def load_data(filename, csv=None, axis=0):
data3d, _ = DR.read(filename)
labels = []
slab = []
if csv:
df = pd.read_csv(csv)
labs = np.unique(df["label"])
vals = range(len(labs))
slab = dict(zip(vals, labs))
rev_slab = dict(zip(labs, vals))
fn_unique = np.unique(df["filename"])
name = filename.split('/')[-1]
file_list = [
i for i, item in enumerate(fn_unique) if item.endswith(name)
]
index = file_list[0]
this_fn = fn_unique[index]
one_file = df[df["filename"] == this_fn]
maximum_slice_number = np.max(
np.max(one_file[["start_slice_number", "stop_slice_number"]]))
labels = [None] * maximum_slice_number
dct = one_file[["label", "start_slice_number",
"stop_slice_number"]].to_dict()
start = dct['start_slice_number'].values()
stop = dct['stop_slice_number'].values()
label = dct['label'].values()
for i in vals:
a = start[i]
b = stop[i]
lab = rev_slab[label[i]]
c = [lab] * (b + 1 - a)
labels[a:b + 1] = c
for ind, position in enumerate(labels):
zer = np.zeros(len(vals))
zer[position - 1] = 1
labels[ind] = zer
if len(data3d.shape) == 3:
if axis != 0:
data3d = np.rollaxis(data3d, axis)
images = list()
for i in data3d:
images.append(i)
else:
if axis != 0:
print 'jednotlivé řezy musí být otočeny kolem správné osy'
images = data3d
return images, labels, slab
def test_write_read_hdf5(self):
import io3d.datawriter as dwriter
import io3d.datareader as dreader
import h5py
filename = 'test_file.hdf5'
data = (np.random.random([30, 100, 120]) * 30).astype(np.int16)
data[0:5, 20:60, 60:70] += 30
metadata = {'voxelsize_mm': [1, 2, 3]}
dwriter.write(data, filename, filetype='hdf5', metadata=metadata)
fi = h5py.File(filename, "r")
for key in fi.keys():
fi [key]
datap = dreader.read(filename, dataplus_format=True)
print(datap)
def test_write_read_hdf5(self):
import io3d.datawriter as dwriter
import io3d.datareader as dreader
import h5py
filename = 'test_file.hdf5'
data = (np.random.random([30, 100, 120]) * 30).astype(np.int16)
data[0:5, 20:60, 60:70] += 30
metadata = {'voxelsize_mm': [1, 2, 3]}
dwriter.write(data, filename, filetype='hdf5', metadata=metadata)
fi = h5py.File(filename, "r")
for key in fi.keys():
fi[key]
datap = dreader.read(filename, dataplus_format=True)
print(datap)
def test_write_and_read_hdf5(self):
filename = 'test_file.hdf5'
data = (np.random.random([30, 100, 120]) * 30).astype(np.int16)
data[0:5, 20:60, 60:70] += 30
metadata = {'voxelsize_mm': [1, 2, 3]}
dwriter.write(data, filename, filetype='hdf5', metadata=metadata)
newdata, newmetadata = dreader.read(filename, dataplus_format=False)
# hack with -1024, because of wrong data reading
self.assertEqual(data[10, 10, 10], newdata[10, 10, 10])
self.assertEqual(data[2, 10, 1], newdata[2, 10, 1])
self.assertEqual(newmetadata['voxelsize_mm'][0],
newmetadata['voxelsize_mm'][0])
# @TODO there is a bug in SimpleITK. slice voxel size must be same
# self. assertEqual(metadata['voxelsize_mm'][1],
# newmetadata['voxelsize_mm'][1])
self.assertEqual(metadata['voxelsize_mm'][2],
newmetadata['voxelsize_mm'][2])
os.remove(filename)
def ircad_group(datadirpath, organ='liver'):
# datadirpath = '/home/trineon/projects/metalisa/data/IRCAD'
for folder in glob.glob(datadirpath + '/labels/*/' + organ + '/'):
name = folder.split('/')[-3]
if (folder + 'IRCAD_' + str(name) + '_' + organ +
'.pklz') in glob.glob(folder + '*'):
continue
