def update(new_displacement, current_displacement):
dim = len(new_displacement.shape)-1
mse = np.sqrt(np.sum((current_displacement**2), -1)).mean()
if dim == 2:
updated, stats = tf.compose_vector_fields(new_displacement,
current_displacement)
else:
updated, stats = tf.compose_vector_fields3D(new_displacement,
current_displacement)
return np.array(updated), np.array(mse)
def estimateNewMonomodalDiffeomorphicField3D(moving,
fixed,
lambdaParam,
maxOuterIter,
previousDisplacement,
reportProgress=False):
'''
Warning: in the monomodal case, the parameter lambda must be significantly lower than in the multimodal case. Try lambdaParam=1,
as opposed as lambdaParam=150 used in the multimodal case
'''
innerTolerance = 1e-3
outerTolerance = 1e-3
displacement = np.zeros(shape=(moving.shape) + (3, ), dtype=np.float64)
residuals = np.zeros(shape=(moving.shape), dtype=np.float64)
gradientField = np.empty(shape=(moving.shape) + (3, ), dtype=np.float64)
totalDisplacement = np.zeros(shape=(moving.shape) + (3, ),
dtype=np.float64)
if (previousDisplacement != None):
totalDisplacement[...] = previousDisplacement
outerIter = 0
while (outerIter < maxOuterIter):
outerIter += 1
if (reportProgress):
print 'Iter:', outerIter, '/', maxOuterIter
warped = np.array(tf.warp_volume(moving, totalDisplacement))
sigmaField = np.ones_like(warped, dtype=np.float64)
deltaField = fixed - warped
g0, g1, g2 = sp.gradient(warped)
gradientField[:, :, :, 0] = g0
gradientField[:, :, :, 1] = g1
gradientField[:, :, :, 2] = g2
maxVariation = 1 + innerTolerance
innerIter = 0
maxResidual = 0
displacement[...] = 0
maxInnerIter = 50
while ((maxVariation > innerTolerance) and (innerIter < maxInnerIter)):
innerIter += 1
maxVariation = tf.iterateDisplacementField3DCYTHON(
deltaField, sigmaField, gradientField, lambdaParam,
totalDisplacement, displacement, residuals)
opt = np.max(residuals)
if (maxResidual < opt):
maxResidual = opt
maxDisplacement = np.max(np.abs(displacement))
totalDisplacement, stats = tf.compose_vector_fields3D(
displacement, totalDisplacement)
if (maxDisplacement < outerTolerance):
break
print "Iter: ", outerIter, "Max lateral displacement:", maxDisplacement, "Max variation:", maxVariation, "Max residual:", maxResidual
if (previousDisplacement != None):
return totalDisplacement - previousDisplacement
return totalDisplacement
def estimateMultimodalSyN3DMultiScale(movingPyramid,
fixedPyramid,
initAffine,
lambdaParam,
maxOuterIter,
level=0):
n = len(movingPyramid)
quantizationLevels = 256
if (level == (n - 1)):
totalF, totalFInv, totalM, totalMInv = estimateNewMultimodalSyNField3D(
movingPyramid[level], fixedPyramid[level], None, None, None, None,
initAffine, lambdaParam, quantizationLevels, maxOuterIter[level],
level == 0)
return totalF, totalFInv, totalM, totalMInv
subAffine = initAffine.copy()
subAffine[:3, 3] *= 0.5
subF, subFInv, subM, subMInv = estimateMultimodalSyN3DMultiScale(
movingPyramid, fixedPyramid, subAffine, lambdaParam, maxOuterIter,
level + 1)
sh = np.array(fixedPyramid[level].shape).astype(np.int32)
upF = np.array(tf.upsample_displacement_field3D(subF, sh)) * 2
upFInv = np.array(tf.upsample_displacement_field3D(subFInv, sh)) * 2
upM = np.array(tf.upsample_displacement_field3D(subM, sh)) * 2
upMInv = np.array(tf.upsample_displacement_field3D(subMInv, sh)) * 2
del subF
del subFInv
del subM
del subMInv
totalF, totalFInv, totalM, totalMInv = estimateNewMultimodalSyNField3D(
movingPyramid[level], fixedPyramid[level], upF, upFInv, upM, upMInv,
initAffine, lambdaParam, quantizationLevels, maxOuterIter[level],
level == 0)
if level == 0:
totalF = np.array(tf.compose_vector_fields3D(
totalF, totalMInv)) #Multiply bw by 0.5??
totalM = np.array(tf.compose_vector_fields3D(
totalM, totalFInv)) #Multiply bw by 0.5??
return totalM, totalF
return totalF, totalFInv, totalM, totalMInv
def compute_inversion_error(self):
r'''
Returns the inversion error of the displacement fields
TO-DO: the inversion error should take into account the affine
transformations as well.
