def get_train_transform(landmarks_path, resection_params=None):
spatial_transform = tio.Compose((
tio.OneOf({
tio.RandomAffine(): 0.9,
tio.RandomElasticDeformation(): 0.1,
}),
tio.RandomFlip(),
))
resolution_transform = tio.OneOf(
(
tio.RandomAnisotropy(),
tio.RandomBlur(),
),
p=0.75,
)
transforms = []
if resection_params is not None:
transforms.append(get_simulation_transform(resection_params))
if landmarks_path is not None:
transforms.append(
tio.HistogramStandardization({'image': landmarks_path}))
transforms.extend([
# tio.RandomGamma(p=0.2),
resolution_transform,
tio.RandomGhosting(p=0.2),
tio.RandomSpike(p=0.2),
tio.RandomMotion(p=0.2),
tio.RandomBiasField(p=0.5),
tio.ZNormalization(masking_method=tio.ZNormalization.mean),
tio.RandomNoise(p=0.75), # always after ZNorm and after blur!
spatial_transform,
get_tight_crop(),
])
return tio.Compose(transforms)
def test_transforms(self):
landmarks_dict = dict(
t1=np.linspace(0, 100, 13),
t2=np.linspace(0, 100, 13),
)
elastic = torchio.RandomElasticDeformation(max_displacement=1)
transforms = (
torchio.CropOrPad((9, 21, 30)),
torchio.ToCanonical(),
torchio.Resample((1, 1.1, 1.25)),
torchio.RandomFlip(axes=(0, 1, 2), flip_probability=1),
torchio.RandomMotion(),
torchio.RandomGhosting(axes=(0, 1, 2)),
torchio.RandomSpike(),
torchio.RandomNoise(),
torchio.RandomBlur(),
torchio.RandomSwap(patch_size=2, num_iterations=5),
torchio.Lambda(lambda x: 2 * x, types_to_apply=torchio.INTENSITY),
torchio.RandomBiasField(),
torchio.RescaleIntensity((0, 1)),
torchio.ZNormalization(masking_method='label'),
torchio.HistogramStandardization(landmarks_dict=landmarks_dict),
elastic,
torchio.RandomAffine(),
torchio.OneOf({
torchio.RandomAffine(): 3,
elastic: 1
}),
torchio.Pad((1, 2, 3, 0, 5, 6), padding_mode='constant', fill=3),
torchio.Crop((3, 2, 8, 0, 1, 4)),
)
transform = torchio.Compose(transforms)
transform(self.sample)
def get_test_transform(landmarks_path):
transforms = []
if landmarks_path is not None:
transforms.append(tio.HistogramStandardization({'image': landmarks_path}))
transforms.extend([
tio.ZNormalization(masking_method=tio.ZNormalization.mean),
get_tight_crop(),
])
return tio.Compose(transforms)
def get_dataset(
input_path,
tta_iterations=0,
interpolation='bspline',
tolerance=0.1,
mni_transform_path=None,
):
if mni_transform_path is None:
image = tio.ScalarImage(input_path)
else:
affine = tio.io.read_matrix(mni_transform_path)
image = tio.ScalarImage(input_path, **{TO_MNI: affine})
subject = tio.Subject({IMAGE_NAME: image})
landmarks = np.array([
0., 0.31331614, 0.61505419, 0.76732501, 0.98887953, 1.71169384,
3.21741126, 13.06931455, 32.70817796, 40.87807389, 47.83508873,
63.4408591, 100.
