def testMultimodalRigidTransformationMultiScale3D_ecqmmf(betaGT, level):
leftName = 'data/t2/t2_icbm_normal_1mm_pn0_rf0.rawb'
rightName = 'data/t1/t1_icbm_normal_1mm_pn0_rf0.rawb'
#rightName='data/t2/t2_icbm_normal_1mm_pn0_rf0.rawb'
#leftName='data/t1/t1_icbm_normal_1mm_pn0_rf0.rawb'
betaGTRads = np.array(betaGT, dtype=np.float64)
betaGTRads[0:3] = np.copy(np.pi * betaGTRads[0:3] / 180.0)
ns = 181
nr = 217
nc = 181
print 'Loading volume...'
left = np.fromfile(leftName, dtype=np.ubyte).reshape(ns, nr, nc)
left = left.astype(np.float64)
print 'Generating pyramid at level', level, '...'
right = np.fromfile(rightName, dtype=np.ubyte).reshape(ns, nr, nc)
right = right.astype(np.float64)
right = rcommon.applyRigidTransformation3D(right, betaGTRads)
leftPyramid = [i for i in rcommon.pyramid_gaussian_3D(left, level)]
rightPyramid = [i for i in rcommon.pyramid_gaussian_3D(right, level)]
print 'Estimation started.'
beta = estimateMultiModalRigidTransformationMultiscale3D(
leftPyramid, rightPyramid)
print 'Estimation finished.'
print 'Ground truth:', betaGT
plotSlicePyramidsAxial(leftPyramid, rightPyramid)
return beta
def testMultimodalRigidTransformationMultiScale3D_ecqmmf(betaGT, level):
leftName='data/t2/t2_icbm_normal_1mm_pn0_rf0.rawb'
rightName='data/t1/t1_icbm_normal_1mm_pn0_rf0.rawb'
#rightName='data/t2/t2_icbm_normal_1mm_pn0_rf0.rawb'
#leftName='data/t1/t1_icbm_normal_1mm_pn0_rf0.rawb'
betaGTRads=np.array(betaGT, dtype=np.float64)
betaGTRads[0:3]=np.copy(np.pi*betaGTRads[0:3]/180.0)
ns=181
nr=217
nc=181
print 'Loading volume...'
left=np.fromfile(leftName, dtype=np.ubyte).reshape(ns,nr,nc)
left=left.astype(np.float64)
print 'Generating pyramid at level',level,'...'
right=np.fromfile(rightName, dtype=np.ubyte).reshape(ns,nr,nc)
right=right.astype(np.float64)
right=rcommon.applyRigidTransformation3D(right, betaGTRads)
leftPyramid=[i for i in rcommon.pyramid_gaussian_3D(left, level)]
rightPyramid=[i for i in rcommon.pyramid_gaussian_3D(right, level)]
print 'Estimation started.'
beta=estimateMultiModalRigidTransformationMultiscale3D(leftPyramid, rightPyramid)
print 'Estimation finished.'
print 'Ground truth:', betaGT
plotSlicePyramidsAxial(leftPyramid, rightPyramid)
return beta
def testMultimodalRigidTransformationMultiScale3D_ecqmmf(
betaGT, level, nclasses, lambdaParam, mu, maxIter, tolerance):
betaGTRads = np.array(betaGT, dtype=np.float64)
betaGTRads[0:3] = np.copy(np.pi * betaGTRads[0:3] / 180.0)
movingName = 'data/t2/t2_icbm_normal_1mm_pn0_rf0_peeled.nii.gz'
fixedName = 'data/t1/t1_icbm_normal_1mm_pn0_rf0_peeled.nii.gz'
print 'Loading data...'
moving = nib.load(movingName)
moving = moving.get_data().squeeze()
moving = moving.astype(np.float64)
fixed = nib.load(fixedName)
fixed = fixed.get_data().squeeze()
fixed = fixed.astype(np.float64)
moving = (moving - moving.min()) / (moving.max() - moving.min())
fixed = (fixed - fixed.min()) / (fixed.max() - fixed.min())
print 'Applying GT transform...'
fixed = rcommon.applyRigidTransformation3D(fixed, betaGTRads)
sh = moving.shape
#leftPyramid=[i for i in rcommon.pyramid_gaussian_3D(moving, level)]
#rightPyramid=[i for i in rcommon.pyramid_gaussian_3D(fixed, level)]
fixedImage = fixed[:, sh[1] // 2, :].copy()
movingImage = moving[:, sh[1] // 2, :].copy()
print 'Initializing registration...'
