def setUp(self):
# define parameters
args = {
'reference_mu_lab': [8.63234435, -0.11501964, 0.03868433],
'reference_std_lab': [0.57506023, 0.10403329, 0.01364062],
'min_radius': 12,
'max_radius': 30,
'foreground_threshold': 60,
'min_nucleus_area': 80,
'local_max_search_radius': 10,
}
args = collections.namedtuple('Parameters', args.keys())(**args)
# read input image
input_image_file = os.path.join(TEST_DATA_DIR, 'Easy1.png')
im_input = skimage.io.imread(input_image_file)[:, :, :3]
# perform color normalization
im_input_nmzd = htk_cnorm.reinhard(im_input, args.reference_mu_lab,
args.reference_std_lab)
# perform color decovolution
w = htk_cdeconv.rgb_separate_stains_macenko_pca(
im_input_nmzd, im_input_nmzd.max())
im_stains = htk_cdeconv.color_deconvolution(im_input_nmzd, w).Stains
nuclei_channel = htk_cdeconv.find_stain_index(
htk_cdeconv.stain_color_map['hematoxylin'], w)
im_nuclei_stain = im_stains[:, :, nuclei_channel].astype(np.float)
cytoplasm_channel = htk_cdeconv.find_stain_index(
htk_cdeconv.stain_color_map['eosin'], w)
im_cytoplasm_stain = im_stains[:, :,
cytoplasm_channel].astype(np.float)
# segment nuclei
im_nuclei_seg_mask = cli_utils.detect_nuclei_kofahi(
im_nuclei_stain, args)
# perform connected component analysis
nuclei_rprops = skimage.measure.regionprops(im_nuclei_seg_mask)
# compute nuclei features
fdata_nuclei = htk_features.compute_nuclei_features(
im_nuclei_seg_mask,
im_nuclei_stain,
im_cytoplasm=im_cytoplasm_stain)
self.im_input = im_input
self.im_input_nmzd = im_input_nmzd
self.im_nuclei_stain = im_nuclei_stain
self.im_nuclei_seg_mask = im_nuclei_seg_mask
self.nuclei_rprops = nuclei_rprops
self.fdata_nuclei = fdata_nuclei
def set_color_normalization_target(self,
ref_image_path,
color_normalization_method='macenko_pca'
):
"""Set color normalization values to use from target image.
Arguments
ref_image_path, str
> path to target (reference) image
color_normalization_method, str
> color normalization method to use. Currently, only
> reinhard and macenko_pca are accepted.
"""
# read input image
ref_im = np.array(imread(ref_image_path, pilmode='RGB'))
# assign target values
color_normalization_method = color_normalization_method.lower()
if color_normalization_method == 'reinhard':
mu, sigma = lab_mean_std(ref_im)
self.target_stats_reinhard['mu'] = mu
self.target_stats_reinhard['sigma'] = sigma
elif color_normalization_method == 'macenko_pca':
self.target_W_macenko = _reorder_stains(
rgb_separate_stains_macenko_pca(ref_im, I_0=None),
stains=['hematoxylin', 'eosin'])
else:
raise ValueError("Unknown color_normalization_method: %s" %
(color_normalization_method))
self.color_normalization_method = color_normalization_method
def test_macenko(self):
im_path = utilities.externaldata('data/Easy1.png.sha512')
im = skimage.io.imread(im_path)[..., :3]
w = htk_dcv.rgb_separate_stains_macenko_pca(im, 255)
w_expected = [[0.089411, 0.558021, -0.130574],
[0.837138, 0.729935, 0.546981],
[0.539635, 0.394725, -0.826899]]
np.testing.assert_allclose(w, w_expected, atol=1e-6)
def test_macenko(self):
im_path = os.path.join(TEST_DATA_DIR, 'Easy1.png')
im = skimage.io.imread(im_path)[..., :3]
w = htk_dcv.rgb_separate_stains_macenko_pca(im, 255)
w_expected = [[0.089411, 0.558021, -0.130574],
