def main(args):
args = utils.splitArgs(args)
args.snmf.I_0 = numpy.array(args.snmf.I_0)
print(">> Starting Dask cluster and sampling pixels")
utils.create_dask_client(args.dask)
sample = utils.sample_pixels(args.sample)
# Create stain matrix
print('>> Creating stain matrix')
args.snmf.w_init = utils.get_stain_matrix(args.stains, 2)
print(args.snmf.w_init)
# Perform color deconvolution
print('>> Performing color deconvolution')
w_est = htk_cdeconv.rgb_separate_stains_xu_snmf(sample.T,
**vars(args.snmf))
w_est = htk_cdeconv.complement_stain_matrix(w_est)
with open(args.returnParameterFile, 'w') as f:
for i, stain in enumerate(w_est.T):
f.write('stainColor_{} = {}\n'.format(i + 1,
','.join(map(str, stain))))
def main(args):
# Read Input Image
print('>> Reading input image')
print(args.inputImageFile)
ts = large_image.getTileSource(args.inputImageFile)
im_input = ts.getRegion(format=large_image.tilesource.TILE_FORMAT_NUMPY,
**utils.get_region_dict(args.region,
args.maxRegionSize, ts))[0]
# Create stain matrix
print('>> Creating stain matrix')
w = utils.get_stain_matrix(args)
print(w)
# Perform color deconvolution
print('>> Performing color deconvolution')
im_stains = htk_cd.color_deconvolution(im_input, w).Stains
# write stain images to output
print('>> Outputting individual stain images')
print(args.outputStainImageFile_1)
skimage.io.imsave(args.outputStainImageFile_1, im_stains[:, :, 0])
print(args.outputStainImageFile_2)
skimage.io.imsave(args.outputStainImageFile_2, im_stains[:, :, 1])
print(args.outputStainImageFile_3)
skimage.io.imsave(args.outputStainImageFile_3, im_stains[:, :, 2])
def detect_tile_nuclei(slide_path, tile_position, args, it_kwargs,
src_mu_lab=None, src_sigma_lab=None):
# get slide tile source
ts = large_image.getTileSource(slide_path)
# get requested tile
tile_info = ts.getSingleTile(
tile_position=tile_position,
format=large_image.tilesource.TILE_FORMAT_NUMPY,
**it_kwargs)
# get tile image
im_tile = tile_info['tile'][:, :, :3]
# perform color normalization
im_nmzd = htk_cnorm.reinhard(im_tile,
args.reference_mu_lab,
args.reference_std_lab,
src_mu=src_mu_lab,
src_sigma=src_sigma_lab)
# perform color decovolution
w = cli_utils.get_stain_matrix(args)
im_stains = htk_cdeconv.color_deconvolution(im_nmzd, w).Stains
im_nuclei_stain = im_stains[:, :, 0].astype(np.float)
# segment nuclear foreground
im_nuclei_fgnd_mask = im_nuclei_stain < args.foreground_threshold
# segment nuclei
im_nuclei_seg_mask = htk_nuclear.detect_nuclei_kofahi(
im_nuclei_stain,
im_nuclei_fgnd_mask,
args.min_radius,
args.max_radius,
args.min_nucleus_area,
args.local_max_search_radius
)
# Delete border nuclei
if args.ignore_border_nuclei is True:
im_nuclei_seg_mask = htk_seg_label.delete_border(im_nuclei_seg_mask)
# generate nuclei annotations
nuclei_annot_list = []
flag_nuclei_found = np.any(im_nuclei_seg_mask)
if flag_nuclei_found:
nuclei_annot_list = cli_utils.create_tile_nuclei_annotations(
im_nuclei_seg_mask, tile_info, args.nuclei_annotation_format)
return nuclei_annot_list
def test_get_stain_matrix(self):
args = Namespace(
stain_1='hematoxylin',
stain_1_vector=[-1, -1, -1],
stain_2='custom',
stain_2_vector=[0.1, 0.2, 0.3],
)
expected = np.array(
[htk_cdeconv.stain_color_map['hematoxylin'], [0.1, 0.2, 0.3]]).T
np.testing.assert_allclose(cli_utils.get_stain_matrix(args, 2),
expected)