'''
if self.dim == 2:
residual, stats = tf.compose_vector_fields(self.forward,
self.backward)
else:
residual, stats = tf.compose_vector_fields3D(self.forward,
self.backward)
return residual, stats
def compose(self, applyFirst):
r'''
Computes the composition G(F(.)) where G is this transformation and
F is the transformation given as parameter
'''
B=applyFirst.affine_post
C=self.affine_pre
if B==None:
affine_prod=C
elif C==None:
affine_prod=B
else:
affine_prod=C.dot(B)
if affine_prod!=None:
affine_prod_inv=linalg.inv(affine_prod).copy(order='C')
else:
affine_prod_inv=None
if self.dim == 2:
forward=applyFirst.forward.copy()
tf.append_affine_to_displacement_field_2d(forward, affine_prod)
forward, stats = tf.compose_vector_fields(forward,
self.forward)
backward=self.backward.copy()
tf.append_affine_to_displacement_field_2d(backward, affine_prod_inv)
backward, stats = tf.compose_vector_fields(backward,
applyFirst.backward)
else:
forward=applyFirst.forward.copy()
tf.append_affine_to_displacement_field_3d(forward, affine_prod)
forward, stats = tf.compose_vector_fields3D(forward,
self.forward)
backward=self.backward.copy()
tf.append_affine_to_displacement_field_3d(backward, affine_prod_inv)
backward, stats = tf.compose_vector_fields3D(backward,
applyFirst.backward)
composition=TransformationModel(forward, backward,
applyFirst.affine_pre, self.affine_post)
return composition
def estimateMultimodalSyN3DMultiScale(movingPyramid, fixedPyramid, initAffine, lambdaParam, maxOuterIter, level=0):
n=len(movingPyramid)
quantizationLevels=256
if(level==(n-1)):
totalF, totalFInv, totalM, totalMInv=estimateNewMultimodalSyNField3D(movingPyramid[level], fixedPyramid[level], None, None, None, None, initAffine, lambdaParam, quantizationLevels, maxOuterIter[level], level==0)
return totalF, totalFInv, totalM, totalMInv
subAffine=initAffine.copy()
subAffine[:3,3]*=0.5
subF, subFInv, subM, subMInv=estimateMultimodalSyN3DMultiScale(movingPyramid, fixedPyramid, subAffine, lambdaParam, maxOuterIter, level+1)
sh=np.array(fixedPyramid[level].shape).astype(np.int32)
upF=np.array(tf.upsample_displacement_field3D(subF, sh))*2
upFInv=np.array(tf.upsample_displacement_field3D(subFInv, sh))*2
upM=np.array(tf.upsample_displacement_field3D(subM, sh))*2
upMInv=np.array(tf.upsample_displacement_field3D(subMInv, sh))*2
del subF
del subFInv
del subM
del subMInv
totalF, totalFInv, totalM, totalMInv=estimateNewMultimodalSyNField3D(movingPyramid[level], fixedPyramid[level], upF, upFInv, upM, upMInv, initAffine, lambdaParam, quantizationLevels, maxOuterIter[level], level==0)
if level==0:
totalF=np.array(tf.compose_vector_fields3D(totalF, totalMInv))#Multiply bw by 0.5??
totalM=np.array(tf.compose_vector_fields3D(totalM, totalFInv))#Multiply bw by 0.5??
return totalM, totalF
return totalF, totalFInv, totalM, totalMInv
def estimateNewMonomodalDiffeomorphicField3D(moving, fixed, lambdaParam, maxOuterIter, previousDisplacement, reportProgress=False):
'''
Warning: in the monomodal case, the parameter lambda must be significantly lower than in the multimodal case. Try lambdaParam=1,
as opposed as lambdaParam=150 used in the multimodal case
'''
innerTolerance=1e-3
outerTolerance=1e-3
displacement =np.zeros(shape=(moving.shape)+(3,), dtype=np.float64)
residuals=np.zeros(shape=(moving.shape), dtype=np.float64)
gradientField =np.empty(shape=(moving.shape)+(3,), dtype=np.float64)
totalDisplacement=np.zeros(shape=(moving.shape)+(3,), dtype=np.float64)
if(previousDisplacement!=None):
totalDisplacement[...]=previousDisplacement
outerIter=0
while(outerIter<maxOuterIter):
outerIter+=1
if(reportProgress):
print 'Iter:',outerIter,'/',maxOuterIter
warped=np.array(tf.warp_volume(moving, totalDisplacement))
sigmaField=np.ones_like(warped, dtype=np.float64)
deltaField=fixed-warped
g0, g1, g2=sp.gradient(warped)
gradientField[:,:,:,0]=g0
gradientField[:,:,:,1]=g1
gradientField[:,:,:,2]=g2
maxVariation=1+innerTolerance
innerIter=0
maxResidual=0
displacement[...]=0
maxInnerIter=50
while((maxVariation>innerTolerance)and(innerIter<maxInnerIter)):
innerIter+=1
maxVariation=tf.iterateDisplacementField3DCYTHON(deltaField, sigmaField, gradientField, lambdaParam, totalDisplacement, displacement, residuals)
