def main():
parser = argparse.ArgumentParser(description='Copy data')
parser.add_argument('--base', default=os.path.dirname(os.path.abspath(__file__)),
help='Base directory path to program files')
parser.add_argument('--input_dir', type=str, default='../../data/raw',
help='Input directory')
parser.add_argument('--output_dir', type=str, default='../../data/interim',
help='Output directory')
args = parser.parse_args()
input_dir = os.path.join(args.base, args.input_dir)
path_list = [os.path.abspath(i) for i in glob.glob("{}/**/*T1*.gz".format(input_dir), recursive=True)]
result_dir = os.path.join(args.base, args.output_dir)
os.makedirs(result_dir, exist_ok=True)
for i, path in enumerate(path_list):
print('Data: {}'.format(path))
img = IO.read_mhd_and_raw(path, False)
#print('{}/{:04d}.mhd'.format(result_dir, i))
# To make clean mhd file
output = sitk.GetArrayFromImage(img)
output = sitk.GetImageFromArray(output)
output.SetSpacing(img.GetSpacing())
output.SetOrigin([0,0,0])
sitk.WriteImage(output, '{}/{:04d}.mhd'.format(result_dir, i))
def get_dataset(input, patch_side, num_of_test):
print('load data')
list = io.load_list(input)
data_set = np.zeros((num_of_test, patch_side, patch_side, patch_side))
for i in trange(num_of_test):
data_set[i, :] = np.reshape(io.read_mhd_and_raw(list[i]), [patch_side, patch_side, patch_side])
return data_set
def making_patch(num, img_path, mask_path, patch_side, threshold):
z_size = 320
y_size = 320
x_size = 320
w = int(patch_side / 2)
path_w = "E:/data/data{}_patch/sigma_0.9/th_{}/size_{}/".format(
num, threshold, patch_side)
# load data
print('load data')
img = io.read_mhd_and_raw(img_path)
mask = io.read_mhd_and_raw(mask_path)
img = np.reshape(img, [z_size, y_size, x_size])
mask = np.reshape(mask, [z_size, y_size, x_size])
# check folder
if not (os.path.exists(path_w)):
os.makedirs(path_w)
file = open(path_w + "filename.txt", mode='w')
count = 0
for z in range(z_size - 1):
for y in range(y_size - 1):
for x in range(x_size - 1):
if mask[z, y, x] > threshold and mask[z, y, x] > mask[z, y, x - 1] and mask[z, y, x] > mask[z, y, x + 1] \
and mask[z, y, x] > mask[z - 1, y, x] and mask[z, y, x] > mask[z + 1, y, x] \
and mask[z, y, x] > mask[z, y - 1, x] and mask[z, y, x] > mask[z, y + 1, x]:
patch = img[z - w:z + w + 1, y - w:y + w + 1,
x - w:x + w + 1]
patch = patch.reshape([patch_side, patch_side, patch_side])
eudt_image = sitk.GetImageFromArray(patch)
eudt_image.SetOrigin([patch_side, patch_side, patch_side])
eudt_image.SetSpacing([0.885, 0.885, 1])
io.write_mhd_and_raw(
eudt_image,
os.path.join(path_w,
"patch_{}_{}_{}.mhd".format(x, y, z)))
file.write(
os.path.join(
path_w,
"data1_patch_{}_{}_{}.mhd".format(x, y, z) + "\n"))
count += 1
print(count)
return 0
def main():
parser = argparse.ArgumentParser(description='Settings')
parser.add_argument('--root',
type=str,
default="E:/data/Tokushima/",
help='root path')
parser.add_argument('--data_n', type=int, default=1, help='index of data')
parser.add_argument('--org',
type=str,
default="float/",
help='target organ')
args = parser.parse_args()
# settings
# data_n = str(args.data_n).zfill(2)
# img_path = os.path.join(args.root, "Fukui_Ai-CT_Sept2015/Fukui_Ai-CT_Sept2015_{}-2.mhd".format(data_n))
# mask_path = os.path.join(args.root, "Fukui_Ai-CT_2015_Label/{}/Fukui_Ai-CT_Sept2015_{}-2_{}.mhd".format(args.org, data_n, args.org))
# check folder
w_path = os.path.join(args.root, "{}/".format(args.org))
