def test_transforms(self):
landmarks_dict = dict(
t1=np.linspace(0, 100, 13),
t2=np.linspace(0, 100, 13),
)
random_transforms = (
RandomFlip(axes=(0, 1, 2), flip_probability=1),
RandomNoise(),
RandomBiasField(),
RandomElasticDeformation(proportion_to_augment=1),
RandomAffine(),
RandomMotion(proportion_to_augment=1),
)
intensity_transforms = (
Rescale(),
ZNormalization(),
HistogramStandardization(landmarks_dict=landmarks_dict),
)
for transform in random_transforms:
sample = self.get_sample()
transformed = transform(sample)
for transform in intensity_transforms:
sample = self.get_sample()
transformed = transform(sample)
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 initialize_transforms_simple(p=0.8):
transforms = [
RandomFlip(axes=(0, 1, 2), flip_probability=1, p=p),
#RandomAffine(scales=(0.9, 1.1), degrees=(10), isotropic=False,
# default_pad_value='otsu', image_interpolation=Interpolation.LINEAR,
# p = p, seed=None),
# *** SLOWS DOWN DATALOADER ***
#RandomElasticDeformation(num_control_points = 7, max_displacement = 7.5,
# locked_borders = 2, image_interpolation = Interpolation.LINEAR,
# p = 0.5, seed = None),
RandomMotion(degrees=10,
translation=10,
num_transforms=2,
image_interpolation='linear',
p=p),
RandomAnisotropy(axes=(0, 1, 2), downsampling=2),
RandomBiasField(coefficients=0.5, order=3, p=p),
RandomBlur(std=(0, 2), p=p),
RandomNoise(mean=0, std=(0, 5), p=p),
RescaleIntensity((0, 255))
]
transform = tio.Compose(transforms)
return transform
def mri_artifact(p=1):
return OneOf(
{
RandomMotion(): 0.34,
RandomGhosting(): 0.33,
RandomSpike(): 0.33
},
p=p)
def motion(parameters):
return RandomMotion(
degrees=parameters["degrees"],
translation=parameters["translation"],
num_transforms=parameters["num_transforms"],
image_interpolation=parameters["interpolation"],
p=parameters["probability"],
)
def _get_default_transforms(self):
io_transforms = Compose([
RandomMotion(),
RandomFlip(axes=(1, )),
RandomAffine(scales=(0.9, 1.2),
degrees=(10),
isotropic=False,
default_pad_value='otsu',
image_interpolation='bspline'),
RescaleIntensity((0, 1))
])
return io_transforms
def transform(self):
if hp.mode == '3d':
training_transform = Compose([
# ToCanonical(),
CropOrPad((hp.crop_or_pad_size, hp.crop_or_pad_size,
hp.crop_or_pad_size),
padding_mode='reflect'),
RandomMotion(),
RandomBiasField(),
ZNormalization(),
RandomNoise(),
RandomFlip(axes=(0, )),
OneOf({
RandomAffine(): 0.8,
RandomElasticDeformation(): 0.2,
}),
])
elif hp.mode == '2d':
training_transform = Compose([
CropOrPad((hp.crop_or_pad_size, hp.crop_or_pad_size, 1),
padding_mode='reflect'),
RandomMotion(),
RandomBiasField(),
ZNormalization(),
RandomNoise(),
RandomFlip(axes=(0, )),
OneOf({
RandomAffine(): 0.8,
RandomElasticDeformation(): 0.2,
}),
])
else:
raise Exception('no such kind of mode!')
