def test_equality(self):
x = 10
y = 10
z = 3
pixel_id = sitk.sitkUInt8
size = (x, y, z)
direction = (0, 1, 0, 1, 0, 0, 0, 0, 1)
image = sitk.Image([x, y, z], pixel_id)
image.SetOrigin(size)
image.SetSpacing(size)
image.SetDirection(direction)
dut1 = img.ImageProperties(image)
dut2 = img.ImageProperties(image)
self.assertTrue(dut1 == dut2)
self.assertFalse(dut1 != dut2)
image = sitk.Image([x, y, z], sitk.sitkInt8)
image.SetOrigin(size)
image.SetSpacing(size)
image.SetDirection(direction)
dut1 = img.ImageProperties(image)
self.assertTrue(dut1 == dut2)
self.assertFalse(dut1 != dut2)
image = sitk.Image([x, y, z], sitk.sitkVectorUInt8, 2)
image.SetOrigin(size)
image.SetSpacing(size)
image.SetDirection(direction)
dut1 = img.ImageProperties(image)
self.assertTrue(dut1 == dut2)
self.assertFalse(dut1 != dut2)
def __call__(self, file_path: str, id_: str, category: str, subject_id: str
) -> typing.Tuple[np.ndarray, typing.Union[miapy_conv.ImageProperties, None]]:
if category == 'images':
img = sitk.ReadImage(file_path)
return sitk.GetArrayFromImage(img), miapy_conv.ImageProperties(img)
if category == 'labels':
img = sitk.ReadImage(file_path, sitk.sitkUInt8)
return sitk.GetArrayFromImage(img), miapy_conv.ImageProperties(img)
if category == 'age' or category == 'resectionstatus' or category == 'survival':
if self.csv_file is None or file_path != self.csv_file:
self.csv_file = file_path
self.csv_content = {}
with open(self.csv_file) as f:
reader = csv.reader(f)
header = next(reader)
for row in reader:
subject = row[0]
self.csv_content[subject] = {header[i]: row[i] for i in range(1, len(header))}
if id_ == 'age':
return np.asarray(float(self.csv_content[subject_id]['Age'])), None
if id_ == 'resectionstatus':
print("working...")
status_class = ResectionStatusConversion.from_status(self.csv_content[subject_id]['ResectionStatus'])
return np.asarray(status_class), None
if id_ == 'survival':
return np.asarray(int(self.csv_content[subject_id]['Survival'])), None
raise ValueError('could not load {}'.format(file_path))
def test_non_equality(self):
x = 10
y = 10
z = 3
pixel_id = sitk.sitkUInt8
size = (x, y, z)
direction = (0, 1, 0, 1, 0, 0, 0, 0, 1)
image = sitk.Image([x, y, z], pixel_id)
image.SetOrigin(size)
image.SetSpacing(size)
image.SetDirection(direction)
dut1 = img.ImageProperties(image)
different_size = (x, y, 2)
# non-equal size
image = sitk.Image(different_size, pixel_id)
image.SetOrigin(size)
image.SetSpacing(size)
image.SetDirection(direction)
dut2 = img.ImageProperties(image)
self.assertFalse(dut1 == dut2)
self.assertTrue(dut1 != dut2)
# non-equal origin
image = sitk.Image(size, pixel_id)
image.SetOrigin(different_size)
image.SetSpacing(size)
image.SetDirection(direction)
dut2 = img.ImageProperties(image)
self.assertFalse(dut1 == dut2)
self.assertTrue(dut1 != dut2)
# non-equal spacing
different_size = (x, y, 2)
image = sitk.Image(size, pixel_id)
image.SetOrigin(size)
image.SetSpacing(different_size)
image.SetDirection(direction)
dut2 = img.ImageProperties(image)
self.assertFalse(dut1 == dut2)
self.assertTrue(dut1 != dut2)
# non-equal direction
different_size = (x, y, 2)
