def initializeECQMMFRegistration(fixedImage, movingImage, nclasses,
lambdaParam, mu, maxIter, tolerance):
meansFixed, variancesFixed = ecqmmf.initialize_constant_models(
fixedImage, nclasses)
meansFixed = np.array(meansFixed)
variancesFixed = np.array(variancesFixed)
meansMoving, variancesMoving = ecqmmf.initialize_constant_models(
movingImage, nclasses)
meansMoving = np.array(meansMoving)
variancesMoving = np.array(variancesMoving)
segmentedFixed, meansFixed, variancesFixed, probsFixed = ecqmmf.ecqmmf(
fixedImage, nclasses, lambdaParam, mu, maxIter, tolerance)
segmentedMoving, meansMoving, variancesMoving, probsMoving = ecqmmf.ecqmmf(
movingImage, nclasses, lambdaParam, mu, maxIter, tolerance)
probsFixed = np.array(probsFixed)
probsMoving = np.array(probsMoving)
ecqmmf.update_variances(fixedImage, probsFixed, meansFixed, variancesFixed)
ecqmmf.update_variances(movingImage, probsMoving, meansMoving,
variancesMoving)
#show variances
plt.figure()
plt.subplot(2, 1, 1)
plt.plot(variancesFixed)
plt.subplot(2, 1, 2)
plt.plot(variancesMoving)
#show mean images
fixedSmooth = probsFixed.dot(meansFixed)
movingSmooth = probsMoving.dot(meansMoving)
plt.figure()
plt.subplot(1, 2, 1)
plt.imshow(fixedSmooth, cmap=plt.cm.gray)
plt.title('Mean fixed')
plt.subplot(1, 2, 2)
plt.imshow(movingSmooth, cmap=plt.cm.gray)
plt.title('Mean moving')
#show mode images
plt.figure()
plt.subplot(1, 2, 1)
plt.imshow(segmentedFixed)
plt.title('Seg. fixed')
plt.subplot(1, 2, 2)
plt.imshow(segmentedMoving)
plt.title('Seg. moving')
#--------------
joint = probsFixed[:, :, :, None] * probsMoving[:, :, None, :]
return meansFixed, variancesFixed, meansMoving, variancesMoving, joint
def initializeECQMMFRegistration(fixedImage, movingImage, nclasses, lambdaParam, mu, maxIter, tolerance):
meansFixed, variancesFixed=ecqmmf.initialize_constant_models(fixedImage, nclasses)
meansFixed=np.array(meansFixed)
variancesFixed=np.array(variancesFixed)
meansMoving, variancesMoving=ecqmmf.initialize_constant_models(movingImage, nclasses)
meansMoving=np.array(meansMoving)
variancesMoving=np.array(variancesMoving)
segmentedFixed, meansFixed, variancesFixed, probsFixed=ecqmmf.ecqmmf(
fixedImage, nclasses, lambdaParam, mu, maxIter, tolerance)
segmentedMoving, meansMoving, variancesMoving, probsMoving=ecqmmf.ecqmmf(
movingImage, nclasses, lambdaParam, mu, maxIter, tolerance)
probsFixed=np.array(probsFixed)
probsMoving=np.array(probsMoving)
ecqmmf.update_variances(fixedImage, probsFixed, meansFixed, variancesFixed)
ecqmmf.update_variances(movingImage, probsMoving, meansMoving, variancesMoving)
#show variances
plt.figure()
plt.subplot(2,1,1)
plt.plot(variancesFixed)
plt.subplot(2,1,2)
plt.plot(variancesMoving)
#show mean images
fixedSmooth=probsFixed.dot(meansFixed)
movingSmooth=probsMoving.dot(meansMoving)
plt.figure()
plt.subplot(1,2,1)
plt.imshow(fixedSmooth, cmap=plt.cm.gray)
plt.title('Mean fixed')
plt.subplot(1,2,2)
plt.imshow(movingSmooth,cmap=plt.cm.gray)
plt.title('Mean moving')
#show mode images
plt.figure()
plt.subplot(1,2,1)
plt.imshow(segmentedFixed)
plt.title('Seg. fixed')
plt.subplot(1,2,2)
plt.imshow(segmentedMoving)
plt.title('Seg. moving')
#--------------
joint=probsFixed[:,:,:,None]*probsMoving[:,:,None,:]
