Ardila et al., 2019, End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography

# 세줄요약 #

1. We propose a deep learning algorithm that uses a patient’s current and prior computed tomography volumes to predict the risk of lung cancer.
2. 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.
3. We conducted two reader studies: First, a 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. Second, a prior computed tomography imaging was available, the model performance was on-par with the same radiologists.

 

* Reference: Ardila, D., Kiraly, A.P., Bharadwaj, S. et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat Med 25, 954–961 (2019) doi:10.1038/s41591-019-0447-x