def init_evaluator() -> eval_.Evaluator:
"""Initializes an evaluator.
Args:
directory (str): The directory for the results file.
result_file_name (str): The result file name (CSV file).
Returns:
eval.Evaluator: An evaluator.
"""
# os.makedirs(directory, exist_ok=True) # generate result directory, if it does not exists
# evaluator = eval_.Evaluator(eval_.ConsoleEvaluatorWriter(5))
evaluation_metrics = [metric.DiceCoefficient(), metric.HausdorffDistance()]
# evaluation_metrics = [metric.DiceCoefficient(), metric.HausdorffDistance(), metric.Accuracy(), metric.CohenKappaCoefficient(), metric.ProbabilisticDistance()]
evaluation_metrics = [metric.DiceCoefficient(), metric.HausdorffDistance(95), metric.CohenKappaCoefficient(), metric.Accuracy(),
metric.JaccardCoefficient(), metric.MutualInformation(), metric.Precision(), metric.VolumeSimilarity(), metric.AreaUnderCurve(),
metric.FalseNegative(),metric.FalsePositive(), metric.TruePositive(), metric.TrueNegative(),metric.Sensitivity(),metric.Specificity()]
evaluation_metrics=[metric.DiceCoefficient(),metric.JaccardCoefficient(),metric.SurfaceDiceOverlap(),metric.Accuracy(),
metric.FMeasure(),metric.CohenKappaCoefficient(),metric.VolumeSimilarity(),metric.MutualInformation(),metric.AreaUnderCurve(),
metric.HausdorffDistance()]
evaluator = eval_.SegmentationEvaluator(evaluation_metrics,{})
# evaluator.add_writer(eval_.CSVEvaluatorWriter(os.path.join(directory, result_file_name)))
evaluator.add_label(1, 'WhiteMatter')
evaluator.add_label(2, 'GreyMatter')
evaluator.add_label(3, 'Hippocampus')
evaluator.add_label(4, 'Amygdala')
evaluator.add_label(5, 'Thalamus')
# warnings.warn('Initialized evaluation with the Dice coefficient. Do you know other suitable metrics?')
# you should add more metrics than just the Hausdorff distance!
return evaluator
def main():
print(f'Welcome to MIALab {datetime.now().year}!')
# --- scikit-learn
sk_ensemble.RandomForestClassifier(max_depth=2, random_state=0)
# --- SimpleITK
image = sitk.Image(256, 128, 64, sitk.sitkInt16)
print('Image dimension:', image.GetDimension())
print('Voxel intensity before setting:', image.GetPixel(0, 0, 0))
image.SetPixel(0, 0, 0, 1)
print('Voxel intensity after setting:', image.GetPixel(0, 0, 0))
# --- numpy and matplotlib
array = np.array([1, 23, 2, 4])
plt.plot(array)
plt.ylabel('Some meaningful numbers')
plt.xlabel('The x-axis')
plt.title('Wohoo')
plt.show()
# --- pymia
pymia_eval.SegmentationEvaluator([], {})
print('Everything seems to work fine!')
def main(data_dir: str, result_file: str, result_summary_file: str):
# initialize metrics
metrics = [
metric.DiceCoefficient(),
metric.HausdorffDistance(percentile=95, metric='HDRFDST95'),
metric.VolumeSimilarity()
]
# define the labels to evaluate
labels = {1: 'WHITEMATTER', 2: 'GREYMATTER', 5: 'THALAMUS'}
evaluator = eval_.SegmentationEvaluator(metrics, labels)
# get subjects to evaluate
subject_dirs = [
subject for subject in glob.glob(os.path.join(data_dir, '*'))
if os.path.isdir(subject)
and os.path.basename(subject).startswith('Subject')
]
for subject_dir in subject_dirs:
subject_id = os.path.basename(subject_dir)
print(f'Evaluating {subject_id}...')