opt=np.max(residuals)
if(maxResidual<opt):
maxResidual=opt
maxDisplacement=np.max(np.abs(displacement))
totalDisplacement, stats=tf.compose_vector_fields3D(displacement, totalDisplacement)
if(maxDisplacement<outerTolerance):
break
print "Iter: ",outerIter, "Max lateral displacement:", maxDisplacement, "Max variation:",maxVariation, "Max residual:", maxResidual
if(previousDisplacement!=None):
return totalDisplacement-previousDisplacement
return totalDisplacement
def testEstimateMultimodalSyN3DMultiScale(fnameMoving, fnameFixed, fnameAffine,
warpDir, lambdaParam):
'''
testEstimateMultimodalDiffeomorphicField3DMultiScale('IBSR_01_ana_strip.nii.gz', 't1_icbm_normal_1mm_pn0_rf0_peeled.nii.gz', 'IBSR_01_ana_strip_t1_icbm_normal_1mm_pn0_rf0_peeledAffine.txt', 100)
'''
print 'Registering', fnameMoving, 'to', fnameFixed, 'with lambda=', lambdaParam
sys.stdout.flush()
moving = nib.load(fnameMoving)
fixed = nib.load(fnameFixed)
referenceShape = np.array(fixed.shape, dtype=np.int32)
M = moving.get_affine()
F = fixed.get_affine()
if not fnameAffine:
T = np.eye(4)
else:
T = rcommon.readAntsAffine(fnameAffine)
initAffine = np.linalg.inv(M).dot(T.dot(F))
print initAffine
moving = moving.get_data().squeeze().astype(np.float64)
fixed = fixed.get_data().squeeze().astype(np.float64)
moving = np.copy(moving, order='C')
fixed = np.copy(fixed, order='C')
moving = (moving - moving.min()) / (moving.max() - moving.min())
fixed = (fixed - fixed.min()) / (fixed.max() - fixed.min())
level = 2
maskMoving = moving > 0
maskFixed = fixed > 0
movingPyramid = [
img for img in rcommon.pyramid_gaussian_3D(moving, level, maskMoving)
]
fixedPyramid = [
img for img in rcommon.pyramid_gaussian_3D(fixed, level, maskFixed)
]
#maxOuterIter=[25,50,100,100, 100, 100]
maxOuterIter = [2, 2, 2, 2, 2, 2]
baseMoving = rcommon.getBaseFileName(fnameMoving)
baseFixed = rcommon.getBaseFileName(fnameFixed)
# if(os.path.exists('disp_'+baseMoving+'_'+baseFixed+'.npy')):
# displacement=np.load('disp_'+baseMoving+'_'+baseFixed+'.npy')
# else:
displacement, directInverse = estimateMultimodalSyN3DMultiScale(
movingPyramid, fixedPyramid, initAffine, lambdaParam, maxOuterIter, 0)
tf.prepend_affine_to_displacement_field(displacement, initAffine)
# np.save('disp_'+baseMoving+'_'+baseFixed+'.npy', displacement)
#####Warp all requested volumes
#---first the target using tri-linear interpolation---
moving = nib.load(fnameMoving).get_data().squeeze().astype(np.float64)
moving = np.copy(moving, order='C')
warped = np.array(tf.warp_volume(moving, displacement)).astype(np.int16)
imgWarped = nib.Nifti1Image(warped, F)
imgWarped.to_filename('warpedDiff_' + baseMoving + '_' + baseFixed +
'.nii.gz')
#---warp using affine only
moving = nib.load(fnameMoving).get_data().squeeze().astype(np.int32)
moving = np.copy(moving, order='C')
warped = np.array(
tf.warp_discrete_volumeNNAffine(moving, referenceShape,
initAffine)).astype(np.int16)
imgWarped = nib.Nifti1Image(
warped, F) #The affine transformation is the reference's one
imgWarped.to_filename('warpedAffine_' + baseMoving + '_' + baseFixed +
'.nii.gz')
#---now the rest of the targets using nearest neighbor
names = [os.path.join(warpDir, name) for name in os.listdir(warpDir)]
for name in names:
#---warp using the non-linear deformation
toWarp = nib.load(name).get_data().squeeze().astype(np.int32)
toWarp = np.copy(toWarp, order='C')
baseWarp = rcommon.getBaseFileName(name)
warped = np.array(tf.warp_discrete_volumeNN(
toWarp, displacement)).astype(np.int16)
imgWarped = nib.Nifti1Image(
warped, F) #The affine transformation is the reference's one
imgWarped.to_filename('warpedDiff_' + baseWarp + '_' + baseFixed +
'.nii.gz')
#---warp using affine inly
warped = np.array(
tf.warp_discrete_volumeNNAffine(toWarp, referenceShape,
initAffine)).astype(np.int16)
imgWarped = nib.Nifti1Image(
warped, F) #The affine transformation is the reference's one
imgWarped.to_filename('warpedAffine_' + baseWarp + '_' + baseFixed +
'.nii.gz')
#---finally, the deformed lattices (forward, inverse and resdidual)---
lambdaParam = 0.9
maxIter = 100
tolerance = 1e-4
print 'Computing inverse...'