[0.837138, 0.729935, 0.546981],
[0.539635, 0.394725, -0.826899]]
np.testing.assert_allclose(w, w_expected, atol=1e-6)
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 detect_nuclei(im_input, min_radius=6, max_radius=10, display_result=False):
# color normalization
ref_mu_lab = (8.63234435, -0.11501964, 0.03868433)
ref_std_lab = (0.57506023, 0.10403329, 0.01364062)
im_nmzd = htk_cnorm.reinhard(im_input, ref_mu_lab, ref_std_lab)
# color deconvolution
w_est = htk_cdeconv.rgb_separate_stains_macenko_pca(im_nmzd, 255)
nuclear_chid = htk_cdeconv.find_stain_index(
htk_cdeconv.stain_color_map['hematoxylin'], w_est)
im_nuclei_stain = htk_cdeconv.color_deconvolution(im_nmzd, w_est,
255).Stains[:, :,
nuclear_chid]
# segment nuclei foreground
th = skimage.filters.threshold_li(im_nuclei_stain) * 0.8
# th = skimage.filters.threshold_otsu(im_nuclei_stain)
im_fgnd_mask = im_nuclei_stain < th
im_fgnd_mask = skimage.morphology.opening(im_fgnd_mask,
skimage.morphology.disk(2))
im_fgnd_mask = skimage.morphology.closing(im_fgnd_mask,
skimage.morphology.disk(1))
# detect nuclei
im_dog, im_dog_sigma = htk_shape_filters.cdog(
im_nuclei_stain,
im_fgnd_mask,
sigma_min=min_radius / np.sqrt(2),
sigma_max=max_radius / np.sqrt(2))
nuclei_coord = skimage.feature.peak_local_max(im_dog,
min_distance=min_radius / 2,
threshold_rel=0.1)
nuclei_coord = nuclei_coord[im_fgnd_mask[nuclei_coord[:, 0],
nuclei_coord[:, 1]], :]
nuclei_rad = np.array([
im_dog_sigma[nuclei_coord[i, 0], nuclei_coord[i, 1]] * np.sqrt(2)
for i in range(nuclei_coord.shape[0])
])
# display result
if display_result:
print 'Number of nuclei = ', nuclei_coord.shape[0]
plt.figure(figsize=(30, 20))
plt.subplot(2, 2, 1)
plt.imshow(im_input)
plt.title('Input', fontsize=labelsize)
plt.axis('off')
plt.subplot(2, 2, 2)
plt.imshow(im_nuclei_stain)
plt.title('Deconv nuclei stain', fontsize=labelsize)
plt.axis('off')
plt.subplot(2, 2, 3)
plt.imshow(im_fgnd_mask)
plt.title('Foreground mask', fontsize=labelsize)
plt.axis('off')
plt.subplot(2, 2, 4)
plt.imshow(im_nmzd)
plt.plot(nuclei_coord[:, 1], nuclei_coord[:, 0], 'k+')
for i in range(nuclei_coord.shape[0]):
cx = nuclei_coord[i, 1]
cy = nuclei_coord[i, 0]
r = nuclei_rad[i]
mcircle = mpatches.Circle((cx, cy), r, color='g', fill=False)
plt.gca().add_patch(mcircle)
plt.title('Nuclei detection', fontsize=labelsize)
plt.axis('off')
plt.tight_layout()
return nuclei_coord, nuclei_rad
def test_segment_nuclei_kofahi(self):
input_image_file = datastore.fetch('Easy1.png')
ref_image_file = datastore.fetch('L1.png')
# read input image
im_input = skimage.io.imread(input_image_file)[:, :, :3]
# read reference image
im_reference = skimage.io.imread(ref_image_file)[:, :, :3]
# get mean and stddev of reference image in lab space
mean_ref, std_ref = htk_cvt.lab_mean_std(im_reference)
# perform color normalization
im_nmzd = htk_cnorm.reinhard(im_input, mean_ref, std_ref)
# perform color decovolution
stain_color_map = {
'hematoxylin': [0.65, 0.70, 0.29],
'eosin': [0.07, 0.99, 0.11],
'dab': [0.27, 0.57, 0.78],
'null': [0.0, 0.0, 0.0]
}
w = htk_cdeconv.rgb_separate_stains_macenko_pca(im_nmzd, im_nmzd.max())
im_stains = htk_cdeconv.color_deconvolution(im_nmzd, w).Stains
nuclei_channel = htk_cdeconv.find_stain_index(
