def export_all_contours(contours, data_path, overlay_path, crop_size=100, num_classes=4, num_phases=5 ):
print('\nProcessing {:d} images and labels ...\n'.format(len(contours)))
images = np.zeros((len(contours), num_phases, crop_size, crop_size, 1))
masks = np.zeros((len(contours), 1, crop_size, crop_size, num_classes))
for idx, contour in enumerate(contours):
img, mask = read_contour(contour, data_path, num_classes, 5, 20, 2)
#draw_contour(contour, data_path, overlay_path)
img = center_crop_3d(img, crop_size=crop_size)
mask = center_crop_3d(mask, crop_size=crop_size)
images[idx] = img
masks[idx] = mask
return images, masks
def export_all_contours(contours,
data_path,
overlay_path,
crop_size,
contour_type,
num_classes=4,
num_phases=5,
phase_dilation=1,
num_phases_in_cycle=30):
print('\nProcessing {:d} images and labels ...\n'.format(len(contours)))
if num_classes == 2:
num_classes = 1
total_number = 0
for volume_ctr in contours:
total_number += volume_ctr.total_number
images = np.zeros((total_number, num_phases, crop_size, crop_size, 1))
masks = np.zeros((total_number, 1, crop_size, crop_size, num_classes))
idx = 0
for contour in contours:
vol, vol_mask = read_contour(contour,
data_path,
num_phases,
num_phases_in_cycle,
phase_dilation,
contour_type=contour_type,
return_mask=True)
#draw_contour(contour, data_path, overlay_path, type=contour_type)
p, w, h, s, d = vol.shape
for i in range(0, s):
img = vol[:, :, :, i, :]
mask = vol_mask[:, :, :, i, :]
img = np.swapaxes(img, 1, 2)
mask = np.swapaxes(mask, 1, 2)
img = center_crop_3d(img, crop_size=crop_size)
mask = center_crop_3d(mask, crop_size=crop_size)
images[idx] = img
masks[idx] = mask
idx = idx + 1
return images, masks
def create_submission(cases, data_path, output_path, contour_type='i'):
weight_t = 'model_logs/sunnybrook_a_unetres_inv_time.h5'
weight_s = 'model_logs/sunnybrook_i_unetres_inv.h5'
crop_size = 128
num_phases = 3
num_classes = 2
input_shape = (num_phases, crop_size, crop_size, 1)
input_shape_s = (crop_size, crop_size, 1)
model_s = unet_res_model_Inv(input_shape,
num_classes,
nb_filters=16,
transfer=True,
contour_type=contour_type,
weights=weight_s)
model_t = unet_res_model_time(input_shape,
num_classes,
nb_filters=16,
n_phases=num_phases,
transfer=True,
contour_type=contour_type,
weights=weight_t)
for idx, case in enumerate(cases):
print('\nPredict image sequence {:d}'.format(idx))
images, _, file_names = read_all_contour(case, data_path, num_classes)
images_crop = center_crop_3d(images, crop_size=crop_size)
pred_masks = model_s.predict(images_crop, batch_size=32, verbose=1)
p, h, w, d = images.shape
for idx in range(p):
image = images[idx, ...]
tmp = pred_masks[idx, :]
out_file = file_names[idx]
tmp = reshape(tmp, to_shape=(h, w, d))
tmp = np.where(tmp > 0.5, 255, 0).astype('uint8')
tmp2, coords, hierarchy = cv2.findContours(tmp.copy(),
cv2.RETR_LIST,
cv2.CHAIN_APPROX_NONE)
if not coords:
print('\nNo detection in case: {:s}; image: {:s}'.format(
case, out_file))
coords = np.ones((1, 1, 1, 2), dtype='int')
output_full_path = os.path.join(output_path, case)
p = re.compile("dcm")
out_file = p.sub('jpg', out_file)
draw_image_overlay(image, out_file, output_full_path, contour_type,
coords)