])
hist_std = tio.HistogramStandardization({IMAGE_NAME: landmarks})
preprocess_transforms = [
tio.ToCanonical(),
hist_std,
tio.ZNormalization(masking_method=tio.ZNormalization.mean),
]
zooms = nib.load(input_path).header.get_zooms()
pixdim = np.array(zooms)
diff_to_1_iso = np.abs(pixdim - 1)
if np.any(diff_to_1_iso > tolerance) or mni_transform_path is not None:
kwargs = {'image_interpolation': interpolation}
if mni_transform_path is not None:
kwargs['pre_affine_name'] = TO_MNI
kwargs['target'] = tio.datasets.Colin27().t1.path
resample_transform = tio.Resample(**kwargs)
preprocess_transforms.append(resample_transform)
preprocess_transforms.append(tio.EnsureShapeMultiple(8, method='crop'))
preprocess_transform = tio.Compose(preprocess_transforms)
no_aug_dataset = tio.SubjectsDataset([subject],
transform=preprocess_transform)
aug_subjects = tta_iterations * [subject]
if not aug_subjects:
return no_aug_dataset
augment_transform = tio.Compose((
preprocess_transform,
tio.RandomFlip(),
tio.RandomAffine(image_interpolation=interpolation),
))
aug_dataset = tio.SubjectsDataset(aug_subjects,
transform=augment_transform)
dataset = torch.utils.data.ConcatDataset((no_aug_dataset, aug_dataset))
return dataset
def get_transform(self, channels, is_3d=True, labels=True):
landmarks_dict = {
channel: np.linspace(0, 100, 13)
for channel in channels
}
disp = 1 if is_3d else (1, 1, 0.01)
elastic = tio.RandomElasticDeformation(max_displacement=disp)
cp_args = (9, 21, 30) if is_3d else (21, 30, 1)
resize_args = (10, 20, 30) if is_3d else (10, 20, 1)
flip_axes = axes_downsample = (0, 1, 2) if is_3d else (0, 1)
swap_patch = (2, 3, 4) if is_3d else (3, 4, 1)
pad_args = (1, 2, 3, 0, 5, 6) if is_3d else (0, 0, 3, 0, 5, 6)
crop_args = (3, 2, 8, 0, 1, 4) if is_3d else (0, 0, 8, 0, 1, 4)
remapping = {1: 2, 2: 1, 3: 20, 4: 25}
transforms = [
tio.CropOrPad(cp_args),
tio.EnsureShapeMultiple(2, method='crop'),
tio.Resize(resize_args),
tio.ToCanonical(),
tio.RandomAnisotropy(downsampling=(1.75, 2), axes=axes_downsample),
tio.CopyAffine(channels[0]),
tio.Resample((1, 1.1, 1.25)),
tio.RandomFlip(axes=flip_axes, flip_probability=1),
tio.RandomMotion(),
tio.RandomGhosting(axes=(0, 1, 2)),
tio.RandomSpike(),
tio.RandomNoise(),
tio.RandomBlur(),
tio.RandomSwap(patch_size=swap_patch, num_iterations=5),
tio.Lambda(lambda x: 2 * x, types_to_apply=tio.INTENSITY),
tio.RandomBiasField(),
tio.RescaleIntensity(out_min_max=(0, 1)),
tio.ZNormalization(),
tio.HistogramStandardization(landmarks_dict),
elastic,
tio.RandomAffine(),
tio.OneOf({
tio.RandomAffine(): 3,
elastic: 1,
}),
tio.RemapLabels(remapping=remapping, masking_method='Left'),
tio.RemoveLabels([1, 3]),
tio.SequentialLabels(),
tio.Pad(pad_args, padding_mode=3),
tio.Crop(crop_args),
]
if labels:
transforms.append(tio.RandomLabelsToImage(label_key='label'))
return tio.Compose(transforms)
def main():
# SubjectsDataset()
# show_subject(tio.ToCanonical()(one_subject), 'mri', label_name='brain')
dataset_dir_name = r'C:\Pycharmclass\NetworkProgramming\Torch\Data\ixi_tiny'
dataset_dir = Path(dataset_dir_name)
images_dir = dataset_dir / 'image'
labels_dir = dataset_dir / 'label'
image_paths = sorted(images_dir.glob('*.nii.gz'))
#histogram(image_paths, compute_histograms=True)
dataset, subject = SubjectsDataset()
one_subject = dataset[0]
# print(one_subject)
# print(one_subject.mri)
# show_sample(tio.ToCanonical()(one_subject), 'mri', label_name='brain')
# show_sample(one_subject, 'mri', label_name='brain')
save_image(one_subject, 'mri', 'jimin.nii.gz')
