def set_superpixel_features(self):
"""Get superpixel features."""
assert (self.cd.use_intensity or self.cd.use_texture)
# Possibly deconvolvve to get hematoxylin channel (cellular areas)
# hematoxylin channel return shows MINIMA so we invert
if self.cd.deconvolve:
Stains, channel = _deconv_color(self.tissue_rgb)
tissue_htx = 255 - Stains[..., channel]
else:
tissue_htx = rgb2gray(self.tissue_rgb)
# calculate features from superpixels
rprops = regionprops(self.spixel_mask)
fdata_list = []
if self.cd.use_intensity:
fdata_list.append(compute_intensity_features(
im_label=self.spixel_mask, im_intensity=tissue_htx,
rprops=rprops))
if self.cd.use_texture:
fdata_list.append(compute_haralick_features(
im_label=self.spixel_mask, im_intensity=tissue_htx,
rprops=rprops))
self.fdata = concat(fdata_list, axis=1)
if self.cd.keep_feats is not None:
self.fdata = self.fdata.loc[:, self.cd.keep_feats]
# Index is corresponding pixel value in the superpixel mask
# IMPORTANT: this assumes that regionprops output is sorted by unique
# pixel values in label mask, which it is by default
self.fdata.index = set(np.unique(self.spixel_mask)) - {0, }
def find_top_cellular_regions(self):
"""Keep largest and most cellular regions."""
# keep only largest n regions regions
top_cellular_mask = _get_largest_regions(
self.maybe_cellular, top_n=self.cdt.cellular_largest_n)
top_cellular = self.maybe_cellular.copy()
top_cellular[top_cellular_mask == 0] = 0
# get intensity features of hematoxylin channel for each region
intensity_feats = compute_intensity_features(
im_label=top_cellular,
im_intensity=self.tissue_htx,
feature_list=['Intensity.Mean'])
unique = np.unique(top_cellular[top_cellular > 0])
intensity_feats.index = unique
# get top n brightest regions from the largest areas
intensity_feats.sort_values("Intensity.Mean", axis=0, inplace=True)
discard = np.array(intensity_feats.index[:-self.cdt.cellular_top_n])
discard = np.in1d(top_cellular, discard).reshape(top_cellular.shape)
top_cellular[discard] = 0
# integrate into labeled mask
self.labeled[top_cellular > 0] = self.cdt.GTcodes.loc['top_cellular',
'GT_code']
