def test_integrity(param_test):
"""
Test integrity of function
"""
# apply transformation to binary mask: template --> anat
sct_apply_transfo.main(args=[
'-i', param_test.fname_gt, '-d', param_test.dict_args_with_path['-s'],
'-w', 'warp_template2anat.nii.gz', '-o', 'test_template2anat.nii.gz',
'-x', 'nn', '-v', '0'
])
# apply transformation to binary mask: anat --> template
sct_apply_transfo.main(args=[
'-i', param_test.dict_args_with_path['-s'], '-d', param_test.fname_gt,
'-w', 'warp_anat2template.nii.gz', '-o', 'test_anat2template.nii.gz',
'-x', 'nn', '-v', '0'
])
# compute dice coefficient between template segmentation warped to anat and segmentation from anat
im_seg = Image(param_test.dict_args_with_path['-s'])
im_template_seg_reg = Image('test_template2anat.nii.gz')
dice_template2anat = compute_dice(im_seg,
im_template_seg_reg,
mode='3d',
zboundaries=True)
# check
param_test.output += 'Dice[seg,template_seg_reg]: ' + str(
dice_template2anat)
if dice_template2anat > param_test.dice_threshold:
param_test.output += '\n--> PASSED'
else:
param_test.status = 99
param_test.output += '\n--> FAILED'
# compute dice coefficient between anat segmentation warped to template and segmentation from template
im_seg_reg = Image('test_anat2template.nii.gz')
im_template_seg = Image(param_test.fname_gt)
dice_anat2template = compute_dice(im_seg_reg,
im_template_seg,
mode='3d',
zboundaries=True)
# check
param_test.output += '\n\nDice[seg_reg,template_seg]: ' + str(
dice_anat2template)
if dice_anat2template > param_test.dice_threshold:
param_test.output += '\n--> PASSED'
else:
param_test.status = 99
param_test.output += '\n--> FAILED'
# update Panda structure
param_test.results['dice_template2anat'] = dice_template2anat
param_test.results['dice_anat2template'] = dice_anat2template
return param_test
def test_integrity(param_test):
"""
Test integrity of function
"""
dice_segmentation = float('nan')
# extract name of output segmentation: data_seg.nii.gz
file_seg = os.path.join(param_test.path_output,
sct.add_suffix(param_test.file_input, '_seg'))
# open output segmentation
im_seg = Image(file_seg)
# open ground truth
im_seg_manual = Image(param_test.fname_gt)
# compute dice coefficient between generated image and image from database
dice_segmentation = compute_dice(im_seg,
im_seg_manual,
mode='3d',
zboundaries=False)
# display
param_test.output += 'Computed dice: ' + str(dice_segmentation)
param_test.output += '\nDice threshold (if computed Dice smaller: fail): ' + str(
param_test.dice_threshold)
if dice_segmentation < param_test.dice_threshold:
param_test.status = 99
param_test.output += '\n--> FAILED'
else:
param_test.output += '\n--> PASSED'
# update Panda structure
param_test.results['dice'] = dice_segmentation
return param_test
def test_integrity(param_test):
"""
Test integrity of function
"""
path_data = os.path.join(param_test.path_data, param_test.contrast,
param_test.file_input)
integrity_value = 1.0
# open output segmentation
try:
im_seg_manual = Image(path_data)
except:
param_test.output += 'ERROR: Cannot open ground truth segmentation: ' + path_data
param_test.status = 99
return param_test
# compute dice coefficient between generated image and image from database
dice_segmentation = compute_dice(im_seg_manual,
im_seg_manual,
mode='3d',
zboundaries=False)
param_test.output += 'Computed dice: ' + str(dice_segmentation)
if dice_segmentation != integrity_value:
param_test.output += '\nERROR: Dice coefficient should be : ' + str(
integrity_value)
param_test.status = 99
return param_test
def test(path_data='', parameters=''):
# initialization
verbose = 0
output = ''
# check if isct_propseg compatibility
status_isct_propseg, output_isct_propseg = commands.getstatusoutput('isct_propseg')
isct_propseg_version = output_isct_propseg.split('\n')[0]
if isct_propseg_version != 'sct_propseg - Version 1.1 (2015-03-24)':
status = 99
output += '\nERROR: isct_propseg does not seem to be compatible with your system or is no up-to-date... Please contact SCT administrators.'