#trained(image_paths)
landmarks = np.load(
"C:\\Pycharmclass\\NetworkProgramming\\Torch\\Data\\landmarks.npy")
landmarks_dict = {'mri': landmarks}
histogram_transform = tio.HistogramStandardization(landmarks_dict)
#landmarks_histogram(dataset, landmarks, compute_histograms=True)
#normalization(histogram_transform, dataset)
training_network(landmarks, dataset, subject)
training_set, validation_set = training_network(landmarks, dataset,
subject)
# learning_stuff1(training_set)
# learning_stuff2(validation_set)
whole_images(training_set, validation_set)
def get_transform(self, channels, is_3d=True, labels=True):
landmarks_dict = {
channel: np.linspace(0, 100, 13)
for channel in channels
}
disp = 1 if is_3d else (1, 1, 0.01)
elastic = torchio.RandomElasticDeformation(max_displacement=disp)
cp_args = (9, 21, 30) if is_3d else (21, 30, 1)
flip_axes = axes_downsample = (0, 1, 2) if is_3d else (0, 1)
swap_patch = (2, 3, 4) if is_3d else (3, 4, 1)
pad_args = (1, 2, 3, 0, 5, 6) if is_3d else (0, 0, 3, 0, 5, 6)
crop_args = (3, 2, 8, 0, 1, 4) if is_3d else (0, 0, 8, 0, 1, 4)
transforms = [
torchio.CropOrPad(cp_args),
torchio.ToCanonical(),
torchio.RandomDownsample(downsampling=(1.75, 2),
axes=axes_downsample),
torchio.Resample((1, 1.1, 1.25)),
torchio.RandomFlip(axes=flip_axes, flip_probability=1),
torchio.RandomMotion(),
torchio.RandomGhosting(axes=(0, 1, 2)),
torchio.RandomSpike(),
torchio.RandomNoise(),
torchio.RandomBlur(),
torchio.RandomSwap(patch_size=swap_patch, num_iterations=5),
torchio.Lambda(lambda x: 2 * x, types_to_apply=torchio.INTENSITY),
torchio.RandomBiasField(),
torchio.RescaleIntensity((0, 1)),
torchio.ZNormalization(),
torchio.HistogramStandardization(landmarks_dict),
elastic,
torchio.RandomAffine(),
torchio.OneOf({
torchio.RandomAffine(): 3,
elastic: 1,
}),
torchio.Pad(pad_args, padding_mode=3),
torchio.Crop(crop_args),
]
if labels:
transforms.append(torchio.RandomLabelsToImage(label_key='label'))
return torchio.Compose(transforms)
def landmarks_histogram(dataset, landmarks, compute_histograms):
landmarks_dict = {'mri': landmarks}
histogram_transform = tio.HistogramStandardization(landmarks_dict)
if compute_histograms:
fig, ax = plt.subplots(dpi=100)
for i, sample in enumerate(tqdm(dataset)):
standard = histogram_transform(sample)
tensor = standard.mri.data
path = str(sample.mri.path)
if 'HH' in path: color = 'red'
elif 'Guys' in path: color = 'green'
elif 'IOP' in path: color = 'blue'
plot_histogram(ax, tensor, color=color)
ax.set_xlim(0, 150)
ax.set_ylim(0, 0.02)
ax.set_title(
'Intensity values of all samples after histogram standardization')
ax.set_xlabel('Intensity')
ax.grid()
plt.show()
ax.show()
one_subject = dataset[430]
print(one_subject)
print(one_subject.mri)
#Normalisation
landmarks = tio.HistogramStandardization.train(
image_paths,
output_path=histogram_landmarks_path,
)
np.set_printoptions(suppress=True, precision=3)
print('\nTrained landmarks:', landmarks)
#Histogram standardisation
#Hist standardization
landmarks_dict = {'mri': landmarks}
histogram_transform = tio.HistogramStandardization(landmarks_dict)
#Z-Norm
znorm_transform = tio.ZNormalization(masking_method=tio.ZNormalization.mean)
sample = dataset[0]
transform = tio.Compose([histogram_transform, znorm_transform])
znormed = transform(sample)
fig, ax = plt.subplots(dpi=100)
plot_histogram(ax, znormed.mri.data, label='Z-normed', alpha=1)
ax.set_title('Intensity values of one sample after z-normalization')
ax.set_xlabel('Intensity')
ax.grid()
training_transform = Compose([