# load ground truth image and create artificial prediction by erosion
ground_truth = sitk.ReadImage(
os.path.join(subject_dir, f'{subject_id}_GT.mha'))
prediction = ground_truth
for label_val in labels.keys():
# erode each label we are going to evaluate
prediction = sitk.BinaryErode(prediction, 1, sitk.sitkBall, 0,
label_val)
# evaluate the "prediction" against the ground truth
evaluator.evaluate(prediction, ground_truth, subject_id)
# use two writers to report the results
writer.CSVWriter(result_file).write(evaluator.results)
print('\nSubject-wise results...')
writer.ConsoleWriter().write(evaluator.results)
# report also mean and standard deviation among all subjects
functions = {'MEAN': np.mean, 'STD': np.std}
writer.CSVStatisticsWriter(result_summary_file,
functions=functions).write(evaluator.results)
print('\nAggregated statistic results...')
writer.ConsoleStatisticsWriter(functions=functions).write(
evaluator.results)
# clear results such that the evaluator is ready for the next evaluation
evaluator.clear()
def init_evaluator() -> eval_.Evaluator:
"""Initializes an evaluator.
Returns:
eval.Evaluator: An evaluator.
"""
# initialize metrics
metrics = [metric.DiceCoefficient(), metric.HausdorffDistance(95.0)]
# define the labels to evaluate
labels = {
1: 'WhiteMatter',
2: 'GreyMatter',
3: 'Hippocampus',
4: 'Amygdala',
5: 'Thalamus'
}
evaluator = eval_.SegmentationEvaluator(metrics, labels)
return evaluator
def init_evaluator() -> eval_.Evaluator:
"""Initializes an evaluator.
Returns:
eval.Evaluator: An evaluator.
"""
# initialize metrics
metrics = [metric.DiceCoefficient()]
# todo: add hausdorff distance, 95th percentile (see metric.HausdorffDistance)
warnings.warn('Initialized evaluation with the Dice coefficient. Do you know other suitable metrics?')
# define the labels to evaluate
labels = {1: 'WhiteMatter',
2: 'GreyMatter',
3: 'Hippocampus',
4: 'Amygdala',
5: 'Thalamus'
}
evaluator = eval_.SegmentationEvaluator(metrics, labels)
return evaluator
def main(hdf_file, log_dir):
# initialize the evaluator with the metrics and the labels to evaluate
metrics = [metric.DiceCoefficient()]
labels = {1: 'WHITEMATTER',
2: 'GREYMATTER',
3: 'HIPPOCAMPUS',
4: 'AMYGDALA',
5: 'THALAMUS'}
evaluator = eval_.SegmentationEvaluator(metrics, labels)
# we want to log the mean and standard deviation of the metrics among all subjects of the dataset
functions = {'MEAN': np.mean, 'STD': np.std}
statistics_aggregator = writer.StatisticsAggregator(functions=functions)
console_writer = writer.ConsoleStatisticsWriter(functions=functions)
# initialize TensorBoard writer
tb = tensorboard.SummaryWriter(os.path.join(log_dir, 'logging-example-torch'))
# setup the training datasource
train_subjects, valid_subjects = ['Subject_1', 'Subject_2', 'Subject_3'], ['Subject_4']
extractor = extr.DataExtractor(categories=(defs.KEY_IMAGES, defs.KEY_LABELS))
indexing_strategy = extr.SliceIndexing()
augmentation_transforms = [augm.RandomElasticDeformation(), augm.RandomMirror()]
transforms = [tfm.Permute(permutation=(2, 0, 1)), tfm.Squeeze(entries=(defs.KEY_LABELS,))]
train_transforms = tfm.ComposeTransform(augmentation_transforms + transforms)
train_dataset = extr.PymiaDatasource(hdf_file, indexing_strategy, extractor, train_transforms,
subject_subset=train_subjects)
# setup the validation datasource
valid_transforms = tfm.ComposeTransform([tfm.Permute(permutation=(2, 0, 1))])
