Projects:ProstateRegistration - Revision history

Ygao at 01:15, 16 November 2013

2013-11-16T01:15:46Z

Ygao: /* DWI registration */

2009-04-12T20:09:28Z

DWI registration

Ygao: /* DWI registration */

2009-04-12T20:09:14Z

DWI registration

Ygao at 20:01, 12 April 2009

2009-04-12T20:01:44Z

Ygao: /* Particle Filter Registration of Medical Imagery */

2009-04-12T20:00:23Z

Particle Filter Registration of Medical Imagery

Ygao at 19:59, 12 April 2009

2009-04-12T19:59:48Z

Ygao: /* Description */

2009-03-23T20:08:42Z

Description

Ygao: /* Description */

2009-03-23T20:03:42Z

Description

Ygao: New page: Back to Georgia Tech Algorithms NOTOC = Prostate Registration = The objective is to register the prostate from a 3D MRI and ultrasound data sets. = Description =...

2009-03-23T19:58:48Z

New page: Back to Georgia Tech Algorithms __NOTOC__ = Prostate Registration = The objective is to register the prostate from a 3D MRI and ultrasound data sets. = Description =...

New page

Back to [[Algorithm:GATech|Georgia Tech Algorithms]]
__NOTOC__
= Prostate Registration =

The objective is to register the prostate from a 3D MRI and ultrasound data sets.

= Description =
The algorithm register the two prostate shapes. It is able to handle the cases where one prostate is in supine and the other is in prone position, and are separated by long distance.

[[Image:ShapeBasePstSegSlicer.png|Shape base prostate segmentation in Slicer through command line module|500px]].

= Key Investigators =

* Georgia Tech Algorithms: Yi Gao, Allen Tannenbaum

= Publications =

[[Category: Segmentation]] [[Category: Prostate]]

@@ Line 1: / Line 1: @@
-Back to [[Algorithm:GATech|Georgia Tech Algorithms]]
+Back to [[Algorithm:Stony Brook|Stony Brook Algorithms]]
 __NOTOC__
 = Particle Filter Registration of Medical Imagery =

@@ Line 22: / Line 22: @@
 [[Image:BrainBefore.png|500px|]]
 Shows the original DWI point set in blue and the affine transformed one in red. The objective is to register the red to the blue.
 [[Image:BrainAfter.png|500px|]]
 The result of using the particle filter image registration.

@@ Line 20: / Line 20: @@
 == DWI registration  ==
 When applying the method to register two point sets generated from DWI images, the local minima of the registration energy is successfully avoided and the figure below shows:
 = Key Investigators =

@@ Line 2: / Line 2: @@
 __NOTOC__
 = Particle Filter Registration of Medical Imagery =
 == Prostate registration ==
-We transform the general problem of image registration to a sparse task of aligning point clouds. This is accomplished by considering the image as a probability density function, from which a point cloud is formed by randomly drawing samples. This allows us to apply a particle filtering technique for the registration. While point set registration and image registration are  generally studied separately, this approach attempts to bridge the two. Thus, our contribution is threefold. Firstly, our method can handle affine transformations. Secondly, registration of partial images is more natural. Lastly, the point cloud representation is much sparser than the usual image representation as a discrete function. This allows us to drastically reduce the computational cost associated with 2D and 3D registration task. Experimental results demonstrate the fast and robust convergence of the proposed algorithm. See Figures below:
+Experimental results demonstrate the fast and robust convergence of the proposed algorithm. See Figures below:
 One the right side:

@@ Line 3: / Line 3: @@
 = Particle Filter Registration of Medical Imagery =
 We transform the general problem of image registration to a sparse task of aligning point clouds. This is accomplished by considering the image as a probability density function, from which a point cloud is formed by randomly drawing samples. This allows us to apply a particle filtering technique for the registration. While point set registration and image registration are  generally studied separately, this approach attempts to bridge the two. Thus, our contribution is threefold. Firstly, our method can handle affine transformations. Secondly, registration of partial images is more natural. Lastly, the point cloud representation is much sparser than the usual image representation as a discrete function. This allows us to drastically reduce the computational cost associated with 2D and 3D registration task. Experimental results demonstrate the fast and robust convergence of the proposed algorithm. See Figures below:
@@ Line 15: / Line 16: @@
 [[Image:ProstateRegSupineToProneInParaview.png|500px|]]
 When applying the method to register two point sets generated from DWI images, the local minima of the registration energy is successfully avoided and the figure below shows:
 = Key Investigators =

@@ Line 16: / Line 16: @@
 One the left:
      Blue: The same prostate in prone position;
-     Yellow: Result of registering the supine towards the prone.
+     Pink: Result of registering the Yellow (supine) towards the Blue (prone).
 [[Image:ProstateRegSupineToProneInParaview.png|500px|]]

@@ Line 8: / Line 8: @@
 The algorithm register the two prostate shapes. It is able to handle the cases where one prostate is in supine and the other is in prone position, and are separated by long distance.
-[[Image:ShapeBasePstSegSlicer.png|Shape base prostate segmentation in Slicer through command line module|500px]].
+In the image below:
 = Key Investigators =

Projects:ProstateRegistration - Revision history

Ygao at 01:15, 16 November 2013

Ygao: /* DWI registration */

Ygao: /* DWI registration */

Ygao at 20:01, 12 April 2009

Ygao: /* Particle Filter Registration of Medical Imagery */

Ygao at 19:59, 12 April 2009

Ygao: /* Description */

Ygao: /* Description */

Ygao: New page: Back to Georgia Tech Algorithms __NOTOC__ = Prostate Registration = The objective is to register the prostate from a 3D MRI and ultrasound data sets. = Description =...

Ygao: New page: Back to Georgia Tech Algorithms NOTOC = Prostate Registration = The objective is to register the prostate from a 3D MRI and ultrasound data sets. = Description =...