Skip to Main Content
An official website of the United States government

Government Funding Lapse

Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted. The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit cc.nih.gov. Updates regarding government operating status and resumption of normal operations can be found at OPM.gov.

Deep learning for lung nodule detection and cancer prediction

Principal Investigator

Name
Quan Chen

Degrees
Ph.D.

Institution
University of Kentucky

Position Title
Associate Professor

Email
quanchen@gmail.com

About this CDAS Project

Study
NLST (Learn more about this study)

Project ID
NLST-320

Initial CDAS Request Approval
Jun 22, 2017

Title
Deep learning for lung nodule detection and cancer prediction

Summary
It has been shown that the low-dose CT screening on the high-risk population can improve the early detection and improve the overall survival. However, the screening will generate large amount of data for radiologist to inspect. This generated a lot of work to the radiologist. In addition, human fatigue may occur which will impact the accuracy. Even with the most up-to-date Lung-RADS guideline, false-positive rate is still high. Those false-positive patients will have to go through biopsy unnecessarily. This further increases the healthcare cost.
The recent success in using Neural Network to detect lung nodules and to predict whether it is cancer from a single CT has shown the power of the deep learning technology. However, more information regarding patient’s medical history, smoke history could be combined to aid the artificial intelligence to make a better decision.

Aims

Specific aim 1: Use deep learning technology to detect suspicious nodules in the Lung CT scans.
Specific aim 2: Use deep learning technology to predict whether subject will develop lung cancer based on CT image alone.
Specific aim 3: Add patient’s demographics, smoke history, and other information to the neural network to see how much improvement in prediction accuracy can be made.

Collaborators

NA