Lung Tumor Diagnostics with Machine Learning
Principal Investigator
Name
Samuel Franklin
Degrees
M.A., M.Phil., Ph.D.
Institution
N/A
Position Title
VP, Data Science
Email
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-232
Initial CDAS Request Approval
Aug 2, 2016
Title
Lung Tumor Diagnostics with Machine Learning
Summary
The goal of this project is to develop automated tools that can provide oncologists, radiologists, and other healthcare professionals with information to facilitate their interpretation of lung CT scans. This could include tumor count, volume, longest diameter, density, and a scaled measure of edge smoothness. Data derived from CT scans and patient history might also be used to predict the likelihood that a tumor is benign or malignant.
I expect to use a variety of statistical and machine learning tools during this project including but not limited to the following: Bayesian methods, Random Forests, Support Vector Machines, Neural Networks, OpenCV, ITK, and Tensorflow for Deep Learning.
I expect to use a variety of statistical and machine learning tools during this project including but not limited to the following: Bayesian methods, Random Forests, Support Vector Machines, Neural Networks, OpenCV, ITK, and Tensorflow for Deep Learning.
Aims
Develop statistical and machine learning tools to improve the accuracy of lung tumor diagnostic information using patient data and CT imagery.
Collaborators
This project is in its earliest stages and selection of team members has not been finalized.