stain_color_map['hematoxylin'], w)
im_nuclei_stain = im_stains[:, :, nuclei_channel].astype(np.float)
# segment nuclei
im_nuclei_seg_mask = htk_seg.nuclear.detect_nuclei_kofahi(
im_nuclei_stain,
im_nuclei_stain < 60,
min_radius=20,
max_radius=30,
min_nucleus_area=80,
local_max_search_radius=10)
num_nuclei = len(np.unique(im_nuclei_seg_mask)) - 1
# check if segmentation mask matches ground truth
gtruth_mask_file = os.path.join(
datastore.fetch('Easy1_nuclei_seg_kofahi.npy'))
im_gtruth_mask = np.load(gtruth_mask_file)
num_nuclei_gtruth = len(np.unique(im_gtruth_mask)) - 1
assert num_nuclei == num_nuclei_gtruth
np.testing.assert_allclose(im_nuclei_seg_mask, im_gtruth_mask)
# check no nuclei case
im_nuclei_seg_mask = htk_seg.nuclear.detect_nuclei_kofahi(
255 * np.ones_like(im_nuclei_stain),
np.ones_like(im_nuclei_stain),
min_radius=20,
max_radius=30,
min_nucleus_area=80,
local_max_search_radius=10)
num_nuclei = len(np.unique(im_nuclei_seg_mask)) - 1
assert num_nuclei == 0
def detect_tile_nuclei(slide_path, tile_position, args, it_kwargs,
src_mu_lab=None, src_sigma_lab=None, debug=False):
# =========================================================================
# ======================= Tile Loading ====================================
# =========================================================================
print('\n>> Loading Tile ... \n')
csv_dict = {}
csv_dict['PreparationTime'] = []
csv_dict['ColorDeconvTime'] = []
csv_dict['TotalTileLoadingTime'] = []
csv_dict['CKPTLoadingTime'] = []
csv_dict['ModelInfernceTime'] = []
csv_dict['DetectionTime'] = []
csv_dict['ROIShape'] = []
csv_dict['ObjectsDict'] = []
csv_dict['NumObjects'] = []
csv_dict['AnnotationWritingTime'] = []
csv_dict['AnnotationDict'] = []
csv_dict['AnalysisDict'] = []
start_time = time.time()
total_tileloading_start_time = time.time()
ts = large_image.getTileSource(slide_path)
tile_info = ts.getSingleTile(
tile_position=tile_position,
format=large_image.tilesource.TILE_FORMAT_NUMPY,
**it_kwargs)
im_tile = tile_info['tile'][:, :, :3]
csv_dict['ROIShape'] = im_tile.shape[:2]
prep_time = time.time() - start_time
csv_dict['PreparationTime'] = round(prep_time, 3)
# =========================================================================
# =================Img Normalization & Color Deconv========================
# =========================================================================
print('\n>> Color Deconvolving ... \n')
start_time = time.time()
im_nmzd = htk_cnorm.reinhard(
im_tile,
REFERENCE_MU_LAB,
REFERENCE_STD_LAB,
src_mu=src_mu_lab,
src_sigma=src_sigma_lab
)
# perform color decovolution
if args.deconv_method == 'ruifrok':
w = cli_utils.get_stain_matrix(args)
im_stains = htk_cdeconv.color_deconvolution(
im_nmzd, w).Stains.astype(np.float)[:, :, :2]
elif args.deconv_method == 'macenko':
w_est = htk_cdeconv.rgb_separate_stains_macenko_pca(im_tile, 255)
im_stains = htk_cdeconv.color_deconvolution(
im_tile, w_est, 255).Stains.astype(np.float)
ch1 = htk_cdeconv.find_stain_index(
htk_cdeconv.stain_color_map[args.stain_1], w_est)
ch2 = htk_cdeconv.find_stain_index(
htk_cdeconv.stain_color_map[args.stain_2], w_est)
im_stains = im_stains[:, :, [ch1, ch2]]
else:
raise ValueError('Invalid deconvolution method parameter.')
