Skip to content

Applied Neural Networks to Johns Hopkins' CancerSEEK blood test data for early detection of eight cancer types before metastasis using Python, Keras, and TensorFlow. Improved accuracy from 70% to 83% while maintaining specificity above 99%.

Notifications You must be signed in to change notification settings

steven7214/CDNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Thesis

How to run

Install TensorFlow

Install TensorFlow by following the instructions at Install TensorFlow

Install Keras

Then follow instructions to Install Keras

Running Code

Run python script in "Python" directory called "cancerseek.py".


Results

The final research paper can be accessed under the file "Research Paper.pdf". More detailed results, including a powerpoint presentation can be found under the "Submit" directory.

About

Applied Neural Networks to Johns Hopkins' CancerSEEK blood test data for early detection of eight cancer types before metastasis using Python, Keras, and TensorFlow. Improved accuracy from 70% to 83% while maintaining specificity above 99%.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published