def test_reinhard_stats(self):
wsi_path = os.path.join(
utilities.externaldata(
'data/sample_svs_image.TCGA-DU-6399-01A-01-TS1.e8eb65de-d63e-42db-af6f-14fefbbdf7bd.svs.sha512' # noqa
))
np.random.seed(1)
# create dask client
args = {
# 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)
cli_utils.create_dask_client(args)
# compute reinhard stats
wsi_mean, wsi_stddev = htk_cn.reinhard_stats(wsi_path,
0.1,
magnification=20)
gt_mean = [8.896134, -0.074579, 0.022006]
gt_stddev = [0.612143, 0.122667, 0.021361]
np.testing.assert_allclose(wsi_mean, gt_mean, atol=1e-2)
np.testing.assert_allclose(wsi_stddev, gt_stddev, atol=1e-2)
def test_background_intensity(self):
wsi_path = os.path.join(
utilities.externaldata(
'data/sample_svs_image.TCGA-DU-6399-01A-01-TS1.e8eb65de-d63e-42db-af6f-14fefbbdf7bd.svs.sha512' # noqa
))
np.random.seed(1)
# create dask client
args = {
# 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)
cli_utils.create_dask_client(args)
# compute background intensity
I_0 = htk_cn.background_intensity(wsi_path,
sample_approximate_total=5000)
np.testing.assert_allclose(I_0, [242, 244, 241], atol=1)
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):
args = utils.splitArgs(args)
args.macenko.I_0 = numpy.array(args.macenko.I_0)
utils.create_dask_client(args.dask)
sample = utils.sample_pixels(args.sample)
stain_matrix = rgb_separate_stains_macenko_pca(sample.T,
**vars(args.macenko))
with open(args.returnParameterFile, 'w') as f:
for i, stain in enumerate(stain_matrix.T):
f.write('stainColor_{} = {}\n'.format(i + 1,
','.join(map(str, stain))))
def main(args):
other_args = set(['returnParameterFile', 'scheduler'])
kwargs = {k: v for k, v in vars(args).items() if k not in other_args}
# Allow (some) default parameters to work. Assume certain values
# are not valid.
for k in 'sample_fraction', 'sample_approximate_total':
if kwargs[k] == -1:
del kwargs[k]
utils.create_dask_client(args)
I_0 = background_intensity(**kwargs)
with open(args.returnParameterFile, 'w') as f:
f.write('BackgroundIntensity = ' + ','.join(map(str, I_0)) + '\n')
def main(args):
utils.create_dask_client(args)
ts = large_image.getTileSource(args.inputImageFile)
make_label_image = getattr(args, 'outputLabelImage', None) is not None
region = utils.get_region_dict(
args.region,
*(args.maxRegionSize, ts) if make_label_image else ()).get('region')
ppc_params = ppc.Parameters(
**{k: getattr(args, k)
for k in ppc.Parameters._fields})
results = ppc.count_slide(
args.inputImageFile,
ppc_params,
region,
args.tile_grouping,
make_label_image,
)
if make_label_image:
stats, label_image = results
# Colorize label image. Colors from the "coolwarm" color map
color_map = np.empty((4, 3), dtype=np.uint8)
color_map[ppc.Labels.NEGATIVE] = 255
color_map[ppc.Labels.WEAK] = 60, 78, 194
color_map[ppc.Labels.PLAIN] = 221, 220, 220
color_map[ppc.Labels.STRONG] = 180, 4, 38
# Cleverly index color_map
label_image = color_map[label_image]
try:
skimage.io.imsave(args.outputLabelImage, label_image)
except ValueError:
# This is likely caused by an unknown extension, so try again
altname = args.outputLabelImage + '.png'
skimage.io.imsave(altname, label_image)
os.rename(altname, args.outputLabelImage)
else:
stats, = results
with open(args.returnParameterFile, 'w') as f:
for k, v in zip(stats._fields, stats):
f.write(f'{k} = {v}\n')
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 main(args):
print('\n>> CLI Parameters ...\n')
print(args)
#
# Initiate Dask client
#
print('\n>> Creating Dask client ...\n')
c = cli_utils.create_dask_client(args)
print(c)
#
# read model file
#
print('\n>> Loading classification model ...\n')
clf_model = joblib.load(args.inputModelFile)
#
# read feature file
#
print('\n>> Loading nuclei feature file ...\n')
ddf = read_feature_file(args)
if len(ddf.columns) != clf_model.n_features_:
raise ValueError('The number of features of the classification model '
'and the input feature file do not match.')
