Difference between revisions of "Project Week 25/CNN for multi-plane prostate segmentation"

From NAMIC Wiki
Jump to: navigation, search
(Created page with "__NOTOC__ Back to Projects List ==Key Investigators== *[http://isgwww.cs.uni-magdeburg.de/isg/meyer.html Anneke Meyer] (University of Magdeburg,...")
 
 
(4 intermediate revisions by 2 users not shown)
Line 8: Line 8:
 
*[http://isgwww.cs.uni-magdeburg.de/cas/ Christian Hansen] (University of Magdeburg, Germany)
 
*[http://isgwww.cs.uni-magdeburg.de/cas/ Christian Hansen] (University of Magdeburg, Germany)
 
*[http://www.spl.harvard.edu/pages/People/fedorov Andrey Fedorov] (Brigham and Women's Hospital, Harvard Medical School, USA)
 
*[http://www.spl.harvard.edu/pages/People/fedorov Andrey Fedorov] (Brigham and Women's Hospital, Harvard Medical School, USA)
 +
*[http://www.mic.uni-bremen.de/jennifer-nitsch/ Jennifer Nitsch] (University of Bremen, Germany)
  
 
==Project Description==
 
==Project Description==
Line 17: Line 18:
 
|
 
|
 
<!-- Objective bullet points -->
 
<!-- Objective bullet points -->
* Fusion of multi-plane segmentations of the prostate in order to obtain better accuracy, especially in the apex and base regions.
+
For prostate lesion assessment, MRI volumes in sagittal, coronal and axial orientation are acquired. The goal is to segment the prostate in these volumes and fuse the segmentations in order to obtain better accuracy, especially in the apex and base regions (compared to segmentations obtained only on axial volumes).
* Investigate multiple ways of fusing the segmentation of three network outputs.
 
 
|
 
|
 
<!-- Approach and Plan bullet points -->
 
<!-- Approach and Plan bullet points -->
Line 30: Line 30:
 
|
 
|
 
<!-- Progress and Next steps (fill out at the end of project week) -->
 
<!-- Progress and Next steps (fill out at the end of project week) -->
 +
* built framework for predicting and fusing the segmentations
 +
* tested simple majority voting in isotropic voxel volumes
 +
* Future Work:
 +
** weighted voting depending on location and plane
 +
** Surface extraction from point clouds
 +
 +
 
|}
 
|}
  
 
==Illustrations==
 
==Illustrations==
 +
{|
 +
|[[File:MRIImage.png|thumb|500px|MRIs of the prostate (axial, sagittal and coronal volume)]]
 +
|-
 +
|[[File:Segmentation2.png|thumb|500px|Example segmentation (apex, mid-gland and base slices).]]
 +
|}
 
==Background and References==
 
==Background and References==
 
<!-- Use this space for information that may help people better understand your project, like links to papers, source code, or data -->
 
<!-- Use this space for information that may help people better understand your project, like links to papers, source code, or data -->

Latest revision as of 11:42, 30 June 2017

Home < Project Week 25 < CNN for multi-plane prostate segmentation


Back to Projects List

Key Investigators

Project Description

Objective Approach and Plan Progress and Next Steps

For prostate lesion assessment, MRI volumes in sagittal, coronal and axial orientation are acquired. The goal is to segment the prostate in these volumes and fuse the segmentations in order to obtain better accuracy, especially in the apex and base regions (compared to segmentations obtained only on axial volumes).

  • Work done:
    • created training data for different orientations
    • Automatic segmentation of each plane with Encoder-Decoder Network
  • Work ahead:
    • Explore, discuss and investigate different approaches for fusion of the segmentations, e.g. simple majority voting, suface reconstruction from point cloud, ...


  • built framework for predicting and fusing the segmentations
  • tested simple majority voting in isotropic voxel volumes
  • Future Work:
    • weighted voting depending on location and plane
    • Surface extraction from point clouds


Illustrations

MRIs of the prostate (axial, sagittal and coronal volume)
Example segmentation (apex, mid-gland and base slices).

Background and References