TY - JOUR
T1 - Sybil
T2 - A Validated Deep Learning Model to Predict Future Lung Cancer Risk from a Single Low-Dose Chest Computed Tomography
AU - Mikhael, Peter G.
AU - Wohlwend, Jeremy
AU - Yala, Adam
AU - Karstens, Ludvig
AU - Xiang, Justin
AU - Takigami, Angelo K.
AU - Bourgouin, Patrick P.
AU - Chan, Puiyee
AU - Mrah, Sofiane
AU - Amayri, Wael
AU - Juan, Yu Hsiang
AU - Yang, Cheng-Ta
AU - Wan, Yung Liang
AU - Lin, Gigin
AU - Sequist, Lecia V.
AU - Fintelmann, Florian J.
AU - Barzilay, Regina
N1 - Publisher Copyright:
© American Society of Clinical Oncology.
PY - 2023/4/20
Y1 - 2023/4/20
N2 - PURPOSE: 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.METHODS: 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).RESULTS: 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.CONCLUSION: 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.UNLABELLED: [Media: see text].
AB - PURPOSE: 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.METHODS: 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).RESULTS: 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.CONCLUSION: 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.UNLABELLED: [Media: see text].
KW - Humans
KW - Lung Neoplasms/diagnostic imaging
KW - Deep Learning
KW - Early Detection of Cancer/methods
KW - Tomography, X-Ray Computed
KW - Lung
KW - Mass Screening/methods
UR - https://www.scopus.com/pages/publications/85148731991
U2 - 10.1200/JCO.22.01345
DO - 10.1200/JCO.22.01345
M3 - 文章
C2 - 36634294
AN - SCOPUS:85148731991
SN - 0732-183X
VL - 41
SP - 2191
EP - 2200
JO - Journal of Clinical Oncology
JF - Journal of Clinical Oncology
IS - 12
ER -