meansFixed, variancesFixed, meansMoving, variancesMoving, joint = initializeECQMMFRegistration(
fixedImage, movingImage, nclasses, lambdaParam, mu, maxIter, tolerance)
joint = np.array(joint)
negLogLikelihood = np.zeros_like(joint)
ecqmmf_reg.compute_registration_neg_log_likelihood_constant_models(
fixedImage, movingImage, joint, meansFixed, meansMoving,
variancesFixed, variancesMoving, negLogLikelihood)
#ecqmmf_reg.initialize_registration_maximum_likelihood_probs(negLogLikelihood, joint):
ecqmmf.initialize_normalized_likelihood(negLogLikelihood, joint)
bufferN = np.array(range(nclasses * nclasses))
bufferD = np.array(range(nclasses * nclasses))
for iter_count in range(maxIter):
print 'Iter:', iter_count, '/', maxIter
ecqmmf_reg.iterate_marginals(negLogLikelihood, joint, lambdaParam, mu,
bufferN, bufferD)
#ecqmmf_reg.integrate_registration_probabilistic_weighted_tensor_field_products(double[:,:,:] q, double[:,:] diff, double[:,:,:,:] probs, double[:] weights)
ecqmmf_reg.compute_registration_neg_log_likelihood_constant_models(
fixedImage, movingImage, joint, meansFixed, meansMoving,
variancesFixed, variancesMoving, negLogLikelihood)
#----plot joint probability maps---
print 'Plotting joint probability maps...'
plt.figure()
plt.title('Joint probability maps')
for i in range(nclasses):
for j in range(nclasses):
plt.subplot(nclasses, nclasses, 1 + i * nclasses + j)
plt.imshow(joint[:, :, i, j], cmap=plt.cm.gray)
plt.title("F=" + str(i) + ", M=" + str(j))
#----plot negLogLikelihood maps---
print 'Plotting negLogLikelihood maps...'
plt.figure()
plt.title('neg-log-likelihood maps')
for i in range(nclasses):
for j in range(nclasses):
plt.subplot(nclasses, nclasses, 1 + i * nclasses + j)
plt.imshow(negLogLikelihood[:, :, i, j], cmap=plt.cm.gray)
plt.title("F=" + str(i) + ", M=" + str(j))
def testMultimodalRigidTransformationMultiScale3D_ecqmmf(betaGT, level, nclasses, lambdaParam, mu, maxIter, tolerance):
betaGTRads=np.array(betaGT, dtype=np.float64)
betaGTRads[0:3]=np.copy(np.pi*betaGTRads[0:3]/180.0)
movingName='data/t2/t2_icbm_normal_1mm_pn0_rf0_peeled.nii.gz'
fixedName ='data/t1/t1_icbm_normal_1mm_pn0_rf0_peeled.nii.gz'
print 'Loading data...'
moving=nib.load(movingName)
moving=moving.get_data().squeeze()
moving=moving.astype(np.float64)
fixed=nib.load(fixedName)
fixed=fixed.get_data().squeeze()
fixed=fixed.astype(np.float64)
moving=(moving-moving.min())/(moving.max()-moving.min())
fixed=(fixed-fixed.min())/(fixed.max()-fixed.min())
print 'Applying GT transform...'
fixed=rcommon.applyRigidTransformation3D(fixed, betaGTRads)
sh=moving.shape
#leftPyramid=[i for i in rcommon.pyramid_gaussian_3D(moving, level)]
#rightPyramid=[i for i in rcommon.pyramid_gaussian_3D(fixed, level)]
fixedImage=fixed[:,sh[1]//2,:].copy()
movingImage=moving[:,sh[1]//2,:].copy()
print 'Initializing registration...'
meansFixed, variancesFixed, meansMoving, variancesMoving, joint=initializeECQMMFRegistration(fixedImage, movingImage, nclasses, lambdaParam, mu, maxIter, tolerance)
joint=np.array(joint)
negLogLikelihood=np.zeros_like(joint)
ecqmmf_reg.compute_registration_neg_log_likelihood_constant_models(fixedImage, movingImage, joint, meansFixed, meansMoving, variancesFixed, variancesMoving, negLogLikelihood)
#ecqmmf_reg.initialize_registration_maximum_likelihood_probs(negLogLikelihood, joint):
ecqmmf.initialize_normalized_likelihood(negLogLikelihood, joint)
bufferN=np.array(range(nclasses*nclasses))
bufferD=np.array(range(nclasses*nclasses))
for iter_count in range(maxIter):
print 'Iter:',iter_count,'/',maxIter
ecqmmf_reg.iterate_marginals(negLogLikelihood, joint, lambdaParam, mu, bufferN, bufferD)
#ecqmmf_reg.integrate_registration_probabilistic_weighted_tensor_field_products(double[:,:,:] q, double[:,:] diff, double[:,:,:,:] probs, double[:] weights)
ecqmmf_reg.compute_registration_neg_log_likelihood_constant_models(fixedImage, movingImage, joint, meansFixed, meansMoving, variancesFixed, variancesMoving, negLogLikelihood)
#----plot joint probability maps---
print 'Plotting joint probability maps...'