os.makedirs(w_path, exist_ok=True)
case_list = io.load_list(args.root + 'filename.txt')
for i in case_list:
img_path = os.path.join(args.root, "CT", i)
out_path = os.path.join(w_path, os.path.basename(img_path))
mask_path = os.path.join(args.root, "Label", i)
# loading data
print("-" * 20, 'Loading data', "-" * 20)
print(img_path)
if os.path.isfile(img_path):
sitkimg = sitk.ReadImage(img_path, sitk.sitkInt16)
img = sitk.GetArrayFromImage(sitkimg)
mask = io.read_mhd_and_raw(mask_path)
# masking
img = np.where((mask == 1) | (mask == 2), img, -2000)
img = np.array(img, dtype='float32')
# cropping
idx = np.where(img != -2000)
z, y, x = idx
img = cropping(img, np.min(x), np.max(x), np.min(y), np.max(y),
np.min(z), np.max(z))
# plt.imshow(img[int(np.mean(z))], cmap='gray', interpolation=None)
# plt.show()
# saving img
eudt_image = sitk.GetImageFromArray(img)
eudt_image.SetSpacing(sitkimg.GetSpacing())
eudt_image.SetOrigin(sitkimg.GetOrigin())
sitk.WriteImage(eudt_image, out_path)
print(out_path)
def get_data_from_list(list, patch_side=9):
print('load data')
list = io.load_list(list)
data_set = np.empty((len(list), patch_side, patch_side, patch_side))
for i, name in enumerate(list):
data_set[i, :] = np.reshape(io.read_mhd_and_raw(name),
[patch_side, patch_side, patch_side])
return data_set
def main():
parser = argparse.ArgumentParser(description='py, in, out, num')
parser.add_argument('--indir', '-i1', default="E:/git/beta-VAE/output/CT/patch/model2/z24/alpha_1e-5/beta_0.1/spe/EUDT/", help='input directory')
parser.add_argument('--side', '-i2', type=int, default=9, help='patch side size')
parser.add_argument('--num_of_data', '-i3', type=int, default=5000, help='number of the input data')
args = parser.parse_args()
# check folder
indir = args.indir
outdir = os.path.join(indir, "dec/")
if not (os.path.exists(outdir)):
os.makedirs(outdir)
num_of_data = args.num_of_data
side = args.side
# load data
print('load data')
data_set = np.zeros((num_of_data, side, side, side))
# file = open(outdir + 'filename.txt', 'w')
list = []
with open(indir + 'filename.txt', 'rt') as f:
i = 0
for line in f:
if i >= num_of_data:
break
line = line.split()
sitkdata = sitk.ReadImage(line[0])
# data = sitk.GetArrayFromImage(sitkdata)
data = np.reshape(io.read_mhd_and_raw(line[0]), [side, side, side])
data_set[i, :] = data
list.append(line[0])
i += 1
print(i)
# for x in line:
# file.write(str(x) + "/n")
# file.close()
# print(list)
img = data_set.reshape(num_of_data, side, side, side)
file = open(outdir + "filename.txt", mode='w')
# Normalization
for i in trange(len(img)):
# print(i)
eudt_image = sitk.GetImageFromArray(img[i].reshape(side, side, side))
eudt_image.SetSpacing(sitkdata.GetSpacing())
eudt_image.SetOrigin(sitkdata.GetOrigin())
sitk.WriteImage(eudt_image, os.path.join(outdir, "{}.mhd".format(str(i).zfill(4))))
file = open(outdir + "filename.txt", mode='a')
file.write(os.path.join(outdir, "{}.mhd".format(str(i).zfill(4)) + "\n"))
file.close()
def main():
parser = argparse.ArgumentParser(
description='Generate low resolution images from HR images')
parser.add_argument('--base',
default=os.path.dirname(os.path.abspath(__file__)),
