2017 Winter Project Week/DeepInfer - Revision history

Mehrtash at 14:56, 13 January 2017

2017-01-13T14:56:17Z

2017-01-13T14:55:52Z

2017-01-13T14:39:45Z

Project Description

2017-01-13T14:32:30Z

2017-01-13T14:32:09Z

2017-01-13T14:29:14Z

2017-01-09T18:26:48Z

2017-01-09T18:26:32Z

2017-01-09T18:15:47Z

Background and References

2017-01-05T00:55:49Z

@@ Line 55: / Line 55: @@
    * Implement instantiation of  CLI UI from the XML description in Python.
    * Test the slicer/docker communication on our prostate-segmenter model.
 |}

@@ Line 40: / Line 40: @@
+|
 <!-- Progress and Next steps bullet points (fill out at the end of project week) -->
+* Helpful discussions about the design of Slicer part.
 |}

@@ Line 31: / Line 31: @@
 <!-- Objective bullet points -->
 * Redesign the architecture of the toolkit considering Docker as the deep learning model deployment engine.
-* Discuss about the implemntation details of Slicer side.
+* Discuss about the implementation details of Slicer side.
 * Planning the structure of the cloud model repository.
+|
 <!-- Approach and Plan bullet points -->
+* Study and evaluate different approaches for passing input images and prediction results between Slicer and Docker including CLI.
+|
 <!-- Progress and Next steps bullet points (fill out at the end of project week) -->
+*
 |}

@@ Line 3: / Line 3: @@
 Image:PW-Winter2017.png|link=2017_Winter_Project_Week#Projects|[[2017_Winter_Project_Week#Projects|Projects List]]
 <!-- Use the "Upload file" link on the left and then add a line to this list like "File:MyAlgorithmScreenshot.png" -->
-File:Deepinfer arch.png|The initial prototype of the DeepInfer with OpenIGTLink!
+File:Deepinfer arch.png|The initial prototype of the DeepInfer with OpenIGTLink.
 </gallery>

← Older revision		Revision as of 14:32, 13 January 2017
Line 1:		Line 1:
	__NOTOC__		__NOTOC__
−		+	<gallery>
		+	Image:PW-Winter2017.png\|link=2017_Winter_Project_Week#Projects\|[[2017_Winter_Project_Week#Projects\|Projects List]]
		+	<!-- Use the "Upload file" link on the left and then add a line to this list like "File:MyAlgorithmScreenshot.png" -->
		+	File:Deepinfer arch.png\|The initial prototype of the DeepInfer with OpenIGTLink!
		+	</gallery>

← Older revision		Revision as of 18:26, 9 January 2017
Line 1:		Line 1:
	__NOTOC__		__NOTOC__

−	~~Image:PW-Winter2017.png\|link=2017_Winter_Project_Week#Projects\|[[2017_Winter_Project_Week#Projects\|Projects List]]~~
−	~~<!-- Use the "Upload file" link on the left and then add a line to this list like "File:MyAlgorithmScreenshot.png" -->~~
−	~~File:Deepinfer_arch.png\|DeepInfer Architecture~~
−	~~</gallery>~~

@@ Line 1: / Line 1: @@
 __NOTOC__
-<gallery>
 Image:PW-Winter2017.png|link=2017_Winter_Project_Week#Projects|[[2017_Winter_Project_Week#Projects|Projects List]]
 <!-- Use the "Upload file" link on the left and then add a line to this list like "File:MyAlgorithmScreenshot.png" -->
 </gallery>
 ==Key Investigators==

@@ Line 16: / Line 16: @@
 ==Background and References==
-Deep  learning  models  have  outperformed  some  of  the  previous  state-of-the-art  approaches  in  medical  image analysis.  However, utilizing deep models during image-guided  therapy  procedures  requires  integration  of  several  software  components  which  is  often  a  tedious  taskfor  clinical  researchers.   Hence,  there  is  a  gap  between  the  state-of-the-art  machine  learning  research  and  itsapplication in clinical setup. DeepInfer  enables  3D  Slicer  to  connect  to  a  powerful processing back-end either on the local machine or a remote processing server. Utilizing a repository of pre-trained, task-specific models, DeepInfer allows clinical researchers and biomedical engineers to choose and deploy a model on new data without the need for software development or configuration.
+Deep  learning  models  have  outperformed  some  of  the  previous  state-of-the-art  approaches  in  medical  image analysis.  However, utilizing deep models during image-guided  therapy  procedures  requires  integration  of  several  software  components  which  is  often  a  tedious  taskfor  clinical  researchers.   Hence,  there  is  a  gap  between  the  state-of-the-art  machine  learning  research  and  itsapplication in clinical setup.
 ==Project Description==

@@ Line 9: / Line 9: @@
 * Alireza Mehrtash (BWH, UBC)
 * Mehran Pesteie (UBC)
-* Silvia (Tianjin University)
+* Yang (Silvia) Yixin (Tianjin University)
 * Tina Kapur (BWH)
 * Sandy Wells (BWH)
 * Purang Abolmaesumi (UBC)
 * Andriy Fedorov (BWH)
 ==Background and References==
 Deep  learning  models  have  outperformed  some  of  the  previous  state-of-the-art  approaches  in  medical  image analysis.  However, utilizing deep models during image-guided  therapy  procedures  requires  integration  of  several  software  components  which  is  often  a  tedious  taskfor  clinical  researchers.   Hence,  there  is  a  gap  between  the  state-of-the-art  machine  learning  research  and  itsapplication in clinical setup. DeepInfer  enables  3D  Slicer  to  connect  to  a  powerful processing back-end either on the local machine or a remote processing server. Utilizing a repository of pre-trained, task-specific models, DeepInfer allows clinical researchers and biomedical engineers to choose and deploy a model on new data without the need for software development or configuration.