コード例 #1
0
ファイル: test_ae.py プロジェクト: cclairec/fmri
def test_infomax(filename='./data/01-001.fmri.rest.1.volreg.band.pca_reduced.nii.gz',filename_mask='./data/01-001.fmri.rest.1.volreg.cortical_mask.nii.gz'):
    from Image import Image
    from sklearn.decomposition import FastICA
    import scipy.io as sio
    img = Image(img_filename=filename, mask_filename=filename_mask, fwhm=6.0)
    xmat = img.image_mat_in_mask_normalised.T
    from InfoMax import InfoMax
    infomax = InfoMax(30).fit(xmat)
    img.write_decomposition(maps=infomax.components_, filename='test_ica_infomax.nii.gz', normalise=True)
コード例 #2
0
def test_ae(
    filename='/Volumes/VAULT/YOAD/all/01-001.fmri.rest.1.volreg.band.nii.gz',
    filename_mask='/Volumes/VAULT/YOAD/all/registrations/01-001.fmri.rest.1.volreg.cortical_mask.nii.gz'
):

    img = Image(img_filename=filename, mask_filename=filename_mask)
    xmat = img.image_mat_in_mask_normalised.T
    ae = Autoencoder(30, max_iter=200, second_nonlinear=True,
                     bias=True).fit(xmat)
    img.write_decomposition(maps=ae.components_,
                            filename='test_ae.nii.gz',
                            normalise=False)
コード例 #3
0
def test_infomax(
        filename='./data/01-001.fmri.rest.1.volreg.band.pca_reduced.nii.gz',
        filename_mask='./data/01-001.fmri.rest.1.volreg.cortical_mask.nii.gz'):
    from Image import Image
    from sklearn.decomposition import FastICA
    import scipy.io as sio
    img = Image(img_filename=filename, mask_filename=filename_mask, fwhm=6.0)
    xmat = img.image_mat_in_mask_normalised.T
    from InfoMax import InfoMax
    infomax = InfoMax(30).fit(xmat)
    img.write_decomposition(maps=infomax.components_,
                            filename='test_ica_infomax.nii.gz',
                            normalise=True)
コード例 #4
0
ファイル: test_ae.py プロジェクト: cclairec/fmri
def test_rica(filename='./data/01-001.fmri.rest.1.volreg.nii.gz', filename_mask='./data/01-001.fmri.rest.1.volreg.cortical_mask.nii.gz'):
    from Image import Image
    import scipy.io as sio
    img = Image(img_filename=filename, mask_filename=filename_mask)
    xmat = img.image_mat_in_mask_normalised.T
    from sklearn.decomposition import PCA, FastICA
    pca = PCA(30)
    xmat_red = pca.fit_transform(xmat.T)
    import matplotlib.pyplot as plt
    plt.plot(pca.components_.T)
    plt.show()
    import pdb; pdb.set_trace()
    rica = RICA(30).fit(xmat)
    img.write_decomposition(maps=rica.components_, filename='test_rica.nii.gz', normalise=False)
コード例 #5
0
def test_rica(
        filename='./data/01-001.fmri.rest.1.volreg.nii.gz',
        filename_mask='./data/01-001.fmri.rest.1.volreg.cortical_mask.nii.gz'):
    from Image import Image
    import scipy.io as sio
    img = Image(img_filename=filename, mask_filename=filename_mask)
    xmat = img.image_mat_in_mask_normalised.T
    from sklearn.decomposition import PCA, FastICA
    pca = PCA(30)
    xmat_red = pca.fit_transform(xmat.T)
    import matplotlib.pyplot as plt
    plt.plot(pca.components_.T)
    plt.show()
    import pdb
    pdb.set_trace()
    rica = RICA(30).fit(xmat)
    img.write_decomposition(maps=rica.components_,
                            filename='test_rica.nii.gz',
                            normalise=False)
コード例 #6
0
ファイル: ae_individual.py プロジェクト: meinternational/fmri

parser = argparse.ArgumentParser(description='matrix decomposition')
parser.add_argument('-gae', metavar='gae', type=str, required=True)
parser.add_argument('-gimg', metavar='gimg', type=str, required=True)
parser.add_argument('-gmask', metavar='gmask', type=str, required=True)
parser.add_argument('-reg', metavar='reg', type=str, nargs='+', required=True)
parser.add_argument('-img', metavar='img', type=str, nargs='+', required=True)
parser.add_argument('-mask', metavar='mask', type=str, nargs='+', required=True)
parser.add_argument('-thr', metavar='thr', type=float, default=0.0)
parser.add_argument('-s', metavar='s', type=int, default=None)
args = parser.parse_args()

