# save images
results = results.astype(np.uint8)
for i_case in range(results.shape[0]):
if post_processing: #Remove very small lesions (3 voxels)
labels_out = cc3d.connected_components(results[i_case,:,:,:])
for i_cc in np.unique(labels_out):
if len(labels_out[labels_out == i_cc]) <= min_area:
results[i_case,:,:,:][labels_out == i_cc] = 0
save_image(results[i_case,:,:,:], jp(path_results, experiment_name_folder,"test"+all_indexes[i_case][0] + "_" + all_indexes[i_case][1] + "_qwertz.nii"))
# Save dictionary that identifies which folds were considered
selection["experiment"] = experiment_name
selection["Postprocessing"] = post_processing
selection["Min-area"] = min_area
create_log(jp(path_results, experiment_name_folder), selection)
z = 0
elif experiment_type == 'l':
path_exp = jp(path_experiments_l, experiment_name)
folds = list_folders(path_exp)
#Read log file to get parameters
parameters_dict = parse_log_file(jp(path_exp, folds[0])) # take file of first fold as reference
all_folds = []
for f in folds:
if selection[f] == False:
print(cnt + 1, "/", len(test_images))
scan_path = jp(path_test, case)
inf_slices = get_inference_slices(scan_path=scan_path,
input_data=options['input_data'],
normalize=True,
norm_type='zero_one')
probs = get_probs(inf_slices, lesion_model, device, options['num_classes'],
options)
labels = np.transpose(np.argmax(probs, axis=1).astype(np.uint8), (1, 2, 0))
labels_gt = nib.load(jp(path_test, case,
options['gt'])).get_fdata().astype(np.uint8) #GT
#DSC
dsc = compute_dices(labels_gt.flatten(), labels.flatten())
hd = compute_hausdorf(labels_gt, labels.astype(np.uint8))
df.loc[i_row] = [case, dsc[0], hd[0]]
i_row += 1
#Save result
img_nib = nib.Nifti1Image(labels, np.eye(4))
create_folder(jp(path_segmentations, case))
nib.save(img_nib, jp(path_segmentations, case, case + "_segm.nii.gz"))
cnt += 1
df.to_csv(jp(path_results, "results.csv"), float_format='%.5f', index=False)
print(df.mean())
create_log(path_results, options)
name_folder_new_ensemble = "Ensemble_" + str(num_ens + 1).zfill(2)
create_folder(jp(path_ensembles, name_folder_new_ensemble))
# Check that listed experiments exist
all_experiments = list_folders(path_base)
all_experiments = [x for x in all_experiments if x in experiments_to_ensemble]
assert len(all_experiments) % 2 != 0 # number of experiments must be odd
all_images = []
for i_exp, exp in enumerate(all_experiments):
print("Current experiment: ", exp, i_exp + 1, "/", len(all_experiments))
all_images_names = list_files_with_extension(jp(path_base, exp), "nii")
all_images_curr_exp = []
for img in all_images_names:
all_images_curr_exp.append(
nib.load(jp(path_base, exp, img)).get_fdata().astype(np.uint8))
all_images.append(np.stack(all_images_curr_exp)) # (61, volume size)
all_images_np = np.stack(all_images)
the_sum = np.sum(all_images_np, axis=0)
voting = the_sum >= np.ceil(len(all_experiments) / 2)
# save images
for i_case in range(voting.shape[0]):
save_image(
voting[i_case, :, :, :].astype(np.uint8),
jp(path_ensembles, name_folder_new_ensemble, all_images_names[i_case]))
create_log(jp(path_ensembles, name_folder_new_ensemble),
{'experiments': all_experiments})