_WARP in record and isinstance(record[COL_POINTS_REF_WARP], str), \
'Missing registered image "%s"' % COL_POINTS_REF_WARP
path_points_warp = update_path_(record[COL_POINTS_REF_WARP], path_experiment)
if not os.path.isfile(path_points_warp):
logging.warning('missing warped landmarks for: %r', dict(record))
return
points_ref, points_move, path_img_ref = _load_landmarks(record, path_dataset)
points_warp = load_landmarks(path_points_warp)
if not list(points_warp):
return
# draw image with landmarks
image_move = load_image(update_path_(record[COL_IMAGE_MOVE], path_dataset))
# image_warp = tl_io.load_image(row['Moving image, Transf.'])
image = draw_image_points(image_move, points_warp)
save_image(os.path.join(update_path_(record[COL_REG_DIR], path_experiment),
NAME_IMAGE_REF_POINTS_WARP), image)
del image
# visualise the landmarks move during registration
image_ref = load_image(path_img_ref)
fig = draw_images_warped_landmarks(image_ref, image_move, points_ref,
points_move, points_warp)
del image_ref, image_move
return fig
def _visual_image_move_warp_lnds_move_warp(cls, item, path_dataset=None, path_experiment=None):
""" visualise the case with warped moving image and landmarks
to the reference frame so they are simple to overlap
:param dict item: row with the experiment
:param str|None path_dataset: path to the dataset folder
:param str|None path_experiment: path to the experiment folder
:return obj|None:
"""
assert isinstance(item.get(cls.COL_POINTS_MOVE_WARP, None), str), \
'Missing registered points in "%s"' % cls.COL_POINTS_MOVE_WARP
path_points_warp = update_path(item[cls.COL_POINTS_MOVE_WARP], pre_path=path_experiment)
if not os.path.isfile(path_points_warp):
logging.warning('missing warped landmarks for: %r', dict(item))
return
points_ref, points_move, path_img_ref = cls._load_landmarks(item, path_dataset)
image_warp = cls._load_warped_image(item, path_experiment)
points_warp = load_landmarks(path_points_warp)
if not list(points_warp):
return
# draw image with landmarks
image = draw_image_points(image_warp, points_warp)
_path = update_path(item[cls.COL_REG_DIR], pre_path=path_experiment)
save_image(os.path.join(_path, cls.NAME_IMAGE_MOVE_WARP_POINTS), image)
del image
# visualise the landmarks move during registration
image_ref = load_image(path_img_ref)
fig = draw_images_warped_landmarks(image_ref, image_warp, points_move, points_ref, points_warp)
del image_ref, image_warp
return fig
def _extract_warped_image_landmarks(self, record):
""" get registration results - warped registered images and landmarks
:param record: {str: value}, dictionary with registration params
:return (str, str, str, str): paths to
"""
logging.debug('.. warp the registered image and get landmarks')
path_dir = self._get_path_reg_dir(record)
_, path_img_move, _, path_lnds_move = self._get_paths(record)
path_lnds_warp, path_img_warp = None, None
# load warped landmarks from TXT
path_lnds = os.path.join(path_dir, NAME_FILE_LANDMARKS)
if os.path.isfile(path_lnds):
points_warp = load_landmarks(path_lnds)
path_lnds_warp = os.path.join(path_dir, os.path.basename(path_lnds_move))
save_landmarks(path_lnds_warp, points_warp)
os.remove(path_lnds)
path_regist = os.path.join(path_dir, NAME_FILE_IMAGE)
if os.path.isfile(path_regist):
name_img_move = os.path.splitext(os.path.basename(path_img_move))[0]
ext_img_warp = os.path.splitext(NAME_FILE_IMAGE)[-1]
path_img_warp = os.path.join(path_dir, name_img_move + ext_img_warp)
os.rename(path_regist, path_img_warp)
return None, path_img_warp, None, path_lnds_warp
def filter_export_landmarks(idx_row, path_output, path_dataset,
path_reference):
""" filter all relevant landmarks which were used and copy them to experiment
The case is that in certain challenge stage users had provided just a subset
of all image landmarks which could be laos shuffled. The idea is to filter identify
all user used (provided in dataset) landmarks and filter them from temporary
reference dataset.
