MRI preprocessing and segmentation

39
MRI preprocessing and segmentation

description

MRI preprocessing and segmentation. Bias References. Segmentation References. Validation. Segmentation pipeline. Clarke, 1995. 1. Preprocessing 1.1. Brain extraction 1.2. Removal of field inhomogeneities (bias-field). 1.1. Brain extraction. - PowerPoint PPT Presentation

Transcript of MRI preprocessing and segmentation

Page 1: MRI preprocessing  and segmentation

MRI preprocessing and

segmentation

Page 2: MRI preprocessing  and segmentation

Bias References

Page 3: MRI preprocessing  and segmentation

Segmentation References

Page 4: MRI preprocessing  and segmentation

Segmentation pipeline

Clarke, 1995

Validation

Page 5: MRI preprocessing  and segmentation

1. Preprocessing

1.1. Brain extraction

1.2. Removal of field inhomogeneities (bias-field)

Page 6: MRI preprocessing  and segmentation

1.1. Brain extraction

MRI of head Intracranial volume Extracted brain

Page 7: MRI preprocessing  and segmentation

1.1. Brain extraction

FSL: Initiate a mesh inside the skull and expand-wrap onto brain surface

Huh, 2002 method: go to mid sagittal, find brain, copy mask on adjacent slicescorrect the copied mask

Page 8: MRI preprocessing  and segmentation

1.1. Brain extraction

initial mask adjacent slice j mask of slice j

challengeHuh, 2002

Page 9: MRI preprocessing  and segmentation

1.1. Brain extraction

restoring truncated boundary

Page 10: MRI preprocessing  and segmentation

Let voxel have a value 1 if its intensity is higher than t

(determine t arbitrarily,increase when needed)

Page 11: MRI preprocessing  and segmentation

1.2. Removal of field inhomogeneities

Bias field

Phantom studies:Typical signal falloff in SI direction is 20%

S

I20 %

x

intensity

Page 12: MRI preprocessing  and segmentation

1.2. Removal of field inhomogeneities

Statistical methods: probabilistic, gaussian and mixture models of bias-field

Polynomial methods: smooth polynomial fit to bias-field

Page 13: MRI preprocessing  and segmentation

1.2. Removal of field inhomogeneitiesPolynomial method example:

Milchenko, 2006

Page 14: MRI preprocessing  and segmentation

Milchenko, 2006

Page 15: MRI preprocessing  and segmentation

1.2. Removal of field inhomogeneities

Shattuck, 2001

orig model

bias result

Page 16: MRI preprocessing  and segmentation

2. Feature extraction

Features:- Intensities in a single MRI: univariate classification

- Feature vector from a single MRI: multi-variate class.ex: [I(x,y,z) f(N(x,y,z)) g(N(x,y,z))]

where N : neighbourhood around (x,y,z) f: distribution of I in neighborhood (entropy) g: average I in neighborhood or f, g specify edge or boundary information

- Intensities in multiple MRIs with different contrast: multi-variate (multi-spectral)

Page 17: MRI preprocessing  and segmentation

3. Segmentation

4 regions:R1: air, scalp, fat, skull (background, removed)R2: subarachnoid space (CSF)R3: parenchyma (GM, WM)R4: ventricles(CSF)

3 tissue types:CSF, GM, WM

Page 18: MRI preprocessing  and segmentation

3. Segmentation

Clarke, 1995

(T1 weighted)(dual echo:T2, PD or T1, T2, PD weighted)

Page 19: MRI preprocessing  and segmentation

3. Segmentation

T1 weighted, single intensity dual echo:T2, PD or T1, T2, PD weighted

or T1 weighted

with feature vector3.1. Histogram based

thresholding

Unsupervised

3.6. k-means 3.7. fuzzy cmeans

Supervised

Parametric Non-parametric ANN

3.3. Max. Likelihood 3.4. k-NN 3.5. MLP

3.2. Bayesian

Page 20: MRI preprocessing  and segmentation
Page 21: MRI preprocessing  and segmentation

3.1. Histogram based thresholding

Schnack, 2001

WM

GM

Histogram of extracted, bias corrected brain in T1-weighted MRI

Lcp crossing point of tangents

L = g * Lcp (set g manually on 80 images)if I(x,y,z) < L then GM else WM

Page 22: MRI preprocessing  and segmentation
Page 23: MRI preprocessing  and segmentation

Population1

Population2

Population3

3.2. Bayesian segmentation

WMGM

Hypothetical distributions

(intensity)