#
# read nuclei annotation file
#
print('\n>> Loading nuclei annotation file ...\n')
with open(args.inputNucleiAnnotationFile) as f:
nuclei_annot_list = json.load(f)['elements']
if len(nuclei_annot_list) != len(ddf.index):
raise ValueError('The number of nuclei in the feature file and the '
'annotation file do not match')
#
# Perform nuclei classification
#
print('\n>> Performing nuclei classification using Dask ...\n')
def predict_nuclei_class_prob(df, clf_model):
return pd.DataFrame(data=clf_model.predict_proba(df.as_matrix()),
columns=clf_model.classes_)
outfmt = pd.DataFrame(columns=clf_model.classes_, dtype=np.float64)
df_class_prob = ddf.map_partitions(predict_nuclei_class_prob, clf_model,
meta=outfmt).compute()
pred_class = df_class_prob.idxmax(axis=1)
#
# Group nuclei annotations by class
#
print('\n>> Grouping nuclei annotations by class ...\n')
num_classes = len(clf_model.classes_)
nuclei_annot_by_class = {c: [] for c in clf_model.classes_}
class_color_map = dict(zip(clf_model.classes_,
gen_distinct_rgb_colors(num_classes, seed=1)))
for i in range(len(nuclei_annot_list)):
cur_class = pred_class.iloc[i]
cur_anot = nuclei_annot_list[i]
cur_anot['lineColor'] = 'rgb(%s)' % ','.join(
[str(int(round(col*255))) for col in class_color_map[cur_class]])
nuclei_annot_by_class[cur_class].append(cur_anot)
#
# Write annotation file
#
print('\n>> Writing classified nuclei annotation file ...\n')
annot_fname = os.path.splitext(
os.path.basename(args.outputNucleiAnnotationFile))[0]
annotation = []
for c in clf_model.classes_:
annotation.append({
"name": annot_fname + '-nuclei-class-' + str(c),
"elements": nuclei_annot_by_class[c]
})
with open(args.outputNucleiAnnotationFile, 'w') as annotation_file:
json.dump(annotation, annotation_file, indent=2, sort_keys=False)
def main(args):
total_start_time = time.time()
print('\n>> CLI Parameters ...\n')
print(args)
check_args(args)
feature_file_format = os.path.splitext(args.outputNucleiFeatureFile)[1]
if np.all(np.array(args.analysis_roi) == -1):
process_whole_image = True
else:
process_whole_image = False
#
# Initiate Dask client
#
print('\n>> Creating Dask client ...\n')
start_time = time.time()
c = cli_utils.create_dask_client(args)
print(c)
dask_setup_time = time.time() - start_time
print(f'Dask setup time = {dask_setup_time} seconds')
#
# Read Input Image
#
print('\n>> Reading input image ... \n')
ts = large_image.getTileSource(args.inputImageFile)
ts_metadata = ts.getMetadata()
print(json.dumps(ts_metadata, indent=2))
is_wsi = ts_metadata['magnification'] is not None
#
# Compute tissue/foreground mask at low-res for whole slide images
#
if is_wsi and process_whole_image:
print('\n>> Computing tissue/foreground mask at low-res ...\n')
start_time = time.time()
im_fgnd_mask_lres, fgnd_seg_scale = \
cli_utils.segment_wsi_foreground_at_low_res(ts)
fgnd_time = time.time() - start_time
print('low-res foreground mask computation time = {}'.format(
cli_utils.disp_time_hms(fgnd_time)))
#
# Compute foreground fraction of tiles in parallel using Dask
#
tile_fgnd_frac_list = [1.0]
it_kwargs = {
'tile_size': {'width': args.analysis_tile_size},
'scale': {'magnification': args.analysis_mag},
}
if not process_whole_image:
it_kwargs['region'] = {
'left': args.analysis_roi[0],
'top': args.analysis_roi[1],
'width': args.analysis_roi[2],
'height': args.analysis_roi[3],
'units': 'base_pixels'
}
if is_wsi:
print('\n>> Computing foreground fraction of all tiles ...\n')
start_time = time.time()
num_tiles = ts.getSingleTile(**it_kwargs)['iterator_range']['position']
print(f'Number of tiles = {num_tiles}')
