def write_shape_stats(labels_or_file=[], sulci=[], fundi=[],
affine_transform_files=[], inverse_booleans=[], transform_format='itk',
area_file='', normalize_by_area=False, mean_curvature_file='',
travel_depth_file='', geodesic_depth_file='',
freesurfer_thickness_file='', freesurfer_curvature_file='',
freesurfer_sulc_file='',
labels_spectra=[], labels_spectra_IDs=[],
sulci_spectra=[], sulci_spectra_IDs=[],
labels_zernike=[], labels_zernike_IDs=[],
sulci_zernike=[], sulci_zernike_IDs=[],
exclude_labels=[-1]):
"""
Make tables of shape statistics per label, sulcus, and/or fundus.
Note ::
This function is tailored for Mindboggle outputs.
Parameters
----------
labels_or_file : list or string
label number for each vertex or name of VTK file with index scalars
sulci : list of integers
indices to sulci, one per vertex, with -1 indicating no sulcus
fundi : list of integers
indices to fundi, one per vertex, with -1 indicating no fundus
affine_transform_files : list of strings
affine transform files to standard space
inverse_booleans : list of of zeros and ones
for each transform, 1 to take the inverse, else 0
transform_format : string
format for transform file
Ex: 'txt' for text, 'itk' for ITK, and 'mat' for Matlab format
area_file : string
name of VTK file with surface area scalar values
normalize_by_area : Boolean
normalize all shape measures by area of label/feature? (UNTESTED)
mean_curvature_file : string
name of VTK file with mean curvature scalar values
travel_depth_file : string
name of VTK file with travel depth scalar values
geodesic_depth_file : string
name of VTK file with geodesic depth scalar values
freesurfer_thickness_file : string
name of VTK file with FreeSurfer thickness scalar values
freesurfer_curvature_file : string
name of VTK file with FreeSurfer curvature (curv) scalar values
freesurfer_sulc_file : string
name of VTK file with FreeSurfer convexity (sulc) scalar values
labels_spectra : list of lists of floats
Laplace-Beltrami spectra for each labeled region
labels_spectra_IDs : list of integers
unique labels for labels_spectra
sulci_spectra : list of lists of floats
Laplace-Beltrami spectra for each sulcus
sulci_spectra_IDs : list of integers
unique sulcus IDs for sulci_spectra
labels_zernike : list of lists of floats
Zernike moments for each labeled region
labels_zernike_IDs : list of integers
unique labels for labels_zernike
sulci_zernike : list of lists of floats
Zernike moments for each sulcus
sulci_zernike_IDs : list of integers
unique sulcus IDs for sulci_zernike
exclude_labels : list of lists of integers
indices to be excluded (in addition to -1)
Returns
-------
label_table : string
output table filename for label shapes
sulcus_table : string
output table filename for sulcus shapes
fundus_table : string
output table filename for fundus shapes
Examples
--------
>>> import os
>>> from mindboggle.mio.vtks import read_scalars
>>> from mindboggle.mio.tables import write_shape_stats
>>> path = '/homedir/mindboggled/Twins-2-1'
>>> labels_or_file = os.path.join(path, 'labels', 'left_cortical_surface', 'freesurfer_cortex_labels.vtk')
>>> sulci_file = os.path.join(path, 'features', 'left_cortical_surface', 'sulci.vtk')
>>> fundi_file = os.path.join(path, 'features', 'left_cortical_surface', 'fundus_per_sulcus.vtk')
>>> sulci, name = read_scalars(sulci_file)
>>> fundi, name = read_scalars(fundi_file)
>>> affine_transform_files = [] #os.path.join(path, 'arno', 'mri', 't1weighted_brain.MNI152Affine.txt')
>>> inverse_booleans = []
>>> #transform_format = 'mat'
>>> transform_format = 'itk'
>>> area_file = os.path.join(path, 'shapes', 'left_cortical_surface', 'area.vtk')
>>> normalize_by_area = False
>>> mean_curvature_file = os.path.join(path, 'shapes', 'left_cortical_surface', 'mean_curvature.vtk')
>>> travel_depth_file = os.path.join(path, 'shapes', 'left_cortical_surface', 'travel_depth.vtk')
>>> geodesic_depth_file = os.path.join(path, 'shapes', 'left_cortical_surface', 'geodesic_depth.vtk')
>>> freesurfer_thickness_file = ''
>>> freesurfer_curvature_file = ''
>>> freesurfer_sulc_file = ''
>>> #
>>> labels, name = read_scalars(labels_or_file)
>>> labels_spectra = []
>>> labels_spectra_IDs = []
>>> sulci_spectra = []
>>> sulci_spectra_IDs = []
>>> labels_zernike = []
