Deep Learning to Optimize Candidate Selection for Lung Cancer CT Screening: Advancing the 2021 USPSTF Recommendations
Related Experiment Video
Updated: Sep 8, 2025
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
Jong Hyuk Lee1, Dongheon Lee1, Michael T Lu1
1From the Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Korea (J.H.L., C.M.P., J.M.G., H.K.); Department of Biomedical Engineering, Chungnam National University College of Medicine, Chungnam National University Hospital, Daejeon, Korea (D.L.); Cardiovascular Imaging Research Center, Massachusetts General Hospital and Harvard Medical School, Boston, Mass (M.T.L., V.K.R.); Department of Radiology, Seoul National University College of Medicine, Seoul, Korea (C.M.P., J.M.G., H.K.); Institute of Radiation Medicine (C.M.P., J.M.G.) and Institute of Medical and Biological Engineering (C.M.P.), Seoul National University Medical Research Center, Seoul, Korea; Cancer Research Institute, Seoul National University, Seoul, Korea (J.M.G.); and Department of Internal Medicine, Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea (S.H.C.).
Abstract:
Background A deep learning (DL) model to identify lung cancer screening candidates based on their chest radiographs requires external validation with a recent real-world non-U.S. sample. Purpose To validate the DL model and identify added benefits to the 2021 U.S. Preventive Services Task Force (USPSTF) recommendations in a health check-up sample. Materials and Methods This single-center retrospective study included consecutive current and former smokers aged 50-80 years who underwent chest radiography during a health check-up between January 2004 and June 2018. Discrimination performance, including receiver operating characteristic curve analysis and area under the receiver operating characteristic curve (AUC) calculation, of the model for incident lung cancers was evaluated. The added value of the model to the 2021 USPSTF recommendations was investigated for lung cancer inclusion rate, proportion of selected CT screening candidates, and positive predictive value (PPV). Results For model validation, a total of 19 488 individuals (mean age, 58 years ± 6 [SD]; 18 467 [95%] men) and the subset of USPSTF-eligible individuals (n = 7835; mean age, 57 years ± 6; 7699 [98%] men) were assessed, and the AUCs for incident lung cancers were 0.68 (95% CI: 0.62, 0.73) and 0.75 (95% CI: 0.68, 0.81), respectively. In individuals with pack-year information (n = 17 390), when excluding low- and indeterminate-risk categories from the USPSTF-eligible sample, the proportion of selected CT screening candidates was reduced to 35.8% (6233 of 17 390) from 45.1% (7835 of 17 390, P < .001), with three missed lung cancers (0.2%). The cancer inclusion rate (0.3% [53 of 17 390] vs 0.3% [56 of 17 390], P = .85) and PPV (0.9% [53 of 6233] vs 0.7% [56 of 7835], P = .42) remained unaffected. Conclusion An externally validated deep learning model showed the added value to the 2021 U.S. Preventive Services Task Force recommendations for low-dose CT lung cancer screening in reducing the number of screening candidates while maintaining the inclusion rate and positive predictive value for incident lung cancer. © RSNA, 2022 Online supplemental material is available for this article.
