def test_add_dimension_with_functional_group_pointer(self) -> None:
seq = DimensionOrganizationSequence()
seq.add_dimension("ReferencedSegmentNumber", "SegmentIdentificationSequence")
assert len(seq) == 1
assert seq[0].DimensionOrganizationUID == seq[0].DimensionOrganizationUID
assert seq[0].DimensionIndexPointer == pydicom.tag.Tag(0x0062, 0x000B)
assert seq[0].FunctionalGroupPointer == pydicom.tag.Tag(0x0062, 0x000A)
def test_add_dimension_without_functional_group_pointer(self):
seq = DimensionOrganizationSequence()
seq.add_dimension('ReferencedSegmentNumber')
assert len(seq) == 1
assert seq[0].DimensionOrganizationUID == seq[
0].DimensionOrganizationUID
assert seq[0].DimensionIndexPointer == pydicom.tag.Tag(0x0062, 0x000b)
assert 'FunctionalGroupPointer' not in seq[0]
def test_add_dimension_with_functional_group_pointer_tag_based(self):
seq = DimensionOrganizationSequence()
seq.add_dimension(pydicom.tag.Tag(0x0062, 0x000b),
pydicom.tag.Tag(0x0062, 0x000a))
assert len(seq) == 1
assert seq[0].DimensionOrganizationUID == seq[
0].DimensionOrganizationUID
assert seq[0].DimensionIndexPointer == pydicom.tag.Tag(0x0062, 0x000b)
assert seq[0].FunctionalGroupPointer == pydicom.tag.Tag(0x0062, 0x000a)
def test_add_multiple_dimensions_copies_same_organization_uid(self):
seq = DimensionOrganizationSequence()
seq.add_dimension('ReferencedSegmentNumber',
'SegmentIdentificationSequence')
seq.add_dimension('ImagePositionPatient', 'PlanePositionSequence')
assert len(seq) == 2
assert seq[0].DimensionOrganizationUID == seq[
1].DimensionOrganizationUID
def test_add_dimension_organization_duplicate(self):
seq = DimensionOrganizationSequence()
seq.add_dimension('ReferencedSegmentNumber',
'SegmentIdentificationSequence')
seq.add_dimension('ImagePositionPatient', 'PlanePositionSequence')
self.dataset.add_dimension_organization(seq)
with pytest.raises(ValueError,
match='Dimension organization with UID.*'):
self.dataset.add_dimension_organization(seq)
def test_add_dimension_organization_duplicate(self) -> None:
seq = DimensionOrganizationSequence()
seq.add_dimension("ReferencedSegmentNumber",
"SegmentIdentificationSequence")
seq.add_dimension("ImagePositionPatient", "PlanePositionSequence")
self.dataset.add_dimension_organization(seq)
with pytest.raises(ValueError,
match="Dimension organization with UID.*"):
self.dataset.add_dimension_organization(seq)
def test_add_multiple_dimension_organizations(self):
for _ in range(2):
seq = DimensionOrganizationSequence()
seq.add_dimension('ReferencedSegmentNumber',
'SegmentIdentificationSequence')
seq.add_dimension('ImagePositionPatient', 'PlanePositionSequence')
self.dataset.add_dimension_organization(seq)
assert len(self.dataset.DimensionOrganizationSequence) == 2
assert len(self.dataset.DimensionIndexSequence) == 4
def test_add_multiple_dimension_organizations(self) -> None:
for _ in range(2):
seq = DimensionOrganizationSequence()
seq.add_dimension("ReferencedSegmentNumber",
"SegmentIdentificationSequence")
seq.add_dimension("ImagePositionPatient", "PlanePositionSequence")
self.dataset.add_dimension_organization(seq)
assert len(self.dataset.DimensionOrganizationSequence) == 2
assert len(self.dataset.DimensionIndexSequence) == 4
def test_add_dimension_organization(self):
assert 'DimensionOrganizationSequence' not in self.dataset
assert 'DimensionIndexSequence' not in self.dataset
seq = DimensionOrganizationSequence()
seq.add_dimension('ReferencedSegmentNumber',
'SegmentIdentificationSequence')
seq.add_dimension('ImagePositionPatient', 'PlanePositionSequence')
self.dataset.add_dimension_organization(seq)
assert len(self.dataset.DimensionOrganizationSequence) == 1
assert len(self.dataset.DimensionIndexSequence) == 2
assert self.dataset.DimensionIndexSequence[
0].DimensionDescriptionLabel == 'ReferencedSegmentNumber'
assert self.dataset.DimensionIndexSequence[
1].DimensionDescriptionLabel == 'ImagePositionPatient'
def test_add_dimension_organization(self) -> None:
assert "DimensionOrganizationSequence" not in self.dataset
assert "DimensionIndexSequence" not in self.dataset
seq = DimensionOrganizationSequence()
seq.add_dimension("ReferencedSegmentNumber",
"SegmentIdentificationSequence")
seq.add_dimension("ImagePositionPatient", "PlanePositionSequence")
self.dataset.add_dimension_organization(seq)
assert len(self.dataset.DimensionOrganizationSequence) == 1
assert len(self.dataset.DimensionIndexSequence) == 2
assert (self.dataset.DimensionIndexSequence[0].