>>> labels_zernike_IDs = []
>>> sulci_zernike = []
>>> sulci_zernike_IDs = []
>>> exclude_labels = [-1]
>>> #
>>> write_shape_stats(labels_or_file, sulci, fundi,
>>> affine_transform_files, inverse_booleans, transform_format,
>>> area_file, normalize_by_area,
>>> mean_curvature_file, travel_depth_file, geodesic_depth_file,
>>> freesurfer_thickness_file, freesurfer_curvature_file,
>>> freesurfer_sulc_file,
>>> labels_spectra, labels_spectra_IDs,
>>> sulci_spectra, sulci_spectra_IDs,
>>> labels_zernike, labels_zernike_IDs,
>>> sulci_zernike, sulci_zernike_IDs,
>>> exclude_labels)
"""
import os
import numpy as np
import pandas as pd
from mindboggle.guts.compute import means_per_label, stats_per_label, \
sum_per_label
from mindboggle.mio.vtks import read_scalars, read_vtk, \
apply_affine_transforms
from mindboggle.mio.labels import DKTprotocol
dkt = DKTprotocol()
# Make sure inputs are lists:
if isinstance(labels_or_file, np.ndarray):
labels = [int(x) for x in labels_or_file]
elif isinstance(labels_or_file, list):
labels = labels_or_file
elif isinstance(labels_or_file, str):
labels, name = read_scalars(labels_or_file)
if isinstance(sulci, np.ndarray):
sulci = [int(x) for x in sulci]
if isinstance(fundi, np.ndarray):
fundi = [int(x) for x in fundi]
if not labels and not sulci and not fundi:
import sys
sys.exit('No feature data to tabulate in write_shape_stats().')
spectrum_start = 1 # Store all columns of spectral components (0),
# or start from higher frequency components (>=1)
#-------------------------------------------------------------------------
# Feature lists, shape names, and shape files:
#-------------------------------------------------------------------------
# Feature lists:
feature_lists = [labels, sulci, fundi]
feature_names = ['label', 'sulcus', 'fundus']
spectra_lists = [labels_spectra, sulci_spectra]
spectra_ID_lists = [labels_spectra_IDs, sulci_spectra_IDs]
zernike_lists = [labels_zernike, sulci_zernike]
zernike_ID_lists = [labels_zernike_IDs, sulci_zernike_IDs]
table_names = ['label_shapes.csv', 'sulcus_shapes.csv',
'fundus_shapes.csv']
# Shape names corresponding to shape files below:
shape_names = ['area', 'travel depth', 'geodesic depth',
'mean curvature', 'freesurfer curvature',
'freesurfer thickness', 'freesurfer convexity (sulc)']
# Load shape files as a list of numpy arrays of per-vertex shape values:
shape_files = [area_file, travel_depth_file, geodesic_depth_file,
mean_curvature_file, freesurfer_curvature_file,
freesurfer_thickness_file, freesurfer_sulc_file]
shape_arrays = []
first_pass = True
area_array = []
for ishape, shape_file in enumerate(shape_files):
if os.path.exists(shape_file):
if first_pass:
points, indices, lines, faces, scalars_array, scalar_names, \
npoints, input_vtk = read_vtk(shape_file, True, True)
points = np.array(points)
first_pass = False
if affine_transform_files and transform_format:
affine_points, \
foo1 = apply_affine_transforms(affine_transform_files,
inverse_booleans, transform_format,
points, vtk_file_stem='')
else:
scalars_array, name = read_scalars(shape_file, True, True)
if scalars_array.size:
shape_arrays.append(scalars_array)
# Store area array:
if ishape == 0:
area_array = scalars_array.copy()
if normalize_by_area:
use_area = area_array
else:
use_area = []
# Initialize table file names:
label_table = ''
sulcus_table = ''
fundus_table = ''
# Loop through features / tables:
for itable, feature_list in enumerate(feature_lists):
column_names = []
#-----------------------------------------------------------------
# Label names:
#-----------------------------------------------------------------
label_title = 'name'
if itable == 0:
label_numbers = dkt.cerebrum_cortex_DKT31_numbers
label_names = dkt.cerebrum_cortex_DKT31_names
elif itable in [1, 2]:
label_numbers = dkt.sulcus_numbers
label_names = dkt.sulcus_names
else:
label_numbers = []
label_names = []
include_labels = label_numbers
nlabels = len(label_numbers)
#---------------------------------------------------------------------
# For each feature, construct a table of average shape values:
#---------------------------------------------------------------------
if feature_list:
feature_name = feature_names[itable]
columns = []
#-----------------------------------------------------------------
