Difference between revisions of "Stanford Simbios group"

From Slicer Wiki
Jump to: navigation, search
 
(16 intermediate revisions by the same user not shown)
Line 15: Line 15:
 
==Atlas Generation from Input MR Images==
 
==Atlas Generation from Input MR Images==
 
===Model Generation from Input MR Images===
 
===Model Generation from Input MR Images===
Pre-Segmented models for femur, patella and tibia are obtained for a patient (in .stl format). This models can be prepared using the hypermesh software. The models contain vertices of triangles representing femur, tibia and patella regions.
+
Pre-Segmented models for femur, patella and tibia are obtained for a patient (in .stl format).  
 
[[Image:All_Three.JPG|left|thumb| Pre-Segmented Femur/Patella/Tibia Model]]
 
[[Image:All_Three.JPG|left|thumb| Pre-Segmented Femur/Patella/Tibia Model]]
  
Line 33: Line 33:
 
We are now in the process of trying to register new patient image to the existing patient image. If we register the images, we can get the transform which can be used to register the existing atlas (label map) to the new patient.  
 
We are now in the process of trying to register new patient image to the existing patient image. If we register the images, we can get the transform which can be used to register the existing atlas (label map) to the new patient.  
  
 +
We think that Pipelined Bspline Registration may give promising results for our dataset. Below are some of the results. Here we consider 64_MRI as the fixed image and 58_MRI as the moving image and used '''Pipelined BSpline Image registration method''' for registration. Also we gave one point as landmark point.
 +
<gallery widths="400px" perrow="6">
 +
Image:58_MRI.jpg
 +
Image:64_MRI.jpg
 +
Image:64_Registered.jpg
 +
</gallery>
  
=Datasets=
+
We also tried '''affine registration''' for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and '''one landmark point'''. The zipped file which contains scene along with screenshots is
Below are the datasets that we used in our experiments. All the images are in standard dicom format.
+
[[Image:64 58 Affine Registration.zip |left|64_Affine_Registered_Scene]]
==Dataset for Patient 58==
+
<gallery widths="400px" perrow="6">
[[Image:58_IM-0009-0001.zip|left|Patient 58]]
+
Image:64 Affine Registration.JPG
==Dataset for Patient 57==
+
Image:64 Registerd SuperImposed On 64 Actual.JPG
[[Image:57_IM-0009-0001.zip|left|Patient 57]]
+
</gallery>
==Dataset for Patient 64==
+
 
[[Image:64_IM-0009-0001.zip|left|Patient 64]]
+
 
==Dataset for Patient 65==
+
We also tried '''BSpline registration''' for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and one landmark point. The zipped file which contains scene along with screenshots is
[[Image:65_IM-0009-0001.zip|left|Patient 65]]
+
[[Image:64 58 BSpline Registration.zip |left|64_BSpline_Registered_Scene]]. Here we used '''4 points''' as landmarks.
 +
<gallery widths="400px" perrow="6">
 +
Image:64 BSpline Registration.JPG
 +
Image:64 BSpline Registered SuperImposed On 64 Actual.JPG
 +
</gallery>
 +
 
 +
 
 +
We also tried '''Affine registration''' for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and four landmark point. The zipped file which contains scene along with screenshots is
 +
[[Image:64_58_Affine_Various_Iterations.zip |left|64_Affine_Registered_Various_Iterations_Scene]]. Here we used '''4 points''' as landmarks. We varied the number of iterations from 200 to 400.
 +
<gallery widths="400px" perrow="6">
 +
Image:64 58 Affine 200 Iterations.JPG
 +
Image:64 58 Affine 300 Iterations.JPG
 +
Image:64 58 Affine 400 Iterations.JPG
 +
</gallery>
 +
 
 +
 
 +
==='''Update May 13, 2009'''===
 +
We tried '''Affine registration''' for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and '''no''' landmark point. The zipped file which contains scene along with screenshots is
 +
[[Image:64_58_Affine_Various_Iterations.zip |left|64_Affine_Registered_Various_Iterations_Scene]]. We varied the number of iterations from 200 to 400.
 +
<gallery widths="400px" perrow="6">
 +
Image:64 58 Affine 200 Iterations.JPG
 +
Image:64 58 Affine 300 Iterations.JPG
 +
Image:64 58 Affine 400 Iterations.JPG
 +
</gallery>
 +
 