return meansFixed, variancesFixed, meansMoving, variancesMoving, joint
#image=nib.load('data/t1/IBSR18/IBSR_01/IBSR_01_ana_strip.nii.gz')
image=nib.load('data/t1/t1_icbm_normal_1mm_pn0_rf0_peeled.nii.gz')
image=image.get_data().squeeze()
image=image.astype(np.float64)
image=(image-image.min())/(image.max()-image.min())
sh=image.shape
img=image[:,sh[1]//2,:].copy()
nclasses=16
lambdaParam=.05
mu=.01
outerIter=20
innerIter=50
tolerance=1e-6
means, variances=ecqmmf.initialize_constant_models(img, nclasses)
means=np.array(means)
variances=np.array(variances)
segmented, means, variances, probs=ecqmmf.ecqmmf(img, nclasses, lambdaParam, mu, outerIter, innerIter, tolerance)
segmented=np.array(segmented)
means=np.array(means)
variances=np.array(variances)
probs=np.array(probs)
meanEstimator=probs.dot(means)
plt.figure()
plt.subplot(1,3,1)
plt.imshow(img)
plt.title('Input')
plt.subplot(1,3,2)
plt.imshow(segmented)
def estimateNewECQMMFMultimodalDeformationField2D(fixed, moving, nclasses, lambdaMeasureField, lambdaDisplacement, mu, maxOuterIter, maxInnerIter, tolerance, previousDisplacement=None):
sh=fixed.shape
X0,X1=np.mgrid[0:sh[0], 0:sh[1]]
displacement =np.empty(shape=(fixed.shape)+(2,), dtype=np.float64)
gradientField =np.empty(shape=(fixed.shape)+(2,), dtype=np.float64)
totalDisplacement=np.zeros(shape=(fixed.shape)+(2,), dtype=np.float64)
gradientField =np.empty(shape=(fixed.shape)+(2,), dtype=np.float64)
residuals =np.zeros_like(fixed)
warped=None
if(previousDisplacement!=None):
totalDisplacement[...]=previousDisplacement
warped=ndimage.map_coordinates(moving, [X0+totalDisplacement[...,0], X1+totalDisplacement[...,1]], prefilter=True)
else:
warped=moving
#run soft segmentation on the fixed image
meansFixed, variancesFixed=ecqmmf.initialize_constant_models(fixed, nclasses)
meansFixed=np.array(meansFixed)
variancesFixed=np.array(variancesFixed)
segFixed, meansFixed, variancesFixed, probsFixed=ecqmmf.ecqmmf(fixed, nclasses, lambdaMeasureField, mu, maxOuterIter, maxInnerIter, tolerance)
meansFixed=np.array(meansFixed)
probsFixed=np.array(probsFixed)
#run soft segmentation on the warped image
meansWarped, variancesWarped=ecqmmf.initialize_constant_models(warped, nclasses)
meansWarped=np.array(meansWarped)
variancesWarped=np.array(variancesWarped)
segWarped, meansWarped, variancesWarped, probsWarped=ecqmmf.ecqmmf(warped, nclasses, lambdaMeasureField, mu, maxOuterIter, maxInnerIter, tolerance)
meansWarped=np.array(meansWarped)
probsWarped=np.array(probsWarped)
#inicialize the joint models (solve assignment problem)
ecqmmf_reg.initialize_coupled_constant_models(probsFixed, probsWarped, meansWarped)
#start optimization
outerIter=0
negLogLikelihood=np.zeros_like(probsFixed)
while(outerIter<maxOuterIter):
outerIter+=1
print "Outer:", outerIter
if(outerIter>1):#avoid warping twice at the first iteration
warped=ndimage.map_coordinates(moving, [X0+totalDisplacement[...,0], X1+totalDisplacement[...,1]], prefilter=True)
movingMask=(moving>0)*1.0
warpedMask=ndimage.map_coordinates(movingMask, [X0+totalDisplacement[...,0], X1+totalDisplacement[...,1]], order=0, prefilter=False)
warpedMask=warpedMask.astype(np.int32)