# =========================================================================
# ====================== Fuse the stain1 & stain2 pix======================
# =========================================================================
# compute nuclear foreground mask
im_fgnd_mask_stain_1 = im_stains[
:, :, 0] < threshold_yen(im_stains[:, :, 0])
im_fgnd_mask_stain_2 = im_stains[
:, :, 1] < threshold_yen(im_stains[:, :, 1])
im_fgnd_seg_mask = im_fgnd_mask_stain_1 | im_fgnd_mask_stain_2
# segment nuclei
im_nuc_det_input = np.squeeze(np.min(im_stains[:, :, :2], axis=2))
print('---> Fusing 2 Stains')
deconv_time = time.time() - start_time
csv_dict['ColorDeconvTime'] = round(deconv_time, 3)
# =========================================================================
# ================= Nuclie Detection Deep Learning Block ==================
# =========================================================================
total_tileloading_time = time.time() - total_tileloading_start_time
csv_dict['TotalTileLoadingTime'] = round(total_tileloading_time, 3)
start_time = time.time()
config = get_config(CONFIG)
config.model.rcnn.proposals.total_max_detections = args.max_det
config.model.rcnn.proposals.min_prob_threshold = args.min_prob
im_nuc_det_input = np.stack((im_nuc_det_input,) * 3, axis=-1)
# ====================================================================================================================================
tf.reset_default_graph()
dataset_class = get_dataset('object_detection')
model_class = get_model('fasterrcnn')
dataset = dataset_class(config)
model = model_class(config)
graph = tf.Graph()
session = tf.Session(graph=graph)
with graph.as_default():
image_placeholder = tf.placeholder(
tf.float32, (None, None, 3), name='Input_Placeholder'
)
pred_dict = model(image_placeholder)
ckpt_loading_start_time = time.time()
saver = tf.train.Saver(sharded=True, allow_empty=True)
saver.restore(session, CKPT_DIR)
tf.logging.info('Loaded checkpoint.')
ckpt_loading_time = time.time() - ckpt_loading_start_time
csv_dict['CKPTLoadingTime'] = round(ckpt_loading_time, 3)
inference_start_time = time.time()
cls_prediction = pred_dict['classification_prediction']
objects_tf = cls_prediction['objects']
objects_labels_tf = cls_prediction['labels']
objects_labels_prob_tf = cls_prediction['probs']
fetches = {
'objects': objects_tf,
'labels': objects_labels_tf,
'probs': objects_labels_prob_tf,
}
fetched = session.run(fetches, feed_dict={
image_placeholder: np.array(im_nuc_det_input)
})
inference_time = time.time() - inference_start_time
csv_dict['ModelInfernceTime'] = round(inference_time, 3)
objects = fetched['objects']
labels = fetched['labels'].tolist()
probs = fetched['probs'].tolist()
# Cast to int to consistently return the same type in Python 2 and 3
objects = [
[int(round(coord)) for coord in obj]
for obj in objects.tolist()
]
predictions = sorted([
{
'bbox': obj,
'label': label,
'prob': round(prob, 4),
} for obj, label, prob in zip(objects, labels, probs)
], key=lambda x: x['prob'], reverse=True)
print('\n>> Finishing Detection ... \n')
print('***** Number of Detected Cells ****** : ', len(predictions))
detection_time = time.time() - start_time
csv_dict['DetectionTime'] = round(detection_time, 3)
