Sybil: A Validated Deep Learning Model to Predict Future Lung Cancer Risk From a Single Low-Dose Chest Computed Tomography

Low-dose computed tomography (LDCT) for lung cancer screening is effective, although most eligible people are not being screened. Tools that provide personalized future cancer risk assessment could focus approaches toward those most likely to benefit. We hypothesized that a deep learning model asses...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of clinical oncology Vol. 41; no. 12; p. 2191
Main Authors:	Mikhael, Peter G, Wohlwend, Jeremy, Yala, Adam, Karstens, Ludvig, Xiang, Justin, Takigami, Angelo K, Bourgouin, Patrick P, Chan, PuiYee, Mrah, Sofiane, Amayri, Wael, Juan, Yu-Hsiang, Yang, Cheng-Ta, Wan, Yung-Liang, Lin, Gigin, Sequist, Lecia V, Fintelmann, Florian J, Barzilay, Regina
Format:	Journal Article
Language:	English
Published:	United States 20.04.2023
Subjects:	Deep Learning Early Detection of Cancer - methods Humans Lung Lung Neoplasms - diagnostic imaging Mass Screening - methods Tomography, X-Ray Computed
ISSN:	1527-7755, 1527-7755
Online Access:	Get more information
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Low-dose computed tomography (LDCT) for lung cancer screening is effective, although most eligible people are not being screened. Tools that provide personalized future cancer risk assessment could focus approaches toward those most likely to benefit. We hypothesized that a deep learning model assessing the entire volumetric LDCT data could be built to predict individual risk without requiring additional demographic or clinical data. We developed a model called Sybil using LDCTs from the National Lung Screening Trial (NLST). Sybil requires only one LDCT and does not require clinical data or radiologist annotations; it can run in real time in the background on a radiology reading station. Sybil was validated on three independent data sets: a heldout set of 6,282 LDCTs from NLST participants, 8,821 LDCTs from Massachusetts General Hospital (MGH), and 12,280 LDCTs from Chang Gung Memorial Hospital (CGMH, which included people with a range of smoking history including nonsmokers). Sybil achieved area under the receiver-operator curves for lung cancer prediction at 1 year of 0.92 (95% CI, 0.88 to 0.95) on NLST, 0.86 (95% CI, 0.82 to 0.90) on MGH, and 0.94 (95% CI, 0.91 to 1.00) on CGMH external validation sets. Concordance indices over 6 years were 0.75 (95% CI, 0.72 to 0.78), 0.81 (95% CI, 0.77 to 0.85), and 0.80 (95% CI, 0.75 to 0.86) for NLST, MGH, and CGMH, respectively. Sybil can accurately predict an individual's future lung cancer risk from a single LDCT scan to further enable personalized screening. Future study is required to understand Sybil's clinical applications. Our model and annotations are publicly available. [Media: see text].
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1527-7755 1527-7755
DOI:	10.1200/JCO.22.01345