plt.figure()
plt.title('Joint probability maps')
for i in range(nclasses):
for j in range(nclasses):
plt.subplot(nclasses,nclasses,1+i*nclasses+j)
plt.imshow(joint[:,:,i,j], cmap=plt.cm.gray)
plt.title("F="+str(i)+", M="+str(j))
#----plot negLogLikelihood maps---
print 'Plotting negLogLikelihood maps...'
plt.figure()
plt.title('neg-log-likelihood maps')
for i in range(nclasses):
for j in range(nclasses):
plt.subplot(nclasses,nclasses,1+i*nclasses+j)
plt.imshow(negLogLikelihood[:,:,i,j], cmap=plt.cm.gray)
plt.title("F="+str(i)+", M="+str(j))
def testIntersubjectRigidRegistration(fname0, fname1, level, outfname):
nib_left = nib.load(fname0)
nib_right = nib.load(fname1)
left=nib_left.get_data().astype(np.double).squeeze()
right=nib_right.get_data().astype(np.double).squeeze()
leftPyramid=[i for i in rcommon.pyramid_gaussian_3D(left, level)]
rightPyramid=[i for i in rcommon.pyramid_gaussian_3D(right, level)]
plotSlicePyramidsAxial(leftPyramid, rightPyramid)
print 'Estimation started.'
beta=estimateRigidTransformationMultiscale3D(leftPyramid, rightPyramid)
print 'Estimation finished.'
rcommon.applyRigidTransformation3D(left, beta)
sl=np.array(left.shape)//2
sr=np.array(right.shape)//2
rcommon.overlayImages(left[sl[0],:,:], leftPyramid[0][sr[0],:,:])
rcommon.overlayImages(left[sl[0],:,:], right[sr[0],:,:])
affine_transform=AffineTransform('ijk', ['aligned-z=I->S','aligned-y=P->A', 'aligned-x=L->R'], np.eye(4))
left=Image(left, affine_transform)
nipy.save_image(left,outfname)
return beta
def testIntersubjectRigidRegistration(fname0, fname1, level, outfname):
nib_left = nib.load(fname0)
nib_right = nib.load(fname1)
left = nib_left.get_data().astype(np.double).squeeze()
right = nib_right.get_data().astype(np.double).squeeze()
leftPyramid = [i for i in rcommon.pyramid_gaussian_3D(left, level)]
rightPyramid = [i for i in rcommon.pyramid_gaussian_3D(right, level)]
plotSlicePyramidsAxial(leftPyramid, rightPyramid)
print 'Estimation started.'
beta = estimateRigidTransformationMultiscale3D(leftPyramid, rightPyramid)
print 'Estimation finished.'
rcommon.applyRigidTransformation3D(left, beta)
sl = np.array(left.shape) // 2
sr = np.array(right.shape) // 2
rcommon.overlayImages(left[sl[0], :, :], leftPyramid[0][sr[0], :, :])
rcommon.overlayImages(left[sl[0], :, :], right[sr[0], :, :])
affine_transform = AffineTransform(
'ijk', ['aligned-z=I->S', 'aligned-y=P->A', 'aligned-x=L->R'],
np.eye(4))
left = Image(left, affine_transform)
nipy.save_image(left, outfname)
return beta
def plotEstimatedTransferedImage(v, numLabels, labels, beta):
vtrans=rcommon.applyRigidTransformation3D(v,beta)
means, variances=tf.computeVolumeClassStatsCYTHON(vtrans, numLabels, labels)
means=np.array(means)
variances=np.array(variances)
sh=labels.shape
meansSlice=means[labels[sh[0]//2]]
varianceSlice=variances[labels[sh[0]//2]]
plt.figure()
plt.subplot(1,2,1)
plt.title('Means ['+str(numLabels)+']')
plt.imshow(meansSlice, cmap=plt.cm.gray)
plt.subplot(1,2,2)
plt.imshow(varianceSlice, cmap=plt.cm.gray)
plt.title('Variances ['+str(numLabels)+']')
def generateTestingPair(betaGT):
betaGTRads=np.array(betaGT, dtype=np.float64)
betaGTRads[0:3]=np.copy(np.pi*betaGTRads[0:3]/180.0)
ns=181
nr=217
nc=181
left=np.fromfile('data/t2/t2_icbm_normal_1mm_pn0_rf0.rawb', dtype=np.ubyte).reshape(ns,nr,nc)
left=left.astype(np.float64)
right=np.fromfile('data/t1/t1_icbm_normal_1mm_pn0_rf0.rawb', dtype=np.ubyte).reshape(ns,nr,nc)
right=right.astype(np.float64)
right=rcommon.applyRigidTransformation3D(right, betaGTRads)
affine_transform=AffineTransform('ijk', ['aligned-z=I->S','aligned-y=P->A', 'aligned-x=L->R'], np.eye(4))
left=Image(left, affine_transform)
right=Image(right, affine_transform)
nipy.save_image(left,'moving.nii')
nipy.save_image(right,'fixed.nii')
def plotEstimatedTransferedImage(v, numLabels, labels, beta):
vtrans = rcommon.applyRigidTransformation3D(v, beta)
means, variances = tf.computeVolumeClassStatsCYTHON(
vtrans, numLabels, labels)
means = np.array(means)
variances = np.array(variances)
sh = labels.shape
meansSlice = means[labels[sh[0] // 2]]
varianceSlice = variances[labels[sh[0] // 2]]
plt.figure()
plt.subplot(1, 2, 1)
plt.title('Means [' + str(numLabels) + ']')
plt.imshow(meansSlice, cmap=plt.cm.gray)
plt.subplot(1, 2, 2)
plt.imshow(varianceSlice, cmap=plt.cm.gray)
plt.title('Variances [' + str(numLabels) + ']')
def testRigidTransformationMultiScale3D(betaGT, level):
betaGTRads=np.array(betaGT, dtype=np.float64)
betaGTRads[0:3]=np.copy(np.pi*betaGTRads[0:3]/180.0)
ns=181
nr=217
nc=181
print 'Loading volume...'
