def attach_image_to_foreground_axes(self, image3d, cmap='gray'):
"""Attaches a given image to the foreground axes and bring it forth"""
image3d = crop_image(image3d, self.padding)
image3d = scale_0to1(image3d)
slices = pick_slices(image3d, self.views, self.num_slices_per_view)
for ax_index, (dim_index, slice_index) in enumerate(slices):
slice_data = get_axis(image3d, dim_index, slice_index)
self.images_fg[ax_index].set(data=slice_data, cmap=cmap)
for ax in self.fg_axes:
ax.set(visible=True, zorder=self.layer_order_zoomedin)
def _compute_background(self):
"""Computes the background image for the current image."""
if not hasattr(self, 'background_img'):
# need to scale the mask, as Collage class does NOT automatically rescale
self.foreground_mask = mask_image(self.current_img, out_dtype=bool)
temp_background_img = np.copy(self.current_img)
temp_background_img[self.foreground_mask] = 0.0
self.background_img = scale_0to1(temp_background_img,
exclude_outliers_below=1,
exclude_outliers_above=1)
def _mix_color(slice1, slice2, alpha_channels, color_space='rgb'):
"""Mixing them as red and green channels"""
if slice1.shape != slice2.shape:
raise ValueError(
'size mismatch between cropped slices and checkers!!!')
alpha_channels = np.array(alpha_channels)
if len(alpha_channels) != 2:
raise ValueError('Alphas must be two value tuples.')
slice1 = scale_0to1(slice1)
slice2 = scale_0to1(slice2)
# masking background
combined_distr = np.concatenate((slice1.flatten(), slice2.flatten()))
image_eps = np.percentile(combined_distr, 5)
background = np.logical_or(slice1 <= image_eps, slice2 <= image_eps)
if color_space.lower() in ['rgb']:
red = alpha_channels[0] * slice1
grn = alpha_channels[1] * slice2
blu = np.zeros_like(slice1)
# foreground = np.logical_not(background)
# blu[foreground] = 1.0
mixed = np.stack((red, grn, blu), axis=2)
elif color_space.lower() in ['hsv']:
raise NotImplementedError(
'This method (color_space="hsv") is yet to fully conceptualized and implemented.'
)
# ensuring all values are clipped to [0, 1]
mixed[mixed <= 0.0] = 0.0
mixed[mixed >= 1.0] = 1.0
return mixed
def show_tails_trimmed(self, no_toggle=False):
"""Callback for ghosting specific review"""
if not self.currently_showing in ['tails_trimmed', ] or no_toggle:
if not hasattr(self, 'tails_trimmed_img'):
self.tails_trimmed_img = scale_0to1(self.current_img,
exclude_outliers_below=1,
exclude_outliers_above=0.05)
self.collage.attach(self.tails_trimmed_img)
self.currently_showing = 'tails_trimmed'
else:
self.show_original()
def load_unit(self, unit_id):
"""Loads the image data for display."""
t1_mri_path = get_freesurfer_mri_path(self.in_dir, unit_id,
self.mri_name)
fs_seg_path = get_freesurfer_mri_path(self.in_dir, unit_id,
self.seg_name)
temp_t1_mri = read_image(t1_mri_path, error_msg='T1 mri')
temp_fs_seg = read_image(fs_seg_path, error_msg='segmentation')
if temp_t1_mri.shape != temp_fs_seg.shape:
raise ValueError('size mismatch! MRI: {} Seg: {}\n'
'Size must match in all dimensions.'.format(
self.current_t1_mri.shape, temp_fs_seg.shape))
skip_subject = False
if self.vis_type in ('cortical_volumetric', 'cortical_contour'):
temp_seg_uncropped, roi_set_is_empty = void_subcortical_symmetrize_cortical(
temp_fs_seg)
elif self.vis_type in ('labels_volumetric', 'labels_contour'):
if self.label_set is not None:
# TODO same colors for same labels is not guaranteed
# if one subject fewer labels than others
# due to remapping of labels for each subject
temp_seg_uncropped, roi_set_is_empty = get_label_set(
temp_fs_seg, self.label_set)
else:
raise ValueError(
'--label_set must be specified for visualization types: '
' labels_volumetric and labels_contour')
else:
raise NotImplementedError(
'Invalid visualization type - '
'choose from: {}'.format(
cfg.visualization_combination_choices))
if roi_set_is_empty:
skip_subject = True
print('segmentation image for {} '
'does not contain requested label set!'.format(unit_id))
return skip_subject
# T1 mri must be rescaled - to avoid strange distributions skewing plots
rescaled_t1_mri = scale_0to1(temp_t1_mri, cfg.max_cmap_range_t1_mri)
self.current_t1_mri, self.current_seg = crop_to_seg_extents(
rescaled_t1_mri, temp_seg_uncropped, self.padding)
out_vis_path = pjoin(
self.out_dir, 'visual_qc_{}_{}_{}'.format(self.vis_type,
self.suffix, unit_id))
return skip_subject
def display_unit(self):
"""Adds slice collage to the given axes"""
# crop and rescale
img = crop_image(self.current_img, self.padding)
img = scale_0to1(img)
# adding slices
slices = pick_slices(img, self.views, self.num_slices_per_view)
for ax_index, (dim_index, slice_index) in enumerate(slices):
slice_data = get_axis(img, dim_index, slice_index)
self.images[ax_index].set_data(slice_data)
# updating histogram
self.update_histogram(img)
def load_unit(self, unit_id):
"""Loads the image data for display."""
# starting fresh
for attr in ('current_img_raw', 'current_img',
'saturated_img', 'tails_trimmed_img', 'background_img'):
if hasattr(self, attr):
delattr(self, attr)
t1_mri_path = self.path_getter_inputs(unit_id)
self.current_img_raw = read_image(t1_mri_path, error_msg='T1 mri')
# crop and rescale
self.current_img = scale_0to1(crop_image(self.current_img_raw, self.padding))
self.currently_showing = None
skip_subject = False
if np.count_nonzero(self.current_img) == 0:
skip_subject = True
print('MR image is empty!')
# # where to save the visualization to
# out_vis_path = pjoin(self.out_dir, 'visual_qc_{}_{}'.format(self.vis_type, unit_id))
return skip_subject