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 main(result_dir: str, data_atlas_dir: str, data_train_dir: str,
data_test_dir: str):
"""Brain tissue segmentation using decision forests.
The main routine executes the medical image analysis pipeline:
- Image loading
- Registration
- Pre-processing
- Feature extraction
- Decision forest classifier model building
- Segmentation using the decision forest classifier model on unseen images
- Post-processing of the segmentation
- Evaluation of the segmentation
"""
# load atlas images
putil.load_atlas_images(data_atlas_dir)
print('-' * 5, 'Training...')
# crawl the training image directories
crawler = futil.FileSystemDataCrawler(data_train_dir, LOADING_KEYS,
futil.BrainImageFilePathGenerator(),
futil.DataDirectoryFilter())
pre_process_params = {
'skullstrip_pre': True,
'normalization_pre': True,
'registration_pre': True,
'coordinates_feature': True,
'intensity_feature': True,
'gradient_intensity_feature': True
}
# load images for training and pre-process
images = putil.pre_process_batch(crawler.data,
pre_process_params,
multi_process=False)
# generate feature matrix and label vector
data_train = np.concatenate([img.feature_matrix[0] for img in images])
labels_train = np.concatenate([img.feature_matrix[1]
for img in images]).squeeze()
#warnings.warn('Random forest parameters not properly set.')
forest = sk_ensemble.RandomForestClassifier(
max_features=images[0].feature_matrix[0].shape[1],
n_estimators=10,
max_depth=10)
start_time = timeit.default_timer()
forest.fit(data_train, labels_train)
print(' Time elapsed:', timeit.default_timer() - start_time, 's')
# create a result directory with timestamp
t = datetime.datetime.now().strftime('%Y-%m-%d-%H-%M-%S')
result_dir = os.path.join(result_dir, t)
os.makedirs(result_dir, exist_ok=True)
print('-' * 5, 'Testing...')
# initialize evaluator
evaluator = putil.init_evaluator()
# crawl the training image directories
crawler = futil.FileSystemDataCrawler(data_test_dir, LOADING_KEYS,
futil.BrainImageFilePathGenerator(),
futil.DataDirectoryFilter())
# load images for testing and pre-process
pre_process_params['training'] = False
images_test = putil.pre_process_batch(crawler.data,
pre_process_params,
multi_process=False)
images_prediction = []
images_probabilities = []
for img in images_test:
print('-' * 10, 'Testing', img.id_)
start_time = timeit.default_timer()
predictions = forest.predict(img.feature_matrix[0])
probabilities = forest.predict_proba(img.feature_matrix[0])
print(' Time elapsed:', timeit.default_timer() - start_time, 's')
# convert prediction and probabilities back to SimpleITK images
image_prediction = conversion.NumpySimpleITKImageBridge.convert(
predictions.astype(np.uint8), img.image_properties)
image_probabilities = conversion.NumpySimpleITKImageBridge.convert(
probabilities, img.image_properties)
# evaluate segmentation without post-processing
evaluator.evaluate(image_prediction,
img.images[structure.BrainImageTypes.GroundTruth],
img.id_)
images_prediction.append(image_prediction)
images_probabilities.append(image_probabilities)
# post-process segmentation and evaluate with post-processing
post_process_params = {'simple_post': True}
images_post_processed = putil.post_process_batch(images_test,
images_prediction,
images_probabilities,
post_process_params,
multi_process=False)
for i, img in enumerate(images_test):
evaluator.evaluate(images_post_processed[i],
img.images[structure.BrainImageTypes.GroundTruth],
img.id_ + '-PP')
# save results
sitk.WriteImage(
images_prediction[i],
os.path.join(result_dir, images_test[i].id_ + '_SEG.mha'), True)
sitk.WriteImage(
images_post_processed[i],
os.path.join(result_dir, images_test[i].id_ + '_SEG-PP.mha'), True)
# use two writers to report the results
os.makedirs(
result_dir,
exist_ok=True) # generate result directory, if it does not exists
result_file = os.path.join(result_dir, 'results.csv')
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
result_summary_file = os.path.join(result_dir, 'results_summary.csv')
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 main(result_dir: str, data_atlas_dir: str, data_train_dir: str,
data_test_dir: str):
"""Brain tissue segmentation using decision forests.
Section of the original main routine. Executes gird search of the probabilistic keyhole filling method parameters:
Must be done separately in advance:
- Image loading
- Registration
- Pre-processing
- Feature extraction
- Decision forest classifier model building
- Segmentation using the decision forest classifier model on unseen images
Is carried out in this section of the pipeline
- Loading of temporary data
- Grid search of PKF parameter of the segmentation
- Evaluation of the segmentation
"""
# load atlas images
putil.load_atlas_images(data_atlas_dir)
print('-' * 5, 'Training...')
