def _extract_patches(self, image, label, patch_size, step):
transforms_ = transforms.Compose(
[PadToPatchShape(patch_size=patch_size, step=step)])
transformed_image = transforms_(image)
transformed_label = transforms_(label)
return ABIDEPreprocessingPipeline.get_filtered_patches(
transformed_image, transformed_label, patch_size, step)
def _extract_patches(self, image, label, patch_size, step):
transforms_ = transforms.Compose(
[PadToPatchShape(patch_size=patch_size, step=step)])
transformed_image = transforms_(image)
transformed_label = transforms_(label)
return MultipleDatasetPipeline.get_filtered_patches(
transformed_image, transformed_label, patch_size, step)
def setUp(self) -> None:
paths = extract_file_paths(self.PATH)
self._dataset = MRBrainSSegmentationFactory.create(
natural_sort(paths), None, modalities=Modality.T1, dataset_id=0)
self._reconstructor = ImageReconstructor([256, 256, 192],
[1, 32, 32, 32], [1, 8, 8, 8])
transforms = Compose(
[ToNumpyArray(),
PadToPatchShape([1, 32, 32, 32], [1, 8, 8, 8])])
self._full_image = transforms(self.FULL_IMAGE_PATH)
def _extract_patches(self, image, subject, modality, patch_size, step):
transforms_ = transforms.Compose(
[PadToPatchShape(patch_size=patch_size, step=step)])
transformed_image = transforms_(image)
patches = ABIDEPreprocessingPipeline.get_patches(
transformed_image, patch_size, step)
for i, patch in enumerate(patches):
x = transformed_image.x[tuple(patch.slice)]
transform_ = transforms.Compose([
ToNifti1Image(),
NiftiToDisk(
os.path.join(
os.path.join(self._output_dir, subject, "mri",
"patches", modality),
str(i) + ".nii.gz"))
])
transform_(x)
def _extract_patches(self, image, subject, modality, patch_size, step):
transforms_ = transforms.Compose(
[PadToPatchShape(patch_size=patch_size, step=step)])
transformed_image = transforms_(image)
patches = iSEGPipeline.get_patches(transformed_image, patch_size, step)
if not os.path.exists(os.path.join(self._output_dir, subject,
modality)):
os.makedirs(os.path.join(self._output_dir, subject, modality))
for i, patch in enumerate(patches):
x = transformed_image[tuple(patch.slice)]
transforms_ = transforms.Compose([
ToNifti1Image(),
NiftiToDisk(
os.path.join(self._output_dir, subject, modality,
str(i) + ".nii.gz"))
])
transforms_(x)
def setUp(self) -> None:
transforms = Compose(
[ToNumpyArray(),
PadToPatchShape((1, 32, 32, 32), (1, 8, 8, 8))])
self._image = transforms(self.FULL_IMAGE_PATH)
self._target = transforms(self.TARGET_PATH)
patches = iSEGSliceDatasetFactory.get_patches([self._image],
[self._target],
(1, 32, 32, 32),
(1, 16, 16, 16))
self._dataset = iSEGSliceDatasetFactory.create(
[self._image], [self._target],
patches,
Modality.T1,
0,
transforms=[ToNDTensor()])
self._reconstructor = ImageReconstructor([256, 192, 160],
[1, 32, 32, 32],
[1, 16, 16, 16],
models=None,
test_image=self._image)
def pad_to_shape(image, patch_size, step):
transforms_ = transforms.Compose(
[PadToPatchShape(patch_size=patch_size, step=step)])
return transforms_(image)