Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Jun;25(6):954-961.
doi: 10.1038/s41591-019-0447-x. Epub 2019 May 20.

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography

Diego Ardila #  1 , Atilla P Kiraly #  1 , Sujeeth Bharadwaj #  1 , Bokyung Choi #  1 , Joshua J Reicher  2 , Lily Peng  1 , Daniel Tse  3 , Mozziyar Etemadi  4 , Wenxing Ye  1 , Greg Corrado  1 , David P Naidich  5 , Shravya Shetty  1
Affiliations

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography

Diego Ardila et al. Nat Med. 2019 Jun.

Erratum in

Abstract

With an estimated 160,000 deaths in 2018, lung cancer is the most common cause of cancer death in the United States1. Lung cancer screening using low-dose computed tomography has been shown to reduce mortality by 20-43% and is now included in US screening guidelines1-6. Existing challenges include inter-grader variability and high false-positive and false-negative rates7-10. We propose a deep learning algorithm that uses a patient's current and prior computed tomography volumes to predict the risk of lung cancer. Our model achieves a state-of-the-art performance (94.4% area under the curve) on 6,716 National Lung Cancer Screening Trial cases, and performs similarly on an independent clinical validation set of 1,139 cases. We conducted two reader studies. When prior computed tomography imaging was not available, our model outperformed all six radiologists with absolute reductions of 11% in false positives and 5% in false negatives. Where prior computed tomography imaging was available, the model performance was on-par with the same radiologists. This creates an opportunity to optimize the screening process via computer assistance and automation. While the vast majority of patients remain unscreened, we show the potential for deep learning models to increase the accuracy, consistency and adoption of lung cancer screening worldwide.

PubMed Disclaimer

Comment in

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. American Lung Association. Lung cancer fact sheet. American Lung Association http://www.lung.org/lung-health-and-diseases/lung-disease-lookup/lung-ca... (accessed 11 September 2018).
    1. Jemal, A. & Fedewa, S. A. Lung cancer screening with low-dose computed tomography in the United States—2010 to 2015. JAMA Oncol. 3, 1278 (2017). - DOI
    1. US Preventive Services Task Force. Final update summary: lung cancer: screening (1AD). US Preventive Services Task Force https://www.uspreventiveservicestaskforce.org/Page/Document/UpdateSummar... (2018).
    1. National Lung Screening Trial Research Team et al. Reduced lung-cancer mortality with low-dose computed tomographic screening. N. Engl. J. Med. 365, 395–409 (2011). - DOI
    1. Black, W. C. et al. Cost-effectiveness of CT screening in the National Lung Screening Trial. N. Engl. J. Med. 371, 1793–1802 (2014). - DOI

Publication types

MeSH terms