# crawl the training image directories
crawler = futil.FileSystemDataCrawler(data_train_dir, LOADING_KEYS,
futil.BrainImageFilePathGenerator(),
futil.DataDirectoryFilter())
pre_process_params = {
'skullstrip_pre': True,
'normalization_pre': True,
'registration_pre': True,
'coordinates_feature': True,
'intensity_feature': True,
'gradient_intensity_feature': True
}
# load images for training and pre-process
images = putil.pre_process_batch(crawler.data,
pre_process_params,
multi_process=False)
# generate feature matrix and label vector
data_train = np.concatenate([img.feature_matrix[0] for img in images])
labels_train = np.concatenate([img.feature_matrix[1]
for img in images]).squeeze()
#warnings.warn('Random forest parameters not properly set.')
forest = sk_ensemble.RandomForestClassifier(
max_features=images[0].feature_matrix[0].shape[1],
n_estimators=20,
max_depth=85)
start_time = timeit.default_timer()
forest.fit(data_train, labels_train)
print(' Time elapsed:', timeit.default_timer() - start_time, 's')
# create a result directory with timestamp
t = datetime.datetime.now().strftime('%Y-%m-%d-%H-%M-%S')
result_dir = os.path.join(result_dir, t)
os.makedirs(result_dir, exist_ok=True)
print('-' * 5, 'Testing...')
# initialize evaluator
evaluator = putil.init_evaluator()
# crawl the training image directories
crawler = futil.FileSystemDataCrawler(data_test_dir, LOADING_KEYS,
futil.BrainImageFilePathGenerator(),
futil.DataDirectoryFilter())
# load images for testing and pre-process
pre_process_params['training'] = False
images_test = putil.pre_process_batch(crawler.data,
pre_process_params,
multi_process=False)
images_prediction = []
images_probabilities = []
for img in images_test:
print('-' * 10, 'Testing', img.id_)
start_time = timeit.default_timer()
predictions = forest.predict(img.feature_matrix[0])
probabilities = forest.predict_proba(img.feature_matrix[0])
print(' Time elapsed:', timeit.default_timer() - start_time, 's')
# convert prediction and probabilities back to SimpleITK images
image_prediction = conversion.NumpySimpleITKImageBridge.convert(
predictions.astype(np.uint8), img.image_properties)
image_probabilities = conversion.NumpySimpleITKImageBridge.convert(
probabilities, img.image_properties)
# evaluate segmentation without post-processing
evaluator.evaluate(image_prediction,
img.images[structure.BrainImageTypes.GroundTruth],
img.id_)
images_prediction.append(image_prediction)
images_probabilities.append(image_probabilities)
# save results without post-processing
name = 'no_PP'
sub_dir = os.path.join(result_dir, name)
os.makedirs(sub_dir, exist_ok=True)
for i, img in enumerate(images_test):
sitk.WriteImage(images_prediction[i],
os.path.join(sub_dir, images_test[i].id_ + '_SEG.mha'),
True)
result_file = os.path.join(sub_dir, 'results.csv')
writer.CSVWriter(result_file).write(evaluator.results)
# report also mean and standard deviation among all subjects
result_summary_file = os.path.join(sub_dir, 'results_summary.csv')
functions = {'MEAN': np.mean, 'STD': np.std}
writer.CSVStatisticsWriter(result_summary_file,
functions=functions).write(evaluator.results)
# clear results such that the evaluator is ready for the next evaluation
evaluator.clear()
# define paramter for grid search
post_process_param_list = []
variance = np.arange(1, 2)
preserve_background = np.asarray([False])
#
# # define paramter for grid search
# post_process_param_list = []
# variance = np.arange(0.5, 4.0, 0.5)
# preserve_background = np.asarray([False, True])
for bg in preserve_background:
for var in variance:
post_process_param_list.append({
'simple_post': bool(True),
'variance': float(var),
'preserve_background': bool(bg)
})
# execute post processing with definde parameters
for post_process_params in post_process_param_list:
# create sub-directory for results
name = 'PP-V-'+ str(post_process_params.get('variance')).replace('.','_') +\
'-BG-' + str(post_process_params.get('preserve_background'))
sub_dir = os.path.join(result_dir, name)
os.makedirs(sub_dir, exist_ok=True)
#write the used parameter into a text file and store it in the result folder
completeName = os.path.join(sub_dir, "parameter.txt")
file1 = open(completeName, "w+")
json.dump(post_process_params, file1)
file1.close()
# post-process segmentation and evaluate with post-processing
images_post_processed = putil.post_process_batch(images_test,
images_prediction,
images_probabilities,
post_process_params,
multi_process=False)
for i, img in enumerate(images_test):
evaluator.evaluate(
images_post_processed[i],
img.images[structure.BrainImageTypes.GroundTruth],
img.id_ + '-PP')
# save results
sitk.WriteImage(
images_post_processed[i],
os.path.join(sub_dir, images_test[i].id_ + '_SEG-PP.mha'),
True)
# save all results in csv file
result_file = os.path.join(sub_dir, 'results.csv')
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
result_summary_file = os.path.join(sub_dir, 'results_summary.csv')
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 main(result_dir: str, data_atlas_dir: str, data_train_dir: str,
data_test_dir: str, tmp_result_dir: str):
"""Brain tissue segmentation using decision forests.