:param tuple(idx,dict|Series) idx_row: experiment DataFrame
:param str path_output: path to output folder
:param str path_dataset: path to provided landmarks
:param str path_reference: path to the complete landmark collection
:return tuple(idx,float): record index and match ratio
"""
idx, row = idx_row
ratio_matches, lnds_filter_ref, lnds_filter_move = \
filter_paired_landmarks(row, path_dataset, path_reference,
ImRegBenchmark.COL_POINTS_MOVE,
ImRegBenchmark.COL_POINTS_REF)
# moving and reference landmarks
for col, lnds_flt in [(ImRegBenchmark.COL_POINTS_REF, lnds_filter_ref),
(ImRegBenchmark.COL_POINTS_MOVE, lnds_filter_move)]:
path_out = update_path(row[col], pre_path=path_output)
create_folder(os.path.dirname(path_out), ok_existing=True)
if os.path.isfile(path_out):
assert np.array_equal(load_landmarks(path_out), lnds_flt), \
'overwrite different set of landmarks'
save_landmarks(path_out, lnds_flt)
return idx, ratio_matches
def _extract_warped_image_landmarks(self, item):
""" get registration results - warped registered images and landmarks
:param dict item: dictionary {str: value} with registration params
:return dict: paths to results
"""
path_dir = self._get_path_reg_dir(item)
path_im_ref, path_im_move, _, path_lnds_move = self._get_paths(item)
name_im_move, _ = os.path.splitext(os.path.basename(path_lnds_move))
name_lnds_move, _ = os.path.splitext(os.path.basename(path_lnds_move))
# simplified version of landmarks
lnds = load_landmarks(path_lnds_move)
path_lnds_warp = os.path.join(path_dir, name_lnds_move + '.csv')
# https://github.com/ANTsX/ANTs/issues/733#issuecomment-472049427
pd.DataFrame(lnds * -1, columns=['x', 'y']).to_csv(path_lnds_warp, index=None)
# list output transformations
tf_elast_inv = sorted(glob.glob(os.path.join(path_dir, 'trans*InverseWarp.nii*')))
tf_elast = [os.path.join(os.path.dirname(p), os.path.basename(p).replace('Inverse', ''))
for p in tf_elast_inv]
tf_affine = sorted(glob.glob(os.path.join(path_dir, 'trans*GenericAffine.mat')))
# generate commands
cmd_warp_img = self.COMMAND_WARP_IMAGE % {
'antsApplyTransforms': self.exec_transf_img,
'output': path_dir,
'img_target': item[self.COL_IMAGE_REF_NII],
'img_source': item[self.COL_IMAGE_MOVE_NII],
'transfs': ' -t '.join(sorted(tf_affine + tf_elast, reverse=True)),
'img_name': name_im_move
}
cmd_warp_pts = self.COMMAND_WARP_POINTS % {
'antsApplyTransformsToPoints': self.exec_transf_pts,
'output': path_dir,
'path_points': path_lnds_warp,
'transfs': ' -t '.join(['[ %s , 1]' % tf if 'Affine' in tf else tf
for tf in sorted(tf_affine + tf_elast_inv)]),
'pts_name': name_lnds_move
}
# execute commands
exec_commands([cmd_warp_img, cmd_warp_pts],
path_logger=os.path.join(path_dir, 'warping.log'))
path_im_nii = os.path.join(path_dir, name_im_move + '.nii')
if os.path.isfile(path_im_nii):
path_img_warp = convert_image_from_nifti(path_im_nii)
else:
path_img_warp = None
if os.path.isfile(path_lnds_warp):
lnds = pd.read_csv(path_lnds_warp, index_col=None).values
save_landmarks(path_lnds_warp, lnds * -1)
else:
path_lnds_warp = None
return {self.COL_IMAGE_MOVE_WARP: path_img_warp,
self.COL_POINTS_MOVE_WARP: path_lnds_warp}
def compute_registration_statistic(idx_row, df_experiments,
path_dataset=None, path_experiment=None):
""" after successful registration load initial nad estimated landmarks
afterwords compute various statistic for init, and finalNoBmTemplatene alignment
:param (int, dict) idx_row: tow from iterated table
:param DF df_experiments: DataFrame with experiments