return training_transform
def training_network(landmarks, dataset, subjects):
training_transform = Compose([
ToCanonical(),
Resample(4),
CropOrPad((48, 60, 48), padding_mode='reflect'),
RandomMotion(),
HistogramStandardization({'mri': landmarks}),
RandomBiasField(),
ZNormalization(masking_method=ZNormalization.mean),
RandomNoise(),
RandomFlip(axes=(0, )),
OneOf({
RandomAffine(): 0.8,
RandomElasticDeformation(): 0.2,
}),
])
validation_transform = Compose([
ToCanonical(),
Resample(4),
CropOrPad((48, 60, 48), padding_mode='reflect'),
HistogramStandardization({'mri': landmarks}),
ZNormalization(masking_method=ZNormalization.mean),
])
training_split_ratio = 0.9
num_subjects = len(dataset)
num_training_subjects = int(training_split_ratio * num_subjects)
training_subjects = subjects[:num_training_subjects]
validation_subjects = subjects[num_training_subjects:]
training_set = tio.SubjectsDataset(training_subjects,
transform=training_transform)
validation_set = tio.SubjectsDataset(validation_subjects,
transform=validation_transform)
print('Training set:', len(training_set), 'subjects')
print('Validation set:', len(validation_set), 'subjects')
return training_set, validation_set
test = {'T1': {'csv_file':'/data/romain/HCPdata/Motion_brain_ms_train_hcp400.csv'} }
conditions = [("corr", "<", 0.98), ("|", "noise", "==", 1)]
subjects_dict, info = get_subject_list_and_csv_info_from_data_prameters(test, fpath_idx='filename', conditions=conditions,shuffle_order=True)
data_parameters = {'image': {'csv_file': '/data/romain/data_exemple/file_ms.csv', 'type': torchio.INTENSITY},
'label1': {'csv_file': '/data/romain/data_exemple/file_p1.csv', 'type': torchio.LABEL},
'label2': {'csv_file': '/data/romain/data_exemple/file_p2.csv', 'type': torchio.LABEL},
'label3': {'csv_file': '/data/romain/data_exemple/file_p3.csv', 'type': torchio.LABEL},
'sampler': {'csv_file': '/data/romain/data_exemple/file_mask.csv', 'type': torchio.SAMPLING_MAP}}
paths_dict, info = get_subject_list_and_csv_info_from_data_prameters(data_parameters) #,shuffle_order=False)
landmarks_file = '/data/romain/data_exemple/landmarks_hcp100.npy'
transforms = (HistogramStandardization(landmarks_file, mask_field_name='sampler'),)
transforms = (RandomElasticDeformation(num_control_points=8, proportion_to_augment=1, deformation_std=25, image_interpolation=Interpolation.BSPLINE),)
transforms = (RandomMotion(seed=42, degrees=0, translation=15, num_transforms=2, verbose=True,proportion_to_augment=1),)
transforms = (RandomBiasField(coefficients_range=(-0.5, 0.5),order=3), )
transform = Compose(transforms) #should be done in ImagesDataset
dataset = ImagesDataset(paths_dict, transform=transform)
dataset_not = ImagesDataset(paths_dict, transform=None)
dataload = torch.utils.data.DataLoader(dataset, num_workers=0, batch_size=1)
dataloadnot = torch.utils.data.DataLoader(dataset_not, num_workers=0, batch_size=1)
ddd = dataset[0] #next(iter(dataset))
ii = np.squeeze( ddd['image']['data'][0], axis=1)
ddno = dataset_not[0] #
dd= next(iter(dataload))
ddno = next(iter(dataloadnot))
def get_data_loader(cfg: DictConfig, _) -> dict:
log = logging.getLogger(__name__)
transform = Compose([
RandomMotion(),
RandomBiasField(),
RandomNoise(),
RandomFlip(axes=(0, )),
])
log.info(f"Data loader selected: {cfg['dataset']}")
try:
log.info("Attempting to use defined data loader")
dataset = getattr(datasets, cfg["dataset"])(cfg, transform)
except ImportError:
log.info(
"Not a defined data loader... Attempting to use torchio loader")
dataset = getattr(torchio.datasets,
cfg["dataset"])(root=cfg["base_path"],
transform=transform,
download=True)
for subject in random.sample(dataset._subjects, cfg["plot_number"]):
plot_subject(
subject,
os.path.join(os.environ["OUTPUT_PATH"], cfg["save_plot_dir"],