# Loop through shape measures:
#-----------------------------------------------------------------
column_names.extend(column_names[:])
for ishape, shape_array in enumerate(shape_arrays):
shape = shape_names[ishape]
print(' Compute statistics on {0} {1}...'.
format(feature_name, shape))
#-------------------------------------------------------------
# Append feature areas to columns:
#-------------------------------------------------------------
if ishape == 0 and np.size(area_array):
sums, label_list = sum_per_label(shape_array,
feature_list, include_labels, exclude_labels)
column_names.append(shape)
columns.append(sums)
#-------------------------------------------------------------
# Append feature shape statistics to columns:
#-------------------------------------------------------------
else:
medians, mads, means, sdevs, skews, kurts, \
lower_quarts, upper_quarts, \
label_list = stats_per_label(shape_array, feature_list,
include_labels, exclude_labels,
area_array, precision=1)
column_names.append(shape + ': median')
column_names.append(shape + ': MAD')
column_names.append(shape + ': mean')
column_names.append(shape + ': SD')
column_names.append(shape + ': skew')
column_names.append(shape + ': kurtosis')
column_names.append(shape + ': 25%')
column_names.append(shape + ': 75%')
columns.append(medians)
columns.append(mads)
columns.append(means)
columns.append(sdevs)
columns.append(skews)
columns.append(kurts)
columns.append(lower_quarts)
columns.append(upper_quarts)
#-----------------------------------------------------------------
# Mean positions in the original space:
#-----------------------------------------------------------------
# Compute mean position per feature:
positions, sdevs, label_list, foo = means_per_label(points,
feature_list, include_labels, exclude_labels, use_area)
# Append mean x,y,z position per feature to columns:
xyz_positions = np.asarray(positions)
for ixyz, xyz in enumerate(['x','y','z']):
column_names.append('mean position: {0}'.format(xyz))
columns.append(xyz_positions[:, ixyz].tolist())
#-----------------------------------------------------------------
# Mean positions in standard space:
#-----------------------------------------------------------------
if affine_transform_files and transform_format:
# Compute standard space mean position per feature:
standard_positions, sdevs, label_list, \
foo = means_per_label(affine_points,
feature_list, include_labels, exclude_labels, use_area)
# Append standard space x,y,z position per feature to columns:
xyz_std_positions = np.asarray(standard_positions)
for ixyz, xyz in enumerate(['x','y','z']):
column_names.append('mean position in standard space:'
' {0}'.format(xyz))
columns.append(xyz_std_positions[:, ixyz].tolist())
#-----------------------------------------------------------------
# Laplace-Beltrami spectra:
#-----------------------------------------------------------------
if itable in [0, 1]:
spectra = spectra_lists[itable]
if spectra:
spectra_IDs = spectra_ID_lists[itable]
# Construct a matrix of spectra:
len_spectrum = len(spectra[0])
spectrum_matrix = np.zeros((nlabels, len_spectrum))
for ilabel, label in enumerate(include_labels):
if label in spectra_IDs:
spectrum = spectra[spectra_IDs.index(label)]
spectrum_matrix[ilabel, 0:len_spectrum] = spectrum
# Append spectral shape name and values to columns:
for ispec in range(spectrum_start, len_spectrum):
columns.append(spectrum_matrix[:, ispec].tolist())
column_names.append('Laplace-Beltrami spectrum:'
' component {0}'.format(ispec+1))
#-----------------------------------------------------------------
# Zernike moments:
#-----------------------------------------------------------------
if itable in [0, 1]:
zernike = zernike_lists[itable]
if zernike:
zernike_IDs = zernike_ID_lists[itable]
# Construct a matrix of Zernike moments:
len_moments = len(zernike[0])
moments_matrix = np.zeros((nlabels, len_moments))
for ilabel, label in enumerate(include_labels):
if label in zernike_IDs:
moments = zernike[zernike_IDs.index(label)]
moments_matrix[ilabel, 0:len_moments] = moments
# Append Zernike shape name and values to columns:
for imoment in range(0, len_moments):
columns.append(moments_matrix[:, imoment].tolist())
column_names.append('Zernike moments: component {0}'.