# first compute individual autoencoders and move them into their group space representation
for i,d in enumerate(args.reg):
	img = Image(img_filename=args.img[i], mask_filename=args.mask[i])
	in_nii__2__mat = args.img[i]
	in_mask = args.mask[i]
	out_nii__2__mat = "{prefix}.mat".format(prefix=in_nii__2__mat[:-7])
	out_autoencoder = "{prefix}.autoencoder.mat".format(prefix=in_nii__2__mat[:-7])
	out_autoencoder_nifti = "{prefix}.autoencoder.nii.gz".format(prefix=in_nii__2__mat[:-7])
	out_autoencoder_nifti_group = "{prefix}.autoencoder.group.nii.gz".format(prefix=in_nii__2__mat[:-7])
	out_autoencoder_mat_group = "{prefix}.autoencoder.group.mat".format(prefix=in_nii__2__mat[:-7])
	if not isfile(out_nii__2__mat):
		cmd = "nii__2__mat.py -img {img} -mask {mask} -mat {mat} -normalise".format(img=in_nii__2__mat, mat=out_nii__2__mat, mask=in_mask)
		print cmd
		call(cmd, shell=True)

	if not isfile(out_autoencoder):
		cmd = "ae.py -mat {mat} -c 200".format(mat=out_nii__2__mat)
		print cmd
コード例 #7
0
def fmri(fmri_collection,
         t1_collection=None,
         seg_collections=None,
         atlas_collections=None,
         directory_reg=None,
         freq_band="0.01 0.1"):
    if directory_reg:
        call("mkdir -p {directory_reg}".format(directory_reg=directory_reg),
             shell=True)

    for index, fmri_scan in enumerate(fmri_collection):
        id_start = fmri_scan.rfind('/') + 1
        id_end = fmri_scan.find('.')
        directory = fmri_scan[0:id_start]
        identifier = fmri_scan[id_start:id_end]
        # distortion correction if still required - deprecated
        VOLUMES = check_output('3dinfo -nv {scan}'.format(scan=fmri_scan),
                               shell=True).rstrip()
        TR = check_output('3dinfo -tr {scan}'.format(scan=fmri_scan),
                          shell=True).rstrip()
        print "scan: {scan} TR={TR} VOLUMES={VOLUMES}".format(scan=identifier,
                                                              TR=TR,
                                                              VOLUMES=VOLUMES)
        ##########################################################################################################
        ################################# FILE SETUP #############################################################
        ##########################################################################################################
        ### 3ddespike
        in_3ddespike = fmri_scan
        out_3ddespike = "{directory}{fmri_id}.fmri.despike.nii.gz".format(
            fmri_id=identifier, directory=directory)
        ### 3dvolreg
        in_3dvolreg = out_3ddespike
        out_3dvolreg = "{prefix}.volreg.nii.gz".format(prefix=in_3dvolreg[:-7])
        out_3dvolreg_txt = "{directory}{fmri_id}.motion.1D".format(
            fmri_id=identifier, directory=directory)
        out_motion = "{directory}{fmri_id}.motion.demean.1D".format(
            fmri_id=identifier, directory=directory)
        out_motion_derv = "{directory}{fmri_id}.motion.demean.derivative.1D".format(
            fmri_id=identifier, directory=directory)
        ### 3dvol to extract 4th volume
        in_3dvol = out_3dvolreg
        out_3dvol = "{prefix}.vol4.nii.gz".format(prefix=in_3dvol[:-7])
        ### fmri brain mask
        in_3dAutomask = out_3dvolreg
        out_3dAutomask = "{prefix}.mask.nii.gz".format(prefix=out_3dvol[:-7])

