def make_candidate_auto_images(candidate_types=[]):
dst_dir = settings.WORKING_DIR + "generated_traindata/luna16_train_cubes_auto/"
if not os.path.exists(dst_dir):
os.mkdir(dst_dir)
for candidate_type in candidate_types:
for file_path in glob.glob(dst_dir + "*_" + candidate_type + ".png"):
os.remove(file_path)
for candidate_type in candidate_types:
if candidate_type == "falsepos":
src_dir = "resources/luna16_falsepos_labels/"
else:
src_dir = settings.LUNA16_EXTRACTED_IMAGE_DIR + "_labels/"
for index, csv_file in enumerate(
glob.glob(src_dir + "*_candidates_" + candidate_type +
".csv")):
patient_id = ntpath.basename(csv_file).replace(
"_candidates_" + candidate_type + ".csv", "")
settings.log.info("{0}, patient: {1}, type:{2} ".format(
index, patient_id, candidate_type))
# if not "148229375703208214308676934766" in patient_id:
# continue
df_annos = pandas.read_csv(csv_file)
if len(df_annos) == 0:
continue
images = helpers.load_patient_images(
patient_id,
settings.LUNA16_EXTRACTED_IMAGE_DIR,
"*" + CUBE_IMGTYPE_SRC + ".png",
exclude_wildcards=[])
row_no = 0
for index, row in df_annos.iterrows():
coord_x = int(row["coord_x"] * images.shape[2])
coord_y = int(row["coord_y"] * images.shape[1])
coord_z = int(row["coord_z"] * images.shape[0])
anno_index = int(row["anno_index"])
cube_img = get_cube_from_img(images, coord_x, coord_y, coord_z,
48)
if cube_img.sum() < 10:
settings.log.info(" ***** Skipping {0} {1} {2} ".format(
coord_x, coord_y, coord_z))
continue
# print(cube_img.sum())
try:
save_cube_img(
dst_dir + patient_id + "_" + str(anno_index) + "_0_" +
candidate_type + ".png", cube_img, 6, 8)
except Exception as ex:
settings.log.exception(ex)
row_no += 1
max_item = 240 if candidate_type == "white" else 200
if candidate_type == "luna":
max_item = 500
if row_no > max_item:
break
def make_pos_annotation_images_manual():
src_dir = "resources/luna16_manual_labels/"
dst_dir = settings.WORKING_DIR + "generated_traindata/luna16_train_cubes_manual/"
if not os.path.exists(dst_dir):
os.mkdir(dst_dir)
for file_path in glob.glob(dst_dir + "*_manual.*"):
os.remove(file_path)
for patient_index, csv_file in enumerate(glob.glob(src_dir + "*.csv")):
patient_id = ntpath.basename(csv_file).replace(".csv", "")
if "1.3.6.1.4" not in patient_id:
continue
print(patient_id)
# if not "172845185165807139298420209778" in patient_id:
# continue
df_annos = pandas.read_csv(csv_file)
if len(df_annos) == 0:
continue
images = helpers.load_patient_images(
patient_id, settings.LUNA16_EXTRACTED_IMAGE_DIR,
"*" + CUBE_IMGTYPE_SRC + ".png")
for index, row in df_annos.iterrows():
coord_x = int(row["x"] * images.shape[2])
coord_y = int(row["y"] * images.shape[1])
coord_z = int(row["z"] * images.shape[0])
diameter = int(row["d"] * images.shape[2])
node_type = int(row["id"])
malscore = int(diameter)
malscore = min(25, malscore)
malscore = max(16, malscore)
anno_index = index
cube_img = get_cube_from_img(images, coord_x, coord_y, coord_z, 64)
if cube_img.sum() < 5:
settings.log.info(" ***** Skipping {0} {1} {2} ".format(
coord_x, coord_y, coord_z))
continue
if cube_img.mean() < 10:
settings.log.info(" ***** Suspicious {0} {1} {2} ".format(
coord_x, coord_y, coord_z))
if cube_img.shape != (64, 64, 64):
settings.log.info(
" ***** incorrect shape !!! {0} - {1} {2} {3} ".format(
str(anno_index), coord_x, coord_y, coord_z))
continue
save_cube_img(
dst_dir + patient_id + "_" + str(anno_index) + "_" +
str(malscore) + "_1_" + ("pos" if node_type == 0 else "neg") +
".png", cube_img, 8, 8)
helpers.print_tabbed([patient_index, patient_id,
len(df_annos)], [5, 64, 8])
def make_pos_annotation_images_manual_ndsb3():
src_dir = "resources/ndsb3_manual_labels/"
dst_dir = settings.WORKING_DIR + "generated_traindata/ndsb3_train_cubes_manual/"
if not os.path.exists(dst_dir):
os.mkdir(dst_dir)
train_label_df = pandas.read_csv("resources/stage1_labels.csv")
train_label_df.set_index(["id"], inplace=True)
for file_path in glob.glob(dst_dir + "*.*"):
os.remove(file_path)
for patient_index, csv_file in enumerate(glob.glob(src_dir + "*.csv")):