inverse = np.array(
tf.invert_vector_field3D(displacement, lambdaParam, maxIter,
tolerance))
residual = np.array(tf.compose_vector_fields3D(displacement, inverse))
saveDeformedLattice3D(
displacement,
'latticeDispDiff_' + baseMoving + '_' + baseFixed + '.nii.gz')
saveDeformedLattice3D(
inverse, 'latticeInvDiff_' + baseMoving + '_' + baseFixed + '.nii.gz')
saveDeformedLattice3D(
residual, 'latticeResdiff_' + baseMoving + '_' + baseFixed + '.nii.gz')
residual = np.sqrt(np.sum(residual**2, 3))
print "Mean residual norm:", residual.mean(), " (", residual.std(
), "). Max residual norm:", residual.max()
def estimateNewMultimodalSyNField3D(moving,
fixed,
fWarp,
fInv,
mWarp,
mInv,
initAffine,
lambdaDisplacement,
quantizationLevels,
maxOuterIter,
reportProgress=False):
'''
fwWarp: forward warp, the displacement field that warps moving towards fixed
bwWarp: backward warp, the displacement field that warps fixed towards moving
initAffine: the affine transformation to bring moving over fixed (this part is not symmetric)
'''
print 'Moving shape:', moving.shape, '. Fixed shape:', fixed.shape
innerTolerance = 1e-3
outerTolerance = 1e-3
fixedMask = (fixed > 0).astype(np.int32)
movingMask = (moving > 0).astype(np.int32)
if (fWarp != None):
totalF = fWarp
totalFInv = fInv
else:
totalF = np.zeros(shape=(fixed.shape) + (3, ), dtype=np.float64)
totalFInv = np.zeros(shape=(fixed.shape) + (3, ), dtype=np.float64)
if (mWarp != None):
totalM = mWarp
totalMInv = mInv
else:
totalM = np.zeros(shape=(moving.shape) + (3, ), dtype=np.float64)
totalMInv = np.zeros(shape=(moving.shape) + (3, ), dtype=np.float64)
finished = False
outerIter = 0
while ((not finished) and (outerIter < maxOuterIter)):
outerIter += 1
if (reportProgress):
print 'Iter:', outerIter, '/', maxOuterIter
#---E step---
wmoving = np.array(tf.warp_volume(moving, totalMInv, initAffine))
wmovingMask = np.array(
tf.warp_discrete_volumeNN(movingMask, totalMInv,
initAffine)).astype(np.int32)
wfixed = np.array(tf.warp_volume(fixed, totalFInv))
wfixedMask = np.array(tf.warp_discrete_volumeNN(
fixedMask, totalFInv)).astype(np.int32)
fixedQ, grayLevels, hist = tf.quantizePositiveVolumeCYTHON(
wfixed, quantizationLevels)
fixedQ = np.array(fixedQ, dtype=np.int32)
movingQ, grayLevels, hist = tf.quantizePositiveVolumeCYTHON(
wmoving, quantizationLevels)
movingQ = np.array(movingQ, dtype=np.int32)
trust = wfixedMask * wmovingMask
meansMoving, variancesMoving = tf.computeMaskedVolumeClassStatsCYTHON(
trust, wmoving, quantizationLevels, fixedQ)
meansFixed, variancesFixed = tf.computeMaskedVolumeClassStatsCYTHON(
trust, wfixed, quantizationLevels, movingQ)
meansMoving[0] = 0
meansFixed[0] = 0
meansMoving = np.array(meansMoving)
meansFixed = np.array(meansFixed)
variancesMoving = np.array(variancesMoving)
sigmaFieldMoving = variancesMoving[fixedQ]
variancesFixed = np.array(variancesFixed)
sigmaFieldFixed = variancesFixed[movingQ]
deltaFieldMoving = meansMoving[fixedQ] - wmoving
deltaFieldFixed = meansFixed[movingQ] - wfixed
#--M step--
movingGradient = np.empty(shape=(moving.shape) + (3, ),
dtype=np.float64)
movingGradient[:, :, :,
0], movingGradient[:, :, :,
1], movingGradient[:, :, :,
2] = sp.gradient(
wmoving)
#iterate forward field
maxVariation = 1 + innerTolerance
innerIter = 0
maxInnerIter = 100
fw = np.zeros_like(totalF)
while ((maxVariation > innerTolerance) and (innerIter < maxInnerIter)):
innerIter += 1
maxVariation = tf.iterateDisplacementField3DCYTHON(
deltaFieldMoving, sigmaFieldMoving, movingGradient,
lambdaDisplacement, totalF, fw, None)
del movingGradient
fw *= 0.5
totalF = np.array(tf.compose_vector_fields3D(
fw, totalF)) #Multiply fw by 0.5??
nrm = np.sqrt(fw[..., 0]**2 + fw[..., 1]**2 + fw[..., 2]**2)
del fw
#iterate backward field
fixedGradient = np.empty(shape=(fixed.shape) + (3, ), dtype=np.float64)
fixedGradient[:, :, :,
0], fixedGradient[:, :, :,
1], fixedGradient[:, :, :,
2] = sp.gradient(
wfixed)
maxVariation = 1 + innerTolerance
innerIter = 0
maxInnerIter = 100
mw = np.zeros_like(totalM)
while ((maxVariation > innerTolerance) and (innerIter < maxInnerIter)):
innerIter += 1
maxVariation = tf.iterateDisplacementField3DCYTHON(
deltaFieldFixed, sigmaFieldFixed, fixedGradient,
lambdaDisplacement, totalM, mw, None)
del fixedGradient
mw *= 0.5
totalM = np.array(tf.compose_vector_fields3D(
mw, totalM)) #Multiply bw by 0.5??