DimensionDescriptionLabel == "ReferencedSegmentNumber")
assert (self.dataset.DimensionIndexSequence[1].
DimensionDescriptionLabel == "ImagePositionPatient")
def test_empty_sequence(self):
seq = DimensionOrganizationSequence()
assert len(seq) == 0
def write(self, segmentation: sitk.Image,
source_images: List[pydicom.Dataset]) -> pydicom.Dataset:
"""Writes a DICOM-SEG dataset from a segmentation image and the
corresponding DICOM source images.
Args:
segmentation: A `SimpleITK.Image` with integer labels and a single
component per spatial location.
source_images: A list of `pydicom.Dataset` which are the
source images for the segmentation image.
Returns:
A `pydicom.Dataset` instance with all necessary information and
meta information for writing the dataset to disk.
"""
if segmentation.GetDimension() != 3:
raise ValueError("Only 3D segmentation data is supported")
if segmentation.GetNumberOfComponentsPerPixel() > 1:
raise ValueError("Multi-class segmentations can only be "
"represented with a single component per voxel")
if segmentation.GetPixelID() not in [
sitk.sitkUInt8,
sitk.sitkUInt16,
sitk.sitkUInt32,
sitk.sitkUInt64,
]:
raise ValueError("Unsigned integer data type required")
# TODO Add further checks if source images are from the same series
slice_to_source_images = self._map_source_images_to_segmentation(
segmentation, source_images)
# Compute unique labels and their respective bounding boxes
label_statistics_filter = sitk.LabelStatisticsImageFilter()
label_statistics_filter.Execute(segmentation, segmentation)
unique_labels = set(
[x for x in label_statistics_filter.GetLabels() if x != 0])
if len(unique_labels) == 0:
raise ValueError("Segmentation does not contain any labels")
# Check if all present labels where declared in the DICOM template
declared_segments = set(
[x.SegmentNumber for x in self._template.SegmentSequence])
missing_declarations = unique_labels.difference(declared_segments)
if missing_declarations:
missing_segment_numbers = ", ".join(
[str(x) for x in missing_declarations])
message = (
f"Skipping segment(s) {missing_segment_numbers}, since their "
"declaration is missing in the DICOM template")
if not self._skip_missing_segment:
raise ValueError(message)
logger.warning(message)
labels_to_process = unique_labels.intersection(declared_segments)
if not labels_to_process:
raise ValueError("No segments found for encoding as DICOM-SEG")
# Compute bounding boxes for each present label and optionally restrict
# the volume to serialize to the joined maximum extent
bboxs = {
x: label_statistics_filter.GetBoundingBox(x)
for x in labels_to_process
}
if self._inplane_cropping:
min_x, min_y, _ = np.min([x[::2] for x in bboxs.values()],
axis=0).tolist()
max_x, max_y, _ = (
np.max([x[1::2]
for x in bboxs.values()], axis=0) + 1).tolist()
logger.info(
"Serializing cropped image planes starting at coordinates "
f"({min_x}, {min_y}) with size ({max_x - min_x}, {max_y - min_y})"
)
else:
min_x, min_y = 0, 0
max_x, max_y = segmentation.GetWidth(), segmentation.GetHeight()
logger.info(
f"Serializing image planes at full size ({max_x}, {max_y})")
# Create target dataset for storing serialized data
result = SegmentationDataset(