def test_create_tile_nuclei_annotations(self):
wsi_path = os.path.join(
utilities.externaldata(
'data/TCGA-06-0129-01Z-00-DX3.bae772ea-dd36-47ec-8185-761989be3cc8.svs.sha512' # noqa
))
# define parameters
args = {
'reference_mu_lab': [8.63234435, -0.11501964, 0.03868433],
'reference_std_lab': [0.57506023, 0.10403329, 0.01364062],
'stain_1': 'hematoxylin',
'stain_2': 'eosin',
'stain_3': 'null',
'stain_1_vector': [-1, -1, -1],
'stain_2_vector': [-1, -1, -1],
'stain_3_vector': [-1, -1, -1],
'min_fgnd_frac': 0.50,
'analysis_mag': 20,
'analysis_tile_size': 1200,
'foreground_threshold': 60,
'min_radius': 6,
'max_radius': 12,
'min_nucleus_area': 25,
'local_max_search_radius': 8,
# In Python 3 unittesting, the scheduler fails if it uses processes
'scheduler': 'multithreading', # None,
'num_workers': -1,
'num_threads_per_worker': 1,
}
args = collections.namedtuple('Parameters', args.keys())(**args)
# read WSI
ts = large_image.getTileSource(wsi_path)
ts_metadata = ts.getMetadata()
analysis_tile_size = {
'width':
int(ts_metadata['tileWidth'] * np.floor(
1.0 * args.analysis_tile_size / ts_metadata['tileWidth'])),
'height':
int(ts_metadata['tileHeight'] * np.floor(
1.0 * args.analysis_tile_size / ts_metadata['tileHeight']))
}
# define ROI
roi = {
'left': ts_metadata['sizeX'] / 2,
'top': ts_metadata['sizeY'] * 3 / 4,
'width': analysis_tile_size['width'],
'height': analysis_tile_size['height'],
'units': 'base_pixels'
}
# define tile iterator parameters
it_kwargs = {
'tile_size': {
'width': args.analysis_tile_size
},
'scale': {
'magnification': args.analysis_mag
},
'region': roi
}
# create dask client
cli_utils.create_dask_client(args)
# get tile foregreoung at low res
im_fgnd_mask_lres, fgnd_seg_scale = \
cli_utils.segment_wsi_foreground_at_low_res(ts)
# compute tile foreground fraction
tile_fgnd_frac_list = htk_utils.compute_tile_foreground_fraction(
wsi_path, im_fgnd_mask_lres, fgnd_seg_scale, it_kwargs)
num_fgnd_tiles = np.count_nonzero(
tile_fgnd_frac_list >= args.min_fgnd_frac)
np.testing.assert_equal(num_fgnd_tiles, 2)
# create nuclei annotations
nuclei_bbox_annot_list = []
nuclei_bndry_annot_list = []
for tile_info in ts.tileIterator(
format=large_image.tilesource.TILE_FORMAT_NUMPY, **it_kwargs):
im_tile = tile_info['tile'][:, :, :3]
# perform color normalization
im_nmzd = htk_cnorm.reinhard(im_tile, args.reference_mu_lab,
args.reference_std_lab)
# perform color deconvolution
w = cli_utils.get_stain_matrix(args)
im_stains = htk_cdeconv.color_deconvolution(im_nmzd, w).Stains
im_nuclei_stain = im_stains[:, :, 0].astype(np.float)
# segment nuclei
im_nuclei_seg_mask = htk_nuclear.detect_nuclei_kofahi(
im_nuclei_stain, im_nuclei_stain < args.foreground_threshold,
args.min_radius, args.max_radius, args.min_nucleus_area,
args.local_max_search_radius)
# generate nuclei annotations as bboxes
cur_bbox_annot_list = cli_utils.create_tile_nuclei_annotations(
im_nuclei_seg_mask, tile_info, 'bbox')
nuclei_bbox_annot_list.extend(cur_bbox_annot_list)
# generate nuclei annotations as boundaries
cur_bndry_annot_list = cli_utils.create_tile_nuclei_annotations(
im_nuclei_seg_mask, tile_info, 'boundary')
nuclei_bndry_annot_list.extend(cur_bndry_annot_list)
# compare nuclei bbox annotations with gtruth
nuclei_bbox_annot_gtruth_file = os.path.join(
utilities.externaldata(
'data/TCGA-06-0129-01Z-00-DX3_roi_nuclei_bbox.anot.sha512' # noqa
))