nrm = np.sqrt(mw[..., 0]**2 + mw[..., 1]**2 + mw[..., 2]**2)
del mw
#invert fields
totalFInv = np.array(
tf.invert_vector_field_fixed_point3D(totalF, 20, 1e-6))
totalMInv = np.array(
tf.invert_vector_field_fixed_point3D(totalM, 20, 1e-6))
totalF = np.array(
tf.invert_vector_field_fixed_point3D(totalFInv, 20, 1e-6))
totalM = np.array(
tf.invert_vector_field_fixed_point3D(totalMInv, 20, 1e-6))
maxDisplacement = np.mean(nrm)
if ((maxDisplacement < outerTolerance) or (outerIter >= maxOuterIter)):
finished = True
print "Iter: ", outerIter, "Mean displacement:", maxDisplacement, "Max variation:", maxVariation
return totalF, totalFInv, totalM, totalMInv
def testEstimateMultimodalSyN3DMultiScale(fnameMoving, fnameFixed, fnameAffine, warpDir, lambdaParam):
'''
testEstimateMultimodalDiffeomorphicField3DMultiScale('IBSR_01_ana_strip.nii.gz', 't1_icbm_normal_1mm_pn0_rf0_peeled.nii.gz', 'IBSR_01_ana_strip_t1_icbm_normal_1mm_pn0_rf0_peeledAffine.txt', 100)
'''
print 'Registering', fnameMoving, 'to', fnameFixed,'with lambda=',lambdaParam
sys.stdout.flush()
moving = nib.load(fnameMoving)
fixed= nib.load(fnameFixed)
referenceShape=np.array(fixed.shape, dtype=np.int32)
M=moving.get_affine()
F=fixed.get_affine()
if not fnameAffine:
T=np.eye(4)
else:
T=rcommon.readAntsAffine(fnameAffine)
initAffine=np.linalg.inv(M).dot(T.dot(F))
print initAffine
moving=moving.get_data().squeeze().astype(np.float64)
fixed=fixed.get_data().squeeze().astype(np.float64)
moving=np.copy(moving, order='C')
fixed=np.copy(fixed, order='C')
moving=(moving-moving.min())/(moving.max()-moving.min())
fixed=(fixed-fixed.min())/(fixed.max()-fixed.min())
level=2
maskMoving=moving>0
maskFixed=fixed>0
movingPyramid=[img for img in rcommon.pyramid_gaussian_3D(moving, level, maskMoving)]
fixedPyramid=[img for img in rcommon.pyramid_gaussian_3D(fixed, level, maskFixed)]
#maxOuterIter=[25,50,100,100, 100, 100]
maxOuterIter=[2,2,2,2,2,2]
baseMoving=rcommon.getBaseFileName(fnameMoving)
baseFixed=rcommon.getBaseFileName(fnameFixed)
# if(os.path.exists('disp_'+baseMoving+'_'+baseFixed+'.npy')):
# displacement=np.load('disp_'+baseMoving+'_'+baseFixed+'.npy')
# else:
displacement, directInverse=estimateMultimodalSyN3DMultiScale(movingPyramid, fixedPyramid, initAffine, lambdaParam, maxOuterIter, 0)
tf.prepend_affine_to_displacement_field(displacement, initAffine)
# np.save('disp_'+baseMoving+'_'+baseFixed+'.npy', displacement)
#####Warp all requested volumes
#---first the target using tri-linear interpolation---
moving=nib.load(fnameMoving).get_data().squeeze().astype(np.float64)
moving=np.copy(moving, order='C')
warped=np.array(tf.warp_volume(moving, displacement)).astype(np.int16)
imgWarped=nib.Nifti1Image(warped, F)
imgWarped.to_filename('warpedDiff_'+baseMoving+'_'+baseFixed+'.nii.gz')
#---warp using affine only
moving=nib.load(fnameMoving).get_data().squeeze().astype(np.int32)
moving=np.copy(moving, order='C')
warped=np.array(tf.warp_discrete_volumeNNAffine(moving, referenceShape, initAffine)).astype(np.int16)
imgWarped=nib.Nifti1Image(warped, F)#The affine transformation is the reference's one
imgWarped.to_filename('warpedAffine_'+baseMoving+'_'+baseFixed+'.nii.gz')
#---now the rest of the targets using nearest neighbor
names=[os.path.join(warpDir,name) for name in os.listdir(warpDir)]
for name in names:
#---warp using the non-linear deformation
toWarp=nib.load(name).get_data().squeeze().astype(np.int32)
toWarp=np.copy(toWarp, order='C')
baseWarp=rcommon.getBaseFileName(name)
warped=np.array(tf.warp_discrete_volumeNN(toWarp, displacement)).astype(np.int16)
imgWarped=nib.Nifti1Image(warped, F)#The affine transformation is the reference's one
imgWarped.to_filename('warpedDiff_'+baseWarp+'_'+baseFixed+'.nii.gz')
#---warp using affine inly
warped=np.array(tf.warp_discrete_volumeNNAffine(toWarp, referenceShape, initAffine)).astype(np.int16)
imgWarped=nib.Nifti1Image(warped, F)#The affine transformation is the reference's one
imgWarped.to_filename('warpedAffine_'+baseWarp+'_'+baseFixed+'.nii.gz')
#---finally, the deformed lattices (forward, inverse and resdidual)---
lambdaParam=0.9
maxIter=100
tolerance=1e-4
print 'Computing inverse...'