image = sitk.Image(size, pixel_id)
image.SetOrigin(size)
image.SetSpacing(size)
image.SetDirection((1, 0, 0, 0, 1, 0, 0, 0, 1))
dut2 = img.ImageProperties(image)
self.assertFalse(dut1 == dut2)
self.assertTrue(dut1 != dut2)
def test_is_two_dimensional(self):
x = 10
y = 10
image = sitk.Image([x, y], sitk.sitkUInt8)
dut = img.ImageProperties(image)
self.assertEqual(dut.is_two_dimensional(), True)
self.assertEqual(dut.is_three_dimensional(), False)
self.assertEqual(dut.is_vector_image(), False)
def test_is_vector_image(self):
x = 10
y = 10
number_of_components_per_pixel = 3
image = sitk.Image([x, y], sitk.sitkVectorUInt8,
number_of_components_per_pixel)
dut = img.ImageProperties(image)
self.assertEqual(dut.is_two_dimensional(), True)
self.assertEqual(dut.is_three_dimensional(), False)
self.assertEqual(dut.is_vector_image(), True)
def setUp(self):
dim_x = 5
dim_y = 10
dim_z = 3
self.no_vector_components = 4
# some unordinary origins, spacings and directions
self.origin_spacing_2d = (dim_x, dim_y)
self.direction_2d = (0, 1, 1, 0)
self.origin_spacing_3d = (dim_x, dim_y, dim_z)
self.direction_3d = (1, 0, 0, 0, 1, 0, 0, 0, 1)
# set up images
image = sitk.Image((dim_x, dim_y, dim_z), sitk.sitkUInt8)
image.SetOrigin(self.origin_spacing_3d)
image.SetSpacing(self.origin_spacing_3d)
image.SetDirection(self.direction_3d)
self.properties_3d = img.ImageProperties(image)
image = sitk.Image((dim_x, dim_y), sitk.sitkUInt8)
image.SetOrigin(self.origin_spacing_2d)
image.SetSpacing(self.origin_spacing_2d)
image.SetDirection(self.direction_2d)
self.properties_2d = img.ImageProperties(image)
# set up numpy arrays (note the inverted order of the dimension)
self.array_image_shape_2d = np.zeros((dim_y, dim_x), np.uint8)
self.array_2d_vector = np.zeros(
(dim_y * dim_x, self.no_vector_components), np.uint8)
self.array_image_shape_2d_vector = np.zeros(
(dim_y, dim_x, self.no_vector_components), np.uint8)
self.array_image_shape_3d = np.zeros((dim_z, dim_y, dim_x), np.uint8)
self.array_3d_vector = np.zeros(
(dim_z * dim_y * dim_x, self.no_vector_components), np.uint8)
self.array_image_shape_3d_vector = np.zeros(
(dim_z, dim_y, dim_x, self.no_vector_components), np.uint8)
def test_properties(self):
x = 10
y = 10
z = 3
pixel_id = sitk.sitkUInt8
size = (x, y, z)
direction = (0, 1, 0, 1, 0, 0, 0, 0, 1)
image = sitk.Image([x, y, z], pixel_id)
image.SetOrigin(size)
image.SetSpacing(size)
image.SetDirection(direction)
dut = img.ImageProperties(image)
self.assertEqual(dut.size, size)
self.assertEqual(dut.origin, size)
self.assertEqual(dut.spacing, size)
self.assertEqual(dut.direction, direction)
self.assertEqual(dut.dimensions, z)
self.assertEqual(dut.number_of_components_per_pixel, 1)
self.assertEqual(dut.pixel_id, pixel_id)
def extract(self, reader: rd.Reader, params: dict,
extracted: dict) -> None:
subject_index_expr = expr.IndexExpression(params['subject_index'])
shape = reader.read(df.INFO_SHAPE, subject_index_expr).tolist()
direction = reader.read(df.INFO_DIRECTION, subject_index_expr).tolist()
spacing = reader.read(df.INFO_SPACING, subject_index_expr).tolist()
origin = reader.read(df.INFO_ORIGIN, subject_index_expr).tolist()