:param str|None path_dataset: path to the dataset folder
:param str|None path_experiment: path to the experiment folder
"""
idx, row = idx_row
row = dict(row) # convert even series to dictionary
points_ref, points_move, path_img_ref = _load_landmarks(row, path_dataset)
img_diag = _image_diag(row, path_img_ref)
df_experiments.loc[idx, COL_IMAGE_DIAGONAL] = img_diag
# compute landmarks statistic
compute_registration_accuracy(df_experiments, idx, points_ref, points_move,
'init', img_diag, wo_affine=False)
# load transformed landmarks
if (COL_POINTS_MOVE_WARP not in row) and (COL_POINTS_REF_WARP not in row):
logging.error('Statistic: no output landmarks')
return
# define what is the target and init state according to the experiment results
is_move_warp = COL_POINTS_MOVE_WARP in row and row[COL_POINTS_MOVE_WARP]
points_init = points_move if is_move_warp else points_ref
points_target = points_ref if is_move_warp else points_move
col_lnds_warp = COL_POINTS_MOVE_WARP if is_move_warp else COL_POINTS_REF_WARP
# load landmarks
path_landmarks = update_path_(row[col_lnds_warp], path_experiment)
if path_landmarks and os.path.isfile(path_landmarks):
points_warp = load_landmarks(path_landmarks)
else:
logging.warning('Invalid path to the landmarks: "%s" <- "%s"',
path_landmarks, row[col_lnds_warp])
return
# compute Affine statistic
affine_diff = compute_affine_transf_diff(points_init, points_target, points_warp)
for name in affine_diff:
df_experiments.loc[idx, name] = affine_diff[name]
# compute landmarks statistic
compute_registration_accuracy(df_experiments, idx, points_target, points_warp,
'elastic', img_diag, wo_affine=True)
# compute landmarks statistic
compute_registration_accuracy(df_experiments, idx, points_target, points_warp,
'final', img_diag, wo_affine=False)
row_ = dict(df_experiments.loc[idx])
if 'TRE Mean (final)' in row_:
robust = row_['TRE Mean (final)'] < row_['TRE Mean (init)']
df_experiments.loc[idx, COL_ROBUSTNESS] = int(robust)
def _extract_warped_image_landmarks(self, item):
""" get registration results - warped registered images and landmarks
:param dict item: dictionary with registration params
:return dict: paths to warped images/landmarks
"""
path_reg_dir = self._get_path_reg_dir(item)
_, path_im_move, path_lnds_ref, _ = self._get_paths(item)
# convert MHD image
path_img_ = convert_image_from_mhd(os.path.join(
path_reg_dir, 'output.mhd'),
scaling=item.get('scaling', 1.))
img_name, _ = os.path.splitext(os.path.basename(path_im_move))
_, img_ext = os.path.splitext(os.path.basename(path_img_))
path_img_warp = path_img_.replace('output' + img_ext,
img_name + img_ext)
shutil.move(path_img_, path_img_warp)
# load transform and warp landmarks
# lnds_move = load_landmarks(path_lnds_move)
lnds_ref = load_landmarks(path_lnds_ref)
lnds_name = os.path.basename(path_lnds_ref)
path_lnds_warp = os.path.join(path_reg_dir, lnds_name)
if lnds_ref is None:
raise ValueError('missing landmarks to be transformed "%s"' %
lnds_name)
# down-scale landmarks if defined
lnds_ref = lnds_ref / item.get('scaling', 1.)
# extract deformation
path_deform_x = os.path.join(path_reg_dir, 'output_x.mhd')
path_deform_y = os.path.join(path_reg_dir, 'output_y.mhd')
try:
shift = self.extract_landmarks_shift_from_mhd(
path_deform_x, path_deform_y, lnds_ref)
except Exception:
logging.exception(path_reg_dir)
shift = np.zeros(lnds_ref.shape)
# lnds_warp = lnds_move - shift
lnds_warp = lnds_ref + shift
# upscale landmarks if defined
lnds_warp = lnds_warp * item.get('scaling', 1.)