inverse=np.array(tf.invert_vector_field3D(displacement, lambdaParam, maxIter, tolerance))
residual=np.array(tf.compose_vector_fields3D(displacement, inverse))
saveDeformedLattice3D(displacement, 'latticeDispDiff_'+baseMoving+'_'+baseFixed+'.nii.gz')
saveDeformedLattice3D(inverse, 'latticeInvDiff_'+baseMoving+'_'+baseFixed+'.nii.gz')
saveDeformedLattice3D(residual, 'latticeResdiff_'+baseMoving+'_'+baseFixed+'.nii.gz')
residual=np.sqrt(np.sum(residual**2,3))
print "Mean residual norm:", residual.mean()," (",residual.std(), "). Max residual norm:", residual.max()
def estimateNewMultimodalSyNField3D(moving, fixed, fWarp, fInv, mWarp, mInv, initAffine, lambdaDisplacement, quantizationLevels, maxOuterIter, reportProgress=False):
'''
fwWarp: forward warp, the displacement field that warps moving towards fixed
bwWarp: backward warp, the displacement field that warps fixed towards moving
initAffine: the affine transformation to bring moving over fixed (this part is not symmetric)
'''
print 'Moving shape:',moving.shape,'. Fixed shape:',fixed.shape
innerTolerance=1e-3
outerTolerance=1e-3
fixedMask=(fixed>0).astype(np.int32)
movingMask=(moving>0).astype(np.int32)
if(fWarp!=None):
totalF=fWarp
totalFInv=fInv
else:
totalF =np.zeros(shape=(fixed.shape)+(3,), dtype=np.float64)
totalFInv =np.zeros(shape=(fixed.shape)+(3,), dtype=np.float64)
if(mWarp!=None):
totalM=mWarp
totalMInv=mInv
else:
totalM =np.zeros(shape=(moving.shape)+(3,), dtype=np.float64)
totalMInv=np.zeros(shape=(moving.shape)+(3,), dtype=np.float64)
finished=False
outerIter=0
while((not finished) and (outerIter<maxOuterIter)):
outerIter+=1
if(reportProgress):
print 'Iter:',outerIter,'/',maxOuterIter
#---E step---
wmoving=np.array(tf.warp_volume(moving, totalMInv, initAffine))
wmovingMask=np.array(tf.warp_discrete_volumeNN(movingMask, totalMInv, initAffine)).astype(np.int32)
wfixed=np.array(tf.warp_volume(fixed, totalFInv))
wfixedMask=np.array(tf.warp_discrete_volumeNN(fixedMask, totalFInv)).astype(np.int32)
fixedQ, grayLevels, hist=tf.quantizePositiveVolumeCYTHON(wfixed, quantizationLevels)
fixedQ=np.array(fixedQ, dtype=np.int32)
movingQ, grayLevels, hist=tf.quantizePositiveVolumeCYTHON(wmoving, quantizationLevels)
movingQ=np.array(movingQ, dtype=np.int32)
trust=wfixedMask*wmovingMask
meansMoving, variancesMoving=tf.computeMaskedVolumeClassStatsCYTHON(trust, wmoving, quantizationLevels, fixedQ)
meansFixed, variancesFixed=tf.computeMaskedVolumeClassStatsCYTHON(trust, wfixed, quantizationLevels, movingQ)
meansMoving[0]=0
meansFixed[0]=0
meansMoving=np.array(meansMoving)
meansFixed=np.array(meansFixed)
variancesMoving=np.array(variancesMoving)
sigmaFieldMoving=variancesMoving[fixedQ]
variancesFixed=np.array(variancesFixed)
sigmaFieldFixed=variancesFixed[movingQ]
deltaFieldMoving=meansMoving[fixedQ]-wmoving
deltaFieldFixed=meansFixed[movingQ]-wfixed
#--M step--
movingGradient =np.empty(shape=(moving.shape)+(3,), dtype=np.float64)
movingGradient[:,:,:,0], movingGradient[:,:,:,1], movingGradient[:,:,:,2]=sp.gradient(wmoving)
#iterate forward field
maxVariation=1+innerTolerance
innerIter=0
maxInnerIter=100
fw=np.zeros_like(totalF)
while((maxVariation>innerTolerance)and(innerIter<maxInnerIter)):
innerIter+=1
maxVariation=tf.iterateDisplacementField3DCYTHON(deltaFieldMoving, sigmaFieldMoving, movingGradient, lambdaDisplacement, totalF, fw, None)
del movingGradient
fw*=0.5
totalF=np.array(tf.compose_vector_fields3D(fw, totalF))#Multiply fw by 0.5??
nrm=np.sqrt(fw[...,0]**2+fw[...,1]**2+fw[...,2]**2)
del fw
#iterate backward field
fixedGradient =np.empty(shape=(fixed.shape)+(3,), dtype=np.float64)
fixedGradient[:,:,:,0], fixedGradient[:,:,:,1], fixedGradient[:,:,:,2]=sp.gradient(wfixed)
maxVariation=1+innerTolerance
innerIter=0
maxInnerIter=100
mw=np.zeros_like(totalM)
while((maxVariation>innerTolerance)and(innerIter<maxInnerIter)):
innerIter+=1
maxVariation=tf.iterateDisplacementField3DCYTHON(deltaFieldFixed, sigmaFieldFixed, fixedGradient, lambdaDisplacement, totalM, mw, None)
del fixedGradient
mw*=0.5
totalM=np.array(tf.compose_vector_fields3D(mw, totalM))#Multiply bw by 0.5??