inImg=np.fromfile('data/t2/t2_icbm_normal_1mm_pn0_rf0.rawb', dtype=np.ubyte).reshape(ns,nr,nc)
inImg=inImg.astype(np.float64)
print 'Generating pyramid at level',level,'...'
left=inImg
right=rcommon.applyRigidTransformation3D(inImg, betaGTRads)
leftPyramid=[i for i in rcommon.pyramid_gaussian_3D(left, level)]
rightPyramid=[i for i in rcommon.pyramid_gaussian_3D(right, level)]
plotSlicePyramidsAxial(leftPyramid, rightPyramid)
print 'Estimation started.'
beta=estimateRigidTransformationMultiscale3D(leftPyramid, rightPyramid)
print 'Estimation finished.'
print 'Ground truth:', betaGT
return beta
def generateTestingPair(betaGT):
betaGTRads = np.array(betaGT, dtype=np.float64)
betaGTRads[0:3] = np.copy(np.pi * betaGTRads[0:3] / 180.0)
ns = 181
nr = 217
nc = 181
left = np.fromfile('data/t2/t2_icbm_normal_1mm_pn0_rf0.rawb',
dtype=np.ubyte).reshape(ns, nr, nc)
left = left.astype(np.float64)
right = np.fromfile('data/t1/t1_icbm_normal_1mm_pn0_rf0.rawb',
dtype=np.ubyte).reshape(ns, nr, nc)
right = right.astype(np.float64)
right = rcommon.applyRigidTransformation3D(right, betaGTRads)
affine_transform = AffineTransform(
'ijk', ['aligned-z=I->S', 'aligned-y=P->A', 'aligned-x=L->R'],
np.eye(4))
left = Image(left, affine_transform)
right = Image(right, affine_transform)
nipy.save_image(left, 'moving.nii')
nipy.save_image(right, 'fixed.nii')
def testRigidTransformationMultiScale3D(betaGT, level):
betaGTRads = np.array(betaGT, dtype=np.float64)
betaGTRads[0:3] = np.copy(np.pi * betaGTRads[0:3] / 180.0)
ns = 181
nr = 217
nc = 181
print 'Loading volume...'
inImg = np.fromfile('data/t2/t2_icbm_normal_1mm_pn0_rf0.rawb',
dtype=np.ubyte).reshape(ns, nr, nc)
inImg = inImg.astype(np.float64)
print 'Generating pyramid at level', level, '...'
left = inImg
right = rcommon.applyRigidTransformation3D(inImg, betaGTRads)
leftPyramid = [i for i in rcommon.pyramid_gaussian_3D(left, level)]
rightPyramid = [i for i in rcommon.pyramid_gaussian_3D(right, level)]
plotSlicePyramidsAxial(leftPyramid, rightPyramid)
print 'Estimation started.'
beta = estimateRigidTransformationMultiscale3D(leftPyramid, rightPyramid)
print 'Estimation finished.'
print 'Ground truth:', betaGT
return beta
def plotToneTransferFunction(left, rightQ, numLevels, beta):
transformed=rcommon.applyRigidTransformation3D(left, beta)
data=[transformed[rightQ==i] for i in range(numLevels)]
plt.figure()
plt.boxplot(data, 0, '')
def plotToneTransferFunction(left, rightQ, numLevels, beta):
transformed = rcommon.applyRigidTransformation3D(left, beta)
data = [transformed[rightQ == i] for i in range(numLevels)]
plt.figure()
plt.boxplot(data, 0, '')