save_landmarks(path_lnds_warp, lnds_warp)
# return formatted results
return {
self.COL_IMAGE_MOVE_WARP: path_img_warp,
self.COL_POINTS_REF_WARP: path_lnds_warp,
}
def _visual_image_move_warp_lnds_ref_warp(cls,
item,
path_dataset=None,
path_experiment=None):
""" visualise the case with warped reference landmarks to the move frame
:param dict item: row with the experiment
:param str|None path_dataset: path to the dataset folder
:param str|None path_experiment: path to the experiment folder
:return obj|None:
"""
if not isinstance(item.get(cls.COL_POINTS_REF_WARP), str):
raise ValueError('Missing registered points in "%s"' %
cls.COL_POINTS_REF_WARP)
path_points_warp = update_path(item[cls.COL_POINTS_REF_WARP],
pre_path=path_experiment)
if not os.path.isfile(path_points_warp):
logging.warning('missing warped landmarks for: %r', dict(item))
return
points_ref, points_move, path_img_ref = cls._load_landmarks(
item, path_dataset)
points_warp = load_landmarks(path_points_warp)
if not list(points_warp):
return
# draw image with landmarks
image_move = load_image(
update_path(item[cls.COL_IMAGE_MOVE], pre_path=path_dataset))
image = draw_image_points(image_move, points_warp)
_path = update_path(item[cls.COL_REG_DIR], pre_path=path_experiment)
save_image(os.path.join(_path, cls.NAME_IMAGE_REF_POINTS_WARP), image)
del image
image_ref = load_image(path_img_ref)
image_warp = cls._load_warped_image(item, path_experiment)
image = overlap_two_images(image_ref, image_warp)
_path = update_path(item[cls.COL_REG_DIR], pre_path=path_experiment)
save_image(os.path.join(_path, cls.NAME_IMAGE_REF_WARP), image)
del image, image_warp
# visualise the landmarks move during registration
fig = draw_images_warped_landmarks(image_ref, image_move, points_ref,
points_move, points_warp)
return fig
def _extract_warped_image_landmarks(self, item):
""" get registration results - warped registered images and landmarks
:param dict item: dictionary with registration params
:return dict: paths to warped images/landmarks
"""
path_dir = self._get_path_reg_dir(item)
path_img_ref, path_img_move, path_lnds_ref, path_lnds_move = self._get_paths(
item)
path_img_warp, path_lnds_warp = None, None
path_log = os.path.join(path_dir, self.NAME_LOG_REGISTRATION)
name_lnds = os.path.basename(path_lnds_ref)
path_lnds_local = save_landmarks_pts(os.path.join(path_dir, name_lnds),
load_landmarks(path_lnds_ref))
# warping the image and points
cmd = self.COMMAND_TRANSFORMATION % {
'exec_transformix': self.exec_transformix,
'source': path_img_move,
'output': path_dir,
'landmarks': path_lnds_local,
}
exec_commands(cmd, path_logger=path_log, timeout=self.EXECUTE_TIMEOUT)
# if there is an output image copy it
path_im_out = glob.glob(os.path.join(path_dir, self.NAME_IMAGE_WARPED))
if path_im_out:
path_im_out = sorted(path_im_out)[0]
_, ext_img = os.path.splitext(path_im_out)
name_img, _ = os.path.splitext(os.path.basename(path_img_move))
path_img_warp = os.path.join(path_dir, name_img + ext_img)
os.rename(path_im_out, path_img_warp)
path_lnds_out = os.path.join(path_dir, self.NAME_LNDS_WARPED)
if os.path.isfile(path_lnds_out):
path_lnds_warp = os.path.join(path_dir, name_lnds)
lnds = self.parse_warped_points(path_lnds_out)
save_landmarks(path_lnds_warp, lnds)
return {
self.COL_IMAGE_MOVE_WARP: path_img_warp,
self.COL_POINTS_REF_WARP: path_lnds_warp
}
def _extract_warped_image_landmarks(self, item):
""" get registration results - warped registered images and landmarks
:param dict item: dictionary with registration params
:return dict: paths to warped images/landmarks
"""
path_reg_dir = self._get_path_reg_dir(item)
_, path_im_move, path_lnds_ref, path_lnds_move = self._get_paths(item)
path_img_warp = os.path.join(path_reg_dir,
os.path.basename(path_im_move))