#--- optimize the measure field and the intensity models ---
ecqmmf_reg.compute_registration_neg_log_likelihood_constant_models(fixed, warped, meansFixed, meansWarped, negLogLikelihood)
#ecqmmf.initialize_normalized_likelihood(negLogLikelihood, probsWarped)
ecqmmf.initialize_maximum_likelihood(negLogLikelihood, probsWarped);
innerIter=0
mse=0
while(innerIter<maxInnerIter):
innerIter+=1
print "\tInner:",innerIter
ecqmmf.optimize_marginals(negLogLikelihood, probsWarped, lambdaMeasureField, mu, maxInnerIter, tolerance)
mseFixed=ecqmmf.update_constant_models(fixed, probsWarped, meansFixed, variancesFixed)
mseWarped=ecqmmf.update_constant_models(warped, probsWarped, meansWarped, variancesWarped)
mse=np.max([mseFixed, mseWarped])
if(mse<tolerance):
break
#---given the intensity models and the measure field, compute the displacement
deltaField=meansWarped[None, None, :]-warped[:,:,None]
gradientField[:,:,0], gradientField[:,:,1]=sp.gradient(warped)
maxDisplacement=ecqmmf_reg.optimize_ECQMMF_displacement_field_2D(deltaField, gradientField, probsWarped, lambdaDisplacement, displacement, residuals, maxInnerIter, tolerance)
totalDisplacement+=displacement
if(maxDisplacement<tolerance):
break
plt.figure()
plt.subplot(2,2,1)
plt.imshow(fixed, cmap=plt.cm.gray)
plt.title("fixed")
plt.subplot(2,2,2)
plt.imshow(warped, cmap=plt.cm.gray)
plt.title("moving")
plt.subplot(2,2,3)
plt.imshow(probsFixed.dot(meansFixed), cmap=plt.cm.gray)
plt.title("E[fixed]")
plt.subplot(2,2,4)
plt.imshow(probsWarped.dot(meansWarped), cmap=plt.cm.gray)
plt.title("E[moving]")
return totalDisplacement
#image=nib.load('data/t1/IBSR18/IBSR_01/IBSR_01_ana_strip.nii.gz')
image = nib.load('data/t1/t1_icbm_normal_1mm_pn0_rf0_peeled.nii.gz')
image = image.get_data().squeeze()
image = image.astype(np.float64)
image = (image - image.min()) / (image.max() - image.min())
sh = image.shape
img = image[:, sh[1] // 2, :].copy()
nclasses = 16
lambdaParam = .05
mu = .01
outerIter = 20
innerIter = 50
tolerance = 1e-6
means, variances = ecqmmf.initialize_constant_models(img, nclasses)
means = np.array(means)
variances = np.array(variances)
segmented, means, variances, probs = ecqmmf.ecqmmf(img, nclasses, lambdaParam,
mu, outerIter, innerIter,
tolerance)
segmented = np.array(segmented)
means = np.array(means)
variances = np.array(variances)
probs = np.array(probs)
meanEstimator = probs.dot(means)
plt.figure()
plt.subplot(1, 3, 1)
plt.imshow(img)
plt.title('Input')
def estimateNewECQMMFMultimodalDeformationField2D(fixed,
moving,
nclasses,
lambdaMeasureField,
lambdaDisplacement,
mu,
maxOuterIter,
maxInnerIter,
tolerance,
previousDisplacement=None):
sh = fixed.shape
X0, X1 = np.mgrid[0:sh[0], 0:sh[1]]
displacement = np.empty(shape=(fixed.shape) + (2, ), dtype=np.float64)
gradientField = np.empty(shape=(fixed.shape) + (2, ), dtype=np.float64)
totalDisplacement = np.zeros(shape=(fixed.shape) + (2, ), dtype=np.float64)
gradientField = np.empty(shape=(fixed.shape) + (2, ), dtype=np.float64)
residuals = np.zeros_like(fixed)
warped = None
if (previousDisplacement != None):
totalDisplacement[...] = previousDisplacement
warped = ndimage.map_coordinates(
moving,
[X0 + totalDisplacement[..., 0], X1 + totalDisplacement[..., 1]],
prefilter=True)