help='Base directory path to program files')
parser.add_argument('--config_path',
type=str,
default='../../configs/base.yml',
help='path to config file')
parser.add_argument('--input_dir',
type=str,
default='../../data/interim',
help='Input directory')
parser.add_argument('--output_dir',
type=str,
default='../../data/processed',
help='Output directory')
args = parser.parse_args()
config = yaml_utils.Config(
yaml.load(open(os.path.join(args.base, args.config_path))))
input_dir = os.path.join(args.base, args.input_dir)
path_list = glob.glob('{}/*.mhd'.format(input_dir))
result_dir = os.path.join(args.base, args.output_dir)
os.makedirs('{}/HR'.format(result_dir), exist_ok=True)
os.makedirs('{}/LR'.format(result_dir), exist_ok=True)
for i, path in enumerate(path_list):
hr_img = IO.read_mhd_and_raw(path, False)
hr_img.SetOrigin([0, 0, 0])
hr_size = hr_img.GetSize()
hr_spacing = hr_img.GetSpacing()
new_spacing = [i * config['upsampling_rate'] for i in hr_spacing]
new_size = [
int(hr_size[0] * (hr_spacing[0] / new_spacing[0]) + 0.5),
int(hr_size[1] * (hr_spacing[1] / new_spacing[1]) + 0.5),
int(hr_size[2] * (hr_spacing[2] / new_spacing[2]) + 0.5)
]
resampleFilter = sitk.ResampleImageFilter()
lr_img = resampleFilter.Execute(hr_img, new_size,
sitk.Transform(), sitk.sitkBSpline,
hr_img.GetOrigin(), new_spacing,
hr_img.GetDirection(), 0,
hr_img.GetPixelID())
# Save HR and LR images
sitk.WriteImage(lr_img, '{}/LR/{:04d}.mhd'.format(result_dir, i))
sitk.WriteImage(hr_img, '{}/HR/{:04d}.mhd'.format(result_dir, i))
if not (os.path.exists(outdir)):
os.makedirs(outdir)
# save parameters
with open(os.path.join(outdir, "params.json"), mode="w") as f:
json.dump(args.__dict__, f, indent=4)
writer = SummaryWriter(log_dir=outdir + "logs")
print('-' * 20, 'loading data', '-' * 20)
list = io.load_list(data_path)
data_set = np.zeros((len(list), patch_side, patch_side, patch_side))
for i in trange(len(list)):
data_set[i, :] = np.reshape(io.read_mhd_and_raw(list[i]),
[patch_side, patch_side, patch_side])
data = data_set.reshape(num_of_data, patch_side * patch_side * patch_side)
data = min_max(data, axis=1)
# split data
test_data = torch.from_numpy(data[:num_of_test]).float()
val_data = torch.from_numpy(data[num_of_test:num_of_test +
num_of_val]).float().to(device)
train_data = torch.from_numpy(data[num_of_test +
num_of_val:]).float().to(device)
train_loader = torch.utils.data.DataLoader(train_data,
batch_size=args.batch_size,
shuffle=True,
import random
import matplotlib.pyplot as plt
import matplotlib.cm as cm
from scipy import ndimage
import utils, os
import torch.nn
# outdir1 = "E:/result/cars/generalization/L1"
outdir2 = "./"
#
# # check folder
# if not (os.path.exists(outdir1)):
# os.makedirs(outdir1)
# img = io.read_mhd_and_raw("E:/from_kubo/vector_rotation/x64/Release/output/output_5_5_2.mhd")
#
img1 = io.read_mhd_and_raw("E:/git/pytorch/vae/results/artificial/hole/z_6/B_0.1/batch128/L_60000/gen/ori/0001.mhd")
# img2 = io.read_mhd_and_raw("E:/git/pytorch/vae/results/artificial/tip/z_24/B_0.1/L_0/gen/rec/0000.mhd")
# # "E:/git/pca/output/CT/patch/z24/EUDT/recon_104.mhd"
#
# img1 = (img1 - np.min(img1))/ (np.max(img1) - np.min(img1))
# img3 = abs(img1 -img2)
# print(img3)
# print(np.max(img3))
# print(np.min(img3))
# ori=np.reshape(img1, [9,9,9])
# preds=np.reshape(img2, [9,9,9])
#
# # plot reconstruction
# utils.display_image(img1, img2, img3, 9, outdir1)
from utils import get_dataset
