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.

Unsupervised Deep Learning Detection of Lung Cancer Nodules

Principal Investigator

Name
Ouwen Huang

Degrees
M.D., Ph.D., Candidate

Institution
Gradient Health

Position Title
Chief Scientific Officer

Email
ouwen.oh@gmail.com

About this CDAS Project

Study
NLST (Learn more about this study)

Project ID
NLST-758

Initial CDAS Request Approval
Feb 8, 2021

Title
Unsupervised Deep Learning Detection of Lung Cancer Nodules

Summary
Deep learning has been shown to successfully detect lung nodules in CT scans and is projected to be used in automated screening pipelines. However, one challenge is the requirement for data labels which are time consuming and costly to obtain. Such algorithms would allow more efficient detection model improvements. We propose using unsupervised learning methods within a human-in-the-loop pipeline to assist in collecting high quality labels that can be used to continuously improve detection models.

Aims

1. Develop unsupervised methods to improve data labeling processes
2. Assess automated cancer detection performance in relation to the number of labelled cases

Collaborators

Gradient Health Inc.