else:
warped = moving
#run soft segmentation on the fixed image
meansFixed, variancesFixed = ecqmmf.initialize_constant_models(
fixed, nclasses)
meansFixed = np.array(meansFixed)
variancesFixed = np.array(variancesFixed)
segFixed, meansFixed, variancesFixed, probsFixed = ecqmmf.ecqmmf(
fixed, nclasses, lambdaMeasureField, mu, maxOuterIter, maxInnerIter,
tolerance)
meansFixed = np.array(meansFixed)
probsFixed = np.array(probsFixed)
#run soft segmentation on the warped image
meansWarped, variancesWarped = ecqmmf.initialize_constant_models(
warped, nclasses)
meansWarped = np.array(meansWarped)
variancesWarped = np.array(variancesWarped)
segWarped, meansWarped, variancesWarped, probsWarped = ecqmmf.ecqmmf(
warped, nclasses, lambdaMeasureField, mu, maxOuterIter, maxInnerIter,
tolerance)
meansWarped = np.array(meansWarped)
probsWarped = np.array(probsWarped)
#inicialize the joint models (solve assignment problem)
ecqmmf_reg.initialize_coupled_constant_models(probsFixed, probsWarped,
meansWarped)
#start optimization
outerIter = 0
negLogLikelihood = np.zeros_like(probsFixed)
while (outerIter < maxOuterIter):
outerIter += 1
print "Outer:", outerIter
if (outerIter > 1): #avoid warping twice at the first iteration
warped = ndimage.map_coordinates(moving, [
X0 + totalDisplacement[..., 0], X1 + totalDisplacement[..., 1]
],
prefilter=True)
movingMask = (moving > 0) * 1.0
warpedMask = ndimage.map_coordinates(
movingMask,
[X0 + totalDisplacement[..., 0], X1 + totalDisplacement[..., 1]],
order=0,
prefilter=False)
warpedMask = warpedMask.astype(np.int32)
#--- optimize the measure field and the intensity models ---
ecqmmf_reg.compute_registration_neg_log_likelihood_constant_models(
fixed, warped, meansFixed, meansWarped, negLogLikelihood)
#ecqmmf.initialize_normalized_likelihood(negLogLikelihood, probsWarped)
ecqmmf.initialize_maximum_likelihood(negLogLikelihood, probsWarped)
innerIter = 0
mse = 0
while (innerIter < maxInnerIter):
innerIter += 1
print "\tInner:", innerIter
ecqmmf.optimize_marginals(negLogLikelihood, probsWarped,
lambdaMeasureField, mu, maxInnerIter,
tolerance)
mseFixed = ecqmmf.update_constant_models(fixed, probsWarped,
meansFixed,
variancesFixed)
mseWarped = ecqmmf.update_constant_models(warped, probsWarped,
meansWarped,
variancesWarped)
mse = np.max([mseFixed, mseWarped])
if (mse < tolerance):
break
#---given the intensity models and the measure field, compute the displacement
deltaField = meansWarped[None, None, :] - warped[:, :, None]
gradientField[:, :, 0], gradientField[:, :, 1] = sp.gradient(warped)
maxDisplacement = ecqmmf_reg.optimize_ECQMMF_displacement_field_2D(
deltaField, gradientField, probsWarped, lambdaDisplacement,
displacement, residuals, maxInnerIter, tolerance)
totalDisplacement += displacement
if (maxDisplacement < tolerance):
break
plt.figure()
plt.subplot(2, 2, 1)
plt.imshow(fixed, cmap=plt.cm.gray)
plt.title("fixed")
plt.subplot(2, 2, 2)
plt.imshow(warped, cmap=plt.cm.gray)
plt.title("moving")
plt.subplot(2, 2, 3)
plt.imshow(probsFixed.dot(meansFixed), cmap=plt.cm.gray)
plt.title("E[fixed]")
plt.subplot(2, 2, 4)
plt.imshow(probsWarped.dot(meansWarped), cmap=plt.cm.gray)
plt.title("E[moving]")
return totalDisplacement