        ### 3dBandpass
        in_3dBandpass = out_3dvolreg
        out_3dBandpass = "******".format(
            prefix=in_3dBandpass[:-7])
        out_3dBandpass_regressors = "{directory}{fmri_id}.bandpass.1D".format(
            fmri_id=identifier, directory=directory)
        ### 3dDeconvolve
        in_3dDeconvolve = out_3dvolreg
        out_3dDeconvolve_err = "{prefix}.deconvolve.err.nii.gz".format(
            prefix=in_3dDeconvolve[:-7])
        out_3dDeconvolve_fit = "{prefix}.deconvolve.fit.nii.gz".format(
            prefix=in_3dDeconvolve[:-7])
        out_3dDeconvolve_stats = "{prefix}.deconvolve.stats.nii.gz".format(
            prefix=in_3dDeconvolve[:-7])
        ### final output
        fmri_preprocessed = out_3dDeconvolve_err

        fvol = out_3dvol

        matching_t1 = [s for s in t1_collection if identifier in s]
        matching_seg = [s for s in seg_collections if identifier in s]
        matching_atlas = [s for s in atlas_collections if identifier in s]
        if len(matching_t1) > 0:
            t1 = matching_t1[0]
            aff_t1_2_fmri = "{directory_reg}{fmri_id}.t1__2__{fmri_id}.fmri.despike.volreg.vol4.txt".format(
                fmri_id=identifier, directory_reg=directory_reg)
            aff_fmri_2_t1 = "{directory_reg}{fmri_id}.fmri.despike.volreg.vol4__2__{fmri_id}.t1.txt".format(
                fmri_id=identifier, directory_reg=directory_reg)
            aff_t1_in_fmri = "{directory_reg}{fmri_id}.t1__in__{fmri_id}.fmri.despike.volreg.vol4.nii.gz".format(
                fmri_id=identifier, directory_reg=directory_reg)
            aff_fmri_in_t1 = "{directory_reg}{fmri_id}.fmri.despike.volreg.vol4__in__{fmri_id}.t1.nii.gz".format(
                fmri_id=identifier, directory_reg=directory_reg)

        if len(matching_seg) > 0 and len(matching_atlas) > 0:
            seg = matching_seg[0]
            atlas = matching_atlas[0]
            fmri_seg = "{directory}{fmri_id}.fmri.despike.volreg.vol4.seg.nii.gz".format(
                directory=directory, fmri_id=identifier)
            fmri_atlas = "{directory}{fmri_id}.fmri.despike.volreg.vol4.atlas.nii.gz".format(
                directory=directory, fmri_id=identifier)

        ##########################################################################################################
        ################################# FMRI PREPROCESSING #####################################################
        ##########################################################################################################
        # despiking
        if not isfile(out_3ddespike):
            cmd = "3dDespike -NEW -nomask -prefix {out_} {in_}".format(
                in_=in_3ddespike, out_=out_3ddespike)
            print cmd
            call(cmd, shell=True)

        # motion realignment
        if not isfile(out_3dvolreg):
            cmd = "3dvolreg -overwrite -zpad 1 -cubic -prefix {out_} -1Dfile {out_txt} {in_}".format(
                out_txt=out_3dvolreg_txt, in_=in_3dvolreg, out_=out_3dvolreg)
            print cmd
            call(cmd, shell=True)
            cmd = "1d_tool.py -infile {in_} -set_nruns 1 -demean -write {out_}".format(
                in_=out_3dvolreg_txt, out_=out_motion)
            print cmd
            call(cmd, shell=True)
            cmd = "1d_tool.py -infile {in_} -set_nruns 1 -derivative -demean -write {out_}".format(
                in_=out_3dvolreg_txt, out_=out_motion_derv)
            print cmd
            call(cmd, shell=True)

        # get one volume
        if not isfile(out_3dvol):
            cmd = "3dcalc -overwrite -a '{in_}[4]' -prefix {out_} -expr a".format(
                in_=in_3dvol, out_=out_3dvol)
            call(cmd, shell=True)

