TubeTK/Anisotropic Hybrid Diffusion with Continuous Switch: Difference between revisions

From KitwarePublic
Jump to navigationJump to search
Line 23: Line 23:
[http://gitorious.org/tubetk/tubetk/blobs/master/Base/Preprocessing/itkStructureTensorRecursiveGaussianImageFilter.h itkStructureTensorRecursiveGaussianImageFilter ]
[http://gitorious.org/tubetk/tubetk/blobs/master/Base/Preprocessing/itkStructureTensorRecursiveGaussianImageFilter.h itkStructureTensorRecursiveGaussianImageFilter ]
= Edge Enhancing Diffusion Filter =
= Edge Enhancing Diffusion Filter =
[http://gitorious.org/tubetk/tubetk/blobs/master/Base/Preprocessing/itkAnisotropicEdgeEnhancementDiffusionImageFilter.h itkAnisotropicEdgeEnhancementDiffusionImageFilter]
*[http://gitorious.org/tubetk/tubetk/blobs/master/Base/Preprocessing/itkAnisotropicEdgeEnhancementDiffusionImageFilter.h itkAnisotropicEdgeEnhancementDiffusionImageFilter]
[http://gitorious.org/tubetk/tubetk/blobs/master/Base/Preprocessing/itkAnisotropicEdgeEnhancementDiffusionFunction.h itkAnisotrpicEdgeEnhancementDiffusionFunction]
*[http://gitorious.org/tubetk/tubetk/blobs/master/Base/Preprocessing/itkAnisotropicEdgeEnhancementDiffusionFunction.h itkAnisotrpicEdgeEnhancementDiffusionFunction]


= Coherence Enhancing Diffusion Filter =
= Coherence Enhancing Diffusion Filter =
= Hybrid Continuous Filter =
= Hybrid Continuous Filter =

Revision as of 02:05, 13 April 2010

This module is an implementation of diffusion based smoothing technique developed by Mendrik et al.

Mendrik AM, Vonken EJ, Rutten A, Viergever MA, van Ginneken B. Noise reduction in computed tomography scans using 3-d anisotropic hybrid diffusion with continuous switch. IEEE Trans Med Imaging. 2009 Oct;28(10):1585-94.

Algorithm synopsis

This algorithm is based on anisotropic non-linear diffusion. The technique combines edge-preserving noise reduction while enhancing local structures. This algorithm uses a hybrid approach that combines the advantages of EED ( Edge enhancing diffusion ) and CED ( Coherence enhancing diffusion ).

EED focuses on edge preservation and enhancement. In EED, strong smoothing is applied along the direction of the edge while the strength of the smoothing along the other perpendicular directions depends on the gradient. The higher the gradient the lower the smoothing strength would be. Applying EED to a medical image would enhance boundaries of larger organs but would blur vessels and smaller structures.

On the other hand, CED is designed to to connect lines and improve flow-like structures. Running CED on medical images would preserve smaller structures and filter vessels but would not filter noise and plate-like structures. Therefore a hybrid technique was proposed to combine intelligently the benefits of the two techniques.

Implementation

The tubetk implementation will follow ITK's finite difference solver framework. The framework uses solver filter and function. The implementation will be done as follows:

  1. Implement structure tensor generation filter ( Second moment matrix generator that is currently not available in ITK )
  2. Implement Edge-enhancing diffusion function and solver filer
  3. Implement Coherence-enhancing diffusion function and solver filter
  4. Hybrid continuous filter

Structure Tensor Generation Filter

itkStructureTensorRecursiveGaussianImageFilter

Edge Enhancing Diffusion Filter

Coherence Enhancing Diffusion Filter

Hybrid Continuous Filter