AI for Multistructure Incidental Findings and Mortality Prediction at Chest CT in Lung Cancer Screening
- Anna M. Marcinkiewicz,
- Mikolaj Buchwald,
- Aakash Shanbhag,
- Bryan P. Bednarski,
- Aditya Killekar,
- Robert J.H. Miller,
- Valerie Builoff,
- Mark Lemley,
- Daniel S. Berman,
- Damini Dey,
- Piotr J. Slomka
- Deputy Editor: Mizuki Nishino
- Scientific Editor: Elizabeth Weintraub
Abstract
A fully automated artificial intelligence model integrated multistructure segmentation, feature extraction, and quantification methods from chest CT scans to identify high-risk extrapulmonary features and predict mortality.
Background
Incidental extrapulmonary findings are commonly detected on chest CT scans and can be clinically important.
Purpose
To integrate artificial intelligence (AI)–based segmentation for multiple structures, coronary artery calcium (CAC), and epicardial adipose tissue with automated feature extraction methods and machine learning to detect extrapulmonary abnormalities and predict all-cause mortality (ACM) in a large multicenter cohort.
Materials and Methods
In this post hoc analysis, baseline chest CT scans in patients enrolled in the National Lung Screening Trial (NLST) from August 2002 to September 2007 were included from 33 participating sites. Per scan, 32 structures were segmented with a multistructure model. For each structure, 15 clinically interpretable radiomic features were quantified. Four general codes describing abnormalities reported by NLST radiologists were applied to identify extrapulmonary significant incidental findings on the CT scans. Death at 2-year and 10-year follow-up and the presence of extrapulmonary significant incidental findings were predicted with ensemble AI models, and individualized structure risk scores were evaluated. Area under the receiver operating characteristic curve (AUC) analysis was used to evaluate the performance of the models for prediction of ACM and extrapulmonary significant incidental findings. The Pearson χ2 test and Kruskal-Wallis rank sum test were used for statistical analyses.
Results
A total of 24 401 participants (median age, 61 years [IQR, 57–65 years]; 14 468 male) were included. In 3880 of 24 401 participants (16%), 4283 extrapulmonary significant incidental findings were reported. During the 10-year follow-up, 3389 of 24 401 participants (14%) died. CAC had the highest feature importance for predicting the three study end points. The 10-year ACM model demonstrated the best AUC performance (0.72; per-year mortality of 2.6% above and 0.8% below the risk threshold), followed by 2-year ACM (0.71; per-year mortality of 1.13% above and 0.3% below the risk threshold) and prediction of extrapulmonary significant incidental findings (0.70; probability of occurrence of 25.4% above and 9.6% below the threshold).
Conclusion
A fully automated AI model indicated extrapulmonary structures at risk on chest CT scans and predicted ACM with explanations.
ClinicalTrials.gov Identifier: NCT00047385
© RSNA, 2024
Supplemental material is available for this article.
See also the editorial by Yanagawa and Hata in this issue.
References
- 1. Computed tomography (CT) exams (indicator). OECD. https://www.oecd.org/en/data/indicators/computed-tomography-ct-exams.html. Published 2021. Accessed November 17, 2023.
- 2. Census 2020 Redistricting Data (Public Law 94-171) Summary Files. U.S. Census Bureau. https://www.census.gov/programs-surveys/decennial-census/about/rdo/summary-files.html. Published 2023. Accessed November 17, 2023.
- 3. . Projected cancer risks from computed tomographic scans performed in the United States in 2007. Arch Intern Med 2009;169(22):2071–2077.
- 4. . Incidental renal tumours on low-dose CT lung cancer screening exams. J Med Screen 2017;24(2):104–109.
- 5. . Automated measurement of liver attenuation to identify moderate-to-severe hepatic steatosis from chest CT scans. Eur J Radiol 2020;122:108723.
- 6. . Managing Incidental Findings on Thoracic CT: Mediastinal and Cardiovascular Findings. A White Paper of the ACR Incidental Findings Committee. J Am Coll Radiol 2018;15(8):1087–1096.
- 7. . Significant Incidental Findings in the National Lung Screening Trial. JAMA Intern Med 2023;183(7):677–684.
- 8. . Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 2011;365(5):395–409.
- 9. . Association of Coronary Artery Calcium With Long-term, Cause-Specific Mortality Among Young Adults. JAMA Netw Open 2019;2(7):e197440.
- 10. . Deep Learning for Malignancy Risk Estimation of Pulmonary Nodules Detected at Low-Dose Screening CT. Radiology 2021;300(2):438–447.
- 11. . Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study. Radiology 2023;306(1):172–182.
- 12. . An administrative data merging solution for dealing with missing data in a clinical registry: adaptation from ICD-9 to ICD-10. BMC Med Res Methodol 2008;8(1):1.
- 13. . Lung Cancer Incidence and Mortality with Extended Follow-up in the National Lung Screening Trial. J Thorac Oncol 2019 ;14(10):1732–1742.
- 14. . The National Lung Screening Trial: overview and study design. Radiology 2011;258(1):243–253.
- 15. . TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images. Radiol Artif Intell 2023;5(5):e230024.
- 16. . Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res 2017;77(21):e104–e107.
- 17. . AI-derived epicardial fat measurements improve cardiovascular risk prediction from myocardial perfusion imaging. NPJ Digit Med 2024;7(1):24.
- 18. . Automated vessel-specific coronary artery calcification quantification with deep learning in a large multi-centre registry. Eur Heart J Cardiovasc Imaging 2024;(7):976–985.
- 19. . A unified approach to interpreting model predictions. Adv Neural Inf Process Syst 2017. arXiv 1705.07874 [preprint] https://arxiv.org/abs/1705.07874. Posted May 22, 2017. Updated November 25, 2017. Accessed May 24, 2024.
- 20. . Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 1988;44(3):837–845.
- 21. . Deep convolutional neural networks to predict cardiovascular risk from computed tomography. Nat Commun 2021;12(1):715.
- 22. . Deep Learning-Quantified Calcium Scores for Automatic Cardiovascular Mortality Prediction at Lung Screening Low-Dose CT. Radiol Cardiothorac Imaging 2021;3(2):e190219.
- 23. . Using machine learning algorithms to review computed tomography scans and assess risk for cardiovascular disease: Retrospective analysis from the National Lung Screening Trial (NLST). PLoS One 2020;15(8):e0236021.
- 24. . AI Body Composition in Lung Cancer Screening: Added Value Beyond Lung Cancer Detection. Radiology 2023;308(1):e222937.
- 25. . Incidence Lung Cancer after a Negative CT Screening in the National Lung Screening Trial: Deep Learning-Based Detection of Missed Lung Cancers. J Clin Med 2020;9(12):3908.
- 26. . Extrapulmonary Findings and Malignancies in Participants Screened With Chest CT in the National Lung Screening Trial. J Am Coll Radiol 2017;14(3):324–330.
- 27. . Incidental Findings on Low-Dose CT Scan Lung Cancer Screenings and Deaths From Respiratory Diseases. Chest 2022;161(4):1092–1100.
Article History
Received: Feb 22 2024Revision requested: Apr 3 2024
Revision received: July 1 2024
Accepted: July 10 2024
Published online: Sept 17 2024