nrm=np.sqrt(mw[...,0]**2+mw[...,1]**2+mw[...,2]**2)
del mw
#invert fields
totalFInv=np.array(tf.invert_vector_field_fixed_point3D(totalF, 20, 1e-6))
totalMInv=np.array(tf.invert_vector_field_fixed_point3D(totalM, 20, 1e-6))
totalF=np.array(tf.invert_vector_field_fixed_point3D(totalFInv, 20, 1e-6))
totalM=np.array(tf.invert_vector_field_fixed_point3D(totalMInv, 20, 1e-6))
maxDisplacement=np.mean(nrm)
if((maxDisplacement<outerTolerance)or(outerIter>=maxOuterIter)):
finished=True
print "Iter: ",outerIter, "Mean displacement:", maxDisplacement, "Max variation:",maxVariation
return totalF, totalFInv, totalM, totalMInv
def estimateNewMultimodalDiffeomorphicField3D(moving,
fixed,
initAffine,
lambdaDisplacement,
quantizationLevels,
maxOuterIter,
previousDisplacement,
reportProgress=False):
innerTolerance = 1e-3
outerTolerance = 1e-3
displacement = np.empty(shape=(fixed.shape) + (3, ), dtype=np.float64)
residuals = np.zeros(shape=(fixed.shape), dtype=np.float64)
gradientField = np.empty(shape=(fixed.shape) + (3, ), dtype=np.float64)
totalDisplacement = np.zeros(shape=(fixed.shape) + (3, ), dtype=np.float64)
if (previousDisplacement != None):
totalDisplacement[...] = previousDisplacement
fixedQ = None
grayLevels = None
fixedQ, grayLevels, hist = tf.quantizePositiveVolumeCYTHON(
fixed, quantizationLevels)
fixedQ = np.array(fixedQ, dtype=np.int32)
finished = False
outerIter = 0
maxDisplacement = None
maxVariation = None
maxResidual = 0
fixedMask = (fixed > 0).astype(np.int32)
movingMask = (moving > 0).astype(np.int32)
trustRegion = fixedMask * np.array(
tf.warp_discrete_volumeNNAffine(
movingMask, np.array(fixedMask.shape, dtype=np.int32),
initAffine)) #consider only the overlap after affine registration
while ((not finished) and (outerIter < maxOuterIter)):
outerIter += 1
if (reportProgress):
print 'Iter:', outerIter, '/', maxOuterIter
#sys.stdout.flush()
#---E step---
#print "Warping..."
#sys.stdout.flush()
warped = np.array(tf.warp_volume(moving, totalDisplacement,
initAffine))
warpedMask = np.array(
tf.warp_discrete_volumeNN(
trustRegion, totalDisplacement, np.eye(4))).astype(
np.int32) #the affine mapping was already applied
#print "Warping NN..."
#sys.stdout.flush()
#warpedMovingMask=np.array(tf.warp_volumeNN(movingMask, totalDisplacement)).astype(np.int32)
#print "Class stats..."
#sys.stdout.flush()
means, variances = tf.computeMaskedVolumeClassStatsCYTHON(
warpedMask, warped, quantizationLevels, fixedQ)
means[0] = 0
means = np.array(means)
variances = np.array(variances)
sigmaField = variances[fixedQ]
deltaField = means[
fixedQ] - warped #########Delta-field using Arce's rule
#--M step--
g0, g1, g2 = sp.gradient(warped)
gradientField[:, :, :, 0] = g0
gradientField[:, :, :, 1] = g1
gradientField[:, :, :, 2] = g2
maxVariation = 1 + innerTolerance
innerIter = 0
maxInnerIter = 100
displacement[...] = 0
#print "Iterating..."
#sys.stdout.flush()
while ((maxVariation > innerTolerance) and (innerIter < maxInnerIter)):
innerIter += 1
maxVariation = tf.iterateDisplacementField3DCYTHON(
deltaField, sigmaField, gradientField, lambdaDisplacement,
totalDisplacement, displacement, residuals)
opt = np.max(residuals)
if (maxResidual < opt):
maxResidual = opt
#--accumulate displacement--
#print "Exponential3D. Range D:", displacement.min(), displacement.max()
#sys.stdout.flush()
expd, inverseNone = tf.vector_field_exponential3D(displacement, False)
expd = np.array(expd)
#print "Range expd:", expd.min(), expd.max(), "Range TD:", totalDisplacement.min(), totalDisplacement.max()
#print "Compose vector fields..."
#sys.stdout.flush()
totalDisplacement, stats = tf.compose_vector_fields3D(
expd, totalDisplacement)
totalDisplacement = np.array(totalDisplacement)
#print "Composed rage:", totalDisplacement.min(), totalDisplacement.max()
#sys.stdout.flush()
#--check stop condition--
nrm = np.sqrt(displacement[..., 0]**2 + displacement[..., 1]**2 +
displacement[..., 2]**2)
#maxDisplacement=np.max(nrm)
maxDisplacement = np.mean(nrm)
if ((maxDisplacement < outerTolerance) or (outerIter >= maxOuterIter)):
finished = True
print "Iter: ", outerIter, "Mean displacement:", maxDisplacement, "Max variation:", maxVariation, "Max residual:", maxResidual
#sh=fixed.shape
#rcommon.overlayImages(warped[:,sh[1]//2,:], fixed[:,sh[1]//2,:])
#rcommon.overlayImages(warped[:,sh[1]//2,:]*warpedMask[:,sh[1]//2,:], fixed[:,sh[1]//2,:])
#sys.stdout.flush()
if (previousDisplacement != None):
#print 'Range TD:', totalDisplacement.min(), totalDisplacement.max(),'. Range PD:', previousDisplacement.min(), previousDisplacement.max()
#sys.stdout.flush()
return totalDisplacement - previousDisplacement
return totalDisplacement
def estimateNewMultimodalDiffeomorphicField3D(moving, fixed, initAffine, lambdaDisplacement, quantizationLevels, maxOuterIter, previousDisplacement, reportProgress=False):
innerTolerance=1e-3
outerTolerance=1e-3
displacement =np.empty(shape=(fixed.shape)+(3,), dtype=np.float64)
residuals=np.zeros(shape=(fixed.shape), dtype=np.float64)
gradientField =np.empty(shape=(fixed.shape)+(3,), dtype=np.float64)
totalDisplacement=np.zeros(shape=(fixed.shape)+(3,), dtype=np.float64)
if(previousDisplacement!=None):
totalDisplacement[...]=previousDisplacement
fixedQ=None
grayLevels=None
fixedQ, grayLevels, hist=tf.quantizePositiveVolumeCYTHON(fixed, quantizationLevels)
fixedQ=np.array(fixedQ, dtype=np.int32)
finished=False
outerIter=0
maxDisplacement=None
maxVariation=None
maxResidual=0
fixedMask=(fixed>0).astype(np.int32)
movingMask=(moving>0).astype(np.int32)
trustRegion=fixedMask*np.array(tf.warp_discrete_volumeNNAffine(movingMask, np.array(fixedMask.shape, dtype=np.int32), initAffine))#consider only the overlap after affine registration
while((not finished) and (outerIter<maxOuterIter)):
outerIter+=1
if(reportProgress):
print 'Iter:',outerIter,'/',maxOuterIter
#sys.stdout.flush()
#---E step---
#print "Warping..."