else:
# concatenate CT slicis to one 3D ndarray [number_of slices, res(1), res(2)]
scan = [None] * len(glob.glob(folder + '*'))
for image in glob.glob(folder + '*'):
label, _ = DR.read(image)
scan[int(image.split('/')[-1].split('_')[-1])] = label
scan = np.array(scan).astype(np.int32)
scan = scan.squeeze()
DW.write(scan,
folder + 'IRCAD_' + str(name) + '_' + organ + '.pklz',
metadata={"voxelsize_mm": [1, 1, 1]})
pass
def test_write_and_read_hdf5(self):
filename = 'test_file.hdf5'
data = (np.random.random([30, 100, 120]) * 30).astype(np.int16)
data[0:5, 20:60, 60:70] += 30
metadata = {'voxelsize_mm': [1, 2, 3]}
metadata[5] = "not a number"
metadata[7] = ["not a number"]
dwriter.write(data, filename, filetype='hdf5', metadata=metadata)
newdata, newmetadata = dreader.read(filename, dataplus_format=False)
# hack with -1024, because of wrong data reading
self.assertEqual(data[10, 10, 10], newdata[10, 10, 10])
self.assertEqual(data[2, 10, 1], newdata[2, 10, 1])
self.assertEqual(newmetadata['voxelsize_mm'][0],
newmetadata['voxelsize_mm'][0])
self.assertEqual(newmetadata[7][0],
newmetadata[7][0])
# @TODO there is a bug in SimpleITK. slice voxel size must be same
# self. assertEqual(metadata['voxelsize_mm'][1],
# newmetadata['voxelsize_mm'][1])
self.assertEqual(metadata['voxelsize_mm'][2],
newmetadata['voxelsize_mm'][2])
os.remove(filename)
def sliver_preparation(datadirpath,
output_datadirpath="output_data",
res=100,
ax=0,
organ='liver'):
csvpath = output_datadirpath + '/sliver_label_' + str(res) + '_' + str(
ax) + '_' + organ + '.csv'
stat = output_datadirpath + '/sliver_stat' + str(res) + '_' + str(
ax) + '_' + organ + '.csv'
# datadirpath = '/home/trineon/projects/metalisa/data/SLIVER'
f = h5py.File(
output_datadirpath + '/sliver_' + str(res) + '_' + str(ax) + '_' +
organ + '.hdf5', 'a')
num = 1
for image in glob.glob(datadirpath + '/*orig*.mhd'):
group = f.create_group(image.split('/')[-1])
orig, _ = DR.read(image)
if ax != 0:
orig = np.rollaxis(orig, ax)
i = orig.shape[0]
orig = misc.resize_to_shape(orig, [i, res, res])
DW.write(orig,
output_datadirpath + '/sliver_' + str(num) + '_' + str(res) +
'_' + str(ax) + '.pklz',
metadata={"voxelsize_mm": [1, 1, 1]})
filename = output_datadirpath + '/sliver' + str(num) + '_' + str(
res) + '_' + str(ax) + '.pklz'
num += 1
seg = image.replace('orig', 'seg')
lab, _ = DR.read(seg)
if ax != 0:
lab = np.rollaxis(lab, ax)
l = list()
a = 1
for slice in lab:
if len(np.unique(slice)) > 1:
l.append(2)
a = 2
else:
if a == 2:
l.append(3)
else:
l.append(1)
del lab
for ind, slice in enumerate(orig):
name = str(ind)
dset = group.create_dataset(name, data=slice)
dset.attrs['teacher'] = l[ind]
dset.attrs['origin file'] = filename
if l[-1] == 2:
x = len(l)
else:
x = l.index(3)
if l[0] == 2:
y = 0
else:
y = l.index(2)
dt = {
'filename': [filename, filename, filename],
'label': ['under ' + organ, organ, 'above ' + organ],
'start_slice_number': [0, y, x],
'stop_slice_number': [y - 1, x - 1, len(l) - 1],
'axis': ax
}
if dt['stop_slice_number'][0] == -1:
dt['stop_slice_number'][0] = 0
if os.path.exists(csvpath):
new_df = pd.read_csv(csvpath)
df = pd.DataFrame.from_dict(dt)
new_df = pd.concat([new_df, df], ignore_index=True)
else:
df0 = pd.DataFrame.from_dict(dt)
new_df = df0
new_df.to_csv(csvpath, index=False)
a = y
b = x - y
c = len(l) - x