Section of the original main routine. Executes post processing part of the medical image analysis pipeline:
Must be done separately in advance:
- Image loading
- Registration
- Pre-processing
- Feature extraction
- Decision forest classifier model building
- Segmentation using the decision forest classifier model on unseen images
Is carried out in this section of the pipeline
- Loading of temporary data
- Post-processing of the segmentation
- Evaluation of the segmentation
"""
# load atlas images
putil.load_atlas_images(data_atlas_dir)
# print('-' * 5, 'Training...')
#
# # crawl the training image directories
# crawler = futil.FileSystemDataCrawler(data_train_dir,
# LOADING_KEYS,
# futil.BrainImageFilePathGenerator(),
# futil.DataDirectoryFilter())
pre_process_params = {
'skullstrip_pre': True,
'normalization_pre': True,
'registration_pre': True,
'coordinates_feature': True,
'intensity_feature': True,
'gradient_intensity_feature': True
}
# create a result directory with timestamp
t = datetime.datetime.now().strftime('%Y-%m-%d-%H-%M-%S')
result_dir = os.path.join(result_dir, t)
os.makedirs(result_dir, exist_ok=True)
# initialize evaluator
evaluator = putil.init_evaluator()
# crawl the test image directories
crawler = futil.FileSystemDataCrawler(data_test_dir, LOADING_KEYS,
futil.BrainImageFilePathGenerator(),
futil.DataDirectoryFilter())
# load necessary data to perform post processing
pre_process_params['training'] = False
images_test = putil.pre_process_batch(crawler.data,
pre_process_params,
multi_process=False)
# load the prediction of the test images (segmented image
images_prediction, images_probabilities = putil.load_prediction_images(
images_test, tmp_result_dir, '2020-10-30-18-31-15')
# evaluate images without post-processing
for i, img in enumerate(images_test):
evaluator.evaluate(images_prediction[i],
img.images[structure.BrainImageTypes.GroundTruth],
img.id_)
# post-process segmentation and evaluate with post-processing
post_process_params = {
'simple_post': True,
'variance': 1.0,
'preserve_background': False
}
images_post_processed = putil.post_process_batch(images_test,
images_prediction,
images_probabilities,
post_process_params,
multi_process=False)
for i, img in enumerate(images_test):
evaluator.evaluate(images_post_processed[i],
img.images[structure.BrainImageTypes.GroundTruth],
img.id_ + '-PP')
# save results
sitk.WriteImage(
images_prediction[i],
os.path.join(result_dir, images_test[i].id_ + '_SEG.mha'), True)
sitk.WriteImage(
images_post_processed[i],
os.path.join(result_dir, images_test[i].id_ + '_SEG-PP.mha'), True)
# use two writers to report the results
os.makedirs(
result_dir,
exist_ok=True) # generate result directory, if it does not exists
result_file = os.path.join(result_dir, 'results.csv')
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
result_summary_file = os.path.join(result_dir, 'results_summary.csv')
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 main(result_dir: str, data_atlas_dir: str, data_train_dir: str, data_test_dir: str, parameters_file: str):
"""Brain tissue segmentation using decision forests.
The main routine executes the medical image analysis pipeline:
- Image loading
- Registration
- Pre-processing
- Feature extraction
- Decision forest classifier model building
- Segmentation using the decision forest classifier model on unseen images
- Post-processing of the segmentation
- Evaluation of the segmentation
"""
start_main = timeit.default_timer()
# load atlas images
putil.load_atlas_images(data_atlas_dir)
print('-' * 5, 'Training...')