valid_dataset = extr.PymiaDatasource(hdf_file, indexing_strategy, extractor, valid_transforms,
subject_subset=valid_subjects)
direct_extractor = extr.ComposeExtractor(
[extr.SubjectExtractor(),
extr.ImagePropertiesExtractor(),
extr.DataExtractor(categories=(defs.KEY_LABELS,))]
)
assembler = assm.SubjectAssembler(valid_dataset)
# torch specific handling
pytorch_train_dataset = pymia_torch.PytorchDatasetAdapter(train_dataset)
train_loader = torch_data.dataloader.DataLoader(pytorch_train_dataset, batch_size=16, shuffle=True)
pytorch_valid_dataset = pymia_torch.PytorchDatasetAdapter(valid_dataset)
valid_loader = torch_data.dataloader.DataLoader(pytorch_valid_dataset, batch_size=16, shuffle=False)
u_net = unet.UNetModel(ch_in=2, ch_out=6, n_channels=16, n_pooling=3).to(device)
print(u_net)
optimizer = optim.Adam(u_net.parameters(), lr=1e-3)
train_batches = len(train_loader)
# looping over the data in the dataset
epochs = 100
for epoch in range(epochs):
u_net.train()
print(f'Epoch {epoch + 1}/{epochs}')
# training
print('training')
for i, batch in enumerate(train_loader):
x, y = batch[defs.KEY_IMAGES].to(device), batch[defs.KEY_LABELS].to(device).long()
logits = u_net(x)
optimizer.zero_grad()
loss = F.cross_entropy(logits, y)
loss.backward()
optimizer.step()
tb.add_scalar('train/loss', loss.item(), epoch*train_batches + i)
print(f'[{i + 1}/{train_batches}]\tloss: {loss.item()}')
# validation
print('validation')
with torch.no_grad():
u_net.eval()
valid_batches = len(valid_loader)
for i, batch in enumerate(valid_loader):
x, sample_indices = batch[defs.KEY_IMAGES].to(device), batch[defs.KEY_SAMPLE_INDEX]
logits = u_net(x)
prediction = logits.argmax(dim=1, keepdim=True)
numpy_prediction = prediction.cpu().numpy().transpose((0, 2, 3, 1))
is_last = i == valid_batches - 1
assembler.add_batch(numpy_prediction, sample_indices.numpy(), is_last)
for subject_index in assembler.subjects_ready:
subject_prediction = assembler.get_assembled_subject(subject_index)
direct_sample = train_dataset.direct_extract(direct_extractor, subject_index)
target, image_properties = direct_sample[defs.KEY_LABELS], direct_sample[defs.KEY_PROPERTIES]
# evaluate the prediction against the reference
evaluator.evaluate(subject_prediction[..., 0], target[..., 0], direct_sample[defs.KEY_SUBJECT])
# calculate mean and standard deviation of each metric
results = statistics_aggregator.calculate(evaluator.results)
# log to TensorBoard into category train
for result in results:
tb.add_scalar(f'valid/{result.metric}-{result.id_}', result.value, epoch)
console_writer.write(evaluator.results)
# clear results such that the evaluator is ready for the next evaluation
evaluator.clear()
def main(hdf_file: str, log_dir: str):
# initialize the evaluator with the metrics and the labels to evaluate
metrics = [metric.DiceCoefficient()]
labels = {1: 'WHITEMATTER', 2: 'GREYMATTER', 5: 'THALAMUS'}
evaluator = eval_.SegmentationEvaluator(metrics, labels)
# we want to log the mean and standard deviation of the metrics among all subjects of the dataset
functions = {'MEAN': np.mean, 'STD': np.std}
statistics_aggregator = writer.StatisticsAggregator(functions=functions)
# initialize TensorBoard writer
# tb = tensorboard.SummaryWriter(os.path.join(log_dir, 'logging-example-torch'))
tb = tf.summary.create_file_writer(
os.path.join(log_dir, 'logging-example-tensorflow'))
