Virtual lung screening trial (VLST): An in silico study inspired by the national lung screening trial for lung cancer detection

Fakrul Islam Tushar, Liesbeth Vancoillie, Cindy McCabe, Amareswararao Kavuri, Lavsen Dahal, Brian Harrawood, Milo Fryling, Mojtaba Zarei, Saman Sotoudeh-Paima, Fong Chi Ho, Dhrubajyoti Ghosh, Michael R. Harowicz, Tina D. Tailor, Sheng Luo, W. Paul Segars, Ehsan Abadi, Kyle J. Lafata, Joseph Y. Lo+, Ehsan Samei+
Center for Virtual Imaging Trials, Carl E. Ravin Advanced Imaging Laboratories, Department of Radiology,Duke University School of Medicine, Durham, NC, 27708, USA
+Indicates Co-Senior Authors

Virtual Lung Screening Trial (VLST) workflow, showcasing AI-driven in silico trials in lung cancer screening—part of CVIT’s Monthly Forum. Watch the full forum here.

Abstract

Clinical imaging trials play a crucial role in advancing medical innovation but are often costly, inefficient, and ethically constrained. Virtual Imaging Trials (VITs) present a solution by simulating clinical trial components in a controlled, risk-free environment. The Virtual Lung Screening Trial (VLST), an in silico study inspired by the National Lung Screening Trial (NLST), illustrates the potential of VITs to expedite clinical trials, minimize risks to participants, and promote optimal use of imaging technologies in healthcare. This study aimed to show that a virtual imaging trial platform could investigate some key elements of a major clinical trial, specifically the NLST, which compared Computed tomography (CT) and chest radiography (CXR) for lung cancer screening. With simulated cancerous lung nodules, a virtual patient cohort of 294 subjects was created using XCAT human models. Each virtual patient underwent both CT and CXR imaging, with deep learning models, the AI CT-Reader and AI CXR-Reader, acting as virtual readers to perform recall patients with suspicion of lung cancer. The primary outcome was the difference in diagnostic performance between CT and CXR, measured by the Area Under the Curve (AUC). The AI CT-Reader showed superior diagnostic accuracy, achieving an AUC of 0.92 (95 % CI: 0.90–0.95) compared to the AI CXR-Reader's AUC of 0.72 (95 % CI: 0.67–0.77). Furthermore, at the same 94 % CT sensitivity reported by the NLST, the VLST specificity of 73 % was similar to the NLST specificity of 73.4 %. This CT performance highlights the potential of VITs to replicate certain aspects of clinical trials effectively, paving the way toward a safe and efficient method for advancing imaging-based diagnostics.

Project Presentation-VLST

VLST-NotebookLM Podcast

Pre-print

SPIE Phy. MedI(2024) Poster

Virtual Imaging Trials in Medicine – International Summit (VITM24) Poster

Won the Best Poster Award

RSNA Annual Meeting (2024) Abstarct

BibTeX

@article{TUSHAR2025103576,
title = {Virtual lung screening trial (VLST): An in silico study inspired by the national lung screening trial for lung cancer detection},
journal = {Medical Image Analysis},
volume = {103},
pages = {103576},
year = {2025},
issn = {1361-8415},
doi = {https://doi.org/10.1016/j.media.2025.103576},
url = {https://www.sciencedirect.com/science/article/pii/S1361841525001239},
author = {Fakrul Islam Tushar and Liesbeth Vancoillie and Cindy McCabe and Amareswararao Kavuri and Lavsen Dahal and Brian Harrawood and Milo Fryling and Mojtaba Zarei and Saman Sotoudeh-Paima and Fong Chi Ho and Dhrubajyoti Ghosh and Michael R. Harowicz and Tina D. Tailor and Sheng Luo and W. Paul Segars and Ehsan Abadi and Kyle J. Lafata and Joseph Y. Lo and Ehsan Samei},
keywords = {Virtual lung screening trial (VLST), National lung screening trials (NLST), Computer-aided diagnosis, Computed tomography (CT), Chest radiography (CXR), Human digital twins, Neural networks}
}
}