def cluster_prediction_result(pred_dir,
eps,
min_samples,
hasHeader,
isWeightedAvg=False,
prob_threshold=0):
""" cluster the prediction results to avoid the duplicated
predictions introduced by the small stride.
Args:
pred_dir: directory for the prediction result
eps: maximum distance between two samples for them to be considered
as in the same neighborhood.
min_samples: number of samples (or total weight) in a neighborhood
for a point to be considered as a core point.
hasHeader: boolean value to indicate if the csv file has the header
isWeightedAvg: boolean value to indicate if add the prediction.
probabilities as the weight to compute the averaged coordinates
of each cluster.
prob_threshold: probability threshold over which the location is
considered a positive prediction for the purposes of clustering.
"""
pred_files = list_files(pred_dir, "*.csv")
pred_files = get_file_id(pred_files, GROUND_TRUTH_FILE_ID_RE)
clustered_dir = os.path.dirname(pred_dir + "/") + "_clustered/"
if os.path.exists(clustered_dir):
print(clustered_dir)
shutil.rmtree(clustered_dir)
for k, pred_file in pred_files.items():
print(pred_file)
pred_locations = get_locations_from_csv(pred_file,
hasHeader=hasHeader,
hasProb=True)
pred_locations = [
p for p in pred_locations if float(p[2]) > prob_threshold
]
# apply dbscan clustering on each prediction file
if len(pred_locations) > 0:
clustered_pred_locations = dbscan_clustering(
pred_locations,
eps=eps,
min_samples=min_samples,
isWeightedAvg=isWeightedAvg)
# save the prediction results
clustered_file_name = pred_file.replace(pred_dir, clustered_dir)
tuple_2_csv(clustered_pred_locations,
clustered_file_name,
columns={'row', 'col', 'avg_prob'})
def detect_prediction_results(pred_dir, img_dir, radius, prob_thresh,
hasHeader):
"""Detect mitoses from probability maps through an iterative
procedure.
This will read csv prediction files, and output csv prediction files
containing coordinates of the predicted mitoses centers.
Args:
pred_dir: Directory containing the prediction results
img_dir: Directory containing the images
radius: Integer value for the radius of the disk kernel.
prob_thresh: A floating value representing the lower bound on
the probability values.
hasHeader: Boolean value to indicate if the csv file has the header
"""
pred_files = list_files(pred_dir, "*.csv")
pred_files = get_file_id(pred_files, GROUND_TRUTH_FILE_ID_RE)
img_files = list_files(img_dir, "*.tif")
img_files = get_file_id(img_files, GROUND_TRUTH_FILE_ID_RE)
for k, pred_file in pred_files.items():
# convert ijv predictions to prob maps
img_file = img_files[k]
h, w = Image.open(img_file).size
probs = csv_2_arr(pred_file, h, w, hasHeader=hasHeader)
# detect the centers of the mitoses
preds_detected = identify_mitoses(probs, radius, prob_thresh)
# save the prediction results
detected_dir = os.path.dirname(pred_dir + "/") + "_detected"
detected_file_name = pred_file.replace(pred_dir, detected_dir)
tuple_2_csv(preds_detected,
detected_file_name,
columns={'row', 'col', 'prob'})
def smooth_prediction_results(pred_dir, img_dir, radius, hasHeader):
"""Smooth the probability maps by convolving them with a disk kernel.
This will read csv prediction files, and output smoothed csv
prediction files.
Args:
pred_dir: Directory containing the prediction results
img_dir: Directory containing the images
radius: Integer value for the radius of the disk kernel.
hasHeader: Boolean value to indicate if the csv file has the header
"""
pred_files = list_files(pred_dir, "*.csv")
pred_files = get_file_id(pred_files, GROUND_TRUTH_FILE_ID_RE)
img_files = list_files(img_dir, "*.tif")
img_files = get_file_id(img_files, GROUND_TRUTH_FILE_ID_RE)
# create conv smoothing graph
probs_tf = tf.placeholder(shape=[None, None], dtype=tf.float32)
probs_smooth_tf = conv_smooth(probs_tf, radius)
with tf.Session() as sess:
for k, pred_file in pred_files.items():
# convert ijv predictions to prob maps
img_file = img_files[k]
h, w = Image.open(img_file).size
probs = csv_2_arr(pred_file, h, w, hasHeader=hasHeader)
# smooth the probability maps
probs_smooth = sess.run(probs_smooth_tf,
feed_dict={probs_tf: probs})
# save the prediction results
smooth_dir = os.path.dirname(pred_dir + "/") + "_smoothed"
smooth_file_name = pred_file.replace(pred_dir, smooth_dir)
arr_2_csv(probs_smooth, smooth_file_name)