Virtual NLST
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.
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.
Fakrul Islam Tushar (lead scientist), Lavsen Dahal, Saman Sotoudeh-Paima, Ehsan Abadi, Paul Segars, Ehsan Samei (CVIT Director), Joseph Y Lo (PI)
-
Virtual lung screening trial (VLST): An in silico study inspired by the national lung screening trial for lung cancer detection.
Tushar FI, Vancoillie L, McCabe C, Kavuri A, Dahal L, Harrawood B, Fryling M, Zarei M, Sotoudeh-Paima S, Ho FC, Ghosh D, Harowicz MR, Tailor TD, Luo S, Segars WP, Abadi E, Lafata KJ, Lo JY, Samei E
Med Image Anal. 2025 Apr 5; Volume 103: Pages 103576 PUBMED