Deep Learning can improve Lung Cancer Screening
In an article in Annals of Internal Medicine, we demonstrate how Lung cancer screening can be improved using an automated deep-learning approach based on chest radiograph images. This approach can identify more smokers at high risk for lung cancer who could benefit from screening with CT. For this purpose, we developed and validated a convolutional neural network (CXR-LC) that predicts long-term incident lung cancer using data commonly available in the electronic medical record (EMR) (chest radiograph, age, sex, and whether currently smoking).
AIM Investigators