format(imoment+1))
#-----------------------------------------------------------------
# Write labels/IDs and values to table:
#-----------------------------------------------------------------
# Write labels/IDs to table:
output_table = os.path.join(os.getcwd(), table_names[itable])
if columns:
df1 = pd.DataFrame({'ID': label_numbers})
df2 = pd.DataFrame(np.transpose(columns),
columns = column_names)
df = pd.concat([df1, df2], axis=1)
if label_names:
df0 = pd.DataFrame({'name': label_names})
df = pd.concat([df0, df], axis=1)
df.to_csv(output_table, index=False)
if not os.path.exists(output_table):
raise(IOError(output_table + " not found"))
#-----------------------------------------------------------------
# Return correct table file name:
#-----------------------------------------------------------------
if itable == 0:
label_table = output_table
elif itable == 1:
sulcus_table = output_table
elif itable == 2:
fundus_table = output_table
return label_table, sulcus_table, fundus_table
def write_shape_stats(labels_or_file=[],
sulci=[],
fundi=[],
affine_transform_files=[],
inverse_booleans=[],
transform_format='itk',
area_file='',
normalize_by_area=False,
mean_curvature_file='',
travel_depth_file='',
geodesic_depth_file='',
freesurfer_thickness_file='',
freesurfer_curvature_file='',
freesurfer_sulc_file='',
labels_spectra=[],
labels_spectra_IDs=[],
sulci_spectra=[],
sulci_spectra_IDs=[],
labels_zernike=[],
labels_zernike_IDs=[],
sulci_zernike=[],
sulci_zernike_IDs=[],
exclude_labels=[-1],
verbose=False):
"""
Make tables of shape statistics per label, sulcus, and/or fundus.
There can be thousands of vertices in a single feature such as a gyrus,
sulcus, or fundus, and for per-vertex shape measures, it makes sense to
characterize their collective shape as a distribution of shape values.
Mindboggle's stats_per_label function generates tables of summary
statistical measures for these distributions, and includes the shape
measures computed on cortical features as well.
Note ::
This function is tailored for Mindboggle outputs.
Parameters
----------
labels_or_file : list or string
label number for each vertex or name of VTK file with index scalars
sulci : list of integers
indices to sulci, one per vertex, with -1 indicating no sulcus
fundi : list of integers
indices to fundi, one per vertex, with -1 indicating no fundus
affine_transform_files : list of strings
affine transform files to standard space
inverse_booleans : list of of zeros and ones
for each transform, 1 to take the inverse, else 0
transform_format : string
format for transform file
Ex: 'txt' for text, 'itk' for ITK, and 'mat' for Matlab format
area_file : string
name of VTK file with surface area scalar values
normalize_by_area : bool
normalize all shape measures by area of label/feature? (UNTESTED)
mean_curvature_file : string
name of VTK file with mean curvature scalar values
travel_depth_file : string
name of VTK file with travel depth scalar values
geodesic_depth_file : string
name of VTK file with geodesic depth scalar values
freesurfer_thickness_file : string
name of VTK file with FreeSurfer thickness scalar values
freesurfer_curvature_file : string
name of VTK file with FreeSurfer curvature (curv) scalar values
freesurfer_sulc_file : string
name of VTK file with FreeSurfer convexity (sulc) scalar values
labels_spectra : list of lists of floats
Laplace-Beltrami spectra for each labeled region
labels_spectra_IDs : list of integers
unique labels for labels_spectra
sulci_spectra : list of lists of floats
Laplace-Beltrami spectra for each sulcus
sulci_spectra_IDs : list of integers
unique sulcus IDs for sulci_spectra
labels_zernike : list of lists of floats
Zernike moments for each labeled region
labels_zernike_IDs : list of integers
unique labels for labels_zernike
sulci_zernike : list of lists of floats
Zernike moments for each sulcus
sulci_zernike_IDs : list of integers
unique sulcus IDs for sulci_zernike
exclude_labels : list of lists of integers
indices to be excluded (in addition to -1)
verbose : bool
print statements?