        # get brain mask for volume
        if not isfile(out_3dAutomask):
            cmd = "3dAutomask -overwrite -prefix {out_} {in_}".format(
                in_=in_3dAutomask, out_=out_3dAutomask)
            call(cmd, shell=True)

        # band passs filter signals
        if not isfile(out_3dBandpass_regressors):
            #cmd = "3dBandpass -overwrite -band 0.01 0.1 -prefix {out_} {in_}".format(in_=in_3dBandpass, out_=out_3dBandpass)
            cmd = "1dBport -nodata {VOLUMES} {TR} -band {band} -invert -nozero > {out_}".format(
                VOLUMES=VOLUMES,
                TR=TR,
                out_=out_3dBandpass_regressors,
                band=freq_band)
            print cmd
            call(cmd, shell=True)

        if not isfile(out_3dDeconvolve_err):
            cmd = """3dDeconvolve -input {in_}                             \
            -ortvec {bandpass} bandpass                                        \
            -polort 3                                                                \
            -num_stimts 12                                                           \
            -stim_file 1 {motion}'[0]' -stim_base 1 -stim_label 1 roll_01    \
            -stim_file 2 {motion}'[1]' -stim_base 2 -stim_label 2 pitch_01   \
            -stim_file 3 {motion}'[2]' -stim_base 3 -stim_label 3 yaw_01     \
            -stim_file 4 {motion}'[3]' -stim_base 4 -stim_label 4 dS_01      \
            -stim_file 5 {motion}'[4]' -stim_base 5 -stim_label 5 dL_01      \
            -stim_file 6 {motion}'[5]' -stim_base 6 -stim_label 6 dP_01      \
            -stim_file 7 {motion_derv}'[0]' -stim_base 7 -stim_label 7 roll_02     \
            -stim_file 8 {motion_derv}'[1]' -stim_base 8 -stim_label 8 pitch_02    \
            -stim_file 9 {motion_derv}'[2]' -stim_base 9 -stim_label 9 yaw_02      \
            -stim_file 10 {motion_derv}'[3]' -stim_base 10 -stim_label 10 dS_02    \
            -stim_file 11 {motion_derv}'[4]' -stim_base 11 -stim_label 11 dL_02    \
            -stim_file 12 {motion_derv}'[5]' -stim_base 12 -stim_label 12 dP_02    \
            -fitts {out_fit}                                                     \
            -errts {out_err}                                                     \
            -bucket {out_stats} """.format(in_=in_3dDeconvolve,
                                           bandpass=out_3dBandpass_regressors,
                                           motion=out_motion,
                                           motion_derv=out_motion_derv,
                                           out_fit=out_3dDeconvolve_fit,
                                           out_err=out_3dDeconvolve_err,
                                           out_stats=out_3dDeconvolve_stats)
            call(cmd, shell=True)

        #########################################################################################################################################
        ################################################### AFFINE REGISTRATIONS ################################################################
        #########################################################################################################################################
        #(i) fmri to t1
        if t1 and atlas and not isfile(aff_fmri_in_t1):
            cmd = "reg_aladin -ref {ref} -rmask {rmask} -flo {flo} -fmask {fmask} -res {res} -aff {aff}".format(
                ref=t1,
                flo=fvol,
                res=aff_fmri_in_t1,
                aff=aff_fmri_2_t1,
                rmask=atlas,
                fmask=out_3dAutomask)
            print cmd
            call(cmd, shell=True)

        #(ii) t1 to fmri
        if t1 and atlas and not isfile(aff_t1_in_fmri):
            cmd = "reg_aladin -ref {ref} -rmask {rmask} -flo {flo} -fmask {fmask} -res {res} -aff {aff}".format(
                ref=fvol,
                flo=t1,
                res=aff_t1_in_fmri,
                aff=aff_t1_2_fmri,
                fmask=atlas,
                rmask=out_3dAutomask)
            print cmd
            call(cmd, shell=True)

        # resample seg in fmri space
        if seg and not isfile(fmri_seg):
            cmd = "reg_resample -ref {ref} -flo {flo} -psf -res {res} -trans {trans}".format(
                ref=fvol, flo=seg, res=fmri_seg, trans=aff_t1_2_fmri)
            print cmd
            call(cmd, shell=True)