return status, output, DataFrame(data={'status': status, 'output': output}, index=[path_data])
# parameters
if not parameters:
parameters = '-i t2/t2.nii.gz -c t2'
dice_threshold = 0.9
parser = sct_propseg.get_parser()
dict_param = parser.parse(parameters.split(), check_file_exist=False)
dict_param_with_path = parser.add_path_to_file(deepcopy(dict_param), path_data, input_file=True)
param_with_path = parser.dictionary_to_string(dict_param_with_path)
# Extract contrast
contrast = ''
input_filename = ''
if dict_param['-i'][0] == '/':
dict_param['-i'] = dict_param['-i'][1:]
input_split = dict_param['-i'].split('/')
if len(input_split) == 2:
contrast = input_split[0]
input_filename = input_split[1]
else:
input_filename = input_split[0]
if not contrast: # if no contrast folder, send error.
status = 1
output += '\nERROR: when extracting the contrast folder from input file in command line: ' + dict_param['-i'] + ' for ' + path_data
return status, output, DataFrame(data={'status': status, 'output': output, 'dice_segmentation': float('nan')}, index=[path_data])
import time, random
subject_folder = path_data.split('/')
if subject_folder[-1] == '' and len(subject_folder) > 1:
subject_folder = subject_folder[-2]
else:
subject_folder = subject_folder[-1]
path_output = sct.slash_at_the_end('sct_propseg_' + subject_folder + '_' + time.strftime("%y%m%d%H%M%S") + '_' + str(random.randint(1, 1000000)), slash=1)
param_with_path += ' -ofolder ' + path_output
sct.create_folder(path_output)
# log file
import sys
fname_log = path_output + 'output.log'
stdout_log = file(fname_log, 'w')
# redirect to log file
stdout_orig = sys.stdout
sys.stdout = stdout_log
# Check if input files exist
if not (os.path.isfile(dict_param_with_path['-i'])):
status = 200
output += '\nERROR: the file(s) provided to test function do not exist in folder: ' + path_data
write_to_log_file(fname_log, output, 'w')
return status, output, DataFrame(
data={'status': status, 'output': output, 'dice_segmentation': float('nan')}, index=[path_data])
# Check if ground truth files exist
if not os.path.isfile(path_data + contrast + '/' + contrast + '_seg_manual.nii.gz'):
status = 201
output += '\nERROR: the file *_labeled_center_manual.nii.gz does not exist in folder: ' + path_data
write_to_log_file(fname_log, output, 'w')
return status, output, DataFrame(data={'status': int(status), 'output': output}, index=[path_data])
# run command
cmd = 'sct_propseg ' + param_with_path
output += '\n====================================================================================================\n'\
+ cmd + \
'\n====================================================================================================\n\n' # copy command
time_start = time.time()
try:
status, o = sct.run(cmd, 0)
except:
status, o = 1, 'ERROR: Function crashed!'
output += o
duration = time.time() - time_start
# extract name of manual segmentation
# by convention, manual segmentation are called inputname_seg_manual.nii.gz where inputname is the filename
# of the input image
segmentation_filename = path_output + sct.add_suffix(input_filename, '_seg')
manual_segmentation_filename = path_data + contrast + '/' + sct.add_suffix(input_filename, '_seg_manual')
dice_segmentation = float('nan')
# if command ran without error, test integrity
if status == 0:
# compute dice coefficient between generated image and image from database
dice_segmentation = compute_dice(Image(segmentation_filename), Image(manual_segmentation_filename), mode='3d', zboundaries=False)
if dice_segmentation < dice_threshold:
status = 99
# transform results into Pandas structure
results = DataFrame(data={'status': status, 'output': output, 'dice_segmentation': dice_segmentation, 'duration [s]': duration}, index=[path_data])
sys.stdout.close()
sys.stdout = stdout_orig
# write log file
write_to_log_file(fname_log, output, mode='r+', prepend=True)
return status, output, results
def test(path_data='', parameters=''):
verbose = 0
# check if isct_propseg compatibility
status_isct_propseg, output_isct_propseg = commands.getstatusoutput('isct_propseg')
isct_propseg_version = output_isct_propseg.split('\n')[0]
if isct_propseg_version != 'sct_propseg - Version 1.1 (2015-03-24)':
status = 99
output = 'ERROR: isct_propseg does not seem to be compatible with your system or is no up-to-date... Please contact SCT administrators.'
