def _test_load_images_from_channels(
metadata: Any,
image_channel: Any,
ground_truth_channel: Any,
mask_channel: Any) -> None:
"""
Test if images are loaded as expected from channels
"""
sample = io_util.load_images_from_dataset_source(
PatientDatasetSource(
metadata=metadata,
image_channels=[image_channel] * 2,
ground_truth_channels=[ground_truth_channel] * 4,
mask_channel=mask_channel
)
)
if image_channel:
image_with_header = io_util.load_image(image_channel)
assert list(sample.image.shape) == [2] + list(image_with_header.image.shape)
assert all([np.array_equal(x, image_with_header.image) for x in sample.image]) # type: ignore
if mask_channel:
assert np.array_equal(sample.mask, image_with_header.image)
if ground_truth_channel:
assert list(sample.labels.shape) == [5] + list(image_with_header.image.shape)
assert np.all(sample.labels[0] == 0) and np.all(sample.labels[1:] == 1)
def load_train_and_test_data_channels(
patient_ids: List[int],
normalization_fn: PhotometricNormalization) -> List[Sample]:
if np.any(np.asarray(patient_ids) <= 0):
raise ValueError("data_items must be >= 0")
file_name = lambda k, y: full_ml_test_data_path("train_and_test_data"
) / f"id{k}_{y}.nii.gz"
get_sample = lambda z: io_util.load_images_from_dataset_source(
dataset_source=PatientDatasetSource(
metadata=PatientMetadata(patient_id=z),
image_channels=[file_name(z, c) for c in TEST_CHANNEL_IDS],
mask_channel=file_name(z, TEST_MASK_ID),
ground_truth_channels=[file_name(z, TEST_GT_ID)]))
samples = []
for x in patient_ids:
sample = get_sample(x)
sample = Sample(image=normalization_fn.transform(
sample.image, sample.mask),
mask=sample.mask,
labels=sample.labels,
metadata=sample.metadata)
samples.append(sample)
return samples
def get_samples_at_index(self, index: int) -> List[Sample]:
# load the channels into memory
ds = self.dataset_sources[self.dataset_indices[index]]
samples = [io_util.load_images_from_dataset_source(dataset_source=ds)
] # type: ignore
return [
Compose3D.apply(self.full_image_sample_transforms, x)
for x in samples
]
def main(yaml_file_path: Path) -> None:
"""
Invoke either by
* specifying a model, '--model Lung'
* or specifying dataset and normalization parameters separately: --azure_dataset_id=foo --norm_method=None
In addition, the arguments '--image_channel' and '--gt_channel' must be specified (see below).
"""
config, runner_config, args = get_configs(
SegmentationModelBase(should_validate=False), yaml_file_path)
dataset_config = DatasetConfig(name=config.azure_dataset_id,
local_folder=config.local_dataset,
use_mounting=True)
local_dataset, mount_context = dataset_config.to_input_dataset_local(
workspace=runner_config.get_workspace())
dataframe = pd.read_csv(local_dataset / DATASET_CSV_FILE_NAME)
normalizer_config = NormalizeAndVisualizeConfig(**args)
actual_mask_channel = None if normalizer_config.ignore_mask else config.mask_id
image_channel = normalizer_config.image_channel or config.image_channels[0]
if not image_channel:
raise ValueError(
"No image channel selected. Specify a model by name, or use the image_channel argument."
)
gt_channel = normalizer_config.gt_channel or config.ground_truth_ids[0]
if not gt_channel:
raise ValueError(
"No GT channel selected. Specify a model by name, or use the gt_channel argument."
)
dataset_sources = load_dataset_sources(
dataframe,
local_dataset_root_folder=local_dataset,
image_channels=[image_channel],
ground_truth_channels=[gt_channel],
mask_channel=actual_mask_channel)
result_folder = local_dataset
if normalizer_config.result_folder is not None:
result_folder = result_folder / normalizer_config.result_folder
if not result_folder.is_dir():
result_folder.mkdir()
all_patient_ids = [*dataset_sources.keys()]
if normalizer_config.only_first == 0:
patient_ids_to_process = all_patient_ids
else:
patient_ids_to_process = all_patient_ids[:normalizer_config.only_first]
args_file = result_folder / ARGS_TXT
args_file.write_text(" ".join(sys.argv[1:]))
config_file = result_folder / "config.txt"
config_file.write_text(str(config))
normalizer = PhotometricNormalization(config)
for patient_id in patient_ids_to_process:
print(f"Starting to process patient {patient_id}")
images = load_images_from_dataset_source(dataset_sources[patient_id])
plotting.plot_normalization_result(images,
normalizer,
result_folder,
result_prefix=image_channel)
def get_samples_at_index(self, index: int) -> List[Sample]:
# load the channels into memory
if not self._is_nifti_dataset():
raise ValueError(
"Unknown file extension. Files should be Nifti or HDF5 format but found "
+ self.file_extension)
ds = self.dataset_sources[self.dataset_indices[index]]
samples = [io_util.load_images_from_dataset_source(dataset_source=ds)
] # type: ignore
return [
Compose3D.apply(self.full_image_sample_transforms, x)
for x in samples
]