#sys.stdout.flush()
warped=np.array(tf.warp_volume(moving, totalDisplacement, initAffine))
warpedMask=np.array(tf.warp_discrete_volumeNN(trustRegion, totalDisplacement, np.eye(4))).astype(np.int32)#the affine mapping was already applied
#print "Warping NN..."
#sys.stdout.flush()
#warpedMovingMask=np.array(tf.warp_volumeNN(movingMask, totalDisplacement)).astype(np.int32)
#print "Class stats..."
#sys.stdout.flush()
means, variances=tf.computeMaskedVolumeClassStatsCYTHON(warpedMask, warped, quantizationLevels, fixedQ)
means[0]=0
means=np.array(means)
variances=np.array(variances)
sigmaField=variances[fixedQ]
deltaField=means[fixedQ]-warped#########Delta-field using Arce's rule
#--M step--
g0, g1, g2=sp.gradient(warped)
gradientField[:,:,:,0]=g0
gradientField[:,:,:,1]=g1
gradientField[:,:,:,2]=g2
maxVariation=1+innerTolerance
innerIter=0
maxInnerIter=100
displacement[...]=0
#print "Iterating..."
#sys.stdout.flush()
while((maxVariation>innerTolerance)and(innerIter<maxInnerIter)):
innerIter+=1
maxVariation=tf.iterateDisplacementField3DCYTHON(deltaField, sigmaField, gradientField, lambdaDisplacement, totalDisplacement, displacement, residuals)
opt=np.max(residuals)
if(maxResidual<opt):
maxResidual=opt
#--accumulate displacement--
#print "Exponential3D. Range D:", displacement.min(), displacement.max()
#sys.stdout.flush()
expd, inverseNone=tf.vector_field_exponential3D(displacement, False)
expd=np.array(expd)
#print "Range expd:", expd.min(), expd.max(), "Range TD:", totalDisplacement.min(), totalDisplacement.max()
#print "Compose vector fields..."
#sys.stdout.flush()
totalDisplacement, stats=tf.compose_vector_fields3D(expd, totalDisplacement)
totalDisplacement=np.array(totalDisplacement)
#print "Composed rage:", totalDisplacement.min(), totalDisplacement.max()
#sys.stdout.flush()
#--check stop condition--
nrm=np.sqrt(displacement[...,0]**2+displacement[...,1]**2+displacement[...,2]**2)
#maxDisplacement=np.max(nrm)
maxDisplacement=np.mean(nrm)
if((maxDisplacement<outerTolerance)or(outerIter>=maxOuterIter)):
finished=True
print "Iter: ",outerIter, "Mean displacement:", maxDisplacement, "Max variation:",maxVariation, "Max residual:", maxResidual
#sh=fixed.shape
#rcommon.overlayImages(warped[:,sh[1]//2,:], fixed[:,sh[1]//2,:])
#rcommon.overlayImages(warped[:,sh[1]//2,:]*warpedMask[:,sh[1]//2,:], fixed[:,sh[1]//2,:])
#sys.stdout.flush()
if(previousDisplacement!=None):
#print 'Range TD:', totalDisplacement.min(), totalDisplacement.max(),'. Range PD:', previousDisplacement.min(), previousDisplacement.max()
#sys.stdout.flush()
return totalDisplacement-previousDisplacement
return totalDisplacement
lambdaParam=0.9
maxIter=100
tolerance=1e-4
if argc>3:
lambdaParam=float(sys.argv[3])
if argc>4:
maxIter=int(sys.argv[4])
if argc>5:
tolerance=float(sys.argv[5])
print 'Inverting displacement: ',dispName, '. With parameters: lambda=',lambdaParam, '. Maxiter=',maxIter, '. Tolerance=',tolerance,'...'
inverse=np.array(tf.invert_vector_field3D(displacement, lambdaParam, maxIter, tolerance))
invName="inv"+dispName
print 'Saving inverse as:', invName
np.save(invName, inverse)
print 'Computing inversion error...'
residual=np.array(tf.compose_vector_fields3D(displacement, inverse))
residualName="res"+dispName
print 'Saving residual as:', residualName
np.save(residualName, residual)
residual=np.sqrt(np.sum(residual**2,3))
print "Mean residual norm:", residual.mean()," (",residual.std(), "). Max residual norm:", residual.max()
sys.exit(0)
elif(sys.argv[1]=='npy2nifti'):
if argc<3:
print 'File name expected.'
sys.exit(0)
fname=sys.argv[2]
try:
inputData=np.load(fname)
except IOError:
print 'Cannot open file:',fname
