NeedleFinder - Revision history

Guillaume: /* Project Results */

2015-01-09T05:57:23Z

Project Results

Guillaume: /* Project Results */

2015-01-09T05:46:44Z

Project Results

Amas: /* Project Results */

2015-01-09T05:29:48Z

Project Results

Amas: /* Project Description */

2015-01-09T05:23:15Z

Project Description

Amas: /* Project Description */

2015-01-09T05:21:05Z

Project Description

Amas: /* Project Results */

2015-01-09T05:19:27Z

Project Results

Amas: /* Project Results */

2015-01-09T05:16:27Z

Project Results

Guillaume: /* Project Results */

2015-01-09T04:24:25Z

Project Results

Amas: /* Project Results */

2015-01-09T03:47:02Z

Project Results

Amas: /* Project Results */

2015-01-09T03:35:00Z

Project Results

@@ Line 53: / Line 53: @@
 - Tip detection : We wrote a script using SimpleITK to extract and re-sample all the tip regions from images using needles from manual segmentation. These 115 cubical regions can now be used for data analysis (machine learning). As a first step, we built an average model (template) of the needle tips to be matched to new data sets, e.g. using convolution/correlation filters:
-[[File:BloomingArtifacts.png|200px|thumb|left|Needle Artifacts]]
+[[File:BloomingArtifacts.png|400px|thumb|none|Example of artifacts from needle tips in MRI]]
-[[File:avgImage.png|200px|thumb|left|avg Image from needle tips]]
+[[File:avgImage.png|400px|thumb|none|Average intensity model from 115 needle tips]]
 Our hypothesis that the needle tip artifact show out in the average needle tip model could not be confirmed at this time: We need to use more cases with needle tip artifacts (instead of mixing with other cases from other MR sequences). Secondly, we should sort out the needle tips from the obturator needles. Third, the little cubic image around the needle tip could be registered to each other before averaging to fit more accurately. For now, the origin is registered, but the orientation could be improved. After convolution (SimpleITK) the average needle tip model with a patient MR image, this approach suffers from over-segmentation.
 - NeedleFinder parameter optimization : We use the workshop as a kickoff on this topic and want to compare the performance of a brute force/randomized parameter search approach with a genetic algorithm after the workshop. Therefore the implementation of a genetic algorithm has been completed (to be able to find a global optimum faster). A cost/fitness function was designed for our problem. Because the parameter optimization is still computationally expensive (several needle detections carried out in every iteration), only exemplary results for individual patients, but not a patient collective could be obtained here.

@@ Line 53: / Line 53: @@
 - Tip detection : We wrote a script using SimpleITK to extract and re-sample all the tip regions from images using needles from manual segmentation. These 115 cubical regions can now be used for data analysis (machine learning). As a first step, we built an average model (template) of the needle tips to be matched to new data sets, e.g. using convolution/correlation filters:
-<pictures of 3 needle tips with artifacts>
+[[File:BloomingArtifacts.png|200px|thumb|left|Needle Artifacts]]
-<picture of the average tip model>
+[[File:avgImage.png|200px|thumb|left|avg Image from needle tips]]
 Our hypothesis that the needle tip artifact show out in the average needle tip model could not be confirmed at this time: We need to use more cases with needle tip artifacts (instead of mixing with other cases from other MR sequences). Secondly, we should sort out the needle tips from the obturator needles. Third, the little cubic image around the needle tip could be registered to each other before averaging to fit more accurately. For now, the origin is registered, but the orientation could be improved. After convolution (SimpleITK) the average needle tip model with a patient MR image, this approach suffers from over-segmentation.

@@ Line 48: / Line 48: @@
 - GUI and workflow : We improved the workflow and the GUI of the slicer module NeedleFinder: the needle grouping feature has been removed, we introduced a new temporary fiducial marker for easier manual needle tracking using the sagittal and axial views. We standardized the workflow by guiding the user though the steps (e.g. providing the axial limit slice is now mandatory as a first step). We introduced new keyboard shortcuts, thus the user can stay focused on the segments, not changing his mouse position to click buttons in the left panel. The last inserted needle can be deleted (with CTRL+Z or button) and the module can be easily reset. The layout of the module UI has been cleaned up.
-- Code profiling : We went through the code to clarify many open questions, removed unused functions. We built a table summarizing the global purpose of each functions (function tagging). We developed a profiling method using print commands and message boxes (using the inspect library).
+- Code profiling : We went through the code to clarify many open questions, removed unused functions. We built a table summarizing the global purpose of each function (function tagging). We developed a profiling method using print commands and message boxes (using the inspect library).
 - Bounding box approach : We discussed this proposal, and found, after slicing to the obturator base, just zooming into the image in the axial view is much easier for the user than defining a complete bounding box. Needle tip clicks are given in this axial view after tracking the needle canals upwards in the sagittal view. So, the idea is not furtherly addressed here.

