def get_cv_fold(fold, dataset="HCP"):
if dataset == "HCP_all":
subjects = get_all_subjects(dataset)
cut_point = int(len(subjects) * 0.9)
return subjects[:cut_point], subjects[cut_point:], ["599671", "599469"]
elif dataset == "biobank_20k":
subjects = get_all_subjects(dataset)
cut_point = int(len(subjects) * 0.9)
return subjects[:cut_point], subjects[cut_point:], ["1000013", "1000013"]
else:
if fold == 0:
train, validate, test = [0, 1, 2], [3], [4]
elif fold == 1:
train, validate, test = [1, 2, 3], [4], [0]
elif fold == 2:
train, validate, test = [2, 3, 4], [0], [1]
elif fold == 3:
train, validate, test = [3, 4, 0], [1], [2]
elif fold == 4:
train, validate, test = [4, 0, 1], [2], [3]
subjects = get_all_subjects(dataset)
if dataset.startswith("HCP"):
subjects = list(utils.chunks(subjects, 21)) #5 folds a 21 subjects
# 5 fold CV ok (score only 1%-point worse than 10 folds (80 vs 60 train subjects) (10 Fold CV impractical!)
elif dataset.startswith("Schizo"):
# ~410 subjects
subjects = list(utils.chunks(subjects, 82)) # 5 folds a 82 subjects
else:
raise ValueError("Invalid dataset name")
subjects = np.array(subjects)
return list(subjects[train].flatten()), list(subjects[validate].flatten()), list(subjects[test].flatten())
# np.save(join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject, filename + ".npy"), data)
nib.save(
nib.Nifti1Image(data, affine),
join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject,
filename + ".nii.gz"))
else:
print("skipping file: {}-{}".format(subject, idx))
raise IOError("File missing")
for filename in filenames_seg:
img = nib.load(
join(C.NETWORK_DRIVE, DATASET_FOLDER, subject,
filename + ".nii.gz"))
data = img.get_data()
data, _, _, _ = data_utils.crop_to_nonzero(data, bbox=bbox)
# np.save(join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject, filename + ".npy"), data)
nib.save(
nib.Nifti1Image(data, img.affine),
join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject,
filename + ".nii.gz"))
if __name__ == "__main__":
print("Output folder: {}".format(DATASET_FOLDER_PREPROC))
subjects = get_all_subjects(dataset=dataset)
Parallel(n_jobs=12)(delayed(create_preprocessed_files)(subject)
for subject in subjects)
# for subject in subjects:
# create_preprocessed_files(subject)