def checkAnotatedLabels(argv):
# Number of input arguments
# 1: Folder containing label images
# 2: Folder to save corrected label images
# 3: Number of expected classes (including background)
# 4: Image type
# 0: nifti format
# 1: matlab format
# Do some sanity checks
if len(argv) < 4:
printUsage(1)
sys.exit()
imagesFolder = argv[0]
imagesFolderdst = argv[1]
numClasses = int(argv[2])
imageType = int(argv[3])
print imagesFolder
imageNames = getImageImageList(imagesFolder)
print imageNames
printFileNames = False
for i_d in xrange(0, len(imageNames)) :
if imageType == 0:
imageFileName = imagesFolder + '/' + imageNames[i_d]
[imageData,img_proxy] = load_nii(imageFileName, printFileNames)
else:
imageFileName = imagesFolder + '/' + imageNames[i_d]
imageData = load_matlab(imageFileName, printFileNames)
labelsOrig = np.unique(imageData)
if (len(labelsOrig) != numClasses):
print(" WARNING!!!!! Number of expected clases ({}) is different to found labels ({}) ".format(numClasses,len(labelsOrig)))
# Correct labels
labelCorrectedImage = np.zeros(imageData.shape,dtype=np.int8)
for i_l in xrange(0,len(labelsOrig)):
idx = np.where(imageData == labelsOrig[i_l])
labelCorrectedImage[idx] = i_l
print(" ... Saving labels...")
nameToSave = imagesFolderdst + '/' + imageNames[i_d]
if imageType == 0: # nifti
imageTypeToSave = np.dtype(np.int8)
saveImageAsNifti(labelCorrectedImage,
nameToSave,
imageFileName,
imageTypeToSave)
else: # Matlab
# Cast to int8 for saving purposes
saveImageAsMatlab(labelCorrectedImage.astype('int8'),nameToSave)
print " ****************************************** PROCESSING LABELS DONE ******************************************"
def checkAnotatedLabels(argv):
# Number of input arguments
# 1: Folder containing label images
# 2: Folder to save corrected label images
# 3: Number of expected classes (including background)
# 4: Image type
# 0: nifti format
# 1: matlab format
# Do some sanity checks
if len(argv) < 4:
printUsage(1)
sys.exit()
imagesFolder = argv[0]
imagesFolderdst = argv[1]
numClasses = int(argv[2])
imageType = int(argv[3])
imageNames = getImageImageList(imagesFolder)
printFileNames = False
for i_d in xrange(0, len(imageNames)) :
if imageType == 0:
imageFileName = imagesFolder + '/' + imageNames[i_d]
[imageData,img_proxy] = load_nii(imageFileName, printFileNames)
else:
imageFileName = imagesFolder + '/' + imageNames[i_d]
imageData = load_matlab(imageFileName, printFileNames)
labelsOrig = np.unique(imageData)
if (len(labelsOrig) != numClasses):
print(" WARNING!!!!! Number of expected clases ({}) is different to found labels ({}) ".format(numClasses,len(labelsOrig)))
# Correct labels
labelCorrectedImage = np.zeros(imageData.shape,dtype=np.int8)
for i_l in xrange(0,len(labelsOrig)):
idx = np.where(imageData == labelsOrig[i_l])
labelCorrectedImage[idx] = i_l
print(" ... Saving labels...")
nameToSave = imagesFolderdst + '/' + imageNames[i_d]
if imageType == 0: # nifti
imageTypeToSave = np.dtype(np.int8)
saveImageAsNifti(labelCorrectedImage,
nameToSave,
imageFileName,
imageTypeToSave)
else: # Matlab
# Cast to int8 for saving purposes
saveImageAsMatlab(labelCorrectedImage.astype('int8'),nameToSave)
print " ****************************************** PROCESSING LABELS DONE ******************************************"
def checkAnotatedLabels(argv):
# Number of input arguments
# 1: Folder containing label images
# 2: Folder to save corrected label images
# 3: Image type
# 0: nifti format
# 1: matlab format
# Do some sanity checks
if len(argv) < 3:
printUsage(1)
sys.exit()
imagesFolder = argv[0]
imagesFolderdst = argv[1]
imageType = int(argv[2])
imageNames = getImageImageList(imagesFolder)
printFileNames = False
for i_d in xrange(len(imageNames)) :
if imageType == 0:
imageFileName = imagesFolder + '/' + imageNames[i_d]
[imageData,img_proxy] = load_nii(imageFileName, printFileNames)
else:
imageFileName = imagesFolder + '/' + imageNames[i_d]
imageData = load_matlab(imageFileName, printFileNames)
# Find voxels different to 0
# NOTE: I assume voxels equal to 0 are outside my ROI (like in the skull stripped datasets)
idx = np.where(imageData > 0 )
# Create ROI and assign those indexes to 1
roiImage = np.zeros(imageData.shape,dtype=np.int8)
roiImage[idx] = 1
print(" ... Saving roi...")
nameToSave = imagesFolderdst + '/ROI_' + imageNames[i_d]
if imageType == 0: # nifti
imageTypeToSave = np.dtype(np.int8)
saveImageAsNifti(roiImage,
nameToSave,
imageFileName,
imageTypeToSave)
else: # Matlab
# Cast to int8 for saving purposes
saveImageAsMatlab(labelCorrectedImage.astype('int8'),nameToSave)
print " ****************************************** PROCESSING LABELS DONE ******************************************"
def checkAnotatedLabels(argv):
# Number of input arguments
# 1: Folder containing label images
# 2: Folder to save corrected label images
# 3: Image type
# 0: nifti format
# 1: matlab format
# Do some sanity checks
if len(argv) < 3:
printUsage(1)
sys.exit()
imagesFolder = argv[0]
imagesFolderdst = argv[1]
imageType = int(argv[2])
imageNames = getImageImageList(imagesFolder)
printFileNames = False
for i_d in xrange(len(imageNames)):
if imageType == 0:
imageFileName = imagesFolder + '/' + imageNames[i_d]
[imageData, img_proxy] = load_nii(imageFileName, printFileNames)
else:
imageFileName = imagesFolder + '/' + imageNames[i_d]
print imageFileName
imageData = load_matlab(imageFileName, printFileNames)
# Find voxels different to 0
# NOTE: I assume voxels equal to 0 are outside my ROI (like in the skull stripped datasets)
idx = np.where(imageData > 0)
# Create ROI and assign those indexes to 1
roiImage = np.zeros(imageData.shape, dtype=np.int8)
roiImage[idx] = 1
print(" ... Saving roi...")
nameToSave = imagesFolderdst + '/ROI_' + imageNames[i_d]
if imageType == 0: # nifti
imageTypeToSave = np.dtype(np.int8)
saveImageAsNifti(roiImage, nameToSave, imageFileName,
imageTypeToSave)
else: # Matlab
# Cast to int8 for saving purposes
saveImageAsMatlab(roiImage.astype('int8'), nameToSave)
print " ****************************************** PROCESSING LABELS DONE ******************************************"