# initialize the data handling
dataset = extr.PymiaDatasource(
hdf_file, extr.SliceIndexing(),
extr.DataExtractor(categories=(defs.KEY_IMAGES, )))
gen_fn = pymia_tf.get_tf_generator(dataset)
tf_dataset = tf.data.Dataset.from_generator(generator=gen_fn,
output_types={
defs.KEY_IMAGES:
tf.float32,
defs.KEY_SAMPLE_INDEX:
tf.int64
})
loader = tf_dataset.batch(100)
assembler = assm.SubjectAssembler(dataset)
direct_extractor = extr.ComposeExtractor([
extr.SubjectExtractor(), # extraction of the subject name
extr.ImagePropertiesExtractor(
), # Extraction of image properties (origin, spacing, etc.) for storage
extr.DataExtractor(
categories=(defs.KEY_LABELS,
)) # Extraction of "labels" entries for evaluation
])
# initialize a dummy network, which returns a random prediction
class DummyNetwork(tf.keras.Model):
def call(self, inputs):
return tf.random.uniform((*inputs.shape[:-1], 1),
0,
6,
dtype=tf.int32)
dummy_network = DummyNetwork()
tf.random.set_seed(0) # set seed for reproducibility
nb_batches = len(dataset) // 2
epochs = 10
for epoch in range(epochs):
print(f'Epoch {epoch + 1}/{epochs}')
for i, batch in enumerate(loader):
# get the data from batch and predict
x, sample_indices = batch[defs.KEY_IMAGES], batch[
defs.KEY_SAMPLE_INDEX]
prediction = dummy_network(x)
# translate the prediction to numpy
numpy_prediction = prediction.numpy()
# add the batch prediction to the assembler
is_last = i == nb_batches - 1
assembler.add_batch(numpy_prediction, sample_indices.numpy(),
is_last)
# process the subjects/images that are fully assembled
for subject_index in assembler.subjects_ready:
subject_prediction = assembler.get_assembled_subject(
subject_index)
# extract the target and image properties via direct extract
direct_sample = dataset.direct_extract(direct_extractor,
subject_index)
reference, image_properties = direct_sample[
defs.KEY_LABELS], direct_sample[defs.KEY_PROPERTIES]
# evaluate the prediction against the reference
evaluator.evaluate(subject_prediction[..., 0], reference[...,
0],
direct_sample[defs.KEY_SUBJECT])
# calculate mean and standard deviation of each metric
results = statistics_aggregator.calculate(evaluator.results)
# log to TensorBoard into category train
for result in results:
with tb.as_default():
tf.summary.scalar(f'train/{result.metric}-{result.id_}',
result.value, epoch)
# clear results such that the evaluator is ready for the next evaluation
evaluator.clear()
def main(hdf_file: str, log_dir: str):
# initialize the evaluator with the metrics and the labels to evaluate
metrics = [metric.DiceCoefficient()]
labels = {1: 'WHITEMATTER', 2: 'GREYMATTER', 5: 'THALAMUS'}
evaluator = eval_.SegmentationEvaluator(metrics, labels)
# we want to log the mean and standard deviation of the metrics among all subjects of the dataset
functions = {'MEAN': np.mean, 'STD': np.std}
statistics_aggregator = writer.StatisticsAggregator(functions=functions)
# initialize TensorBoard writer
tb = tensorboard.SummaryWriter(
os.path.join(log_dir, 'logging-example-torch'))
# initialize the data handling
transform = tfm.Permute(permutation=(2, 0, 1), entries=(defs.KEY_IMAGES, ))
dataset = extr.PymiaDatasource(
hdf_file, extr.SliceIndexing(),
extr.DataExtractor(categories=(defs.KEY_IMAGES, )), transform)
pytorch_dataset = pymia_torch.PytorchDatasetAdapter(dataset)
loader = torch_data.dataloader.DataLoader(pytorch_dataset,