with open(nuclei_bbox_annot_gtruth_file, 'r') as fbbox_annot:
nuclei_bbox_annot_list_gtruth = json.load(fbbox_annot)['elements']
# Check that nuclei_bbox_annot_list is nearly equal to
# nuclei_bbox_annot_list_gtruth
assert len(nuclei_bbox_annot_list) == len(
nuclei_bbox_annot_list_gtruth)
for pos in range(len(nuclei_bbox_annot_list)):
np.testing.assert_array_almost_equal(
nuclei_bbox_annot_list[pos]['center'],
nuclei_bbox_annot_list_gtruth[pos]['center'], 0)
np.testing.assert_almost_equal(
nuclei_bbox_annot_list[pos]['width'],
nuclei_bbox_annot_list_gtruth[pos]['width'], 1)
np.testing.assert_almost_equal(
nuclei_bbox_annot_list[pos]['height'],
nuclei_bbox_annot_list_gtruth[pos]['height'], 1)
# compare nuclei boundary annotations with gtruth
nuclei_bndry_annot_gtruth_file = os.path.join(
utilities.externaldata(
'data/TCGA-06-0129-01Z-00-DX3_roi_nuclei_boundary.anot.sha512' # noqa
))
with open(nuclei_bndry_annot_gtruth_file, 'r') as fbndry_annot:
nuclei_bndry_annot_list_gtruth = json.load(
fbndry_annot)['elements']
assert len(nuclei_bndry_annot_list) == len(
nuclei_bndry_annot_list_gtruth)
for pos in range(len(nuclei_bndry_annot_list)):
np.testing.assert_array_almost_equal(
nuclei_bndry_annot_list[pos]['points'],
nuclei_bndry_annot_list_gtruth[pos]['points'], 0)
def compute_tile_nuclei_features(slide_path, tile_position, args, it_kwargs,
src_mu_lab=None, src_sigma_lab=None):
# get slide tile source
ts = large_image.getTileSource(slide_path)
# get requested tile
tile_info = ts.getSingleTile(
tile_position=tile_position,
format=large_image.tilesource.TILE_FORMAT_NUMPY,
**it_kwargs)
# get tile image
im_tile = tile_info['tile'][:, :, :3]
# perform color normalization
im_nmzd = htk_cnorm.reinhard(im_tile,
args.reference_mu_lab,
args.reference_std_lab,
src_mu=src_mu_lab,
src_sigma=src_sigma_lab)
# perform color decovolution
w = cli_utils.get_stain_matrix(args)
im_stains = htk_cdeconv.color_deconvolution(im_nmzd, w).Stains
im_nuclei_stain = im_stains[:, :, 0].astype(np.float)
# segment nuclear foreground
im_nuclei_fgnd_mask = im_nuclei_stain < args.foreground_threshold
# segment nuclei
im_nuclei_seg_mask = htk_nuclear.detect_nuclei_kofahi(
im_nuclei_stain,
im_nuclei_fgnd_mask,
args.min_radius,
args.max_radius,
args.min_nucleus_area,
args.local_max_search_radius
)
# Delete border nuclei
if args.ignore_border_nuclei is True:
im_nuclei_seg_mask = htk_seg_label.delete_border(im_nuclei_seg_mask)
# generate nuclei annotations
nuclei_annot_list = []
flag_nuclei_found = np.any(im_nuclei_seg_mask)
if flag_nuclei_found:
nuclei_annot_list = cli_utils.create_tile_nuclei_annotations(
im_nuclei_seg_mask, tile_info, args.nuclei_annotation_format)
# compute nuclei features
fdata = None
if flag_nuclei_found:
if args.cytoplasm_features:
im_cytoplasm_stain = im_stains[:, :, 1].astype(np.float)
else:
im_cytoplasm_stain = None
fdata = htk_features.compute_nuclei_features(
im_nuclei_seg_mask, im_nuclei_stain, im_cytoplasm_stain,
fsd_bnd_pts=args.fsd_bnd_pts,
fsd_freq_bins=args.fsd_freq_bins,
cyto_width=args.cyto_width,
num_glcm_levels=args.num_glcm_levels,
morphometry_features_flag=args.morphometry_features,
fsd_features_flag=args.fsd_features,
intensity_features_flag=args.intensity_features,
gradient_features_flag=args.gradient_features,
)
fdata.columns = ['Feature.' + col for col in fdata.columns]
return nuclei_annot_list, fdata
