Artificial intelligence propels lung cancer screening: innovations and the challenges of explainability and reproducibility

Abstract

In a recent study published in Nature Medicine, Wang, Shao, and colleagues successfully addressed two critical issues of lung cancer (LC) screening with low-dose computed tomography (LDCT) whose widespread implementation, despite its capacity to decrease LC mortality, remains challenging: (1) the difficulty in accurately distinguishing malignant nodules from the far more common benign nodules detected on LDCT, and (2) the insufficient coverage of LC screening in resource-limited areas.¹