def plot_hist(g_hist, th_v):
plt.plot(g_hist)
plt.axvline(x=th_v, color='red', label='otsu')
plt.legend(loc='upper right')
plt.title("histogram, otsu and ave value")
plt.xlabel("brightness")
plt.ylabel("frequency")
plt.show()
print("load data")
path = "E:/data/Tokushima/Lung/t0000190_6.mhd"
img = io.read_mhd_and_raw(path)
target = np.where(img == -2000, False, img)
val = filters.threshold_otsu(target)
# val = -700
# hist, bins_center = exposure.histogram(img, nbins=10)
print(img.shape)
print(val)
slice = np.argmax(np.average(np.average(img, axis=2), axis=1), axis=0)
print(slice)
plt.figure(figsize=(9, 4))
plt.subplot(131)
plt.imshow(img[slice], cmap='gray', interpolation=None)
plt.axis('off')
writer = SummaryWriter(log_dir=outdir+"logs")
if not (os.path.exists(outdir)):
os.makedirs(outdir)
# save parameters
with open(os.path.join(outdir, "params.json"), mode="w") as f:
json.dump(args.__dict__, f, indent=4)
print('load data')
list = io.load_list(data_path)
data_set = np.zeros((len(list), image_size, image_size, image_size))
for i in trange(len(list)):
data_set[i, :] = np.reshape(io.read_mhd_and_raw(list[i]), [image_size, image_size, image_size])
data = data_set.reshape(num_of_data, image_size * image_size * image_size)
def min_max(x, axis=None):
x_min = x.min(axis=axis, keepdims=True)
x_max = x.max(axis=axis, keepdims=True)
return (x - x_min) / (x_max - x_min)
data = min_max(data, axis=1)
test_data = torch.from_numpy(data[:num_of_test]).float()
val_data = torch.from_numpy(data[num_of_test:num_of_test+num_of_val]).float().to(device)
train_data = torch.from_numpy(data[num_of_test+num_of_val:]).float().to(device)
def main():
parser = argparse.ArgumentParser(description='py, in, out, num')
parser.add_argument(
'--indir',
'-i1',
default="E:/git/TFRecord_example/input/CT/patch/size9/",
help='input directory')
parser.add_argument('--side',
'-i2',
type=int,
default=9,
help='patch side size')
parser.add_argument('--num_of_data',
'-i3',
type=int,
default=3039,
help='number of the input data')
args = parser.parse_args()
# check folder
indir = args.indir
outdir = os.path.join(indir, "cc1/")
if not (os.path.exists(outdir)):
os.makedirs(outdir + 'test')
os.makedirs(outdir + 'val')
os.makedirs(outdir + 'train')
num_of_data = args.num_of_data
side = args.side
# load data
print('load data')
data_set = np.zeros((num_of_data, side, side, side))
# file = open(outdir + 'filename.txt', 'w')
list = []
with open(indir + 'filename.txt', 'rt') as f:
i = 0
for line in f:
if i >= num_of_data:
break
line = line.split()
sitkdata = sitk.ReadImage(line[0])
# data = sitk.GetArrayFromImage(sitkdata)
data = np.reshape(io.read_mhd_and_raw(line[0]), [side, side, side])
data_set[i, :] = data
list.append(line[0])
i += 1
print(i)
# for x in line:
# file.write(str(x) + "/n")
# file.close()
# print(list)
# load mask
# topo = pd.read_csv(indir + "topo.csv", header=None).values.tolist()
# print(topo)
# topo = np.loadtxt(indir + "topo.csv", delimiter=",", dtype="unicode")
# topo = [flatten for inner in topo for flatten in inner]
# file = open(outdir + "filename.txt", mode='w')
# Normalization
data_set = rank_norm(data_set.reshape(num_of_data, side * side * side))