(#of voxels/#ofallvoxels in the brain)

Page 24: MRI preprocessing  and segmentation

3.2. Bayes’ classifier

For each voxel, x,y,z:Assume K tissue types (for eg. T1, T2, ..., Tk) possible, for 1 observed intensity, I:

P(Tj ! I) = P(I ! Tj) . P(Tj)

Ξ P(I ! Tk). P(Tk) k

GM, WM, CSF ratiosfrom volumetric studies

setup graphs above from regional data

Decide on tissue type m if: P(Tm ! I) > P(Tj ! I) for all j

Kovacevic, 2002

J,k=1,2,3:1: CSF, 2: GM, 3:WM

Page 25: MRI preprocessing  and segmentation

Methods based on feature vector or multi-spectral data

Supervised vs unsupervised Methods

Supervised: - Color indicates known classes - Separation contour is to be found during training phase- Separation contour is used for classification during recall phase

Unsupervised: - No color, classes unknown- Clusters are found during training phase- Association with clusters are made during recall phase

Page 26: MRI preprocessing  and segmentation

Kovacevic, 2001

T2 weightedvoxel x,y,z

PD weightedimage

T2 weightedimage

intensity

intensity

Page 27: MRI preprocessing  and segmentation

Suckling, 1999

Page 28: MRI preprocessing  and segmentation

3.3. Maximum likelihood classifier

- Assume the distribution P(I ! Tj) in Bayes can be obtained by a mixture of Gaussian or Normal distribution- Estimate means and co-variance matrix- For better results use Hidden Markov fields within neighborhoods

Zavaljevski, 2000

15 classes

Page 29: MRI preprocessing  and segmentation

3.3. Maximum likelihood classifier

Zavaljevski, 2000

Normal subject Stroke patient

Page 30: MRI preprocessing  and segmentation

3.4. K-NN, K-Nearest neighbor classifier

T1 intensity

T2 intensity

Hypothetical distribution

- k is always odd, 1<k<15 (as k increases comput time increases)- given a point p find k closest samples known from before- decide on class m where m is the highest number of classes among these k samples

Page 31: MRI preprocessing  and segmentation

3.4. K-NN classifier

k=1 k=45

manual atlas labels atlas labels labels with linear reg. with non-lin reg.

Vrooman, 2007

Uses 5 different contrast MRIs

Page 32: MRI preprocessing  and segmentation

MLPArchitecture:1 layer: linear contour

>1 layers: complex contours

countours areused for classseparation

transfer fcn: sigmoid

W1 W3

:F

3.5. ANN, MLP classifier

for segmentation,M = 3, 3 classes

feature vector

Page 33: MRI preprocessing  and segmentation

3.5. ANN, MLP classifier

Results

This page is empty on purpose

Page 34: MRI preprocessing  and segmentation

3.6. k-means classifier

Algorithm:- k is equal to number of classes- choose k arbitrary initial seed points (*)- assume seed points are class centroids1 for each sample point j, find distance to all k centroids Let j belong to class m if j is closest to centroid m2 for each class k, recalculate centroids

repeat steps 1 and 2 above until no change in centroids

Note how class assignments changeat each iteration

Minimized measure:

This classifier is not used much in segmentation, but explained here as an introduction to fuzzy c-means

Page 35: MRI preprocessing  and segmentation

3.7. fuzzy c-means (FCM) classifier

k-means classifier FCM classifier

U: membership row=each sample xcol=each class

minimized cost

Page 36: MRI preprocessing  and segmentation

3.7. fuzzy c-means (FCM) classifier

initial

iteration 8

iteration 37

Initialize U=[uij] matrix, U(0)

At k-step: calculate the centers vectors C(k)=[cj] with U(k)

Update U(k) , U(k+1)

If || U(k+1) - U(k)||< then STOP; otherwise return to step 2.

Page 37: MRI preprocessing  and segmentation

3.7. fuzzy c-means classifier

Results

Page 38: MRI preprocessing  and segmentation

4. Validation

Important issues:

- Partial volume effect, visualization

- Validation in manually segmented image

- Performance comparison with other methods on simulated image: Ex: Brainweb from Mcgill

Page 39: MRI preprocessing  and segmentation

4. Validation

Partial volume effectfor boundary separationShattuck, 2001

corrrect WM misclassified(colored by subejct number

there are a total of 10 subjects)

segmentedgold std

Clark, 2006