Returns
-------
label_table : string
output table filename for label shapes
sulcus_table : string
output table filename for sulcus shapes
fundus_table : string
output table filename for fundus shapes
Examples
--------
>>> from mindboggle.mio.tables import write_shape_stats
>>> from mindboggle.mio.vtks import read_scalars
>>> from mindboggle.mio.fetch_data import prep_tests
>>> urls, fetch_data = prep_tests()
>>> label_file = fetch_data(urls['left_freesurfer_labels'], '', '.vtk')
>>> sulci_file = fetch_data(urls['left_sulci'], '', '.vtk')
>>> fundi_file = fetch_data(urls['left_fundus_per_sulcus'], '', '.vtk')
>>> mean_curvature_file = fetch_data(urls['left_mean_curvature'], '', '.vtk')
>>> travel_depth_file = fetch_data(urls['left_travel_depth'], '', '.vtk')
>>> geodesic_depth_file = fetch_data(urls['left_geodesic_depth'], '', '.vtk')
>>> area_file = fetch_data(urls['left_area'], '', '.vtk')
>>> freesurfer_thickness_file = ''
>>> freesurfer_curvature_file = ''
>>> freesurfer_sulc_file = ''
>>> sulci, name = read_scalars(sulci_file)
>>> fundi, name = read_scalars(fundi_file)
>>> affine_transform_files = []
>>> inverse_booleans = []
>>> transform_format = 'itk'
>>> normalize_by_area = False
>>> labels, name = read_scalars(label_file)
>>> labels_spectra = []
>>> labels_spectra_IDs = []
>>> sulci_spectra = []
>>> sulci_spectra_IDs = []
>>> labels_zernike = []
>>> labels_zernike_IDs = []
>>> sulci_zernike = []
>>> sulci_zernike_IDs = []
>>> exclude_labels = [-1]
>>> verbose = False
>>> label_table, sulcus_table, fundus_table = write_shape_stats(label_file,
... sulci, fundi, affine_transform_files, inverse_booleans,
... transform_format, area_file, normalize_by_area,
... mean_curvature_file, travel_depth_file, geodesic_depth_file,
... freesurfer_thickness_file, freesurfer_curvature_file,
... freesurfer_sulc_file, labels_spectra, labels_spectra_IDs,
... sulci_spectra, sulci_spectra_IDs, labels_zernike,
... labels_zernike_IDs, sulci_zernike, sulci_zernike_IDs,
... exclude_labels, verbose)
"""
import os
import numpy as np
import pandas as pd
from mindboggle.guts.compute import stats_per_label
from mindboggle.guts.compute import means_per_label
from mindboggle.guts.compute import sum_per_label
from mindboggle.mio.vtks import read_scalars, read_vtk
from mindboggle.mio.vtks import apply_affine_transforms
from mindboggle.mio.labels import DKTprotocol
dkt = DKTprotocol()
# Make sure inputs are lists:
if isinstance(labels_or_file, np.ndarray):
labels = [int(x) for x in labels_or_file]
elif isinstance(labels_or_file, list):
labels = labels_or_file
elif isinstance(labels_or_file, str):
labels, name = read_scalars(labels_or_file)
if isinstance(sulci, np.ndarray):
sulci = [int(x) for x in sulci]
if isinstance(fundi, np.ndarray):
fundi = [int(x) for x in fundi]
if not labels and not sulci and not fundi:
raise IOError('No feature data to tabulate in write_shape_stats().')
