def main(unused_args):
test_data = load_train_data_folder('../input/norm1/', data_type=0, number_files=4)
test_data = np.reshape(test_data, [-1, 64, 64, 64])
# print("Input Data...")
# print("Shape: ", np.shape(test_data))
# print("Max: ", np.max(test_data))
# print("Min: ", np.min(test_data))
# print("Mean: ", np.mean(test_data))
# Create the Estimator
mnist_classifier = tf.estimator.Estimator(
model_fn=cnn_model_fn, model_dir="/home/joseph/Desktop/models/gilestest")
predict_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": test_data},
batch_size=1,
num_epochs=1,
shuffle=False)
# Predict data
predictions = mnist_classifier.predict(input_fn=predict_input_fn)
predictions = np.array(list(predictions))
print(predictions[0])
result = predictions[0]['classes']
# print(result)
# print(np.shape(result))
write_itk_imageArray(result, '../output/detected.nii.gz')
def main(unused_args):
test_data = load_test_data_folder('../input/norm2/', )
test_data = np.reshape(test_data, [-1, 64, 64])
print("Input Data...")
print("Shape: ", np.shape(test_data))
print("Max: ", np.max(test_data))
print("Min: ", np.min(test_data))
print("Mean: ", np.mean(test_data))
# Create the Estimator
mnist_classifier = tf.estimator.Estimator(
model_fn=cnn_model_fn, model_dir="/home/joseph/Projects/vascularnetworks/models/giles2d_deep")
predict_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": test_data},
batch_size=1,
num_epochs=1,
shuffle=False)
# Predict data
predictions = mnist_classifier.predict(input_fn=predict_input_fn)
predictions = np.array(list(predictions))
print(np.shape(predictions))
print(predictions[0]['classes'])
print(np.shape(predictions[0]['classes']))
result = np.zeros([64, 64, 64, 64], dtype='uint8')
for i in utility.my_range(0, 64, 1):
for j in utility.my_range(0, 64, 1):
result[i, j, :, :] = predictions[i * 64 + j]['classes']
# print(result)
# print(np.shape(result))
for i in utility.my_range(0, 64, 1):
write_itk_imageArray(result[i], '../input/myseg2/cropped' + str(i) + '.nii.gz')
def main(unused_args):
# Load training and eval data
# mnist = tf.contrib.learn.datasets.load_dataset("mnist")
# train_data = mnist.train.images # Returns np.array (55000, 784)
# train_labels = np.asarray(mnist.train.labels, dtype=np.int32) # (55000, 1)
test_data = load_test_data('..\\input\\test.mhd')
# print("Input Data...")
# print("Shape: ", np.shape(test_data))
# print("Max: ", np.max(test_data))
# print("Min: ", np.min(test_data))
# print("Mean: ", np.mean(test_data))
# Create the Estimator
mnist_classifier = tf.estimator.Estimator(
model_fn=cnn_model_fn, model_dir="/tmp/mnist_convnet_model")
predict_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": test_data},
batch_size=100,
num_epochs=1,
shuffle=False)
# Predict data
predictions = mnist_classifier.predict(input_fn=predict_input_fn)
predictions = np.array(list(predictions))
result = np.zeros(np.shape(predictions))
for index in utility.my_range(0, np.shape(predictions)[0], 1):
result[index] = predictions[index]['classes']
# print(result)
write_itk_imageArray(np.reshape(result, [128, 128, 128]), '..\\output\\detected.nii.gz')
from itkutilities import get_itk_array, write_itk_imageArray
import numpy as np
import sys
if __name__ == '__main__':
if len(sys.argv) != 3:
print("Usage: " + sys.argv[0] + " <inputImage> <outputImage>")
sys.exit(1)
inputimg = np.array(get_itk_array(sys.argv[1]), dtype="uint8")
outputimg = sys.argv[2]
inputimg = np.subtract(inputimg, inputimg.min())
inputimg = np.multiply(inputimg, 1.0 / inputimg.max(), casting='unsafe')
write_itk_imageArray(np.asarray(inputimg), outputimg)
# Crop image and write it.
# Checks surrounding. If no bifurc. Add it.
surrounding = bifimg[(i - 2 * stepsize - 1):i,
(j - 2 * stepsize):j,
(k - 2 * stepsize):k]
# If no bifurc
if np.max(surrounding) == 0:
cropped = inputimg[(i - blocksize - stepsize):(i + blocksize - stepsize + 1),
(j - blocksize - stepsize):(j + blocksize + 1 - stepsize),
(k - blocksize - stepsize):(k + blocksize + 1 - stepsize)]
# cropped_seg = segimg[(i - blocksize - stepsize):(i + blocksize + 1 - stepsize),
# (j - blocksize - stepsize):(j + blocksize + 1 - stepsize),
# (k - blocksize - stepsize):(k + blocksize + 1 - stepsize)]
write_itk_imageArray(cropped, workfolder + "cropped" + str(index) + ".nii.gz")
# write_itk_imageArray(cropped_seg, workfolder + "cropped" + str(index) + "_seg.nii.gz")
# Update indices
index = index + 1
print("Total bifurcations: ", index)
file.write(str(index) + "\n")
file.close()
print("Done.")
