Difference between revisions of "2017 Winter Project Week/Web-based system to federate biological, clinical and morphological data"

From NAMIC Wiki
Jump to: navigation, search
 
Line 30: Line 30:
 
<!-- Progress and Next steps bullet points (fill out at the end of project week) -->
 
<!-- Progress and Next steps bullet points (fill out at the end of project week) -->
 
* Talks about existing other web projects. We gave demos and had feedbacks.
 
* Talks about existing other web projects. We gave demos and had feedbacks.
* We added few scripts on a remote server to be run directly from Slicer. We were able to train a network giving a dataset in Slicer, then enter an input shape and have a classification result.
+
* We added few scripts on a remote server to be run directly from Slicer.  
 +
* We were able to train a neural network giving a dataset in Slicer, then enter an input shape and have a classification result.
 
|}
 
|}
  

Latest revision as of 15:11, 13 January 2017

Home < 2017 Winter Project Week < Web-based system to federate biological, clinical and morphological data

Key Investigators

  • Juan Carlos Prieto (University of North Carolina)
  • Clément Mirabel (University of Michigan)

Project Description

Objective Approach and Plan Progress and Next Steps
  • Allow users to store online the data they use for their studies, with the possibility to share their data with other projects to have bigger datasets.
  • Develop a Slicer module to ease the upload of morphological (imaging) data.
  • Federate different statistics tools and facilitate their use for project managers.
  • Help project managers to know the progression of their project and collection of their data with visual graphs.
  • Have user feedback about the Slicer module.
  • Integrate R functions in the server to do statistical analysis with imaging data and biological data.
  • Add functionalities to facilitate the use of the website to clinicians.
  • Talks about existing other web projects. We gave demos and had feedbacks.
  • We added few scripts on a remote server to be run directly from Slicer.
  • We were able to train a neural network giving a dataset in Slicer, then enter an input shape and have a classification result.

Background and References

Website URL
Website source code
Slicer module source code