subject["subject_id"]),
)
sampler = GridSampler(patch_size=cfg["patch_size"])
samples_per_volume = len(sampler._compute_locations(
dataset[0])) # type: ignore
with open_dict(cfg):
cfg["size"] = dataset[0].spatial_shape
val_size = max(1, int(0.2 * len(dataset)))
test_set, train_set, val_set = split_dataset(
dataset, [21, len(dataset) - val_size - 21, val_size])
train_loader = __create_data_loader(
train_set,
queue_max_length=samples_per_volume * cfg["queue_length"],
queue_samples_per_volume=samples_per_volume,
sampler=sampler,
verbose=log.level > 0,
batch_size=cfg["batch"],
)
val_loader = __create_data_loader(
val_set,
queue_max_length=samples_per_volume * cfg["queue_length"],
queue_samples_per_volume=samples_per_volume,
sampler=sampler,
verbose=log.level > 0,
batch_size=cfg["batch"],
)
test_loader = __create_data_loader(
test_set,
queue_max_length=samples_per_volume * cfg["queue_length"],
queue_samples_per_volume=samples_per_volume,
sampler=sampler,
verbose=log.level > 0,
batch_size=cfg["batch"],
)
return {
"data_loader_train": train_loader,
"data_loader_val": val_loader,
"data_loader_test": test_loader,
}
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 define_transform(transform,
p,
blur_std=4,
motion_trans=10,
motion_deg=10,
motion_num=2,
biascoeff=0.5,
noise_std=0.25,
affine_trans=10,
affine_deg=10,
elastic_disp=7.5,
resample_size=1,
target_shape=0):
### (1) try with different blur
if transform == 'blur':
transforms = [RandomBlur(std=(blur_std, blur_std), p=p, seed=None)]
transforms = Compose(transforms)
### (2) try with different motion artifacts
if transform == 'motion':
transforms = [
RandomMotion(degrees=motion_deg,
translation=motion_trans,
num_transforms=motion_num,
image_interpolation=Interpolation.LINEAR,
p=p,
seed=None),
]
transforms = Compose(transforms)
### (3) with random bias fields
if transform == 'biasfield':
transforms = [
RandomBiasField(coefficients=biascoeff, order=3, p=p, seed=None)
]
transforms = Compose(transforms)
### (4) try with different noise artifacts
if transform == 'noise':
transforms = [
RandomNoise(mean=0, std=(noise_std, noise_std), p=p, seed=None)
]
transforms = Compose(transforms)
### (5) try with different warp (affine transformatins)
if transform == 'affine':
transforms = [
RandomAffine(scales=(1, 1),
degrees=(affine_deg),
isotropic=False,
default_pad_value='otsu',
image_interpolation=Interpolation.LINEAR,
p=p,
seed=None)
]
transforms = Compose(transforms)
### (6) try with different warp (elastic transformations)
if transform == 'elastic':
transforms = [
RandomElasticDeformation(num_control_points=elastic_disp,
max_displacement=20,
locked_borders=2,
image_interpolation=Interpolation.LINEAR,
p=p,
seed=None),
]
transforms = Compose(transforms)
if transform == 'resample':
transforms = [
Resample(target=resample_size,
image_interpolation=Interpolation.LINEAR,
p=p),
CropOrPad(target_shape=target_shape, p=1)
]
transforms = Compose(transforms)
return transforms
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([
ToCanonical(),
# Resample(4),
CropOrPad((112, 112, 48), padding_mode=0), #reflect , original 112,112,48
RandomMotion(num_transforms=6, image_interpolation='nearest', p=0.2),
HistogramStandardization({'mri': landmarks}),
RandomBiasField(p=0.2),
RandomBlur(p=0.2),
ZNormalization(masking_method=ZNormalization.mean),
RandomFlip(axes=['inferior-superior'], flip_probability=0.2),
# RandomNoise(std=0.5, p=0.2),
RandomGhosting(intensity=1.8, p=0.2),
# RandomNoise(),
# RandomFlip(axes=(0,)),
# OneOf({
# RandomAffine(): 0.8,
# RandomElasticDeformation(): 0.2,
# }),
])
def main():
opt = parsing_data()
print("[INFO]Reading data")
# Dictionary with data parameters for NiftyNet Reader
if torch.cuda.is_available():
print('[INFO] GPU available.')