data_set = data_set.reshape(num_of_data, side, side, side)
for i in trange(len(data_set)):
# if topo[i] == 1:
# print(i)
eudt_image = sitk.GetImageFromArray(data_set[i].reshape(
side, side, side))
eudt_image.SetSpacing(sitkdata.GetSpacing())
eudt_image.SetOrigin(sitkdata.GetOrigin())
if i <= 602: folder = "test/"
elif i <= 602 * 2: folder = "val/"
else: folder = "train/"
sitk.WriteImage(
eudt_image,
os.path.join(outdir, folder, "{}.mhd".format(str(i).zfill(4))))
file = open(outdir + folder + "filename.txt", mode='a')
file.write(
os.path.join(outdir, folder,
"{}.mhd".format(str(i).zfill(4)) + "\n"))
file.close()
# setting
# center of the vessel
x_center, y_center, z_center = 6, 4, 7
size = 9
# ROI
s_roi = 1
e_roi = size - 1
roi = e_roi - s_roi
# path
path = "./input/"
file = "data"
# input
print("load data")
img = io.read_mhd_and_raw(path + file + ".mhd", 'double')
img = np.reshape(img, (size, size, size))
# roi
profile = img[z_center:z_center + 1, y_center:y_center + 1, s_roi:e_roi]
# profile = np.reshape(profile, (roi, 1))
x_fit = np.linspace(0, roi - 1, roi * 10)
# fitting
print("start fitting")
x = np.linspace(0, roi - 1, roi)
y = np.reshape(profile, (roi))
print("-" * 20, "Gaussian fitting", "-" * 20)
r = scipy_fit(x, y)
def main():
parser = argparse.ArgumentParser(
description='py, data_list, num_per_tfrecord, outdir')
parser.add_argument('--data_list',
'-i1',
default='F:/data_info/TFrecord/liver/set_2/train.txt',
help='data list')
parser.add_argument('--num_per_tfrecord',
'-i2',
default=250,
help='number per tfrecord')
parser.add_argument('--outdir',
'-i3',
default='F:/data/tfrecord/liver/test',
help='outdir')
parser.add_argument('--tfrc_index',
'-i4',
default='1',
help='tfrecord index')
args = parser.parse_args()
# check folder
if not (os.path.exists(args.outdir)):
os.makedirs(args.outdir)
# load list
input_list = io.load_list(args.data_list)
# shuffle
random.shuffle(input_list)
print('data size: {}'.format(len(input_list)))
num_per_tfrecord = int(args.num_per_tfrecord)
num_of_total_image = len(input_list)
if (num_of_total_image % num_per_tfrecord != 0):
num_of_recordfile = num_of_total_image // num_per_tfrecord + 1
else:
num_of_recordfile = num_of_total_image // num_per_tfrecord
num_per_tfrecord_final = num_of_total_image - num_per_tfrecord * (
num_of_recordfile - 1)
print('number of total TFrecordfile: {}'.format(num_of_recordfile))
# write TFrecord
for i in range(num_of_recordfile):
tfrecord_filename = os.path.join(
args.outdir, 'recordfile_{}'.format(args.tfrc_index))
options = tf.python_io.TFRecordOptions(
tf.python_io.TFRecordCompressionType.GZIP)
write = tf.python_io.TFRecordWriter(tfrecord_filename, options=options)
print('Writing recordfile_{}'.format(i + 1))
if i == num_of_recordfile - 1:
loop_buf = num_per_tfrecord_final
else:
loop_buf = num_per_tfrecord
for image_index in range(loop_buf):
# load data
print('image from: {}'.format(input_list[image_index +
i * num_per_tfrecord]))
data = io.read_mhd_and_raw(
input_list[image_index +
i * num_per_tfrecord]).astype('float32')
image = data.flatten()
example = tf.train.Example(features=tf.train.Features(
feature={
'img_raw':
tf.train.Feature(float_list=tf.train.FloatList(
value=image)),
}))
write.write(example.SerializeToString())
write.close()
