def find_normalization_params(pat_adc, pat_gt, label, pat_model):
# Create the normalization object and load the model
adc_norm = PiecewiseLinearNormalization(ADCModality())
adc_norm.load_model(pat_model)
# Read the ADC
adc_mod = ADCModality()
adc_mod.read_data_from_path(pat_adc)
# Read the GT
gt_mod = GTModality()
gt_mod.read_data_from_path(label, pat_gt)
# Find the normalization parameters
adc_norm.fit(adc_mod, ground_truth=gt_mod, cat=label[0])
return adc_norm
# Remove a part of the string to have only the id
nb_patient = id_patient_list[id_p].replace('Patient ', '')
# Read the image data
adc_mod = ADCModality()
adc_mod.read_data_from_path(p_adc)
# Read the GT
gt_mod = GTModality()
gt_mod.read_data_from_path(label_gt, p_gt)
# Read the normalization information
pat_chg = id_patient_list[id_p].lower().replace(' ', '_') + '_norm.p'
filename = os.path.join(path_piecewise, pat_chg)
adc_norm = PiecewiseLinearNormalization.load_from_pickles(filename)
# Normalize the data
adc_mod = adc_norm.normalize(adc_mod)
# Create an object to extract the data in a matrix format using
# the ground-truth
ise = IntensitySignalExtraction(adc_mod)
# Get the data
print 'Extract the signal intensity for the ROI'
data = ise.transform(adc_mod, ground_truth=gt_mod, cat=label_gt[0])
# Store the data
print 'Store the matrix'
# Generate the different path to be later treated
path_patients_list_adc = []
path_patients_list_gt = []
# Create the generator
id_patient_list = (name for name in os.listdir(path_patients)
if os.path.isdir(os.path.join(path_patients, name)))
for id_patient in id_patient_list:
# Append for the ADC data
path_patients_list_adc.append(
os.path.join(path_patients, id_patient, path_adc))
# Append for the GT data - Note that we need a list of gt path
path_patients_list_gt.append(
[os.path.join(path_patients, id_patient, path_gt)])
# Create the model iteratively
adc_model = PiecewiseLinearNormalization(ADCModality())
for pat_adc, pat_gt in zip(path_patients_list_adc, path_patients_list_gt):
# Read the ADC
adc_mod = ADCModality()
adc_mod.read_data_from_path(pat_adc)
# Read the GT
gt_mod = GTModality()
gt_mod.read_data_from_path(label_gt, pat_gt)
# Fit the model
adc_model.partial_fit_model(adc_mod, ground_truth=gt_mod, cat=label_gt[0])
# Define the path where to store the model
path_store_model = '/data/prostate/pre-processing/mp-mri-prostate/adc-model'
filename_model = os.path.join(path_store_model, 'piecewise_model.npy')