Difference between revisions of "2017 Winter Project Week/Evaluate Deep Learning for binary cancer legion classification"

From NAMIC Wiki
Jump to: navigation, search
Line 23: Line 23:
 
* Start with a dataset, prepared at the Frederick National Lab for Cancer Research, to use to train a classifier.  
 
* Start with a dataset, prepared at the Frederick National Lab for Cancer Research, to use to train a classifier.  
 
* The dataset consists of a series of 50x50 Region Of Interest images containing cancer lesions and two image series which do not contain lesions.  
 
* The dataset consists of a series of 50x50 Region Of Interest images containing cancer lesions and two image series which do not contain lesions.  
* We plan to collect advice from others at the Project Week to select a deep learning framework and attempt to build a classifer using this training data.
+
* We plan to collect advice from others at the Project Weekselect a deep learning framework, and attempt to build a classifer using this training data.
 
|
 
|
 
<!-- 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) -->
*  
+
* Initial testing  with DIGITS 4 is underway.  Preparing the dataset in the style of the MNIST example.
 
|}
 
|}
  
 
==Background and References==
 
==Background and References==
 
<!-- Use this space for information that may help people better understand your project, like links to papers, source code, or data -->
 
<!-- Use this space for information that may help people better understand your project, like links to papers, source code, or data -->

Revision as of 12:57, 9 January 2017

Home < 2017 Winter Project Week < Evaluate Deep Learning for binary cancer legion classification

Key Investigators

  • Curt Lisle, KnowledgeVis, LLC
  • others are invited

Project Description

Objective Approach and Plan Progress and Next Steps
  • Train a neural network to become a binary classifier for the detection of cancer lesions using T2 ROI images
  • Start with a dataset, prepared at the Frederick National Lab for Cancer Research, to use to train a classifier.
  • The dataset consists of a series of 50x50 Region Of Interest images containing cancer lesions and two image series which do not contain lesions.
  • We plan to collect advice from others at the Project Week, select a deep learning framework, and attempt to build a classifer using this training data.
  • Initial testing with DIGITS 4 is underway. Preparing the dataset in the style of the MNIST example.

Background and References