Download presentation
Presentation is loading. Please wait.
1
Matching a 3D Active Shape Model on sparse cardiac image data, a comparison of two methods Marleen Engels Supervised by: dr. ir. H.C. van Assen Committee: prof. dr. ir. B.M. ter Haar Romeny dr. A. Vilanova Bartroli dr. ir. H.C. van Assen dr. ir. H.M.M. ten Eikelder June 2007
2
Outline Introduction Active Shape Model Optimization methods Method of Least Squares Cross Out method Experiments with phantoms Experiments with real data Results Conclusions and discussion Future work
3
Introduction Anatomy of the heart Supplying the entire body of blood
4
Introduction
5
Increasing number image acquisitions Automate segmentation and diagnosis Reduce scanning time by reducing the number of image slices per acquisition → sparse data Motivation
6
Introduction Goal of the project To segment sparse cardiac image, using a 3D Active Shape Model, implementing and testing 2 different approaches 1)Optimization methods, like Lötjönen et al. did. 2)Cross Out, newly developed in this project
7
Active Shape Model A Statistical Shape Model (SSM) contains information about the mean shape and shape variations based on a representative training set. x = x mean + Φb b = Φ T (x - x mean ) When a SSM is used to segment unseen data then it is called an Active Shape Model (ASM).
8
Active Shape Model first modethird modesecond mode
9
Active Shape Model
10
An ASM requires complete data sets Modify ASMs SPASM by van Assen et al. Optimization Methods by Lötjönen et al. Cross Out Method (new)
11
Optimization methods A different b vector generates a different shape x Finding a vector b which generates a shape that fits the sparse data best → using optimization methods Optimization methods: finding an optimum (global minimum or maximum) of a (cost)function
12
Optimization methods Steepest Descent method Conjugate Gradients method Space method … It is application dependent which method works best
13
Optimization methods Steepest Descent method A new point, closer to the minimum, is found by searching for a minimum in the opposite direction of the gradient at the current point Bad convergence if x o is badly chosen
14
Optimization methods Uses non-interfering search directions, conjugate directions A minimum can be found in a t-dimensional space in t iterations Conjugate Gradients method
15
Optimization methods Conjugate Gradients method x2x2 x2x2 x1x1 x1x1 Steepest descent Conjugate gradients
16
Optimization methods Repetitive search to find the optimal vector b opt Each element of b, b i for i = 1,…,t, is separately optimized The initial b is b opt = 0, b i,opt = 0 Space method
17
Optimization methods Space method f(b) bibi b i,opt -3√λ i 3√λi3√λi
18
Method of Least Squares
19
Can be applied to solve a linear system Ax = b x * = (A T A) -1 A T b is the least squares solution of the linear system Ax = b, the distance between Ax * and b minimized A is the coefficient matrix, x are the unknown variables, and b are the known variables
20
A shape can be generated with: x = x mean + Φb Linear system: Φb = (x – x mean ), Φ the coefficient matrix, b the unknown variables, (x – x mean ) the known variables Least squares solution is: b* = ( Φ T Φ) -1 Φ T (x – x mean ) In literature: b* = Φ T (x – x mean ) Method of Least Squares Application to ASM’s
21
Method of Least Squares Application to ASM’s A shape x 0 is generated with b 0 b * calc,1 = Φ T (x 0 – x mean ) b * calc,2 = (Φ T Φ) -1 Φ T (x 0 – x mean )
22
Cross Out method When x is not complete (sparse data) the equation Φ b = (x – x mean ) = dx still holds, when corresponding rows of dx and Φ are crossed regarding the dimensions [3N x t][t x 1] = [3N x 1] → [3N – 3R x t][t x 1] = [3N – 3R x 1]
23
Cross Out Method Now a sparse linear system is created Φ sparse b = dx sparse = x sparse – x mean,sparse Using the method of least squares to calculate b * sparse b * sparse =( Φ sparse T Φ sparse ) -1 Φ sparse T (x sparse – x mean,sparse )
24
Experiments Error : average point to point distance between the point of calculated shape and the original shape ptosError : average point to surface distance between the points of the calculated shape and the surface of the original shape The performance of the cross out method and the optimization methods can be determined by:
25
Experiments with phantoms Per experiment a set of 15 shapes is used 15 different b vectors Each element of b is randomly chosen with the restriction that the generated shape resembles the shapes of the training set.
26
Experiments with phantoms 1)Deleting 500 points with the most variation with the least variation randomly 2)Deleting points in slices and vary the number of deleted slices 3)Using 60 and 89 modes Testing the Cross Out method
27
Experiments with phantoms Testing the Cross Out method (1), deleting 500 points Complete shapeShape without points with least variation Shape without points with most variation Shape without 500 random points
28
Experiments with phantoms Testing the Cross Out method (1), deleting 500 points
29
Experiments with phantoms Testing the Cross Out method (2), vary the number of slices to delete X = deleted
30
Experiments with phantoms Testing the Cross Out method (2), vary the number of slices to delete
31
Experiments with phantoms The complete model has 89 modes of variations, 100 % of all the variation present in the training set 60 modes contains about 97 % of the variation present in the training set 15 shapes in 5 configurations Testing the Cross Out method (3), using 60 and 89 modes
32
Experiments with phantoms Testing the Cross Out method (3), using 60 and 89 modes X = deleted
33
Experiments with phantoms Testing the Cross Out method (3), using 60 and 89 modes
34
Experiments with phantoms It does matter which points are deleted, deleting points with least variation gives the best result Up till 8 slices can be deleted and still a good shape is found Using 89 modes gives a better result than 60 modes Testing the Cross Out method, conclusions
35
Experiments with phantoms Implemented in C by dr. J. Lötjönen using 60 modes Optimization method Step size of the gradient Range of the parameter space 15 shapes in 4 different configurations Conjugate gradients method with step size 0.1 for Error Steepest descent method with step size 0.1 for ptosError Optimization methods
36
Experiments with phantoms 15 shapes in 4 configurations Cross Out method with 60 modes Cross Out method with 89 modes Conjugate gradients with step size 0.1 Steepest Descent with step size 0.1 Optimization versus Cross Out
37
Experiments with phantoms Optimization versus Cross Out 11 slices9 slices7 slices 5 slices
38
Results Optimization versus Cross Out, using phantoms
39
Results Optimization versus Cross Out, using phantoms
40
Experiments with real data 15 shapes in 4 configurations Cross Out 60 modes, Cross Out 89 modes, Conjugate gradients step size 0.1 11 slices6 slices4 slices8 slices
41
Results Real data
42
Conclusions and Discussion When using a ASM it is better to use the least squares method The Cross Out method gives better results than the optimization methods The performance of ASM depends on how well the training set represents the entire population
43
Future work Test the robustness of the Cross Out method Cross Out method should implemented as iterative procedure Designing a smart scanning protocol
44
Questions? Special thanks to Hans van Assen Bart ter Haar Romeny
Similar presentations
© 2024 SlidePlayer.com Inc.
All rights reserved.