# crawl the training image directories
crawler = futil.FileSystemDataCrawler(data_train_dir,
LOADING_KEYS,
futil.BrainImageFilePathGenerator(),
futil.DataDirectoryFilter())
fof_parameters = {'10Percentile': True,
'90Percentile': True,
'Energy': True,
'Entropy': True,
'InterquartileRange': True,
'Kurtosis': True,
'Maximum': True,
'MeanAbsoluteDeviation': True,
'Mean': True,
'Median': True,
'Minimum': True,
'Range': True,
'RobustMeanAbsoluteDeviation': True,
'RootMeanSquared': True,
'Skewness': True,
'TotalEnergy': True,
'Uniformity': True,
'Variance': True}
glcm_parameters = {'Autocorrelation': True,
'ClusterProminence': True,
'ClusterShade': True,
'ClusterTendency': True,
'Contrast': True,
'Correlation': True,
'DifferenceAverage': True,
'DifferenceEntropy': True,
'DifferenceVariance': True,
'Id': True,
'Idm': True,
'Idmn': True,
'Idn': True,
'Imc1': True,
'Imc2': True,
'InverseVariance': True,
'JointAverage': True,
'JointEnergy': True,
'JointEntropy': True,
'MCC': True,
'MaximumProbability': True,
'SumAverage': True,
'SumEntropy': True,
'SumSquares': True}
pre_process_params = {'skullstrip_pre': True,
'normalization_pre': True,
'registration_pre': True,
'save_features': False,
'coordinates_feature': True,
'intensity_feature': False,
'gradient_intensity_feature': False,
'first_order_feature': False,
'first_order_feature_parameters': fof_parameters,
'HOG_feature': False,
'GLCM_features': False,
'GLCM_features_parameters': glcm_parameters,
'n_estimators': 50,
'max_depth': 60,
'experiment_name': 'default'
}
parameters = json.load(open(parameters_file, 'r'))
if bool(parameters):
pre_process_params = parameters
# load images for training and pre-process
images = putil.pre_process_batch(crawler.data, pre_process_params, multi_process=False)
# generate feature matrix and label vector
data_train = np.concatenate([img.feature_matrix[0] for img in images])
labels_train = np.concatenate([img.feature_matrix[1] for img in images]).squeeze()
np.nan_to_num(data_train, copy=False)
# warnings.warn('Random forest parameters not properly set.')
forest = sk_ensemble.RandomForestClassifier(max_features=images[0].feature_matrix[0].shape[1],
n_estimators=pre_process_params['n_estimators'], # 100
max_depth=pre_process_params['max_depth']) # 10
# Debugging
nan_data_idx = np.argwhere(np.isnan(data_train))
np.savez('data_train.npz', data_train)
np.save('data_nan.npy', nan_data_idx)
start_time = timeit.default_timer()
forest.fit(data_train, labels_train)
print(' Time elapsed:', timeit.default_timer() - start_time, 's')
# create a result directory with timestamp
result_dir = os.path.join(result_dir, pre_process_params['experiment_name'])
os.makedirs(result_dir, exist_ok=True)
print('-' * 5, 'Testing...')
# initialize evaluator
evaluator = putil.init_evaluator()
# crawl the training image directories
crawler = futil.FileSystemDataCrawler(data_test_dir,
LOADING_KEYS,
futil.BrainImageFilePathGenerator(),
futil.DataDirectoryFilter())
# load images for testing and pre-process
pre_process_params['training'] = False
images_test = putil.pre_process_batch(crawler.data, pre_process_params, multi_process=False)
images_prediction = []
images_probabilities = []
for img in images_test:
print('-' * 10, 'Testing', img.id_)
start_time = timeit.default_timer()
predictions = forest.predict(np.nan_to_num(img.feature_matrix[0],copy=False))
probabilities = forest.predict_proba(np.nan_to_num(img.feature_matrix[0],copy=False))
print(' Time elapsed:', timeit.default_timer() - start_time, 's')
# convert prediction and probabilities back to SimpleITK images
image_prediction = conversion.NumpySimpleITKImageBridge.convert(predictions.astype(np.uint8),
img.image_properties)
image_probabilities = conversion.NumpySimpleITKImageBridge.convert(probabilities, img.image_properties)
# evaluate segmentation without post-processing
evaluator.evaluate(image_prediction, img.images[structure.BrainImageTypes.GroundTruth], img.id_)
images_prediction.append(image_prediction)
images_probabilities.append(image_probabilities)
# post-process segmentation and evaluate with post-processing
post_process_params = {'simple_post': True}
images_post_processed = putil.post_process_batch(images_test, images_prediction, images_probabilities,
post_process_params, multi_process=False)
for i, img in enumerate(images_test):
evaluator.evaluate(images_post_processed[i], img.images[structure.BrainImageTypes.GroundTruth],
img.id_ + '-PP')
# save results
sitk.WriteImage(images_prediction[i], os.path.join(result_dir, images_test[i].id_ + '_SEG.mha'), True)
sitk.WriteImage(images_post_processed[i], os.path.join(result_dir, images_test[i].id_ + '_SEG-PP.mha'), True)
# use two writers to report the results
os.makedirs(result_dir, exist_ok=True) # generate result directory, if it does not exists
result_file = os.path.join(result_dir, 'results.csv')
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
result_summary_file = os.path.join(result_dir, 'results_summary.csv')
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()
end_main = timeit.default_timer()
main_time = end_main - start_main
# writing information on a txt file
reporter.feature_writer(result_dir, pre_process_params, main_time, 'feature_report')