Difference between revisions of "2010 Summer Project Week Best Regularization Term for Demons Registration Algorithm"

From NAMIC Wiki
Jump to: navigation, search
Line 47: Line 47:
 
==References==
 
==References==
 
<div>
 
<div>
[1]. '''''Demons algorithms for fluid and curvature registration''.''' Cahill, N.D., Noble, J.A., Hawkes, D.J.  ISBI 2009.
+
[1]. ''Demons algorithms for fluid and curvature registration''. Cahill, N.D., Noble, J.A., Hawkes, D.J.  ISBI 2009.
 
</div>
 
</div>
 
<div>
 
<div>
[2]. '''''A Demons Algorithm for Image Registration with Locally Adaptive Regularization''.''' Cahill, N.D., Noble, J.A., Hawkes, D.J.. MICCAI 2009.
+
[2]. ''A Demons Algorithm for Image Registration with Locally Adaptive Regularization''. Cahill, N.D., Noble, J.A., Hawkes, D.J.. MICCAI 2009.
 
</div>
 
</div>
 
<div>
 
<div>
[3]. '''''High Accuracy Optical Flow Estimation Based on a Theory for Warping''.''' Brox, T. et al., ECCV 2004
+
[3]. ''High Accuracy Optical Flow Estimation Based on a Theory for Warping''. Brox, T. et al., ECCV 2004
 
</div>
 
</div>

Revision as of 03:28, 25 June 2010

Home < 2010 Summer Project Week Best Regularization Term for Demons Registration Algorithm

Key Investigators

  • MGH: Rui Li, Greg Sharp

Objective

  • Show comparison of the demons algorithm performance with different regularization terms.

Approach, Plan

Our plan is to find a way to convert the current research code into an itk module that can be loaded into slicer.

Progress

The research code is a mixture of MATLAB and C code. Thanks to the discussion with Luis, we have successfully implemented itkCurvatureDemonsFilter.* and itkCurvatureDemonsFunction.* for a variant of the Demons algorithm with the curvature regularization term.

Our next steps after this project week are: (1). implement locally adaptive curvature based Demons algorithm. (2). implement Demons algorithm that uses L1-regularization term, this step will take more time and effort. itkPDEDeformableRegistrationFilter.* and itkPDEDeformableRegistrationFunction.* need to be rewritten.


Delivery Mechanism

All the implementations will be included into plastimatch.

References

[1]. Demons algorithms for fluid and curvature registration. Cahill, N.D., Noble, J.A., Hawkes, D.J. ISBI 2009.

[2]. A Demons Algorithm for Image Registration with Locally Adaptive Regularization. Cahill, N.D., Noble, J.A., Hawkes, D.J.. MICCAI 2009.

[3]. High Accuracy Optical Flow Estimation Based on a Theory for Warping. Brox, T. et al., ECCV 2004