Project Week 25/NeedleSegmentation - Revision history

P.zaffino: /* Project Description */

2017-06-30T09:08:25Z

Project Description

2017-06-30T08:56:56Z

Illustrations

2017-06-30T08:48:36Z

Project Description

2017-06-25T20:20:54Z

Project Description

2017-06-22T15:09:30Z

Project Description

2017-06-22T15:08:25Z

Project Description

2017-06-22T07:12:11Z

Project Description

2017-06-22T07:09:16Z

Project Description

2017-06-22T07:07:25Z

Project Description

2017-06-22T07:05:01Z

Project Description

@@ Line 30: / Line 30: @@
+|
 <!-- 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.
 |}

@@ Line 36: / Line 36: @@
 ==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>

@@ Line 30: / Line 30: @@
+|
 <!-- Progress and Next steps (fill out at the end of project week) -->
-TBD
+* 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.
 |}

@@ Line 13: / Line 13: @@
 ==Project Description==
-NeedleFinder offers tools to segment needles from MRI/CT. It has mostly been tested on MRI from GYN brachytherapy cases. Anyway, this tool requires manual interaction.
+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.
 {| class="wikitable"
@@ Line 32: / Line 30: @@
+|
 <!-- Progress and Next steps (fill out at the end of project week) -->
-TDB
+TBD
 |}

@@ Line 25: / Line 25: @@
 <!-- Objective bullet points -->
 * Refine/clear the segmentations coming from the CNN algorithm.
-* Figure out how to transfer MRIs to a server hosting the CNN code and how to get back the results.
+* Figure out how to transfer MRIs to a server hosting the CNN code and get back the results.
+|
 <!-- Approach and Plan bullet points -->
-* Clustering and morphological filter for data cleaning.
+* Clustering and morphological filters for data cleaning.
-* Talk with someone of core team to figure out how to remotely process the data.
+* Talk with someone from the core team to figure out how to remotely process the data.
+|
 <!-- Progress and Next steps (fill out at the end of project week) -->

@@ Line 15: / Line 15: @@
 NeedleFinder offers tools to segment needles from MRI/CT. It has mostly been tested on MRI from GYN brachytherapy cases. Anyway, this tool requires manual interaction.
 Now we want to develop a completely automatic strategy to segment the needles.
-For this purpose, we 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 segmentation.
+For this purpose, we 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.
 {| class="wikitable"
@@ Line 24: / Line 24: @@
+|
 <!-- Objective bullet points -->
-Please start each sentence in a new line.
+* Refine/clear the segmentations coming from the CNN algorithm
+|
 <!-- Approach and Plan bullet points -->