return status, output, DataFrame(data={'status': status, 'output': output}, index=[path_data])
# parameters
if not parameters:
parameters = '-i t2/t2.nii.gz -c t2'
dice_threshold = 0.9
parser = sct_propseg.get_parser()
dict_param = parser.parse(parameters.split(), check_file_exist=False)
dict_param_with_path = parser.add_path_to_file(deepcopy(dict_param), path_data, input_file=True)
param_with_path = parser.dictionary_to_string(dict_param_with_path)
# Extract contrast
contrast = ''
input_filename = ''
if dict_param['-i'][0] == '/':
dict_param['-i'] = dict_param['-i'][1:]
input_split = dict_param['-i'].split('/')
if len(input_split) == 2:
contrast = input_split[0]
input_filename = input_split[1]
else:
input_filename = input_split[0]
if not contrast: # if no contrast folder, send error.
status = 1
output = 'ERROR: when extracting the contrast folder from input file in command line: ' + dict_param['-i'] + ' for ' + path_data
return status, output, DataFrame(data={'status': status, 'output': output, 'dice_segmentation': float('nan')}, index=[path_data])
# Check if input files exist
if not (os.path.isfile(dict_param_with_path['-i'])):
status = 200
output = 'ERROR: the file(s) provided to test function do not exist in folder: ' + path_data
return status, output, DataFrame(
data={'status': status, 'output': output, 'dice_segmentation': float('nan')}, index=[path_data])
# Check if ground truth files exist
if not os.path.isfile(path_data + contrast + '/' + contrast + '_seg_manual.nii.gz'):
status = 200
output = 'ERROR: the file *_labeled_center_manual.nii.gz does not exist in folder: ' + path_data
return status, output, DataFrame(data={'status': int(status), 'output': output}, index=[path_data])
import time, random
subject_folder = path_data.split('/')
if subject_folder[-1] == '' and len(subject_folder) > 1:
subject_folder = subject_folder[-2]
else:
subject_folder = subject_folder[-1]
path_output = sct.slash_at_the_end('sct_propseg_' + subject_folder + '_' + time.strftime("%y%m%d%H%M%S") + '_' + str(random.randint(1, 1000000)), slash=1)
param_with_path += ' -ofolder ' + path_output
# run command
cmd = 'sct_propseg ' + param_with_path
output = '\n====================================================================================================\n'\
+ cmd + \
'\n====================================================================================================\n\n' # copy command
time_start = time.time()
status, o = sct.run(cmd, verbose)
output += o
duration = time.time() - time_start
# extract name of manual segmentation
# by convention, manual segmentation are called inputname_seg_manual.nii.gz where inputname is the filename
# of the input image
segmentation_filename = path_output + sct.add_suffix(input_filename, '_seg')
manual_segmentation_filename = path_data + contrast + '/' + sct.add_suffix(input_filename, '_seg_manual')
dice_segmentation = float('nan')
# if command ran without error, test integrity
if status == 0:
# compute dice coefficient between generated image and image from database
dice_segmentation = compute_dice(Image(segmentation_filename), Image(manual_segmentation_filename), mode='3d', zboundaries=False)
if dice_segmentation < dice_threshold:
status = 99
# transform results into Pandas structure
results = DataFrame(data={'status': status, 'output': output, 'dice_segmentation': dice_segmentation, 'duration [s]': duration}, index=[path_data])
return status, output, results