def add_label_stats_to_dataframe(input_dataframe: pd.DataFrame,
dataset_root_directory: Path,
target_label_names: List[str]) -> pd.DataFrame:
"""
Loops through all available subject IDs, generates ground-truth label statistics and updates input dataframe
with the computed stats by adding new columns. In particular, it checks the overlapping regions between
different structures and volume of labels.
:param input_dataframe: Input Pandas dataframe object containing subjectIds and label names
:param dataset_root_directory: Path to dataset root directory
:param target_label_names: A list of label names that are used in label stat computations
"""
dataset_sources = load_dataset_sources(input_dataframe,
local_dataset_root_folder=dataset_root_directory,
image_channels=["ct"],
ground_truth_channels=target_label_names,
mask_channel=None)
# Iterate over subjects and check overlapping labels
for subject_id in [*dataset_sources.keys()]:
labels = io_util.load_labels_from_dataset_source(dataset_sources[subject_id])
overlap_stats = metrics_util.get_label_overlap_stats(labels=labels[1:, ...],
label_names=target_label_names)
header = io_util.load_nifti_image(dataset_sources[subject_id].ground_truth_channels[0]).header
volume_stats = metrics_util.get_label_volume(labels=labels[1:, ...],
label_names=target_label_names,
label_spacing=header.spacing)
# Log the extracted label statistics
for col_name, col_stats in zip(("LabelOverlap", "LabelVolume (mL)"), (overlap_stats, volume_stats)):
input_dataframe.loc[input_dataframe.subject == subject_id, col_name] = \
input_dataframe.loc[input_dataframe.subject == subject_id, "channel"].map(col_stats)
return input_dataframe
def test_get_label_overlap_stats() -> None:
"""
Test of the computed label overlap stats are computed
as expected.
"""
test_data = {'spleen': np.array([[0, 1], [1, 1]]),
'liver': np.array([[0, 1], [1, 0]]),
'prostate': np.array([[0, 0], [0, 1]]),
'bladder': np.array([[1, 0], [0, 0]])}
label_overlap_stats = get_label_overlap_stats(labels=np.stack(test_data.values()),
label_names=list(test_data.keys()))
assert label_overlap_stats['spleen'] == 3
assert label_overlap_stats['liver'] == 2
assert label_overlap_stats['prostate'] == 1
assert label_overlap_stats['bladder'] == 0