def run(self, output_filename: str):
source_paths_t2 = list()
source_paths_t1 = list()
target_paths = list()
for subject in sorted(os.listdir(os.path.join(self._source_dir))):
source_paths_t1.append(
extract_file_paths(
os.path.join(self._source_dir, subject, "T1")))
source_paths_t2.append(
extract_file_paths(
os.path.join(self._source_dir, subject, "T2")))
target_paths.append(
extract_file_paths(
os.path.join(self._source_dir, subject, "Labels")))
subjects = np.arange(1, 11)
source_paths_t1 = natural_sort(
[item for sublist in source_paths_t1 for item in sublist])
source_paths_t2 = natural_sort(
[item for sublist in source_paths_t2 for item in sublist])
target_paths = natural_sort(
[item for sublist in target_paths for item in sublist])
with open(os.path.join(self._output_dir, output_filename),
mode='a+') as output_file:
writer = csv.writer(output_file,
delimiter=',',
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
writer.writerow([
"T1", "T2", "labels", "subject", "T1_min", "T1_max", "T1_mean",
"T1_std", "T2_min", "T2_max", "T2_mean", "T2_std"
])
for source_path, source_path_t2, target_path, subject in zip(
source_paths_t1, source_paths_t2, target_paths, subjects):
self.LOGGER.info("Processing file {}".format(source_path))
t1 = ToNumpyArray()(source_path)
t2 = ToNumpyArray()(source_path_t2)
csv_data = np.vstack((source_path, source_path_t2, target_path,
subject, str(t1.min()), str(t1.max()),
str(t1.mean()), str(t1.std()),
str(t2.min()), str(t2.max()),
str(t2.mean()), str(t2.std())))
for item in range(csv_data.shape[1]):
writer.writerow([
csv_data[0][item], csv_data[1][item],
csv_data[2][item], csv_data[3][item],
csv_data[4][item], csv_data[5][item],
csv_data[6][item], csv_data[7][item],
csv_data[8][item], csv_data[9][item],
csv_data[10][item], csv_data[11][item]
])
output_file.close()
def run(self, output_filename: str):
source_paths = list()
target_paths = list()
subjects = list()
sites = list()
for dir in sorted(os.listdir(self._source_dir)):
source_paths_ = extract_file_paths(
os.path.join(self._source_dir, dir, "mri", "T1"), "T1.nii.gz")
target_paths_ = extract_file_paths(
os.path.join(self._source_dir, dir, "mri", "Labels"),
"Labels.nii.gz")
subject_ = dir
source_paths.append(source_paths_)
target_paths.append(target_paths_)
if len(source_paths_) is not 0:
match = re.search('(?P<site>.*)_(?P<patient_id>[0-9]*)',
str(dir))
site_ = match.group("site")
sites.append(site_)
subjects.append(subject_)
source_paths = list(filter(None, source_paths))
target_paths = list(filter(None, target_paths))
with open(os.path.join(self._output_dir, output_filename),
mode='a+') as output_file:
writer = csv.writer(output_file,
delimiter=',',
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
writer.writerow([
"T1", "labels", "subject", "site", "min", "max", "mean", "std"
])
for source_path, target_path, subject, site in zip(
source_paths, target_paths, subjects, sites):
self.LOGGER.info("Processing file {}".format(source_path))
image = ToNumpyArray()(source_path[0])
csv_data = np.vstack(
(source_path, target_path, subject, site, (image.min()),
(image.max()), (image.mean()), (image.std())))
for item in range(csv_data.shape[1]):
writer.writerow([
csv_data[0][item], csv_data[1][item],
csv_data[2][item], csv_data[3][item],
csv_data[4][item], csv_data[5][item],
csv_data[6][item], csv_data[7][item]
])
output_file.close()