# todo: everything in memory?
image = sitk.Image(shape, sitk.sitkUInt8)
image.SetDirection(direction)
image.SetSpacing(spacing)
image.SetOrigin(origin)
# todo number_of_components_per_pixel and pixel_id
img_properties = conv.ImageProperties(image)
if self.do_pickle:
# pickle to prevent from problems since own class
img_properties = pickle.dumps(img_properties)
extracted['properties'] = img_properties
def __call__(self, file_name: str, id_: str, category: str, subject_id: str) -> \
typing.Tuple[np.ndarray, typing.Union[conv.ImageProperties, None]]:
if id_ == FileTypes.AGE.name:
with open(file_name, 'r') as f:
value = np.asarray([int(f.readline().split(':')[1].strip())])
return value, None
if id_ == FileTypes.GPA.name:
with open(file_name, 'r') as f:
value = np.asarray([float(f.readlines()[1].split(':')[1].strip())])
return value, None
if id_ == FileTypes.SEX.name:
with open(file_name, 'r') as f:
value = np.asarray([f.readlines()[2].split(':')[1].strip()])
return value, None
if category == 'images':
img = sitk.ReadImage(file_name, sitk.sitkFloat32)
else:
img = sitk.ReadImage(file_name, sitk.sitkUInt8)
return sitk.GetArrayFromImage(img), conv.ImageProperties(img)
def main(hdf_file: str):
extractor = extr.ComposeExtractor([
extr.NamesExtractor(),
extr.DataExtractor(),
extr.SelectiveDataExtractor(),
extr.DataExtractor(('numerical', ), ignore_indexing=True),
extr.DataExtractor(('sex', ), ignore_indexing=True),
extr.DataExtractor(('mask', ), ignore_indexing=False),
extr.SubjectExtractor(),
extr.FilesExtractor(categories=('images', 'labels', 'mask',
'numerical', 'sex')),
extr.IndexingExtractor(),
extr.ImagePropertiesExtractor()
])
dataset = extr.ParameterizableDataset(hdf_file, extr.SliceIndexing(),
extractor)
for i in range(len(dataset)):
item = dataset[i]
index_expr = item['index_expr'] # type: miapy_data.IndexExpression
root = item['file_root']
image = None # type: sitk.Image
for i, file in enumerate(item['images_files']):
image = sitk.ReadImage(os.path.join(root, file))
np_img = sitk.GetArrayFromImage(image).astype(np.float32)
np_img = (np_img - np_img.mean()) / np_img.std()
np_slice = np_img[index_expr.expression]
if (np_slice != item['images'][..., i]).any():
raise ValueError('slice not equal')
# for any image
image_properties = conv.ImageProperties(image)
if image_properties != item['properties']:
raise ValueError('image properties not equal')
for file in item['labels_files']:
image = sitk.ReadImage(os.path.join(root, file))
np_img = sitk.GetArrayFromImage(image)
np_img = np.expand_dims(
np_img, axis=-1
) # due to the convention of having the last dim as number of channels
np_slice = np_img[index_expr.expression]
if (np_slice != item['labels']).any():
raise ValueError('slice not equal')
for file in item['mask_files']:
image = sitk.ReadImage(os.path.join(root, file))
np_img = sitk.GetArrayFromImage(image)
np_img = np.expand_dims(
np_img, axis=-1
) # due to the convention of having the last dim as number of channels
np_slice = np_img[index_expr.expression]
if (np_slice != item['mask']).any():
raise ValueError('slice not equal')
for file in item['numerical_files']:
with open(os.path.join(root, file), 'r') as f:
lines = f.readlines()
age = float(lines[0].split(':')[1].strip())
gpa = float(lines[1].split(':')[1].strip())
if age != item['numerical'][0][0] or gpa != item['numerical'][0][1]:
raise ValueError('value not equal')
for file in item['sex_files']:
with open(os.path.join(root, file), 'r') as f:
sex = f.readlines()[2].split(':')[1].strip()
if sex != str(item['sex'][0]):
raise ValueError('value not equal')
print('All test passed!')