shutil.move(os.path.join(path_reg_dir, 'output.jpeg'), path_img_warp)
# load transform and warp landmarks
lnds_ = load_landmarks(path_lnds_ref)
# this was in case you run inverse registration co you could warp the landmarks directly
# lnds_ = load_landmarks(path_lnds_move)
lnds_name = os.path.basename(path_lnds_move)
path_lnds_warp = os.path.join(path_reg_dir, lnds_name)
if lnds_ is None:
raise ValueError('missing landmarks to be transformed "%s"' %
lnds_name)
# extract deformation
path_deform_x = os.path.join(path_reg_dir, 'output_field_x.nii.gz')
path_deform_y = os.path.join(path_reg_dir, 'output_field_y.nii.gz')
try:
shift = self.extract_landmarks_shift_from_nifty(
path_deform_x, path_deform_y, lnds_)
except Exception:
logging.exception(path_reg_dir)
shift = np.zeros(lnds_.shape)
lnds_warp = lnds_ + shift
save_landmarks(path_lnds_warp, lnds_warp)
# return formatted results
return {
self.COL_IMAGE_MOVE_WARP: path_img_warp,
self.COL_POINTS_REF_WARP: path_lnds_warp,
}
def compute_registration_statistic(
cls,
idx_row,
df_experiments,
path_dataset=None,
path_experiment=None,
path_reference=None,
):
""" after successful registration load initial nad estimated landmarks
afterwords compute various statistic for init, and final alignment
:param tuple(int,dict) df_row: row from iterated table
:param DF df_experiments: DataFrame with experiments
:param str|None path_dataset: path to the provided dataset folder
:param str|None path_reference: path to the complete landmark collection folder
:param str|None path_experiment: path to the experiment folder
"""
idx, row = idx_row
row = dict(row) # convert even series to dictionary
# load common landmarks and image size
points_ref, points_move, path_img_ref = cls._load_landmarks(
row, path_dataset)
img_diag = cls._image_diag(row, path_img_ref)
df_experiments.loc[idx, cls.COL_IMAGE_DIAGONAL] = img_diag
# compute landmarks statistic
cls.compute_registration_accuracy(df_experiments,
idx,
points_ref,
points_move,
'init',
img_diag,
wo_affine=False)
# define what is the target and init state according to the experiment results
use_move_warp = isinstance(row.get(cls.COL_POINTS_MOVE_WARP), str)
if use_move_warp:
points_init, points_target = points_move, points_ref
col_source, col_target = cls.COL_POINTS_MOVE, cls.COL_POINTS_REF
col_lnds_warp = cls.COL_POINTS_MOVE_WARP
else:
points_init, points_target = points_ref, points_move
col_lnds_warp = cls.COL_POINTS_REF_WARP
col_source, col_target = cls.COL_POINTS_REF, cls.COL_POINTS_MOVE
# optional filtering
if path_reference:
ratio, points_target, _ = \
filter_paired_landmarks(row, path_dataset, path_reference, col_source, col_target)
df_experiments.loc[idx, COL_PAIRED_LANDMARKS] = np.round(ratio, 2)
# load transformed landmarks
if (cls.COL_POINTS_MOVE_WARP not in row) and (cls.COL_POINTS_REF_WARP
not in row):
logging.error('Statistic: no output landmarks')
return
# check if there are reference landmarks
if points_target is None:
logging.warning(
'Missing landmarks in "%s"',
cls.COL_POINTS_REF if use_move_warp else cls.COL_POINTS_MOVE)
return
# load warped landmarks
path_lnds_warp = update_path(row[col_lnds_warp],
pre_path=path_experiment)
if path_lnds_warp and os.path.isfile(path_lnds_warp):
points_warp = load_landmarks(path_lnds_warp)
points_warp = np.nan_to_num(points_warp)
else:
logging.warning('Invalid path to the landmarks: "%s" <- "%s"',
path_lnds_warp, row[col_lnds_warp])
return
df_experiments.loc[idx, cls.COL_NB_LANDMARKS_INPUT] = min(
len(points_init), len(points_target))
df_experiments.loc[idx, cls.COL_NB_LANDMARKS_WARP] = len(points_warp)
# compute Affine statistic
affine_diff = compute_affine_transf_diff(points_init, points_target,
points_warp)
for name in affine_diff:
