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.

Virtual NLST

Principal Investigator
Name
Joseph Lo
Degrees
Ph.D.
Institution
Center for Virtual Imaging Trials (CVIT), Dept. of Radiology, Duke University School of Medicine
Position Title
Professor and Vice Chair for Research of Radiology, TRD3 Project Lead for CVIT
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-1020
Initial CDAS Request Approval
Feb 28, 2023
Title
Virtual NLST
Summary
This project is supported by the NIBIB P41-funded Center for Virtual Imaging Trials https://cvit.duke.edu, which is developing a virtual platform for evaluating imaging technologies. Virtual imaging trials or VITs offer a computational alternative to clinical trials, which are slow, expensive, and often lack ground truth, while exposing subjects to ionizing radiation. Our VIT platform emulates key elements of the imaging chain, from virtual patients to virtual scanners to virtual readers. In this proposed study, we plan to validate our virtual imaging trial platform by replicating the low-dose computed tomography (CT) and chest radiography (CXR) outcomes of the NLST for lung cancer screening.

In previous work, we have already developed virtual patients, virtual scanners, and virtual readers for multiple chest imaging applications. For example, in the 2022 AAPM TrueCT Reconstruction Grand Challenge, we created 200 patients. We have emulated both CT and CXR for studies of COPD and COVID-19. For the virtual reading of images, we have developed mathematical observer models, radiomics systems, and machine learning algorithms. For this proposed study, we will demonstrate the robustness of these tools by reproducing the NLST trial, which will in turn allow using these tools to conduct other virtual imaging trials in the future.
Aims

This work will proceed with three Specific Aims:
(1) Replicate the NLST patient population as a virtual patient population with disease findings by using NLST demographic and imaging data.
(2) Replicate the NLST imaging technologies in terms of CXR and CT to produce virtual images of the virtual NLST patients.
(3) Perform virtual reader studies on the virtual images to emulate the NLST radiologist interpretations.

Collaborators

Fakrul Islam Tushar (lead scientist), Lavsen Dahal, Saman Sotoudeh-Paima, Ehsan Abadi, Paul Segars, Ehsan Samei (CVIT Director), Joseph Y Lo (PI)

Related Publications