AI for Multistructure Incidental Findings and Mortality Prediction at Chest CT in Lung Cancer Screening.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: Radiological Society of North America Country of Publication: United States NLM ID: 0401260 Publication Model: Print Cited Medium: Internet ISSN: 1527-1315 (Electronic) Linking ISSN: 00338419 NLM ISO Abbreviation: Radiology Subsets: MEDLINE
    • Publication Information:
      Publication: Easton, PA : Radiological Society of North America
      Original Publication: [Illinois?] : Radiological Society of North America, [1923]-
    • Subject Terms:
      Incidental Findings* ; Tomography, X-Ray Computed*/methods ; Lung Neoplasms*/diagnostic imaging ; Lung Neoplasms*/mortality ; Early Detection of Cancer*/methods; Humans ; Male ; Female ; Middle Aged ; Aged ; Artificial Intelligence ; Radiography, Thoracic/methods ; Lung/diagnostic imaging
    • Abstract:
      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 χ 2 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:
      N Engl J Med. 2011 Aug 4;365(5):395-409. (PMID: 21714641)
      JAMA Netw Open. 2019 Jul 3;2(7):e197440. (PMID: 31322693)
      PLoS One. 2020 Aug 3;15(8):e0236021. (PMID: 32745082)
      Radiol Artif Intell. 2023 Jul 05;5(5):e230024. (PMID: 37795137)
      Eur J Radiol. 2020 Jan;122:108723. (PMID: 31778964)
      Nat Commun. 2021 Jan 29;12(1):715. (PMID: 33514711)
      Chest. 2022 Apr;161(4):1092-1100. (PMID: 34838524)
      JAMA Intern Med. 2023 Jul 1;183(7):677-684. (PMID: 37155190)
      Biometrics. 1988 Sep;44(3):837-45. (PMID: 3203132)
      Radiology. 2023 Jul;308(1):e222937. (PMID: 37489991)
      Radiology. 2021 Aug;300(2):438-447. (PMID: 34003056)
      Arch Intern Med. 2009 Dec 14;169(22):2071-7. (PMID: 20008689)
      NPJ Digit Med. 2024 Feb 3;7(1):24. (PMID: 38310123)
      Eur Heart J Cardiovasc Imaging. 2024 Jun 28;25(7):976-985. (PMID: 38376471)
      J Clin Med. 2020 Dec 02;9(12):. (PMID: 33276433)
      J Am Coll Radiol. 2018 Aug;15(8):1087-1096. (PMID: 29941240)
      J Am Coll Radiol. 2017 Mar;14(3):324-330. (PMID: 28259326)
      BMC Med Res Methodol. 2008 Jan 23;8:1. (PMID: 18215293)
      Radiol Cardiothorac Imaging. 2021 Apr 15;3(2):e190219. (PMID: 33969304)
      Radiology. 2011 Jan;258(1):243-53. (PMID: 21045183)
      J Med Screen. 2017 Jun;24(2):104-109. (PMID: 28482765)
      J Thorac Oncol. 2019 Oct;14(10):1732-1742. (PMID: 31260833)
      Cancer Res. 2017 Nov 1;77(21):e104-e107. (PMID: 29092951)
      Radiology. 2023 Jan;306(1):172-182. (PMID: 36098642)
    • Grant Information:
      R01 HL148787 United States HL NHLBI NIH HHS; R01 HL151266 United States HL NHLBI NIH HHS; R35 HL161195 United States HL NHLBI NIH HHS
    • Molecular Sequence:
      ClinicalTrials.gov NCT00047385
    • Publication Date:
      Date Created: 20240917 Date Completed: 20240917 Latest Revision: 20241004
    • Publication Date:
      20241005
    • Accession Number:
      PMC11427857
    • Accession Number:
      10.1148/radiol.240541
    • Accession Number:
      39287522