patient_id = ntpath.basename(csv_file).replace(".csv", "")
if "1.3.6.1.4.1" in patient_id:
continue
cancer_label = train_label_df.loc[patient_id]["cancer"]
df_annos = pandas.read_csv(csv_file)
if len(df_annos) == 0:
continue
images = helpers.load_patient_images(
patient_id, settings.NDSB3_EXTRACTED_IMAGE_DIR,
"*" + CUBE_IMGTYPE_SRC + ".png")
anno_index = 0
for index, row in df_annos.iterrows():
pos_neg = "pos" if row["id"] == 0 else "neg"
coord_x = int(row["x"] * images.shape[2])
coord_y = int(row["y"] * images.shape[1])
coord_z = int(row["z"] * images.shape[0])
malscore = int(round(row["dmm"]))
anno_index += 1
cube_img = get_cube_from_img(images, coord_x, coord_y, coord_z, 64)
if cube_img.sum() < 5:
settings.log.info(" ***** Skipping {0} {1} {2} ".format(
coord_x, coord_y, coord_z))
continue
if cube_img.mean() < 10:
settings.log.info(" ***** Suspicious {0} {1} {2} ".format(
coord_x, coord_y, coord_z))
if cube_img.shape != (64, 64, 64):
settings.log.info(
" ***** incorrect shape !!! {0} - {1} {2} {3} ".format(
str(anno_index), coord_x, coord_y, coord_z))
continue
print(patient_id)
assert malscore > 0 or pos_neg == "neg"
save_cube_img(
dst_dir + "ndsb3manual_" + patient_id + "_" + str(anno_index) +
"_" + pos_neg + "_" + str(cancer_label) + "_" + str(malscore) +
"_1_pn.png", cube_img, 8, 8)
helpers.print_tabbed([patient_index, patient_id,
len(df_annos)], [5, 64, 8])
def make_annotation_images_lidc():
src_dir = settings.LUNA16_EXTRACTED_IMAGE_DIR + "_labels/"
dst_dir = settings.WORKING_DIR + "generated_traindata/luna16_train_cubes_lidc/"
if not os.path.exists(dst_dir):
os.mkdir(dst_dir)
for file_path in glob.glob(dst_dir + "*.*"):
os.remove(file_path)
for patient_index, csv_file in enumerate(
glob.glob(src_dir + "*_annos_pos_lidc.csv")):
patient_id = ntpath.basename(csv_file).replace("_annos_pos_lidc.csv",
"")
df_annos = pandas.read_csv(csv_file)
if len(df_annos) == 0:
continue
images = helpers.load_patient_images(
patient_id, settings.LUNA16_EXTRACTED_IMAGE_DIR,
"*" + CUBE_IMGTYPE_SRC + ".png")
for index, row in df_annos.iterrows():
coord_x = int(row["coord_x"] * images.shape[2])
coord_y = int(row["coord_y"] * images.shape[1])
coord_z = int(row["coord_z"] * images.shape[0])
malscore = int(row["malscore"])
anno_index = row["anno_index"]
anno_index = str(anno_index).replace(" ", "xspacex").replace(
".", "xpointx").replace("_", "xunderscorex")
cube_img = get_cube_from_img(images, coord_x, coord_y, coord_z, 64)
if cube_img.sum() < 5:
settings.log.info(" ***** Skipping {0} {1} {2} ".format(
coord_x, coord_y, coord_z))
continue
if cube_img.mean() < 10:
settings.log.info(" ***** Suspicious {0} {1} {2} ".format(
coord_x, coord_y, coord_z))
if cube_img.shape != (64, 64, 64):
settings.log.info(
" ***** incorrect shape !!! {0} - {1} {2} {3} ".format(
str(anno_index), coord_x, coord_y, coord_z))
continue
save_cube_img(
dst_dir + patient_id + "_" + str(anno_index) + "_" +
str(malscore * malscore) + "_1_pos.png", cube_img, 8, 8)
helpers.print_tabbed([patient_index, patient_id,
len(df_annos)], [5, 64, 8])
def filter_patient_nodules_predictions(self, df_nodule_predictions, patient_id, image_dir, view_size):
# def filter_patient_nodules_predictions(self, df_nodule_predictions: pandas.DataFrame, patient_id, image_dir, view_size):
patient_mask = helpers.load_patient_images(patient_id, image_dir, "*_m.png")
delete_indices = []
for index, row in df_nodule_predictions.iterrows():
z_perc = row["coord_z"]
y_perc = row["coord_y"]
center_x = int(round(row["coord_x"] * patient_mask.shape[2]))
center_y = int(round(y_perc * patient_mask.shape[1]))
center_z = int(round(z_perc * patient_mask.shape[0]))
mal_score = row["diameter_mm"]
start_y = center_y - view_size / 2
start_x = center_x - view_size / 2
nodule_in_mask = False
for z_index in [-1, 0, 1]:
img = patient_mask[z_index + center_z]
start_x = int(start_x)
start_y = int(start_y)
view_size = int(view_size)
img_roi = img[start_y:start_y + view_size, start_x:start_x + view_size]
if img_roi.sum() > 255: # more than 1 pixel of mask.
