2016 Summer Project Week/Needle Segmentation from MRI - Revision history

Guillaume at 09:08, 25 June 2016

2016-06-25T09:08:44Z

2016-06-25T07:48:49Z

2016-06-25T07:47:19Z

Key Investigators

2016-06-25T07:41:54Z

Project Description

2016-06-25T07:40:21Z

Project Description

2016-06-20T09:12:29Z

Project Description

2016-06-20T09:09:30Z

Project Description

2016-06-20T09:06:56Z

Project Description

2016-06-20T09:02:50Z

Key Investigators

2016-06-20T09:01:14Z

Project Description

@@ Line 31: / Line 31: @@
 <h3>Progress</h3>
 * GMM strategy failed.
-* CNN strategies has some accuracy problem but this can be the right way to get needles tips. In order to increase the accuracy some aspects can be investigated (patch size, dataset size, network architecture, data augmentation)
+* We designed a pipeline to prepare the data for supervised learning.
 </div>
 </div>

@@ Line 2: / Line 2: @@
 <gallery>
 Image:PW-Summer2016.png|[[2016_Summer_Project_Week#Projects|Projects List]]
 </gallery>

@@ Line 5: / Line 5: @@
 ==Key Investigators==
-* Guillaume Pernelle, Imperial College
+* Guillaume Pernelle, Imperial College London
 * Tina Kapur, BWH/HMS
 * Paolo Zaffino, ImagEngLab

@@ Line 24: / Line 24: @@
 <h3>Approach, Plan</h3>
 * 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 (pizel by pizel classification or entire patch classification).
+* 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.
 </div>
@@ Line 30: / Line 30: @@
 <h3>Progress</h3>
 * GMM strategy failed.
-* CNN strategies has some accuracy problem but it can be the right way to get needles tips. In order to increase the accuracy some aspects can be investigated (patch size, dataset size, network architecture, data augmentation)
+* CNN strategies has some accuracy problem but this can be the right way to get needles tips. In order to increase the accuracy some aspects can be investigated (patch size, dataset size, network architecture, data augmentation)
 </div>
 </div>

@@ Line 23: / Line 23: @@
 <div style="width: 27%; float: left; padding-right: 3%;">
 <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).
 * Integrate algorithm to Slicer.
 </div>
 <div style="width: 27%; float: left; padding-right: 3%;">
 <h3>Progress</h3>
+* GMM strategy failed.
 </div>
 </div>

@@ Line 13: / Line 13: @@
 ==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 tip 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;">

@@ Line 19: / Line 19: @@
 <h3>Objective</h3>
-* Tip detection
+* Automatic detection of needle tips in MRI from GYN brachytherapy cases.
 </div>
 <div style="width: 27%; float: left; padding-right: 3%;">