if process_whole_image:
tile_fgnd_frac_list = htk_utils.compute_tile_foreground_fraction(
args.inputImageFile, im_fgnd_mask_lres, fgnd_seg_scale,
it_kwargs
)
else:
tile_fgnd_frac_list = [1.0] * num_tiles
num_fgnd_tiles = np.count_nonzero(
tile_fgnd_frac_list >= args.min_fgnd_frac)
percent_fgnd_tiles = 100.0 * num_fgnd_tiles / num_tiles
fgnd_frac_comp_time = time.time() - start_time
print('Number of foreground tiles = {:d} ({:2f}%%)'.format(
num_fgnd_tiles, percent_fgnd_tiles))
print('Tile foreground fraction computation time = {}'.format(
cli_utils.disp_time_hms(fgnd_frac_comp_time)))
#
# Compute reinhard stats for color normalization
#
src_mu_lab = None
src_sigma_lab = None
if is_wsi and process_whole_image:
print('\n>> Computing reinhard color normalization stats ...\n')
start_time = time.time()
src_mu_lab, src_sigma_lab = htk_cnorm.reinhard_stats(
args.inputImageFile, 0.01, magnification=args.analysis_mag)
rstats_time = time.time() - start_time
print('Reinhard stats computation time = {}'.format(
cli_utils.disp_time_hms(rstats_time)))
#
# Detect and compute nuclei features in parallel using Dask
#
print('\n>> Detecting nuclei and computing features ...\n')
start_time = time.time()
tile_result_list = []
for tile in ts.tileIterator(**it_kwargs):
tile_position = tile['tile_position']['position']
if is_wsi and tile_fgnd_frac_list[tile_position] <= args.min_fgnd_frac:
continue
# detect nuclei
cur_result = dask.delayed(compute_tile_nuclei_features)(
args.inputImageFile,
tile_position,
args, it_kwargs,
src_mu_lab, src_sigma_lab
)
# append result to list
tile_result_list.append(cur_result)
tile_result_list = dask.delayed(tile_result_list).compute()
nuclei_annot_list = [annot
for annot_list, fdata in tile_result_list
for annot in annot_list]
nuclei_fdata = pd.DataFrame()
if len(nuclei_annot_list) > 0:
nuclei_fdata = pd.concat([
fdata
for annot_list, fdata in tile_result_list if fdata is not None],
ignore_index=True
)
nuclei_detection_time = time.time() - start_time
print('Number of nuclei = {}'.format(len(nuclei_annot_list)))
print('Nuclei detection time = {}'.format(
cli_utils.disp_time_hms(nuclei_detection_time)))
#
# Write annotation file
#
print('\n>> Writing annotation file ...\n')
annot_fname = os.path.splitext(
os.path.basename(args.outputNucleiAnnotationFile))[0]
annotation = {
'name': annot_fname + '-nuclei-' + args.nuclei_annotation_format,
'elements': nuclei_annot_list
}
with open(args.outputNucleiAnnotationFile, 'w') as annotation_file:
json.dump(annotation, annotation_file, indent=2, sort_keys=False)
#
# Create CSV Feature file
#
print('>> Writing CSV feature file')
if feature_file_format == '.csv':
nuclei_fdata.to_csv(args.outputNucleiFeatureFile, index=False)
elif feature_file_format == '.h5':
nuclei_fdata.to_hdf(args.outputNucleiFeatureFile, 'Features',
format='table', mode='w')
else:
raise ValueError('Extension of output feature file must be .csv or .h5')
total_time_taken = time.time() - total_start_time
print('Total analysis time = {}'.format(
cli_utils.disp_time_hms(total_time_taken)))
def main(args):
total_start_time = time.time()
print('\n>> CLI Parameters ...\n')
print(args)
if not os.path.isfile(args.inputImageFile):
raise OSError('Input image file does not exist.')
if len(args.reference_mu_lab) != 3:
raise ValueError('Reference Mean LAB should be a 3 element vector.')
if len(args.reference_std_lab) != 3:
raise ValueError('Reference Stddev LAB should be a 3 element vector.')
if len(args.analysis_roi) != 4:
raise ValueError('Analysis ROI must be a vector of 4 elements.')