batch_size=100,
shuffle=False)
assembler = assm.SubjectAssembler(dataset)
direct_extractor = extr.ComposeExtractor([
extr.SubjectExtractor(), # extraction of the subject name
extr.ImagePropertiesExtractor(
), # Extraction of image properties (origin, spacing, etc.) for storage
extr.DataExtractor(
categories=(defs.KEY_LABELS,
)) # Extraction of "labels" entries for evaluation
])
# initialize a dummy network, which returns a random prediction
class DummyNetwork(nn.Module):
def forward(self, x):
return torch.randint(0, 6, (x.size(0), 1, *x.size()[2:]))
dummy_network = DummyNetwork()
torch.manual_seed(0) # set seed for reproducibility
nb_batches = len(loader)
epochs = 10
for epoch in range(epochs):
print(f'Epoch {epoch + 1}/{epochs}')
for i, batch in enumerate(loader):
# get the data from batch and predict
x, sample_indices = batch[defs.KEY_IMAGES], batch[
defs.KEY_SAMPLE_INDEX]
prediction = dummy_network(x)
# translate the prediction to numpy and back to (B)HWC (channel last)
numpy_prediction = prediction.numpy().transpose((0, 2, 3, 1))
# add the batch prediction to the assembler
is_last = i == nb_batches - 1
assembler.add_batch(numpy_prediction, sample_indices.numpy(),
is_last)
# process the subjects/images that are fully assembled
for subject_index in assembler.subjects_ready:
subject_prediction = assembler.get_assembled_subject(
subject_index)
# extract the target and image properties via direct extract
direct_sample = dataset.direct_extract(direct_extractor,
subject_index)
reference, image_properties = direct_sample[
defs.KEY_LABELS], direct_sample[defs.KEY_PROPERTIES]
# evaluate the prediction against the reference
evaluator.evaluate(subject_prediction[..., 0], reference[...,
0],
direct_sample[defs.KEY_SUBJECT])
# calculate mean and standard deviation of each metric
results = statistics_aggregator.calculate(evaluator.results)
# log to TensorBoard into category train
for result in results:
tb.add_scalar(f'train/{result.metric}-{result.id_}', result.value,
epoch)
# clear results such that the evaluator is ready for the next evaluation
evaluator.clear()
def main(hdf_file, log_dir):
# initialize the evaluator with the metrics and the labels to evaluate
metrics = [metric.DiceCoefficient()]
labels = {
1: 'WHITEMATTER',
2: 'GREYMATTER',
3: 'HIPPOCAMPUS',
4: 'AMYGDALA',
5: 'THALAMUS'
}
evaluator = eval_.SegmentationEvaluator(metrics, labels)
# we want to log the mean and standard deviation of the metrics among all subjects of the dataset
functions = {'MEAN': np.mean, 'STD': np.std}
statistics_aggregator = writer.StatisticsAggregator(functions=functions)
console_writer = writer.ConsoleStatisticsWriter(functions=functions)
# initialize TensorBoard writer
summary_writer = tf.summary.create_file_writer(
os.path.join(log_dir, 'logging-example-tensorflow'))
# setup the training datasource
train_subjects, valid_subjects = ['Subject_1', 'Subject_2',
'Subject_3'], ['Subject_4']
extractor = extr.DataExtractor(categories=(defs.KEY_IMAGES,
defs.KEY_LABELS))
indexing_strategy = extr.SliceIndexing()
augmentation_transforms = [
augm.RandomElasticDeformation(),
augm.RandomMirror()
]
transforms = [tfm.Squeeze(entries=(defs.KEY_LABELS, ))]
train_transforms = tfm.ComposeTransform(augmentation_transforms +
transforms)
train_dataset = extr.PymiaDatasource(hdf_file,
indexing_strategy,
extractor,
train_transforms,