@@ Line 38: / Line 38: @@
 ** Tuesday started - Wednesday finished
 ** Tuesday started - Wednesday finished
-*** Tuesday started / Wednesday - to discuss later
+*** Tuesday started / Wednesday - idea abandoned
 ** Wednesday started - Thursday finished
 ** Thursday started - Friday morning finished

@@ Line 35: / Line 35: @@
 <div style="width: 27%; float: left; padding-right: 3%;">
 <h3>Progress</h3>
-* Overall: 4/5
+* Overall: 5/5
 ** Tuesday started - Wednesday finished
 ** Tuesday started - Wednesday finished
 *** Tuesday started / Wednesday - to discuss later
 ** Wednesday started - Thursday finished
-** Thursday started
+** Thursday started - Friday morning finished
 </div>
 </div>

@@ Line 46: / Line 46: @@
 ==Project Results==
-- GUI and workflow : We improved the workflow and the GUI of the slicer module NeedleFinder: the needle grouping feature has been removed, we introduced a temporary fiducial marker for easier manual needle tracking. We standardized the workflow by guiding the user though the steps (eg. providing the axial limit slice is now mandatory). We introduced new keyboard shortcuts, thus the user can stay focused on the segments, not changing his mouse position to click buttons. The last inserted needle can be deleted (with CTRL+Z or button) and the scene can be easily reset. Layout of the module UI has been cleaned up.
+- GUI and workflow : We improved the workflow and the GUI of the slicer module NeedleFinder: the needle grouping feature has been removed, we introduced a new temporary fiducial marker for easier manual needle tracking. We standardized the workflow by guiding the user though the steps (e.g. providing the axial limit slice is now mandatory as a first step). We introduced new keyboard shortcuts, thus the user can stay focused on the segments, not changing his mouse position to click buttons in the left panel. The last inserted needle can be deleted (with CTRL+Z or button) and the module can be easily reset. The layout of the module UI has been cleaned up.
-- Code profiling : We went through the code to clarify opened questions, removed unused functions. We built a table summarizing the global purpose of each functions (function tagging). We developed a profiling method using message boxes (using the inspect library).
+- Code profiling : We went through the code to clarify many open questions, removed unused functions. We built a table summarizing the global purpose of each functions (function tagging). We developed a profiling method using print commands and message boxes (using the inspect library).
-- Bounding box approach: we discussed this proposal, and found, after slicing to the obturator base, just zooming into the image in the axial view is much easier for the user than defining a complete bounding box.
+- Bounding box approach : We discussed this proposal, and found, after slicing to the obturator base, just zooming into the image in the axial view is much easier for the user than defining a complete bounding box.
-- Tip detection : We wrote a script to extract, transform and re-sample all the tips from images with needles from manual segmentation. These 115 cubical regions can now be used for data analysis, machine learning. We built an average model of the needle tips to be matched to new data sets, e.g. using convolution filters:
+- Tip detection : We wrote a script using SimpleITK to extract and re-sample all the tip regions from images using needles from manual segmentation. These 115 cubical regions can now be used for data analysis (machine learning). As a first step, we built an average model (template) of the needle tips to be matched to new data sets, e.g. using convolution/correlation filters:
 <pictures of 3 needle tips with artifacts>
-<picture of the model>
+<picture of the average tip model>
-<picture of the results of the convolution filter>
+Our hypothesis that the needle tip artifact show out in the average needle tip model could not be confirmed at this time: We need to use more cases with needle tip artifacts (instead of mixing with other cases from other MR sequences). Secondly, we should sort out the needle tips from the obturator needles. Third, the little cubic image around the needle tip could be registered to each other before averaging to fit more accurately. For now, the origin is registered, but the orientation could be improved. After convolution (SimpleITK) the average needle tip model with a patient MR image, our approach suffers from oversegmentation.
-- NeedleFinder parameter optimization : we want to use the workshop as a kickoff on this topic and want to compare the performance of a brute force/randomized parameter search approach with a genetic algorithm after the workshop. Therefore the implementation of a genetic algorithm was carried out (to find an optimum faster). A cost function was designed for our problem. Because the parameter optimization is still computationally expensive, only exemplary results for individual patients, but not a patient collective could be obtained here.
+- NeedleFinder parameter optimization : We use the workshop as a kickoff on this topic and want to compare the performance of a brute force/randomized parameter search approach with a genetic algorithm after the workshop. Therefore the implementation of a genetic algorithm has been completed (to be able to find a global optimum faster). A cost/fitness function was designed for our problem. Because the parameter optimization is still computationally expensive (several needle detections carried out in every iteration), only exemplary results for individual patients, but not a patient collective could be obtained here.
 ==References==

← Older revision		Revision as of 04:24, 9 January 2015
Line 47:		Line 47:

	- GUI and workflow : We improved the workflow and the GUI of the slicer module NeedleFinder: the needle grouping feature has been removed, we introduced a temporary fiducial marker for easier manual needle tracking. We standardized the workflow by guiding the user though the steps (eg. providing the axial limit slice is now mandatory). We introduced new keyboard shortcuts, thus the user can stay focused on the segments, not changing his mouse position to click buttons. The last inserted needle can be deleted (with CTRL+Z or button) and the scene can be easily reset. Layout of the module UI has been cleaned up.		- GUI and workflow : We improved the workflow and the GUI of the slicer module NeedleFinder: the needle grouping feature has been removed, we introduced a temporary fiducial marker for easier manual needle tracking. We standardized the workflow by guiding the user though the steps (eg. providing the axial limit slice is now mandatory). We introduced new keyboard shortcuts, thus the user can stay focused on the segments, not changing his mouse position to click buttons. The last inserted needle can be deleted (with CTRL+Z or button) and the scene can be easily reset. Layout of the module UI has been cleaned up.
−	~~The results can be viewed in the NeedleFinder tutorial project: [http://www.na-mic.org/Wiki/index.php/Needle_Finder_Tutorial].~~

	- Code profiling : We went through the code to clarify opened questions, removed unused functions. We built a table summarizing the global purpose of each functions (function tagging). We developed a profiling method using message boxes (using the inspect library).		- Code profiling : We went through the code to clarify opened questions, removed unused functions. We built a table summarizing the global purpose of each functions (function tagging). We developed a profiling method using message boxes (using the inspect library).

@@ Line 49: / Line 49: @@
 The results can be viewed in the NeedleFinder tutorial project: [http://www.na-mic.org/Wiki/index.php/Needle_Finder_Tutorial].
-- Code profiling : We went through the code to clarify opened questions, removed unused functions. We built a table summarising the global purpose of each functions (function taging). We developed a profiling method using message boxes (using the inspect library).
+- Code profiling : We went through the code to clarify opened questions, removed unused functions. We built a table summarizing the global purpose of each functions (function tagging). We developed a profiling method using message boxes (using the inspect library).
-- Bounding box approach: we discussed this proposal, and found after slicing to the obturator base, just zooming into the image in the axial view is much easier for the user.
+- Bounding box approach: we discussed this proposal, and found, after slicing to the obturator base, just zooming into the image in the axial view is much easier for the user than defining a complete bounding box.
-- Tip detection : We wrote a script to extract, transform and resample all the tips from images with needles from manual segmentation. These 115 cubical regions can now be used for data analysis, machine learning. We built an average model of the needle tips to be matched to new datasets eg. using convolution filters:
+- Tip detection : We wrote a script to extract, transform and re-sample all the tips from images with needles from manual segmentation. These 115 cubical regions can now be used for data analysis, machine learning. We built an average model of the needle tips to be matched to new data sets, e.g. using convolution filters:
-<pcitures of 3 needle tips with artifacts>
+<pictures of 3 needle tips with artifacts>
 <picture of the model>
 <picture of the results of the convolution filter>
-Our hypothesis that the needle tip artifact show out in the average needle tip model could not be confirmed at this time: We need to use more cases with needle tip artifacts (instead of mixing with other cases from other MR sequences). Secondly, we should sort out the needle tips from the obturator needles. Third, the little cubic image around the needle tip could be registered to each other before averaging to fit more accurate. For now, the origin is registered, but the orientation could be improved. After convoluting the average needle tip model with a patient MR image, our simple approach suffers from oversegmentation.
+Our hypothesis that the needle tip artifact show out in the average needle tip model could not be confirmed at this time: We need to use more cases with needle tip artifacts (instead of mixing with other cases from other MR sequences). Secondly, we should sort out the needle tips from the obturator needles. Third, the little cubic image around the needle tip could be registered to each other before averaging to fit more accurate. For now, the origin is registered, but the orientation could be improved. After convolution the average needle tip model with a patient MR image, our approach suffers from oversegmentation.
-- Parameter optimization: we want to compare the performance of a brute force/randomized parameter search approach with a genetic algorithm after the workshop. Therefore this implementation of a genetic algorithm was carried out (to find an optimum faster). A cost function was designed for our problem. Because the parameter optimization is still computationally expensive only exemplary results for individual patients, but not a patient collective could be obtained.
+- NeedleFinder parameter optimization : we want to use the workshop as a kickoff on this topic and want to compare the performance of a brute force/randomized parameter search approach with a genetic algorithm after the workshop. Therefore the implementation of a genetic algorithm was carried out (to find an optimum faster). A cost function was designed for our problem. Because the parameter optimization is still computationally expensive, only exemplary results for individual patients, but not a patient collective could be obtained here.
 ==References==