outputfile = sys.argv[2]
inputimg = np.array(get_itk_array(inputfile), dtype="uint8")
# perform skeletonization
skeleton = skeletonize_3d(inputimg)
if display == True:
# display results
fig, axes = plt.subplots(nrows=1,
ncols=2,
figsize=(8, 4),
sharex=True,
sharey=True,
subplot_kw={'adjustable': 'box-forced'})
ax = axes.ravel()
ax[0].imshow(inputimg[55], cmap=plt.cm.gray)
ax[0].axis('off')
ax[0].set_title('original', fontsize=20)
ax[1].imshow(skeleton[55], cmap=plt.cm.gray)
ax[1].axis('off')
ax[1].set_title('skeleton', fontsize=20)
fig.tight_layout()
plt.show()
write_itk_imageArray(skeleton, outputfile)
if len(sys.argv) != 9:
print(
"Usage: " + sys.argv[0] +
" <inputImage> <outputImage> <startX> <startY> <startZ> <sizeX> <sizeY> <sizeZ>"
)
sys.exit(1)
inputimg = get_itk_array(sys.argv[1])
outfile = sys.argv[2]
startX = int(sys.argv[3])
startY = int(sys.argv[4])
startZ = int(sys.argv[5])
sizeX = int(sys.argv[6])
sizeY = int(sys.argv[7])
sizeZ = int(sys.argv[8])
endX = startX + sizeX
endY = startY + sizeY
endZ = startZ + sizeZ
print(np.shape(inputimg))
print(startX, startY, startZ)
print(endX, endY, endZ)
cropped = inputimg[startX:endX, startY:endY, startZ:endZ]
write_itk_imageArray(cropped, outfile)
from itkutilities import get_itk_array, write_itk_imageArray
import numpy as np
import sys
if __name__ == '__main__':
inputimg = np.array(get_itk_array(sys.argv[1]), dtype='uint8')
# Write to File
write_itk_imageArray(inputimg, sys.argv[2])
from itkutilities import get_itk_array, write_itk_imageArray
import numpy as np
import sys
if __name__ == '__main__':
if len(sys.argv) != 3:
print("Usage: " + sys.argv[0] + " <inputImage> <outputImage>")
sys.exit(1)
inputimg = get_itk_array(sys.argv[1])
outputimg = sys.argv[2]
inputimg = np.multiply(inputimg, inputimg)
inputimg = np.multiply(inputimg, 255)
write_itk_imageArray(np.asarray(inputimg, dtype='uint8'), outputimg)
index = 0
for i in utility.my_range(0, xSize, stepsize):
for j in utility.my_range(0, ySize, stepsize):
for k in utility.my_range(0, zSize, stepsize):
print("Step at: (", index, ")", startX, startY, startZ)
endX = startX + stepsize
endY = startY + stepsize
endZ = startZ + stepsize
currentfilename = splitfolder + "/cropped" + str(index) + ".nii.gz"
currentfile = np.array(get_itk_array(currentfilename),
dtype='uint8')
joinedfile[startX:endX, startY:endY, startZ:endZ] = currentfile
# Update indices
startZ = startZ + stepsize
index = index + 1
startY = startY + stepsize
startZ = 0
startX = startX + stepsize
startY = 0
# Write the file on to disk.
print("Writing File to Disk...")
write_itk_imageArray(joinedfile, outputfile)
print("Done.")
counts = np.zeros(num_points)
for i in range(0, num_cells):
data = output.GetCell(i).GetPointIds()
counts[data.GetId(0)] += 1
counts[data.GetId(1)] += 1
# Indices start with 0.
for i in range(0, num_points):
# If bifurcation
if counts[i] > 2:
# print "index: ", i, " with ", counts[i], " connections"
pt = output.GetPoint(i)
x = int(pt[0] / xscale)
y = int(pt[1] / yscale)
z = int(pt[2] / zscale)
# print x, y, z
for j in range(-2, 3):
for k in range(-2, 3):
for l in range(-2, 3):
xinc = x + j
yinc = y + k
zinc = z + l
if xinc < 0 or yinc < 0 or zinc < 0 or xinc >= xwidth or yinc >= ywidth or zinc >= zwidth:
continue
else:
a[xinc, yinc, zinc] = 1
# Write the image.
itkutilities.write_itk_imageArray(a, output_file_name)
from itkutilities import get_itk_array, write_itk_imageArray
import numpy as np
import sys
if __name__ == '__main__':
if len(sys.argv) != 4:
print("Usage: " + sys.argv[0] + " <inputImage> <outputImage> <threshold>")
sys.exit(1)
inputimg = get_itk_array(sys.argv[1])
outputimg = sys.argv[2]
threshold = float(sys.argv[3])
write_itk_imageArray(np.asarray(inputimg >= threshold, dtype='uint8'), outputimg)
segment = False
if segment:
for i in utility.my_range(0, xSize, stepsize):
for j in utility.my_range(0, ySize, stepsize):
for k in utility.my_range(0, zSize, stepsize):
print("Step at: (", index, ")", startX, startY, startZ)
endX = startX + stepsize
endY = startY + stepsize
endZ = startZ + stepsize
# Crop image and write it.
cropped = inputimg[startX:endX, startY:endY, startZ:endZ]
write_itk_imageArray(
cropped, workfolder + "/cropped" + str(index) + ".nii.gz")
# Apply segmentation to it.
os.system("THEANO_FLAGS='device=gpu,floatX=float32' python " +
testfilename + " --model " + modelfilename + " " +
workfolder + "/cropped" + str(index) + ".nii.gz")
# Update indices
startZ = startZ + stepsize
index = index + 1
startY = startY + stepsize
startZ = 0
startX = startX + stepsize
startY = 0