def fuse_labels(valGen, model, dataGenerator, outFile="TRAIN_MERGED.h5"):
'''
Method to create dataset that contains labels from both datasets (SegTHOR & LCTSC)
'''
#create instance of Plotter class
plotter = Plotter()
#create instance of FeatureLabelReader object, I will use "save_image_mask" method
# reader = FeatureLabelReader()
imgNum = 0
# while imgNum<config1["VALSIZE"]:
while imgNum < 5981: #total number of slices in LCTSC file
imgBatch, label = next(valGen)
labelBatch = label["organ_output"]
#denormalize image for plotting
# imgBatchDeNorm = dataGenerator.denormalize(imgBatch)
imgOriginal = dataGenerator.images
#output of image is one-hot encoded, so take argmax
#labelTrue = dataGenerator.morphological_operation(labelBatch.argmax(axis=-1).astype('uint8'),'open')
labelOriginal = dataGenerator.labels
#predict labels and apply inverse transformation
labelPred = model.predict(imgBatch)
labelPredUnZoom = dataGenerator.unzoom_label(
labelPred,
numClasses=5) #model predicts 5 labels, true labels contain 6
labelPredDeCrop = dataGenerator.uncrop_label(labelPredUnZoom,
numClasses=5)
#get selected index of predictions
labelPredMorph = dataGenerator.morphological_operation(
labelPredDeCrop.argmax(axis=-1).astype('uint8'), 'open')
#create merged labels
labelMerged = label_merger(labelOriginal, labelPredMorph)
k = plotter.plot_label_prediction(imgOriginal, labelMerged,
labelPredMorph)
if k == 27: break
elif k == ord('s'):
print("Saving ", imgNum)
FeatureLabelReader.save_image_mask(imgOriginal,
labelMerged,
fileName=outFile)
#print("Processed ",imgNum)
imgNum += imgBatch.shape[0]
def merged_datasets(valGen, model, dataGenerator, outFile="TRAIN_MERGED.h5"):
'''
Method used to merge SegTHOR and LCTSC dataset
SegTHOR has {'esophagus':1,'heart':2,'trachea':3,'aorta'}
LCTSC has {'esophagus':1, 'heart':2, 'spinal cord':3 ,'L-R Lung':4,5}
'''
#create instance of Plotter class
plotter = Plotter()
imgNum = 0
while imgNum < 5981: #total number of slices in LCTSC file
imgBatch, label = next(valGen)
imgOriginal = dataGenerator.images
labelOriginal = dataGenerator.labels
#I am assigning different value to spinal cord
#labelOriginal[labelOriginal==3] = 6
labelOriginal[labelOriginal == 4] = 0
labelOriginal[labelOriginal == 5] = 0
labelOriginal[labelOriginal == 3] = 0
#look for slices that has non-zero label
zSlices = np.array([
np.max(labelOriginal[idx, ...]) > 0
for idx in range(imgBatch.shape[0])
],
dtype=np.bool)
print(imgOriginal.shape)
imgSave = imgOriginal[zSlices, ...]
labelSave = labelOriginal[zSlices, ...]