spectrum_start = 1 # Store all columns of spectral components (0),
# or start from higher frequency components (>=1)
# ------------------------------------------------------------------------
# Feature lists, shape names, and shape files:
# ------------------------------------------------------------------------
# Feature lists:
feature_lists = [labels, sulci, fundi]
feature_names = ['label', 'sulcus', 'fundus']
spectra_lists = [labels_spectra, sulci_spectra]
spectra_ID_lists = [labels_spectra_IDs, sulci_spectra_IDs]
zernike_lists = [labels_zernike, sulci_zernike]
zernike_ID_lists = [labels_zernike_IDs, sulci_zernike_IDs]
table_names = [
'label_shapes.csv', 'sulcus_shapes.csv', 'fundus_shapes.csv'
]
# Shape names corresponding to shape files below:
shape_names = [
'area', 'travel depth', 'geodesic depth', 'mean curvature',
'freesurfer curvature', 'freesurfer thickness',
'freesurfer convexity (sulc)'
]
# Load shape files as a list of numpy arrays of per-vertex shape values:
shape_files = [
area_file, travel_depth_file, geodesic_depth_file, mean_curvature_file,
freesurfer_curvature_file, freesurfer_thickness_file,
freesurfer_sulc_file
]
shape_arrays = []
first_pass = True
area_array = []
for ishape, shape_file in enumerate(shape_files):
if os.path.exists(shape_file):
if first_pass:
points, indices, lines, faces, scalars_array, scalar_names, \
npoints, input_vtk = read_vtk(shape_file, True, True)
points = np.array(points)
first_pass = False
if affine_transform_files and transform_format:
affine_points, \
foo1 = apply_affine_transforms(affine_transform_files,
inverse_booleans, transform_format,
points, vtk_file_stem='')
else:
scalars_array, name = read_scalars(shape_file, True, True)
if scalars_array.size:
shape_arrays.append(scalars_array)
# Store area array:
if ishape == 0:
area_array = scalars_array.copy()
if normalize_by_area:
use_area = area_array
else:
use_area = []
# Initialize table file names:
label_table = ''
sulcus_table = ''
fundus_table = ''
# Loop through features / tables:
for itable, feature_list in enumerate(feature_lists):
column_names = []
# ----------------------------------------------------------------
# Label names:
# ----------------------------------------------------------------
label_title = 'name'
if itable == 0:
label_numbers = dkt.cerebrum_cortex_DKT31_numbers
label_names = dkt.cerebrum_cortex_DKT31_names
elif itable in [1, 2]:
label_numbers = dkt.sulcus_numbers
label_names = dkt.sulcus_names
else:
label_numbers = []
label_names = []
include_labels = label_numbers
nlabels = len(label_numbers)
# --------------------------------------------------------------------
# For each feature, construct a table of average shape values:
# --------------------------------------------------------------------
if feature_list:
feature_name = feature_names[itable]
columns = []
# ----------------------------------------------------------------
# Loop through shape measures:
# ----------------------------------------------------------------
column_names.extend(column_names[:])
for ishape, shape_array in enumerate(shape_arrays):
shape = shape_names[ishape]
if verbose:
print(' Compute statistics on {0} {1}...'.format(
feature_name, shape))
# ------------------------------------------------------------
# Append feature areas to columns:
# ------------------------------------------------------------
if ishape == 0 and np.size(area_array):
sums, label_list = sum_per_label(shape_array, feature_list,
include_labels,
exclude_labels)
column_names.append(shape)
columns.append(sums)
# ------------------------------------------------------------
# Append feature shape statistics to columns:
# ------------------------------------------------------------
else:
medians, mads, means, sdevs, skews, kurts, \
lower_quarts, upper_quarts, \
label_list = stats_per_label(shape_array, feature_list,
include_labels, exclude_labels,
area_array, precision=1)
column_names.append(shape + ': median')
column_names.append(shape + ': MAD')
column_names.append(shape + ': mean')
column_names.append(shape + ': SD')
column_names.append(shape + ': skew')
