Difference between revisions of "Project Week 25/NeedleSegmentation"

From NAMIC Wiki
Jump to: navigation, search
 
(One intermediate revision by the same user not shown)
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) -->
* A bridge between data coming by the unet and the already existing NeedleFinder module was implemented. Now we are able to use the segmentations generated by the unet to initialize the NeedleFinder algorithm. The process is completely automatic.
+
* A bridge between data coming by the unet and the already existing NeedleFinder module was implemented. Now we are able to use the segmentations generated by the unet to initialize the NeedleFinder algorithm. The process is completely automatic. [https://github.com/needlefinder/NunetFinder/blob/master/NunetFinder.py The code is here]
 
* We had an interesting discussion with Steve about DeepInfer.
 
* We had an interesting discussion with Steve about DeepInfer.
 
|}
 
|}
Line 36: Line 36:
 
==Illustrations==
 
==Illustrations==
  
http://needlefinder.org/assets/images/home_cropped.jpg
+
[[File:NunetFinder.png|900px|thumb|left|Red volume: ground truth, yellow circles: needle coming from NeedleFinder, labels: segmentation coming from unet]]
  
 
<embedvideo service="youtube">https://youtu.be/5G9t6DZ8KrM</embedvideo>
 
<embedvideo service="youtube">https://youtu.be/5G9t6DZ8KrM</embedvideo>

Latest revision as of 09:08, 30 June 2017

Home < Project Week 25 < NeedleSegmentation


Back to Projects List

Key Investigators

Project Description

NeedleFinder is a tool for segmentation of needles from MR scans which requires manual initialization of the tip of the needle. It has been tested extensively on MR-guided gynecologic brachytherapy data, and preliminarily on MR-guided prostate biopsy data. In this project, we aim to eliminate this reliance on manual interaction and develop a completely automatic strategy to segment the needles. We have tested a CNN approach that provides good results, even if a post processing step must be implemented in order to remove some noise and to refine the obtained segmentations.

Objective Approach and Plan Progress and Next Steps
  • Refine/clear the segmentations coming from the CNN algorithm.
  • Figure out how to transfer MRIs to a server hosting the CNN code and get back the results.
  • Clustering and morphological filters for data cleaning.
  • Talk with someone from the core team to figure out how to remotely process the data.
  • A bridge between data coming by the unet and the already existing NeedleFinder module was implemented. Now we are able to use the segmentations generated by the unet to initialize the NeedleFinder algorithm. The process is completely automatic. The code is here
  • We had an interesting discussion with Steve about DeepInfer.

Illustrations

Red volume: ground truth, yellow circles: needle coming from NeedleFinder, labels: segmentation coming from unet

Background and References

  1. NeedleFinder website
  2. Model-based Catheter Segmentation in MRI-images