Difference between revisions of "2017 Winter Project Week/Evaluate Deep Learning for binary cancer legion classification"
From NAMIC Wiki
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 | + | * 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== | ==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 classificationKey Investigators
- Curt Lisle, KnowledgeVis, LLC
- others are invited
Project Description
Objective | Approach and Plan | Progress and Next Steps |
---|---|---|
|
|
|