self.logger.info("More than 1 pixel of mask. nodule_in_mask is true")
nodule_in_mask = True
if not nodule_in_mask:
self.logger.info("Nodule not in mask: {0} {1} {2}".format(center_x, center_y, center_z))
if mal_score > 0:
mal_score *= -1
df_nodule_predictions.loc[index, "diameter_mm"] = mal_score
else:
if center_z < 30:
self.logger.info("Z < 30: {0} center z: {1} y_perc: {2} ".format(patient_id, center_z, y_perc))
if mal_score > 0:
mal_score *= -1
df_nodule_predictions.loc[index, "diameter_mm"] = mal_score
if (z_perc > 0.75 or z_perc < 0.25) and y_perc > 0.85:
self.logger.info("SUSPICIOUS FALSEPOSITIVE: {0} center z: {1} y_perc: {2}".format(patient_id, center_z,
y_perc))
if center_z < 50 and y_perc < 0.30:
self.logger.info(
"SUSPICIOUS FALSEPOSITIVE OUT OF RANGE: {0} center z: {1} y_perc: {2}".format(patient_id,
center_z, y_perc))
df_nodule_predictions.drop(df_nodule_predictions.index[delete_indices], inplace=True)
return df_nodule_predictions
def make_pos_annotation_images():
src_dir = settings.LUNA_16_TRAIN_DIR2D2 + "metadata/"
dst_dir = settings.WORKING_DIR + "luna16_train_cubes_pos/"
for file_path in glob.glob(dst_dir + "*.*"):
os.remove(file_path)
for patient_index, csv_file in enumerate(
glob.glob(src_dir + "*_annos_pos.csv")):
patient_id = ntpath.basename(csv_file).replace("_annos_pos.csv", "")
# print(patient_id)
# if not "148229375703208214308676934766" in patient_id:
# continue
df_annos = pandas.read_csv(csv_file)
if len(df_annos) == 0:
continue
images = helpers.load_patient_images(patient_id,
settings.LUNA_16_TRAIN_DIR2D2,
"*" + CUBE_IMGTYPE_SRC + ".png")
for index, row in df_annos.iterrows():
coord_x = int(row["coord_x"] * images.shape[2])
coord_y = int(row["coord_y"] * images.shape[1])
coord_z = int(row["coord_z"] * images.shape[0])
diam_mm = int(row["diameter"] * images.shape[2])
anno_index = int(row["anno_index"])
cube_img = get_cube_from_img(images, coord_x, coord_y, coord_z, 64)
if cube_img.sum() < 5:
settings.log.info(" ***** Skipping {0} {1} {2}".format(
coord_x, coord_y, coord_z))
continue
if cube_img.mean() < 10:
settings.log.info(" ***** Suspicious {0} {1} {2}".format(
coord_x, coord_y, coord_z))
save_cube_img(
dst_dir + patient_id + "_" + str(anno_index) + "_" +
str(diam_mm) + "_1_" + "pos.png", cube_img, 8, 8)
helpers.print_tabbed([patient_index, patient_id,
len(df_annos)], [5, 64, 8])
def predict_patient(self, patient_id, image_dir, result_dir, magnification=1, flip=False):
if self.model is None:
self.logger.error("The model is None. Please call generate_model() to generate the model at first.")