subject_subset=train_subjects)
# setup the validation datasource
batch_size = 16
valid_transforms = tfm.ComposeTransform([])
valid_dataset = extr.PymiaDatasource(hdf_file,
indexing_strategy,
extractor,
valid_transforms,
subject_subset=valid_subjects)
direct_extractor = extr.ComposeExtractor([
extr.SubjectExtractor(),
extr.ImagePropertiesExtractor(),
extr.DataExtractor(categories=(defs.KEY_LABELS, ))
])
assembler = assm.SubjectAssembler(valid_dataset)
# tensorflow specific handling
train_gen_fn = pymia_tf.get_tf_generator(train_dataset)
tf_train_dataset = tf.data.Dataset.from_generator(
generator=train_gen_fn,
output_types={
defs.KEY_IMAGES: tf.float32,
defs.KEY_LABELS: tf.int64,
defs.KEY_SAMPLE_INDEX: tf.int64
})
tf_train_dataset = tf_train_dataset.batch(batch_size).shuffle(
len(train_dataset))
valid_gen_fn = pymia_tf.get_tf_generator(valid_dataset)
tf_valid_dataset = tf.data.Dataset.from_generator(
generator=valid_gen_fn,
output_types={
defs.KEY_IMAGES: tf.float32,
defs.KEY_LABELS: tf.int64,
defs.KEY_SAMPLE_INDEX: tf.int64
})
tf_valid_dataset = tf_valid_dataset.batch(batch_size)
u_net = unet.build_model(channels=2,
num_classes=6,
layer_depth=3,
filters_root=16)
optimizer = tf.keras.optimizers.Adam(learning_rate=1e-3)
train_loss = tf.keras.metrics.Mean('train_loss', dtype=tf.float32)
train_batches = len(train_dataset) // batch_size
# looping over the data in the dataset
epochs = 100
for epoch in range(epochs):
print(f'Epoch {epoch + 1}/{epochs}')
# training
print('training')
for i, batch in enumerate(tf_train_dataset):
x, y = batch[defs.KEY_IMAGES], batch[defs.KEY_LABELS]
with tf.GradientTape() as tape:
logits = u_net(x, training=True)
loss = tf.keras.losses.sparse_categorical_crossentropy(
y, logits, from_logits=True)
grads = tape.gradient(loss, u_net.trainable_variables)
optimizer.apply_gradients(zip(grads, u_net.trainable_variables))
train_loss(loss)
with summary_writer.as_default():
tf.summary.scalar('train/loss',
train_loss.result(),
step=epoch * train_batches + i)
print(
f'[{i + 1}/{train_batches}]\tloss: {train_loss.result().numpy()}'
)
# validation
print('validation')
valid_batches = len(valid_dataset) // batch_size
for i, batch in enumerate(tf_valid_dataset):
x, sample_indices = batch[defs.KEY_IMAGES], batch[
defs.KEY_SAMPLE_INDEX]
logits = u_net(x)
prediction = tf.expand_dims(tf.math.argmax(logits, -1), -1)
numpy_prediction = prediction.numpy()
is_last = i == valid_batches - 1
assembler.add_batch(numpy_prediction, sample_indices.numpy(),
is_last)
for subject_index in assembler.subjects_ready:
subject_prediction = assembler.get_assembled_subject(
subject_index)
direct_sample = train_dataset.direct_extract(
direct_extractor, subject_index)
target, image_properties = direct_sample[
defs.KEY_LABELS], direct_sample[defs.KEY_PROPERTIES]
# evaluate the prediction against the reference
evaluator.evaluate(subject_prediction[..., 0], target[..., 0],
direct_sample[defs.KEY_SUBJECT])
# calculate mean and standard deviation of each metric
results = statistics_aggregator.calculate(evaluator.results)
# log to TensorBoard into category train
with summary_writer.as_default():
for result in results:
tf.summary.scalar(f'valid/{result.metric}-{result.id_}',
result.value, epoch)
console_writer.write(evaluator.results)
# clear results such that the evaluator is ready for the next evaluation
evaluator.clear()