 +
==='''Update May 14, 2009'''===
 +
We tried '''Affine registration''' for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and '''10''' landmark point. The zipped file which contains scene along with screenshots is
 +
[[Image:Affine Registration 10 Landmark Points Varying Iterations.zip |left|64_Affine_Registered_10_Landmarks_Various_Iterations_Scene]]. We varied the number of iterations from 50 to 450.
 +
<gallery widths="200px" perrow="6">
 +
Image:64 58 Affine 50 Iterations 10 Landmark Points.jpg
 +
Image:64 58 Affine 100 Iterations 10 Landmark Points.jpg
 +
Image:64 58 Affine 150 Iterations 10 Landmark Points.jpg
 +
Image:64 58 Affine 250 Iterations 10 Landmark Points.jpg
 +
Image:64 58 Affine 350 Iterations 10 Landmark Points.jpg
 +
Image:64 58 Affine 450 Iterations 10 Landmark Points.jpg
 +
</gallery>
 +
 
 +
 
 +
==='''Update May 20, 2009'''===
 +
We tried '''BSpline registration''' for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and '''no''' landmark point. The zipped file which contains scene along with screenshots is
 +
[[Image:Affine Registration 10 Landmark Points Varying Iterations.zip |left|64_Affine_Registered_10_Landmarks_Various_Iterations_Scene]]. We varied the number of iterations from 50 to 450.
 +
<gallery widths="200px" perrow="6">
 +
Image:64 58 BSpline 10 Iterations.JPG
 +
Image:64 58 BSpline 110 Iterations.JPG
 +
Image:64 58 BSpline 160 Iterations.JPG
 +
Image:64 58 BSpline 210 Iterations.JPG
 +
Image:64 58 BSpline 260 Iterations.JPG
 +
Image:64 58 BSpline 360 Iterations.JPG
 +
</gallery>
 +
 
 +
 
 +
==='''Update May 21, 2009'''===
 +
We tried '''Pipelined Affine registration''' for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and '''no''' landmark point. The zipped file which contains scene along with screenshots is
 +
[[Image:BSpline_Registration_Varying_Iterations.zip‎ |left|BSpline_Registration_Varying_Iterations]]. We varied the number of iterations from 50 to 450.
 +
<gallery widths="200px" perrow="6">
 +
Image:64 58 PipeLinedAffine Registration 50 Iterations.JPG
 +
Image:64 58 PipeLinedAffine Registration 100 Iterations.JPG
 +
Image:64 58 PipeLinedAffine Registration 150 Iterations.JPG
 +
Image:64 58 PipeLinedAffine Registration 200 Iterations.JPG
 +
Image:64 58 PipeLinedAffine Registration 300 Iterations.JPG
 +
Image:64 58 PipeLinedAffine Registration 400 Iterations.JPG
 +
</gallery>
 +
 
 +
 
 +
==='''Update May 25, 2009'''===
 +
We tried '''Affine registration''' for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and '''no''' landmark point. The zipped file which contains scene along with screenshots is
 +
[[Image:BSpline_Registration_Varying_Iterations.zip‎ |left|BSpline_Registration_Varying_Iterations]]. We varied the number of iterations from 50 to 5000.
 +
<gallery widths="200px" perrow="6">
 +
Image:AffineRegistration InitialTransform 200Iterations.JPG
 +
Image:AffineRegistration InitialTransform 300Iterations.JPG
 +
Image:AffineRegistration InitialTransform 400Iterations.JPG
 +
</gallery>
 +
 
 +
 
 +
===Multi Image Registration===
 +
We have also tried the approach of Non-rigid Groupwise Registration using Bspline Deformation Model by Serdar K. Balci, Polina Golland and William M. Wells. In this approach, we try to give one slice each of two different patients we need to register as input. Here are some of the results of their approach.
 +
 
