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

Peter G MikhaelJeremy WohlwendAdam Yala Ludvig KarstensJustin XiangAngelo K Takigami Patrick P Bourgouin Pui-Yee Chan Sofiane MrahWael AmayriYu-Hsiang JuanCheng-Ta YangYung Liang Wan Gigin Lin Lecia V Sequist Florian J FintelmannRegina Barzilay

Published in: Journal of clinical oncology : official journal of the American Society of Clinical Oncology (2023)

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.

Keyphrases

computed tomography
current status
low dose
deep learning
positron emission tomography
magnetic resonance imaging
high dose
artificial intelligence
convolutional neural network