def __call__(self, file_name: str, id_: str, category: str) -> \
t.Tuple[np.ndarray, t.Union[conv.ImageProperties, None]]:
img = sitk.ReadImage(file_name)
return sitk.GetArrayFromImage(img), conv.ImageProperties(img)
def __call__(
self, file_path: str, id_: str, category: str
) -> typing.Tuple[np.ndarray, typing.Union[miapy_conv.ImageProperties,
None]]:
if id_ == FileTypes.BRAIN_MRI.name:
img = sitk.ReadImage(file_path)
return sitk.GetArrayFromImage(img), miapy_conv.ImageProperties(img)
if id_ == FileTypes.MORPHOMETRY_STATS.name:
metrics = {}
subject_name = file_path.split('/')[-2]
print(subject_name)
# aseg.stats
with open(os.path.join(file_path, 'aseg.stats'), 'r') as f:
for line in f.readlines():
# Parse header lines
# Example: '# Measure TotalGray, TotalGrayVol, Total gray matter volume, 666685.704205, mm^3'
matcher = re.match(
'# Measure (\w+), \w+, [\w\s]+, ([0-9.]+),.*', line)
if matcher:
key = matcher.group(1)
value = float(matcher.group(2))
metrics[key] = value
# Parse body lines
# Example: ' 13 18 1442 1442.0 Left-Amygdala 74.0193 6.1854 48.0000 94.0000 46.0000'
matcher = re.match(
'\s+[0-9.]+\s+[0-9.]+\s+[0-9.]+\s+([0-9.]+)\s+([\w\-_]+).*',
line)
if matcher:
key = matcher.group(2)
value = float(matcher.group(1))
metrics[key] = value
# sum up Corpus Callosum
metrics['CC_sum'] = sum(
[v for k, v in metrics.items() if k.startswith('CC_')])
# old freesurfer versions only
if 'IntraCranialVol' in metrics:
metrics['EstimatedTotalIntraCranialVol'] = metrics.pop(
'IntraCranialVol')
print('WARN: ' + file_path + '. Using IntraCranialVol')
# lh.aparc.stats, rh.aparc.stats
for hemi in ['lh', 'rh']:
with open(
os.path.join(file_path, '{}.aparc.stats'.format(hemi)),
'r') as f:
for line in f.readlines():
# Parse body lines
# StructName NumVert SurfArea GrayVol ThickAvg ThickStd MeanCurv GausCurv FoldInd CurvInd
# Example: 'bankssts 1507 1003 2841 2.494 0.553 0.146 0.076 29 4.7'
matcher = re.match(
'(\w+)\s+[0-9.]+\s+[0-9.]+\s+[0-9.]+\s+([0-9.]+)\s+[0-9.]+\s+([0-9.]+).*',
line)
if matcher:
key = matcher.group(1)
thick_avg = float(matcher.group(2))
mean_curv = float(matcher.group(3))
metrics['{}-{}-ThickAvg'.format(hemi,
key)] = thick_avg
metrics['{}-{}-MeanCurv'.format(hemi,
key)] = mean_curv
# add additional meta data from dict (read from csv)
if self.meta_dict: #and subject_name in self.meta_dict:
meta = self.meta_dict[subject_name]
for key in meta:
metrics[key] = meta[key]
if len(self.morphometry_column_names) == 0:
self.morphometry_column_names = np.array(
[key for key in metrics.keys()])
# if a structure has no voxels for a particular subject, entry is not available
# in aparc.stats (e.g. entorhinal can be 0)
for col in self.morphometry_column_names:
if col not in metrics:
print('No {} found for {}. Assuming 0.0'.format(
col, subject_name))
metrics[col] = 0.0
return np.array([
metrics[value] for value in self.morphometry_column_names
]), None