Difference between revisions of "2016 Summer Project Week/Needle Segmentation from MRI"

From NAMIC Wiki
Jump to: navigation, search
 
(9 intermediate revisions by 2 users not shown)
Line 2: Line 2:
 
<gallery>
 
<gallery>
 
Image:PW-Summer2016.png|[[2016_Summer_Project_Week#Projects|Projects List]]
 
Image:PW-Summer2016.png|[[2016_Summer_Project_Week#Projects|Projects List]]
 +
Image:CNN_pixel_by_pixel_tip_classification.png|[[2016_Summer_Project_Week#Projects|CNN pixel by pixel tip classification]]
 
</gallery>
 
</gallery>
  
 
==Key Investigators==
 
==Key Investigators==
* Guillaume Pernelle, Imperial College
+
* Guillaume Pernelle, Imperial College London
 
* Tina Kapur, BWH/HMS
 
* Tina Kapur, BWH/HMS
*Andre Mastmeyer, Univeristy of Lubeck
+
* Paolo Zaffino, ImagEngLab
 
+
* Salvatore Scaramuzzino, ImagEngLab
 +
* Maria Francesca Spadea, ImagEngLab
  
 
==Project Description==
 
==Project Description==
  
NeedleFinder offers tools to segment needles from MRI/CT. It has been mostly tested on MRI from GYN brachytherapy cases. Currently the user must provide the needle for the segmentation to start. We aim to detect the tip automatically to make the needle segmentation fully automatic
+
NeedleFinder offers tools to segment needles from MRI/CT. It has mostly been tested on MRI from GYN brachytherapy cases. Currently the user must provide the needle tip for the segmentation to start. We aim to detect the tip automatically to make the needle segmentation fully automatic.
  
 
<div style="margin: 20px;">
 
<div style="margin: 20px;">
Line 18: Line 20:
  
 
<h3>Objective</h3>
 
<h3>Objective</h3>
* Tip detection
+
* Automatic detection of needle tips in MRI from GYN brachytherapy cases.
 
</div>
 
</div>
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<h3>Approach, Plan</h3>
 
<h3>Approach, Plan</h3>
* Develop a detection method based on Gaussian Mixture Models for different spaces: inputs: intensity, Frangi's filter, needle-tip cross-correlation, Hough transform
+
* First possible strategy: to develop a detection method based on Gaussian Mixture Models (GMM) supplied with different inputs (intensity, Frangi's filter, needle-tip cross-correlation and Hough transform).
 +
* Second possible strategy: Convolutional Neural Network (CNN) over MRI patches. Two implementation can be investigated (pixel by pixel classification or entire patch classification).
 
* Integrate algorithm to Slicer.
 
* Integrate algorithm to Slicer.
 
</div>
 
</div>
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<h3>Progress</h3>
 
<h3>Progress</h3>
*  
+
* GMM strategy failed.
 +
* We designed a pipeline to prepare the data for supervised learning.
 +
* We explored two strategies implementing Convolutional Neural Network.
 +
* CNN strategies have some accuracy problem but look promising. In order to increase the accuracy some aspects can be investigated such as patch size, dataset size, network architecture, data augmentation, MR data synthesising from CT. 
 
</div>
 
</div>
 
</div>
 
</div>

Latest revision as of 09:08, 25 June 2016

Home < 2016 Summer Project Week < Needle Segmentation from MRI

Key Investigators

  • Guillaume Pernelle, Imperial College London
  • Tina Kapur, BWH/HMS
  • Paolo Zaffino, ImagEngLab
  • Salvatore Scaramuzzino, ImagEngLab
  • Maria Francesca Spadea, ImagEngLab

Project Description

NeedleFinder offers tools to segment needles from MRI/CT. It has mostly been tested on MRI from GYN brachytherapy cases. Currently the user must provide the needle tip for the segmentation to start. We aim to detect the tip automatically to make the needle segmentation fully automatic.

Objective

  • Automatic detection of needle tips in MRI from GYN brachytherapy cases.

Approach, Plan

  • First possible strategy: to develop a detection method based on Gaussian Mixture Models (GMM) supplied with different inputs (intensity, Frangi's filter, needle-tip cross-correlation and Hough transform).
  • Second possible strategy: Convolutional Neural Network (CNN) over MRI patches. Two implementation can be investigated (pixel by pixel classification or entire patch classification).
  • Integrate algorithm to Slicer.

Progress

  • GMM strategy failed.
  • We designed a pipeline to prepare the data for supervised learning.
  • We explored two strategies implementing Convolutional Neural Network.
  • CNN strategies have some accuracy problem but look promising. In order to increase the accuracy some aspects can be investigated such as patch size, dataset size, network architecture, data augmentation, MR data synthesising from CT.