        # resample atlas in fmri space
        if atlas and not isfile(fmri_atlas):
            cmd = "reg_resample -ref {ref} -flo {flo} -inter 0 -res {res} -trans {trans}".format(
                ref=fvol, flo=atlas, res=fmri_atlas, trans=aff_t1_2_fmri)
            print cmd
            call(cmd, shell=True)
            # build atlas based correlation matrices
            img = Image(img_filename=fmri_preprocessed,
                        mask_filename=fmri_atlas,
                        atlas_filename=fmri_atlas,
                        atlas_thr=1)
            sio.savemat(
                "{prefix}.corr.mat".format(prefix=fmri_preprocessed[:-7]),
                {'CorrMatrix': img.atlas_corr})
            sio.savemat(
                "{prefix}.rois.mat".format(prefix=fmri_preprocessed[:-7]),
                {'ROISignals': img.image_mat_in_mask_normalised_atlas})
            labels = np.unique(img.atlas_v)
            labels = labels[labels > 0]
            sio.savemat(
                "{prefix}.rois_label.mat".format(
                    prefix=fmri_preprocessed[:-7]), {'ROILabels': labels})
コード例 #8
0
ファイル: mat__2__nii.py プロジェクト: meinternational/fmri
import argparse
import numpy as np

parser = argparse.ArgumentParser(description='build nifti file from mat file')
parser.add_argument('-img', metavar='img', nargs='+', type=str, required=True)
parser.add_argument('-mask', metavar='mask', nargs='+', type=str, required=True)
parser.add_argument('-mat', metavar='mat', nargs='+', type=str, required=True)

parser.add_argument('-normalise', dest='normalise', action='store_true')
parser.set_defaults(normalise=False)

args = parser.parse_args()
if len(args.img)>1 and len(args.mask)>1:
    for i, mat in enumerate(args.mat):
        print args.img[i], args.mask[i], mat
        img = Image(img_filename=args.img[i], mask_filename=args.mask[i])
        f = sio.loadmat(mat)
        hiddenlayer = f['h']
        img.write_decomposition(maps=hiddenlayer, filename="{prefix}.nii.gz".format(prefix=mat[0:mat.find('.mat')]), normalise=args.normalise)

else:
    img = Image(img_filename=args.img[0], mask_filename=args.mask[0])
    mat = args.mat[0]
    f = sio.loadmat(mat)
    if 'h' in f.keys():
        hiddenlayer = f['h']

    if 'mat' in f.keys():
        hiddenlayer = f['mat']

    if 'x_tilde' in f.keys():
コード例 #9
0
group = sio.loadmat(args.group_decomp)
W1group=group['W1']
b1group=group['b1']
W2group=group['W2']
b2group=group['b2']
number_subjects = len(args.ind_decomp)
number_individual_hiddenlayer = W1group.shape[1]/number_subjects
number_group_hiddenlayer = W1group.shape[0]
W1group=np.reshape(W1group,[number_subjects, number_group_hiddenlayer, number_individual_hiddenlayer])
W2group=np.reshape(W1group,[number_individual_hiddenlayer,number_subjects,number_group_hiddenlayer])
#W1group=np.reshape(W1group,[number_group_hiddenlayer, number_individual_hiddenlayer, number_subjects])
#bgroup=np.reshape(b1group, [number_subjects, number_individual_hiddenlayer])

W1group[np.abs(W1group)<args.thr]=0
for i,d in enumerate(args.ind_decomp):
	img = Image(img_filename=args.ind_fmri_nii[i], mask_filename=args.ind_mask[i])
	individual = sio.loadmat(d)
	mat = sio.loadmat(args.ind_fmri_mat[i])
	mat = mat['mat']
	W1g = np.squeeze(W1group[i,:,:])
	W2g = np.squeeze(W2group[:,i,:])
	Wi = individual['W1']
	bi = individual['b1']
	#hi = individual['h']
	pdb.set_trace()
	hi = Wi.dot(mat)+np.tile(bi, (mat.shape[1], 1)).transpose()
	hi=sigmoid(hi)
	img.write_decomposition(maps=hi, filename="{prefix}.hdummy.nii.gz".format(prefix=d[0:d.find('.mat')]), normalise=False)
	#pdb.set_trace()
	h = W1g.dot(hi)+np.tile(b1group, (hi.shape[1], 1)).transpose()
	h = sigmoid(h)
コード例 #10
0
from niftybold.img.Image import Image