dt = {
'filename': [filename],
'under liver': [a],
'liver': [b],
'above liver': [c],
'slices': [len(l)]
}
if os.path.exists(stat):
new_df = pd.read_csv(stat)
df = pd.DataFrame.from_dict(dt)
new_df = pd.concat([new_df, df], ignore_index=True)
else:
df0 = pd.DataFrame.from_dict(dt)
new_df = df0
new_df.to_csv(stat, index=False)
pass
def ircad_preparation(datadirpath,
output_datadirpath="output_data",
organ="liver",
res=100,
ax=0):
#test
stat = output_datadirpath + '/stat_ircad' + str(res) + '_' + str(
ax) + '_' + organ + '.csv'
csvpath = output_datadirpath + '/label_ircad_' + str(res) + '_' + str(
ax) + '_' + organ + '.csv'
# datadirpath = '/home/trineon/projects/metalisa/data/IRCAD'
seznam = [None] * 20
for folder in glob.glob(datadirpath + '/Pacient/*/'):
count = len(glob.glob(folder + '*'))
l = [None] * count
for image in glob.glob(folder + '*'):
number = int(image.split('/')[-1].split('_')[-1]) - 1
l[number], _ = DR.read(image)
if ax != 0:
l[number] = np.rollaxis(l[number], ax)
for ind, i in enumerate(l):
l[ind] = misc.resize_to_shape(i, [1, res, res])
scan = np.array(l)
if ax != 0:
np.rollaxis(scan, ax)
name = folder.split('/')[-2]
scan = scan.squeeze()
DW.write(scan,
output_datadirpath + '/IRCAD_' + str(name) + '_' + str(res) +
'_' + str(ax) + '.pklz',
metadata={"voxelsize_mm": [1, 1, 1]})
seznam[int(name) - 1] = output_datadirpath + '/IRCAD_' + str(
name) + '_' + str(res) + '_' + str(ax) + '.pklz'
ll = [None] * 20
for folder in glob.glob(datadirpath + '/labels/*/' + organ + '/'):
count = len(glob.glob(folder + '*'))
sez = list()
for image in glob.glob(folder + 'IRCAD*.pklz'):
label, _ = DR.read(image)
if ax != 0:
label = np.rollaxis(label, ax)
l = list()
a = 1
for slice in label:
if len(np.unique(slice)) > 1:
l.append(2)
a = 2
else:
if a == 2:
l.append(3)
else:
l.append(1)
ll[int(folder.split('/')[-3]) - 1] = l
file = seznam[int(folder.split('/')[-3]) - 1]
if l[-1] == 2:
x = len(l)
else:
x = l.index(3)
if l[0] == 2:
y = 0
else:
y = l.index(2)
dt = {
'filename': [file, file, file],
'label': ['under ' + organ, organ, 'above ' + organ],
'start_slice_number': [0, y, x],
'stop_slice_number': [y - 1, x - 1, len(l) - 1],
'axis': ax
}
if dt['stop_slice_number'][0] == -1:
dt['stop_slice_number'][0] = 0
if os.path.exists(csvpath):
new_df = pd.read_csv(csvpath)
df = pd.DataFrame.from_dict(dt)
new_df = pd.concat([new_df, df], ignore_index=True)
else:
df0 = pd.DataFrame.from_dict(dt)
new_df = df0
new_df.to_csv(csvpath, index=False)
a = y
b = x - y
c = len(l) - x
dt = {
'filename': [file],
'under liver': [a],
'liver': [b],
'above liver': [c],
'slices': [len(l)]
}
if os.path.exists(stat):
new_df = pd.read_csv(stat)
df = pd.DataFrame.from_dict(dt)
new_df = pd.concat([new_df, df], ignore_index=True)
else:
df0 = pd.DataFrame.from_dict(dt)
new_df = df0
new_df.to_csv(stat, index=False)
output_datadirpath + '/sliver_' + str(res) + '_' + str(
ax) + '_' + organ + '.hdf5'
f = h5py.File(
output_datadirpath + '/sliver_' + str(res) + '_' + str(ax) + '_' +
str(organ) + '.hdf5', 'a')
for index, file in enumerate(seznam):
group = f.create_group(file.split('/')[-1])
l = ll[index]
scan, _ = DR.read(file)
for ind, slice in enumerate(scan):
name = str(ind)
dset = group.create_dataset(name, data=slice)
dset.attrs['teacher'] = l[ind]
dset.attrs['origin file'] = file
f.close()
pass