medical imaging

32
1 Medical Imaging, SS-2011 Mohammad Dawood Medical Imaging Mohammad Dawood Department of Computer Science University of Münster Germany

Upload: topaz

Post on 24-Feb-2016

23 views

Category:

Documents


0 download

DESCRIPTION

Medical Imaging. Mohammad Dawood Department of Computer Science University of Münster Germany. Recap. Sound wavesPiezoelectric crystalsWave front formation. Inverse Radon transform Filtered back projection. Filtered back projection. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Medical Imaging

Medical Imaging

Mohammad Dawood

Department of Computer Science

University of MünsterGermany

Page 2: Medical Imaging

2

Medical Imaging, SS-2011

Mohammad Dawood

Recap

Page 3: Medical Imaging

3

Medical Imaging, SS-2011

Mohammad Dawood

Sound waves Piezoelectric crystals Wave front formation

Page 4: Medical Imaging

4

Medical Imaging, SS-2011

Mohammad Dawood

Inverse Radon transform Filtered back projection

Filtered back projection

Page 5: Medical Imaging

5

Medical Imaging, SS-2011

Mohammad Dawood

Fourier slice theorem Kaczmarz Method (=ART)

Page 6: Medical Imaging

6

Medical Imaging, SS-2011

Mohammad Dawood

Image Registration

Page 7: Medical Imaging

7

Medical Imaging, SS-2011

Mohammad Dawood

Registration

T : Transformation

In this lecture

Floating image : The image to be registered

Target image : The stationary image

Page 8: Medical Imaging

8

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Linear Transformations

- Translation

- Rotation

- Scaling

- Affine

Page 9: Medical Imaging

9

Medical Imaging, SS-2011

Mohammad Dawood

Registration

3D Translation

Page 10: Medical Imaging

10

Medical Imaging, SS-2011

Mohammad Dawood

Registration

3D Rotation

Page 11: Medical Imaging

11

Medical Imaging, SS-2011

Mohammad Dawood

Registration

3D Scaling

Page 12: Medical Imaging

12

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Rigid registration

Angles are preserved Parallel lines remain parallel

Page 13: Medical Imaging

13

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Affine registration

Page 14: Medical Imaging

14

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Feature Points

Page 15: Medical Imaging

15

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Feature Points

1. De-mean

2. Compute SVD

3. Calculate the transform

Page 16: Medical Imaging

16

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Feature Points

Iterative Closest Points Algorithm (ICP)

1. Associate points by the nearest neighbor criteria.2. Estimate transformation parameters using a mean square cost function.3. Apply registration and update parameters.

Page 17: Medical Imaging

17

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Feature Points

Page 18: Medical Imaging

18

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Feature Points

Random Sample Consensus Algorithm (RNSAC)

1. Transformation is calculated from hypothetical inliers2. All other data are then tested against the fitted model and, if a point fits well to the model, also considered as a hypothetical inlier3. The estimated model is reasonably good if sufficiently many points have been classified as hypothetical inliers.4. The model is re-estimated from all assumed inliers5. Finally, the model is evaluated by estimating the error of the inliers relative to the model

Page 19: Medical Imaging

19

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Phase Correlation

Page 20: Medical Imaging

20

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Distance Measures

- Sum of Squared Differences (SSD)

- Root Mean Square Difference (RMSD)

- Normalized Cross Correlation (NXCorr)

- Mutual Information (MI)

Page 21: Medical Imaging

21

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Sum of Squared Differences

SSD(f,t) SSD(20f,t)

Page 22: Medical Imaging

22

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Root Mean Squared Differences

RMS(f,t) RMS(20f,t)

Page 23: Medical Imaging

23

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Normalized Cross Correlation

NXCorr(f,t) NXCorr(20f,t)

Page 24: Medical Imaging

24

Medical Imaging, SS-2011

Mohammad Dawood

Registration

Mutual Information

MI(f,t) MI(20f,t)

Page 25: Medical Imaging

25

Medical Imaging, SS-2011

Mohammad Dawood

Entropy for Image Registration

Define a joint probability distribution:– Generate a 2-D histogram where each axis is the number of possible

greyscale values in each image– each histogram cell is incremented each time a pair (I1(x,y), I2(x,y))

occurs in the pair of images• If the images are perfectly aligned then the histogram is highly

focused. As the images mis-align the dispersion grows• recall Entropy is a measure of histogram dispersion

Page 26: Medical Imaging

26

Medical Imaging, SS-2011

Mohammad Dawood

Optical Flow

Page 27: Medical Imaging

27

Medical Imaging, SS-2011

Mohammad Dawood

Optical flow

Brightness consistency constraint

With Taylor expansion

V : Flow (Motion)

Page 28: Medical Imaging

28

Medical Imaging, SS-2011

Mohammad Dawood

Page 29: Medical Imaging

29

Medical Imaging, SS-2011

Mohammad Dawood

Optical flow

Lucas Kanade Algorithm: Assume locally constant flow

=>

Page 30: Medical Imaging

30

Medical Imaging, SS-2011

Mohammad Dawood

Optical flow

Horn Schunck Algorithm: Assume globally smooth flow

Page 31: Medical Imaging

31

Medical Imaging, SS-2011

Mohammad Dawood

Optical flow

Bruhn’s Non-linear Algorithm

Page 32: Medical Imaging

32

Medical Imaging, SS-2011

Mohammad Dawood

Visit

23.05.2011 14:00

EIMITechnologiehof, Mendelstr. 11

48149 Münster

www.uni-muenster.de/eimi