import scipy.io as sio
import argparse
import numpy as np

parser = argparse.ArgumentParser(description='build nifti file from mat file')
parser.add_argument('-img', metavar='img', type=str, required=True)
parser.add_argument('-mask', metavar='mask', type=str, required=True)
parser.add_argument('-mat', metavar='mat', type=str, required=True)
parser.add_argument('-normalise',
                    metavar='normalises',
                    type=bool,
                    default=False)
args = parser.parse_args()
f = sio.loadmat(args.mat)
hiddenlayer = f['h']
img = Image(img_filename=args.img, mask_filename=args.mask)
img.write_decomposition(maps=hiddenlayer,
                        filename="{prefix}.nii.gz".format(
                            prefix=args.mat[0:args.mat.find('.mat')]),
                        normalise=args.normalise)
コード例 #11
0
ファイル: test_ae.py プロジェクト: cclairec/fmri
def test_ae(filename='/Volumes/VAULT/YOAD/all/01-001.fmri.rest.1.volreg.band.nii.gz', filename_mask='/Volumes/VAULT/YOAD/all/registrations/01-001.fmri.rest.1.volreg.cortical_mask.nii.gz'):

    img = Image(img_filename=filename, mask_filename=filename_mask)
    xmat = img.image_mat_in_mask_normalised.T
    ae = Autoencoder(30, max_iter=200, second_nonlinear=True, bias=True).fit(xmat)
    img.write_decomposition(maps=ae.components_, filename='test_ae.nii.gz', normalise=False)
コード例 #12
0
ファイル: ica_nii__2__mat.py プロジェクト: cclairec/fmri
from niftybold.img.Image import Image

import scipy.io as sio
import argparse
import numpy as np

parser = argparse.ArgumentParser(description='build mat file from nifti file')
parser.add_argument('-img', metavar='img', type=str, required=True)
parser.add_argument('-mask', metavar='mask', type=str, required=True)
parser.add_argument('-mat', metavar='mat', type=str, required=True)
parser.add_argument('-normalise',
                    metavar='normalises',
                    type=bool,
                    default=True)
parser.add_argument('-asl', metavar='asl', type=bool, default=False)
parser.add_argument('-fwhm', metavar='fwhm', type=float, default=0.0)
args = parser.parse_args()

img = Image(img_filename=args.img,
            mask_filename=args.mask,
            fwhm=args.fwhm,
            asl=args.asl)
if args.normalise:
    _mat = img.image_mat_in_mask_normalised.T

else:
    _mat = img.image_mat_in_mask.T

sio.savemat(args.mat, {'mat': _mat})
コード例 #13
0
ファイル: ica_build_group_mat.py プロジェクト: cclairec/fmri
import argparse
import numpy as np

parser = argparse.ArgumentParser(
    description='build mat file for matrix decomposition')
parser.add_argument('-groupimg',
                    metavar='groupimg',
                    type=str,
                    nargs='+',
                    required=True)
parser.add_argument('-groupmask', metavar='groupmask', type=str, required=True)
parser.add_argument('-fwhm', metavar='fwhm', type=float, default=0.0)
parser.add_argument('-mat', metavar='mat', type=str, default='ica_ready.mat')
args = parser.parse_args()

mat = None
for index, scan in enumerate(args.groupimg):
    print scan
    img = Image(img_filename=scan,
                mask_filename=args.groupmask,
                fwhm=args.fwhm)
    _mat = img.image_mat_in_mask_normalised.T
    sio.savemat("{prefix}.mat".format(prefix=scan[0:scan.find('.nii')]),
                {'mat': _mat})
    if index == 0:
        mat = _mat
    else:
        mat = np.concatenate((mat, _mat))

sio.savemat(args.mat, {'mat': mat})