def test_transforms(self):
landmarks_dict = dict(
t1=np.linspace(0, 100, 13),
t2=np.linspace(0, 100, 13),
)
transforms = (
CenterCropOrPad((9, 21, 30)),
ToCanonical(),
Resample((1, 1.1, 1.25)),
RandomFlip(axes=(0, 1, 2), flip_probability=1),
RandomMotion(proportion_to_augment=1),
RandomGhosting(proportion_to_augment=1, axes=(0, 1, 2)),
RandomSpike(),
RandomNoise(),
RandomBlur(),
RandomSwap(patch_size=2, num_iterations=5),
Lambda(lambda x: 1.5 * x, types_to_apply=INTENSITY),
RandomBiasField(),
Rescale((0, 1)),
ZNormalization(masking_method='label'),
HistogramStandardization(landmarks_dict=landmarks_dict),
RandomElasticDeformation(proportion_to_augment=1),
RandomAffine(),
Pad((1, 2, 3, 0, 5, 6)),
Crop((3, 2, 8, 0, 1, 4)),
)
transformed = self.get_sample()
for transform in transforms:
transformed = transform(transformed)
def mri_artifact(p=1):
return OneOf(
{
RandomMotion(): 0.34,
RandomGhosting(): 0.33,
RandomSpike(): 0.33
},
p=p)
def test_reproducibility_compose(self):
trsfm = Compose([RandomNoise(p=0.0), RandomSpike(num_spikes=3, p=1.0)])
subject1, subject2 = self.get_subjects()
transformed1 = trsfm(subject1)
history1 = transformed1.history
trsfm_hist, seeds_hist = compose_from_history(history=history1)
transformed2 = self.apply_transforms(subject2,
trsfm_list=trsfm_hist,
seeds_list=seeds_hist)
data1, data2 = transformed1.img.data, transformed2.img.data
self.assertTensorEqual(data1, data2)
def compose_transforms() -> Compose:
print(f"{ctime()}: Setting up transformations...")
"""
# Our Preprocessing Options available in TorchIO are:
* Intensity
- NormalizationTransform
- RescaleIntensity
- ZNormalization
- HistogramStandardization
* Spatial
- CropOrPad
- Crop
- Pad
- Resample
- ToCanonical
We should read and experiment with these, but for now will just use a bunch with
the default values.
"""
preprocessors = [
ToCanonical(p=1),
ZNormalization(masking_method=None,
p=1), # alternately, use RescaleIntensity
]
"""
# Our Augmentation Options available in TorchIO are:
* Spatial
- RandomFlip
- RandomAffine
- RandomElasticDeformation
* Intensity
- RandomMotion
- RandomGhosting
- RandomSpike
- RandomBiasField
- RandomBlur
- RandomNoise
- RandomSwap
We should read and experiment with these, but for now will just use a bunch with
the default values.
"""
augments = [
RandomFlip(axes=(0, 1, 2), flip_probability=0.5),
RandomAffine(image_interpolation="linear",
p=0.8), # default, compromise on speed + quality
# this will be most processing intensive, leave out for now, see results
# RandomElasticDeformation(p=1),
RandomMotion(),
RandomSpike(),
RandomBiasField(),
RandomBlur(),
RandomNoise(),
]
transform = Compose(preprocessors + augments)
print(f"{ctime()}: Transformations registered.")
return transform
def mri_artifact(parameters):
return OneOf(
{RandomGhosting(): 0.5, RandomSpike(): 0.5},
p=parameters["probability"],
)
}
t = RandomMotionFromTimeCourse(**dico_params)
t._calc_dimensions((100,20,50))
fitP = t._simulate_random_trajectory()
fitP = t.fitpars
if True:# y_Disp>0:
plt.figure()
plt.plot(fit_pars.T)
plt.plot(fitP.T,'--')
#test transforms
from torchio.transforms import RandomSpike
t = RandomSpike(num_spikes_range=(5,10), intensity_range=(0.1,0.2))
dataset = ImagesDataset(suj, transform=t)
for i in range(1,10):
sample = dataset[0]
fout='/tmp/toto{}_nb{}_I{}.nii'.format(i,sample['T1']['random_spike_num_spikes'],np.floor(sample['T1']['random_spike_intensity']*100))
dataset.save_sample(sample, dict(T1=fout))
out_dir = '/data/ghiles/motion_simulation/tests/'
def corrupt_data(data, percentage):
n_pts_to_corrupt = int(round(percentage * len(data)))