if np.all(np.array(args.analysis_roi) == -1):
process_whole_image = True
else:
process_whole_image = False
#
# Initiate Dask client
#
print('\n>> Creating Dask client ...\n')
start_time = time.time()
c = cli_utils.create_dask_client(args)
print(c)
dask_setup_time = time.time() - start_time
print('Dask setup time = {}'.format(
cli_utils.disp_time_hms(dask_setup_time)))
#
# Read Input Image
#
print('\n>> Reading input image ... \n')
ts = large_image.getTileSource(args.inputImageFile)
ts_metadata = ts.getMetadata()
print(json.dumps(ts_metadata, indent=2))
is_wsi = ts_metadata['magnification'] is not None
#
# Compute tissue/foreground mask at low-res for whole slide images
#
if is_wsi and process_whole_image:
print('\n>> Computing tissue/foreground mask at low-res ...\n')
start_time = time.time()
im_fgnd_mask_lres, fgnd_seg_scale = \
cli_utils.segment_wsi_foreground_at_low_res(ts)
fgnd_time = time.time() - start_time
print('low-res foreground mask computation time = {}'.format(
cli_utils.disp_time_hms(fgnd_time)))
#
# Compute foreground fraction of tiles in parallel using Dask
#
tile_fgnd_frac_list = [1.0]
it_kwargs = {
'tile_size': {
'width': args.analysis_tile_size
},
'scale': {
'magnification': args.analysis_mag
},
}
if not process_whole_image:
it_kwargs['region'] = {
'left': args.analysis_roi[0],
'top': args.analysis_roi[1],
'width': args.analysis_roi[2],
'height': args.analysis_roi[3],
'units': 'base_pixels'
}
if is_wsi:
print('\n>> Computing foreground fraction of all tiles ...\n')
start_time = time.time()
num_tiles = ts.getSingleTile(**it_kwargs)['iterator_range']['position']
print(f'Number of tiles = {num_tiles}')
if process_whole_image:
tile_fgnd_frac_list = htk_utils.compute_tile_foreground_fraction(
args.inputImageFile, im_fgnd_mask_lres, fgnd_seg_scale,
it_kwargs)
else:
tile_fgnd_frac_list = np.full(num_tiles, 1.0)
num_fgnd_tiles = np.count_nonzero(
tile_fgnd_frac_list >= args.min_fgnd_frac)
percent_fgnd_tiles = 100.0 * num_fgnd_tiles / num_tiles
fgnd_frac_comp_time = time.time() - start_time
print('Number of foreground tiles = {:d} ({:2f}%%)'.format(
num_fgnd_tiles, percent_fgnd_tiles))
print('Tile foreground fraction computation time = {}'.format(
cli_utils.disp_time_hms(fgnd_frac_comp_time)))
#
# Compute reinhard stats for color normalization
#
src_mu_lab = None
src_sigma_lab = None
if is_wsi and process_whole_image:
print('\n>> Computing reinhard color normalization stats ...\n')
start_time = time.time()
src_mu_lab, src_sigma_lab = htk_cnorm.reinhard_stats(
args.inputImageFile, 0.01, magnification=args.analysis_mag)
rstats_time = time.time() - start_time
print('Reinhard stats computation time = {}'.format(
cli_utils.disp_time_hms(rstats_time)))
#
# Detect nuclei in parallel using Dask
#
print('\n>> Detecting nuclei ...\n')
start_time = time.time()
tile_nuclei_list = []
for tile in ts.tileIterator(**it_kwargs):
tile_position = tile['tile_position']['position']
if is_wsi and tile_fgnd_frac_list[tile_position] <= args.min_fgnd_frac:
continue
# detect nuclei
cur_nuclei_list = dask.delayed(detect_tile_nuclei)(args.inputImageFile,
tile_position, args,
it_kwargs,
src_mu_lab,
src_sigma_lab)
# append result to list
tile_nuclei_list.append(cur_nuclei_list)
tile_nuclei_list = dask.delayed(tile_nuclei_list).compute()
nuclei_list = [
anot for anot_list in tile_nuclei_list for anot in anot_list
]
nuclei_detection_time = time.time() - start_time
print('Number of nuclei = {}'.format(len(nuclei_list)))
print('Nuclei detection time = {}'.format(
cli_utils.disp_time_hms(nuclei_detection_time)))
#
# Write annotation file
#
print('\n>> Writing annotation file ...\n')
annot_fname = os.path.splitext(
os.path.basename(args.outputNucleiAnnotationFile))[0]
annotation = {
"name": annot_fname + '-nuclei-' + args.nuclei_annotation_format,
"elements": nuclei_list
}
with open(args.outputNucleiAnnotationFile, 'w') as annotation_file:
json.dump(annotation, annotation_file, indent=2, sort_keys=False)
total_time_taken = time.time() - total_start_time
print('Total analysis time = {}'.format(
cli_utils.disp_time_hms(total_time_taken)))