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

From NAMIC Wiki
Jump to: navigation, search
Line 27: Line 27:
 
|
 
|
 
<!-- 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) -->
−
* created a DIGITS 4 Amazon instance using NVIDIA's marketplace image
+
* created a DIGITS Amazon instance using NVIDIA's marketplace image before project week
−
* Initial exploration with DIGITS 4 has begun.  Preparing the dataset in the style of the MNIST example.
+
* Prepared the dataset in the style of the MNIST example
 +
* Trained LeNet and AlexNet CNNs using DIGITS interface and Caffe learning framework
 +
* Data augmentation was crucial to improve results up to 83% detection accuracy for 2D case
 +
* 3D data was presented without augmentation and yielded better results than 2D alone
 +
* We believe results will further improve when better data augmentation and 3D slice data are used simultaneously
 
|}
 
|}
  
 
==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 14:58, 13 January 2017

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

  • Example Cancer ROI

  • Initial LeNet training with DIGITS/Caffe

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 52x52 Region Of Interest T2 MR images containing cancer lesions and two T2 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.
  • created a DIGITS Amazon instance using NVIDIA's marketplace image before project week
  • Prepared the dataset in the style of the MNIST example
  • Trained LeNet and AlexNet CNNs using DIGITS interface and Caffe learning framework
  • Data augmentation was crucial to improve results up to 83% detection accuracy for 2D case
  • 3D data was presented without augmentation and yielded better results than 2D alone
  • We believe results will further improve when better data augmentation and 3D slice data are used simultaneously

Background and References

Retrieved from "https://www.na-mic.org/w/index.php?title=2017_Winter_Project_Week/Evaluate_Deep_Learning_for_binary_cancer_legion_classification&oldid=95027"