return None
if not os.path.exists(result_dir):
os.makedirs(result_dir)
sw = helpers.Stopwatch.start_new()
csv_target_path = result_dir + patient_id + ".csv"
all_predictions_csv = []
patient_img = helpers.load_patient_images(patient_id, image_dir, "*_i.png", [])
if magnification != 1:
patient_img = helpers.rescale_patient_images(patient_img, (1, 1, 1), magnification)
patient_mask = helpers.load_patient_images(patient_id, image_dir, "*_m.png", [])
if magnification != 1:
patient_mask = helpers.rescale_patient_images(patient_mask, (1, 1, 1), magnification, is_mask_image=True)
step = self.PREDICT_STEP
CROP_SIZE = self.CUBE_SIZE
# CROP_SIZE = 48
predict_volume_shape_list = [0, 0, 0]
for dim in range(3):
dim_indent = 0
while dim_indent + CROP_SIZE < patient_img.shape[dim]:
predict_volume_shape_list[dim] += 1
dim_indent += step
predict_volume_shape = (
predict_volume_shape_list[0], predict_volume_shape_list[1], predict_volume_shape_list[2])
predict_volume = numpy.zeros(shape=predict_volume_shape, dtype=float)
self.logger.info("Predict volume shape: {0}".format(predict_volume.shape))
done_count = 0
skipped_count = 0
batch_size = 128
batch_list = []
batch_list_coords = []
patient_predictions_csv = []
cube_img = None
annotation_index = 0
for z in range(0, predict_volume_shape[0]):
for y in range(0, predict_volume_shape[1]):
for x in range(0, predict_volume_shape[2]):
# if cube_img is None:
cube_img = patient_img[z * step:z * step + CROP_SIZE, y * step:y * step + CROP_SIZE,
x * step:x * step + CROP_SIZE]
cube_mask = patient_mask[z * step:z * step + CROP_SIZE, y * step:y * step + CROP_SIZE,
x * step:x * step + CROP_SIZE]
if cube_mask.sum() < 2000:
skipped_count += 1
self.logger.info("Cube x {0} y {1} z {2} is skipped!!!".format(x, y, z))
else:
if flip:
cube_img = cube_img[:, :, ::-1]
if CROP_SIZE != self.CUBE_SIZE:
cube_img = helpers.rescale_patient_images2(cube_img, (self.CUBE_SIZE, self.CUBE_SIZE, self.CUBE_SIZE))
# helpers.save_cube_img("c:/tmp/cube.png", cube_img, 8, 4)
# cube_mask = helpers.rescale_patient_images2(cube_mask, (CUBE_SIZE, CUBE_SIZE, CUBE_SIZE))
img_prep = self.prepare_image_for_net3D(cube_img)
batch_list.append(img_prep)
batch_list_coords.append((z, y, x))
if len(batch_list) % batch_size == 0:
batch_data = numpy.vstack(batch_list)
p = self.model.predict(batch_data, batch_size=batch_size)
for i in range(len(p[0])):
p_z = batch_list_coords[i][0]
p_y = batch_list_coords[i][1]
p_x = batch_list_coords[i][2]
nodule_chance = p[0][i][0]
predict_volume[p_z, p_y, p_x] = nodule_chance
if nodule_chance > self.P_TH:
self.logger.info(
"Cube x {0} y {1} z {2} is possible nodule, nodule_chance is {3}!!!".format(
p_x, p_y, p_z, nodule_chance))
p_z = p_z * step + CROP_SIZE / 2
p_y = p_y * step + CROP_SIZE / 2
p_x = p_x * step + CROP_SIZE / 2
self.logger.info("Cube center x {0} y {1} z {2} ".format(p_x, p_y, p_z))
p_z_perc = round(p_z / patient_img.shape[0], 4)
p_y_perc = round(p_y / patient_img.shape[1], 4)
p_x_perc = round(p_x / patient_img.shape[2], 4)
diameter_mm = round(p[1][i][0], 4)
self.logger.info("Cube diameter_mm {0} ".format(diameter_mm))
# diameter_perc = round(2 * step / patient_img.shape[2], 4)
diameter_perc = round(2 * step / patient_img.shape[2], 4)
diameter_perc = round(diameter_mm / patient_img.shape[2], 4)
self.logger.info(
"Cube center percentage x {0} y {1} z {2} diamm {3} ".format(p_x_perc, p_y_perc,
p_z_perc,
diameter_mm))
nodule_chance = round(nodule_chance, 4)
patient_predictions_csv_line = [annotation_index, p_x_perc, p_y_perc, p_z_perc,
diameter_perc, nodule_chance, diameter_mm]
patient_predictions_csv.append(patient_predictions_csv_line)
all_predictions_csv.append([patient_id] + patient_predictions_csv_line)
annotation_index += 1
batch_list = []
batch_list_coords = []
done_count += 1
if done_count % 10000 == 0:
self.logger.info("Done: {0} skipped: {1}".format(done_count, skipped_count))
df = pandas.DataFrame(patient_predictions_csv,
columns=["anno_index", "coord_x", "coord_y", "coord_z", "diameter",
"nodule_chance", "diameter_mm"])
self.filter_patient_nodules_predictions(df, patient_id, image_dir, CROP_SIZE * magnification)
df.to_csv(csv_target_path, index=False)
self.logger.info("predict_volume mean is {0}".format(predict_volume.mean()))
self.logger.info("Done in {0} seconds".format(sw.get_elapsed_seconds()))