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
else:
raise Exception(
"[INFO] No GPU found or Wrong gpu id, please run without --cuda")
# FOLDERS
fold_dir = opt.model_dir
fold_dir_model = os.path.join(fold_dir, 'models')
if not os.path.exists(fold_dir_model):
os.makedirs(fold_dir_model)
save_path = os.path.join(fold_dir_model, './CP_{}.pth')
output_path = os.path.join(fold_dir, 'output')
if not os.path.exists(output_path):
os.makedirs(output_path)
output_path = os.path.join(output_path, 'output_{}.nii.gz')
# LOGGING
orig_stdout = sys.stdout
if os.path.exists(os.path.join(fold_dir, 'out.txt')):
compt = 0
while os.path.exists(
os.path.join(fold_dir, 'out_' + str(compt) + '.txt')):
compt += 1
f = open(os.path.join(fold_dir, 'out_' + str(compt) + '.txt'), 'w')
else:
f = open(os.path.join(fold_dir, 'out.txt'), 'w')
sys.stdout = f
# SPLITS
split_path = dict()
split_path['control'] = opt.split_control
split_path['augm_control'] = opt.split_control
split_path['lesion'] = opt.split_lesion
for dataset in DATASETS:
assert os.path.isfile(
split_path[dataset]), f'{dataset}: split not found'
path_file = dict()
path_file['control'] = opt.path_control
path_file['augm_control'] = opt.path_control
path_file['lesion'] = opt.path_lesion
list_split = ['training', 'validation']
paths_dict = dict()
for dataset in DATASETS:
df_split = pd.read_csv(split_path[dataset], header=None)
list_file = dict()
for split in list_split:
list_file[split] = df_split[df_split[1].isin([split])][0].tolist()
paths_dict_dataset = {split: [] for split in list_split}
for split in list_split:
for subject in list_file[split]:
subject_data = []
for modality in MODALITIES[dataset]:
subject_data.append(
Image(
modality, path_file[dataset] + subject + modality +
'.nii.gz', torchio.INTENSITY))
if split in ['training', 'validation']:
subject_data.append(
Image('label',
path_file[dataset] + subject + 'Label.nii.gz',
torchio.LABEL))
paths_dict_dataset[split].append(Subject(*subject_data))
print(dataset, split, len(paths_dict_dataset[split]))
paths_dict[dataset] = paths_dict_dataset
# PREPROCESSING
transform_training = dict()
transform_validation = dict()
for dataset in DATASETS:
if dataset == 'augm_control':
transform_training[dataset] = (
Rescale((0, 1)),
ToCanonical(),
RandomMotion(),
RandomGhosting(),
RandomBiasField(),
RandomBlur((0, 2)),
ZNormalization(),
CenterCropOrPad((144, 192, 144)),
RandomAffine(scales=(0.9, 1.1), degrees=10),
RandomNoise(std_range=(0, 0.10)),
RandomFlip(axes=(0, )),
)
transform_training[dataset] = Compose(transform_training[dataset])
else:
transform_training[dataset] = (
ToCanonical(),
ZNormalization(),
CenterCropOrPad((144, 192, 144)),
RandomAffine(scales=(0.9, 1.1), degrees=10),
RandomNoise(std_range=(0, 0.10)),
RandomFlip(axes=(0, )),
)
transform_training[dataset] = Compose(transform_training[dataset])
transform_validation[dataset] = (
ToCanonical(),
ZNormalization(),
CenterCropOrPad((144, 192, 144)),
)
transform_validation[dataset] = Compose(transform_validation[dataset])
transform = {
'training': transform_training,
'validation': transform_validation
}
# MODEL
norm_op_kwargs = {'eps': 1e-5, 'affine': True}
dropout_op_kwargs = {'p': 0, 'inplace': True}
net_nonlin = nn.LeakyReLU
net_nonlin_kwargs = {'negative_slope': 1e-2, 'inplace': True}
print("[INFO] Building model")
model = Generic_UNet(input_modalities=['T1', 'all'],
base_num_features=32,
num_classes=nb_classes,
num_pool=4,
num_conv_per_stage=2,
feat_map_mul_on_downscale=2,
conv_op=torch.nn.Conv3d,
norm_op=torch.nn.InstanceNorm3d,
norm_op_kwargs=norm_op_kwargs,
nonlin=net_nonlin,
nonlin_kwargs=net_nonlin_kwargs,
convolutional_pooling=False,
convolutional_upsampling=False,
final_nonlin=torch.nn.Softmax(1),
input_features={
'T1': 1,
'all': 4
})
print("[INFO] Training")
train(paths_dict, model, transform, device, save_path, opt)
sys.stdout = orig_stdout
f.close()