df_experiments.loc[idx, name] = affine_diff[name]
# compute landmarks statistic
cls.compute_registration_accuracy(df_experiments,
idx,
points_target,
points_warp,
'elastic',
img_diag,
wo_affine=True)
# compute landmarks statistic
cls.compute_registration_accuracy(df_experiments,
idx,
points_target,
points_warp,
'target',
img_diag,
wo_affine=False)
row_ = dict(df_experiments.loc[idx])
# compute the robustness
if 'TRE Mean' in row_:
df_experiments.loc[idx, cls.COL_ROBUSTNESS] = \
compute_tre_robustness(points_target, points_init, points_warp)
def _load_landmarks(cls, item, path_dataset):
path_img_ref, _, path_lnds_ref, path_lnds_move = \
[update_path(item[col], pre_path=path_dataset) for col in cls.COVER_COLUMNS]
points_ref = load_landmarks(path_lnds_ref)
points_move = load_landmarks(path_lnds_move)
return points_ref, points_move, path_img_ref
def compute_registration_statistic(cls,
idx_row,
df_experiments,
path_dataset=None,
path_experiment=None):
""" after successful registration load initial nad estimated landmarks
afterwords compute various statistic for init, and final alignment
:param tuple(int,dict) df_row: row from iterated table
:param DF df_experiments: DataFrame with experiments
:param str|None path_dataset: path to the dataset folder
:param str|None path_experiment: path to the experiment folder
"""
idx, row = idx_row
row = dict(row) # convert even series to dictionary
points_ref, points_move, path_img_ref = cls._load_landmarks(
row, path_dataset)
img_diag = cls._image_diag(row, path_img_ref)
df_experiments.loc[idx, cls.COL_IMAGE_DIAGONAL] = img_diag
# compute landmarks statistic
cls.compute_registration_accuracy(df_experiments,
idx,
points_ref,
points_move,
'init',
img_diag,
wo_affine=False)
# load transformed landmarks
if (cls.COL_POINTS_MOVE_WARP not in row) and (cls.COL_POINTS_REF_WARP
not in row):
logging.error('Statistic: no output landmarks')
return
# define what is the target and init state according to the experiment results
is_move_warp = isinstance(row.get(cls.COL_POINTS_MOVE_WARP, None), str)
points_init = points_move if is_move_warp else points_ref
points_target = points_ref if is_move_warp else points_move
col_lnds_warp = cls.COL_POINTS_MOVE_WARP if is_move_warp else cls.COL_POINTS_REF_WARP
# check if there are reference landmarks
if points_target is None:
logging.warning(
'Missing landmarks in "%s"',
cls.COL_POINTS_REF if is_move_warp else cls.COL_POINTS_MOVE)
return
# load warped landmarks
path_lnds_wapr = update_path(row[col_lnds_warp],
pre_path=path_experiment)
if path_lnds_wapr and os.path.isfile(path_lnds_wapr):
points_warp = load_landmarks(path_lnds_wapr)
points_warp = np.nan_to_num(points_warp)
else:
logging.warning('Invalid path to the landmarks: "%s" <- "%s"',
path_lnds_wapr, row[col_lnds_warp])
return
# compute Affine statistic
affine_diff = compute_affine_transf_diff(points_init, points_target,
points_warp)
for name in affine_diff:
df_experiments.loc[idx, name] = affine_diff[name]
# compute landmarks statistic
cls.compute_registration_accuracy(df_experiments,
idx,
points_target,
points_warp,
'elastic',
img_diag,
wo_affine=True)
# compute landmarks statistic
cls.compute_registration_accuracy(df_experiments,
idx,
points_target,
points_warp,
'target',
img_diag,
wo_affine=False)
row_ = dict(df_experiments.loc[idx])
# compute the robustness
if 'TRE Mean' in row_:
df_experiments.loc[idx, cls.COL_ROBUSTNESS] = \
compute_tre_robustness(points_target, points_init, points_warp)
def _load_landmarks(record, path_dataset):
path_img_ref, _, path_lnds_ref, path_lnds_move = \
[update_path_(record[col], path_dataset) for col in COVER_COLUMNS]
points_ref = load_landmarks(path_lnds_ref)
points_move = load_landmarks(path_lnds_move)
return points_ref, points_move, path_img_ref