reference_dicom=source_images[0] if source_images else None,
rows=max_y - min_y,
columns=max_x - min_x,
segmentation_type=SegmentationType.BINARY,
)
dimension_organization = DimensionOrganizationSequence()
dimension_organization.add_dimension("ReferencedSegmentNumber",
"SegmentIdentificationSequence")
dimension_organization.add_dimension("ImagePositionPatient",
"PlanePositionSequence")
result.add_dimension_organization(dimension_organization)
writer_utils.copy_segmentation_template(
target=result,
template=self._template,
segments=labels_to_process,
skip_missing_segment=self._skip_missing_segment,
)
writer_utils.set_shared_functional_groups_sequence(
target=result, segmentation=segmentation)
# FIX - Use ImageOrientationPatient value from DICOM source rather than the segmentation
result.SharedFunctionalGroupsSequence[0].PlaneOrientationSequence[
0].ImageOrientationPatient = source_images[
0].ImageOrientationPatient
buffer = sitk.GetArrayFromImage(segmentation)
for segment in labels_to_process:
logger.info(f"Processing segment {segment}")
if self._skip_empty_slices:
bbox = bboxs[segment]
min_z, max_z = bbox[4], bbox[5] + 1
else:
min_z, max_z = 0, segmentation.GetDepth()
logger.info(
"Total number of slices that will be processed for segment "
f"{segment} is {max_z - min_z} (inclusive from {min_z} to {max_z})"
)
skipped_slices = []
for slice_idx in range(min_z, max_z):
frame_index = (min_x, min_y, slice_idx)
frame_position = segmentation.TransformIndexToPhysicalPoint(
frame_index)
frame_data = np.equal(
buffer[slice_idx, min_y:max_y, min_x:max_x], segment)
if self._skip_empty_slices and not frame_data.any():
skipped_slices.append(slice_idx)
continue
frame_fg_item = result.add_frame(
data=frame_data.astype(np.uint8),
referenced_segment=segment,
referenced_images=slice_to_source_images[slice_idx],
)
frame_fg_item.FrameContentSequence = [pydicom.Dataset()]
frame_fg_item.FrameContentSequence[0].DimensionIndexValues = [
segment, # Segment number
slice_idx - min_z + 1, # Slice index within cropped volume
]
frame_fg_item.PlanePositionSequence = [pydicom.Dataset()]
frame_fg_item.PlanePositionSequence[0].ImagePositionPatient = [
f"{x:e}" for x in frame_position
]
if skipped_slices:
logger.info(f"Skipped empty slices for segment {segment}: "
f'{", ".join([str(x) for x in skipped_slices])}')
# Encode all frames into a bytearray
if self._inplane_cropping or self._skip_empty_slices:
num_encoded_bytes = len(result.PixelData)
max_encoded_bytes = (segmentation.GetWidth() *
segmentation.GetHeight() *
segmentation.GetDepth() *
len(result.SegmentSequence) // 8)
savings = (1 - num_encoded_bytes / max_encoded_bytes) * 100
logger.info(
f"Optimized frame data length is {num_encoded_bytes:,}B "
f"instead of {max_encoded_bytes:,}B (saved {savings:.2f}%)")
result.SegmentsOverlap = "NO"
return result
def test_add_multiple_dimensions_copies_same_organization_uid(self) -> None:
seq = DimensionOrganizationSequence()
seq.add_dimension("ReferencedSegmentNumber", "SegmentIdentificationSequence")
seq.add_dimension("ImagePositionPatient", "PlanePositionSequence")
assert len(seq) == 2
assert seq[0].DimensionOrganizationUID == seq[1].DimensionOrganizationUID