column_names.append(shape + ': kurtosis')
column_names.append(shape + ': 25%')
column_names.append(shape + ': 75%')
columns.append(medians)
columns.append(mads)
columns.append(means)
columns.append(sdevs)
columns.append(skews)
columns.append(kurts)
columns.append(lower_quarts)
columns.append(upper_quarts)
# ----------------------------------------------------------------
# Mean positions in the original space:
# ----------------------------------------------------------------
# Compute mean position per feature:
positions, sdevs, label_list, foo = means_per_label(
points, feature_list, include_labels, exclude_labels, use_area)
# Append mean x,y,z position per feature to columns:
xyz_positions = np.asarray(positions)
for ixyz, xyz in enumerate(['x', 'y', 'z']):
column_names.append('mean position: {0}'.format(xyz))
columns.append(xyz_positions[:, ixyz].tolist())
# ----------------------------------------------------------------
# Mean positions in standard space:
# ----------------------------------------------------------------
if affine_transform_files and transform_format:
# Compute standard space mean position per feature:
standard_positions, sdevs, label_list, \
foo = means_per_label(affine_points,
feature_list, include_labels, exclude_labels, use_area)
# Append standard space x,y,z position per feature to columns:
xyz_std_positions = np.asarray(standard_positions)
for ixyz, xyz in enumerate(['x', 'y', 'z']):
column_names.append('mean position in standard space:'
' {0}'.format(xyz))
columns.append(xyz_std_positions[:, ixyz].tolist())
# ----------------------------------------------------------------
# Laplace-Beltrami spectra:
# ----------------------------------------------------------------
if itable in [0, 1]:
spectra = spectra_lists[itable]
if spectra:
spectra_IDs = spectra_ID_lists[itable]
# Construct a matrix of spectra:
len_spectrum = len(spectra[0])
spectrum_matrix = np.zeros((nlabels, len_spectrum))
for ilabel, label in enumerate(include_labels):
if label in spectra_IDs:
spectrum = spectra[spectra_IDs.index(label)]
spectrum_matrix[ilabel, 0:len_spectrum] = spectrum
# Append spectral shape name and values to columns:
for ispec in range(spectrum_start, len_spectrum):
columns.append(spectrum_matrix[:, ispec].tolist())
column_names.append('Laplace-Beltrami spectrum:'
' component {0}'.format(ispec + 1))
# ----------------------------------------------------------------
# Zernike moments:
# ----------------------------------------------------------------
if itable in [0, 1]:
zernike = zernike_lists[itable]
if zernike:
zernike_IDs = zernike_ID_lists[itable]
# Construct a matrix of Zernike moments:
len_moments = len(zernike[0])
moments_matrix = np.zeros((nlabels, len_moments))
for ilabel, label in enumerate(include_labels):
if label in zernike_IDs:
moments = zernike[zernike_IDs.index(label)]
moments_matrix[ilabel, 0:len_moments] = moments
# Append Zernike shape name and values to columns:
for imoment in range(0, len_moments):
columns.append(moments_matrix[:, imoment].tolist())
column_names.append(
'Zernike moments: component {0}'.format(imoment +
1))
# ----------------------------------------------------------------
# Write labels/IDs and values to table:
# ----------------------------------------------------------------
# Write labels/IDs to table:
output_table = os.path.join(os.getcwd(), table_names[itable])
if columns:
df1 = pd.DataFrame({'ID': label_numbers})
df2 = pd.DataFrame(np.transpose(columns), columns=column_names)
df = pd.concat([df1, df2], axis=1)
if label_names:
df0 = pd.DataFrame({'name': label_names})
df = pd.concat([df0, df], axis=1)
df.to_csv(output_table, index=False, encoding='utf-8')
if not os.path.exists(output_table):
raise IOError(output_table + " not found")
# ----------------------------------------------------------------
# Return correct table file name:
# ----------------------------------------------------------------
if itable == 0:
label_table = output_table
elif itable == 1:
sulcus_table = output_table
elif itable == 2:
fundus_table = output_table
return label_table, sulcus_table, fundus_table