 +
<gallery widths="200px" perrow="2">
 +
Slice 1:
 +
Image:1_Slicez0.JPG‎
 +
Slice 2:
 +
Image:1_Slicez1.JPG
 +
Mean Slice of above two :
 +
Image:1_MeanSliceZ.JPG
 +
</gallery>
 +
 
 +
<gallery widths="200px" perrow="2">
 +
Slice 1:
 +
Image:2_Z0.JPG
 +
Slice 2:
 +
Image:2_Z1.JPG
 +
Mean Slice of above two :
 +
Image:2_MeanSliceZ.JPG
 +
</gallery>

Latest revision as of 02:48, 30 May 2009

Home < Stanford Simbios group


Aim

To develop a generic semi-automatic segmentation toolkit to convert images of musculoskeletal structures to 3D models.

Process Flowchart

Process Diagram.

Progress

Atlas Generation from Input MR Images

Model Generation from Input MR Images

Pre-Segmented models for femur, patella and tibia are obtained for a patient (in .stl format).

Pre-Segmented Femur/Patella/Tibia Model

Create a filled label map using PolyDataToFilledLabelMap module in slicer

The models generated in the above step are closed but hollow. But EM Segmentation requires the atlas given to be in closed filled format. Hence we converted the hollow closed models into filled label volumes using the module PolyDataToFilledLabelMap module in Slicer. The output label map of this module is of datatype unsigned char and is converted to short datatype.

EM Segmentation based on the atlas

The output label map in the above is given as input atlas in the EM Segmentation step. As an initial step we ran EM Segmentation on the same patient. The EM Segmented output is given in the below figure.

EM Segmented Output

Register Images

Register Images Module in Slicer

We are now in the process of trying to register new patient image to the existing patient image. If we register the images, we can get the transform which can be used to register the existing atlas (label map) to the new patient.

We think that Pipelined Bspline Registration may give promising results for our dataset. Below are some of the results. Here we consider 64_MRI as the fixed image and 58_MRI as the moving image and used Pipelined BSpline Image registration method for registration. Also we gave one point as landmark point.

We also tried affine registration for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and one landmark point. The zipped file which contains scene along with screenshots is File:64 58 Affine Registration.zip


We also tried BSpline registration for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and one landmark point. The zipped file which contains scene along with screenshots is File:64 58 BSpline Registration.zip. Here we used 4 points as landmarks.


We also tried Affine registration for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and four landmark point. The zipped file which contains scene along with screenshots is File:64 58 Affine Various Iterations.zip. Here we used 4 points as landmarks. We varied the number of iterations from 200 to 400.


Update May 13, 2009

We tried Affine registration for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and no landmark point. The zipped file which contains scene along with screenshots is File:64 58 Affine Various Iterations.zip. We varied the number of iterations from 200 to 400.

Update May 14, 2009

We tried Affine registration for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and 10 landmark point. The zipped file which contains scene along with screenshots is File:Affine Registration 10 Landmark Points Varying Iterations.zip. We varied the number of iterations from 50 to 450.


Update May 20, 2009

We tried BSpline registration for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and no landmark point. The zipped file which contains scene along with screenshots is File:Affine Registration 10 Landmark Points Varying Iterations.zip. We varied the number of iterations from 50 to 450.


Update May 21, 2009

We tried Pipelined Affine registration for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and no landmark point. The zipped file which contains scene along with screenshots is File:BSpline Registration Varying Iterations.zip. We varied the number of iterations from 50 to 450.


Update May 25, 2009

We tried Affine registration for the above mentioned patients with 64 as fixed MRI and 58 as moving MRI and no landmark point. The zipped file which contains scene along with screenshots is File:BSpline Registration Varying Iterations.zip. We varied the number of iterations from 50 to 5000.


Multi Image Registration

We have also tried the approach of Non-rigid Groupwise Registration using Bspline Deformation Model by Serdar K. Balci, Polina Golland and William M. Wells. In this approach, we try to give one slice each of two different patients we need to register as input. Here are some of the results of their approach.