truly_longitudinal_study = True if len(layout.get_sessions()) > 1 else False
subjects_to_analyze, sessions_to_analyze, freesurfer_subjects_to_analyze = get_subjects_session(layout,
args.participant_label,
truly_longitudinal_study)
if args.analysis_level == "participant":
data_files = run_prepare_all(args.bids_dir, freesurfer_dir, out_dir, subjects_to_analyze,
sessions_to_analyze, args.n_cpus, args.license_key, args.skip_missing)
for subject, d in data_files.items():
d["out_dir"] = out_dir
d["model_dir"] = model_dir
d["models"] = args.models
d["subject_label"] = subject
predict_brain_age_single_subject(**d)
elif args.analysis_level == "group":
print("Creating group table...")
df = pd.DataFrame([])
for subject in freesurfer_subjects_to_analyze:
in_file = os.path.join(out_dir, subject, subject + "_predicted_age.tsv")
if os.path.isfile(in_file):
df = df.append(pd.read_csv(in_file, sep="\t"))
elif not args.skip_missing:
raise FileNotFoundError(in_file)
group_out_dir = os.path.join(out_dir, "00_group")
if not os.path.isdir(group_out_dir):
os.makedirs(group_out_dir)
out_file = os.path.join(group_out_dir, "group_predicted_age.tsv")
default=["Liem2016__OCI_norm"],
help='',
nargs="+")
parser.add_argument('--lh_thickness_file', required=True, help='')
parser.add_argument('--rh_thickness_file', required=True, help='')
parser.add_argument('--lh_area_file', required=True, help='')
parser.add_argument('--rh_area_file', required=True, help='')
parser.add_argument('--aseg_file', required=True, help='')
parser.add_argument('-v',
'--version',
action='version',
version='BARACUS version {}'.format(__version__))
args = parser.parse_args()
model_dir = resource_filename(Requirement.parse("baracus"), 'models')
if args.participant_label:
subject = args.participant_label
else:
subject = ""
predict_brain_age_single_subject(out_dir=args.out_dir,
lh_thickness_file=args.lh_thickness_file,
rh_thickness_file=args.rh_thickness_file,
lh_area_file=args.lh_area_file,
rh_area_file=args.rh_area_file,
aseg_file=args.aseg_file,
model_dir=model_dir,
models=args.models,
subject_label=subject)