csv_dict['NumObjects'] = len(predictions)
csv_dict['ObjectsDict'] = predictions
# =========================================================================
# ======================= TODO: Implement border deletion =================
# =========================================================================
# =========================================================================
# ======================= Write Annotations ===============================
# =========================================================================
start_time = time.time()
objects_df = pd.DataFrame(objects)
formatted_annot_list,\
formatter_analysis_list = cli_utils.convert_preds_to_utilformat(
objects_df,
probs,
args.ignore_border_nuclei,
im_tile_size=args.analysis_tile_size)
nuclei_annot_list = cli_utils.create_tile_nuclei_annotations(
formatted_annot_list, tile_info, args.nuclei_annotation_format)
csv_dict['AnnotationDict'] = nuclei_annot_list
csv_dict['AnalysisDict'] = formatter_analysis_list
num_nuclei = len(nuclei_annot_list)
anot_time = time.time() - start_time
csv_dict['AnnotationWritingTime'] = round(anot_time, 3)
return csv_dict
def test_segment_nuclei_kofahi(self):
input_image_file = os.path.join(TEST_DATA_DIR, 'Easy1.png')
ref_image_file = os.path.join(TEST_DATA_DIR, 'L1.png')
# read input image
im_input = skimage.io.imread(input_image_file)[:, :, :3]
# read reference image
im_reference = skimage.io.imread(ref_image_file)[:, :, :3]
# get mean and stddev of reference image in lab space
mean_ref, std_ref = htk_cvt.lab_mean_std(im_reference)
# perform color normalization
im_nmzd = htk_cnorm.reinhard(im_input, mean_ref, std_ref)
# perform color decovolution
stain_color_map = {
'hematoxylin': [0.65, 0.70, 0.29],
'eosin': [0.07, 0.99, 0.11],
'dab': [0.27, 0.57, 0.78],
'null': [0.0, 0.0, 0.0]
}
w = htk_cdeconv.rgb_separate_stains_macenko_pca(im_nmzd, im_nmzd.max())
im_stains = htk_cdeconv.color_deconvolution(im_nmzd, w).Stains
nuclei_channel = htk_cdeconv.find_stain_index(stain_color_map['hematoxylin'], w)
im_nuclei_stain = im_stains[:, :, nuclei_channel].astype(np.float)
# segment foreground (assumes nuclei are darker on a bright background)
im_nuclei_fgnd_mask = sp.ndimage.morphology.binary_fill_holes(
im_nuclei_stain < 60)
# run adaptive multi-scale LoG filter
im_log, im_sigma_max = htk_shape_filters.clog(
im_nuclei_stain, im_nuclei_fgnd_mask,
sigma_min=20 / np.sqrt(2), sigma_max=30 / np.sqrt(2))
# apply local maximum clustering
im_nuclei_seg_mask, seeds, maxima = htk_seg.nuclear.max_clustering(
im_log, im_nuclei_fgnd_mask, 10)
# filter out small objects
im_nuclei_seg_mask = htk_seg.label.area_open(
im_nuclei_seg_mask, 80).astype(np.uint8)
# perform connected component analysis
obj_props = skimage.measure.regionprops(im_nuclei_seg_mask)
num_nuclei = len(obj_props)
# check if segmentation mask matches ground truth
gtruth_mask_file = os.path.join(TEST_DATA_DIR,
'Easy1_nuclei_seg_kofahi_adaptive.npy')
im_gtruth_mask = np.load(gtruth_mask_file)
obj_props_gtruth = skimage.measure.regionprops(im_gtruth_mask)
num_nuclei_gtruth = len(obj_props_gtruth)
assert(num_nuclei == num_nuclei_gtruth)
np.testing.assert_allclose(im_nuclei_seg_mask, im_gtruth_mask)