print(imgSave.shape)
if imgSave.shape[0] > 0:
print("Saving ", imgNum)
FeatureLabelReader.save_image_mask(imgSave,
labelSave,
fileName=outFile)
#k = plotter.plot_slice_label(imgOriginal,labelOriginal)
#if k==27: break
imgNum += imgBatch.shape[0]
def compile_dataset(pathToFiles,fileName):
myParser = FeatureLabelReader(pathToFiles=pathToFiles,structNameMap=prostate_struct)
images = myParser.end_point_parser(dirPattern=["CT"],filePattern="*.dcm")
labels = myParser.end_point_parser(dirPattern=["RTst"],filePattern="*.dcm")
#now test compile dataset
myParser.compile_dataset(imgFiles=images,labelFiles=labels,fileName=fileName)
def compile_dataset(pathToFiles, fileName):
#test path in which feature label are same folder
myParser = FeatureLabelReader(pathToFiles=pathToFiles)
images = myParser.end_point_parser(filePath=pathToFiles,
filePattern="Patient*.nii.gz")
labels = myParser.end_point_parser(filePath=pathToFiles,
filePattern="GT*.nii.gz")
#now test compile dataset
myParser.compile_dataset(imgFiles=images,
labelFiles=labels,
fileName=fileName,
batchSize=1) #each nii contains ~220 slices
def compile_dataset(pathToFiles, fileName):
myParser = FeatureLabelReader(pathToFiles=pathToFiles)
images = myParser.end_point_parser(filePattern="*.dcm",
dirPattern=["DICOM_anon"])
labels = myParser.end_point_parser(filePattern="liver_GT*.png",
dirPattern=["Ground"])
#length has to be equal
assert (images.__len__() == labels.__len__())
#now test compile dataset
myParser.compile_dataset(imgFiles=images,
labelFiles=labels,
fileName=fileName)
def compile_dataset2(pathToFiles, fileName):
#test path in which feature label are same folder
myParser = FeatureLabelReader(pathToFiles=pathToFiles,
structNameMap=lung_struct)
images = myParser.end_point_parser(filePath=pathToFiles,
filePattern="*.dcm",
dirPattern=["Scan", "Train"])
labels = myParser.end_point_parser(filePath=pathToFiles,
filePattern="*.dcm",
dirPattern=["RTst", "Train"])
#now test compile dataset
myParser.compile_dataset(imgFiles=images,
labelFiles=labels,
fileName=fileName)
def compile_dataset_unit_tester():
#test path in which feature label are seperated
pathToFiles = "../../SegmentationDataSets/CHAOS/CT_data_batch1/"
myParser = FeatureLabelReader(pathToFiles=pathToFiles,
structNameMap=prostate_struct)
images = myParser.end_point_parser(filePattern="i*.dcm")
labels = myParser.end_point_parser(filePattern="liver_GT*.png")
#length has to be equal
assert (images.__len__() == labels.__len__())
#testing RS file format
pathToFiles = "../../SegmentationDataSets/SBRT_Lung/"
myParser = FeatureLabelReader(pathToFiles=pathToFiles,
structNameMap=sbrt_lung_struct)
images = myParser.end_point_parser(filePath=pathToFiles,
filePattern="CT*.dcm")
labels = myParser.end_point_parser(filePath=pathToFiles,
filePattern="RS*.dcm")
#now test compile dataset
myParser.compile_dataset(imgFiles=images,
labelFiles=labels,
fileName="TRAIN_LUNG.h5")
#test path in which CT and RS in different directory
pathToFiles = "../TrainData/"
images = myParser.end_point_parser(filePath=pathToFiles,
dirPattern=["PROSTATE", "CT"],
filePattern="*.dcm")
labels = myParser.end_point_parser(filePath=pathToFiles,
dirPattern=["PROSTATE", "RTst"],
filePattern="*.dcm")
def end_point_unit_tester():
#test path in which feature label are seperates
pathToFiles = "../../SegmentationDataSets/CHAOS/CT_data_batch1/"
myParser = FeatureLabelReader(pathToFiles=pathToFiles)
images = myParser.end_point_parser(filePattern="i*.dcm")
labels = myParser.end_point_parser(filePattern="liver_GT*.png")
#length has to be equal
assert (images.__len__() == labels.__len__())
#test path in which feature label are same folder
pathToFiles = "../../SegmentationDataSets/SegTHOR/train/"
images = myParser.end_point_parser(filePath=pathToFiles,
filePattern="Patient*.nii.gz")
labels = myParser.end_point_parser(filePath=pathToFiles,
filePattern="GT*.nii.gz")
#length has to be equal
assert (images.__len__() == labels.__len__())
#test path in which CT and RS in different directory
pathToFiles = "../TrainData/"
images = myParser.end_point_parser(filePath=pathToFiles,
dirPattern=["PROSTATE", "CT"],
filePattern="*.dcm")
labels = myParser.end_point_parser(filePath=pathToFiles,
dirPattern=["PROSTATE", "RTst"],
filePattern="*.dcm")
#test path in which CT and RS struct in same directory
pathToFiles = "../../SegmentationDataSets/SBRT_Lung/"
images = myParser.end_point_parser(filePath=pathToFiles,
filePattern="CT*.dcm")
labels = myParser.end_point_parser(filePath=pathToFiles,
filePattern="RS*.dcm")
#test only images
pathToFiles = "../ValData/"
images = myParser.end_point_parser(filePath=pathToFiles)
print(images)