Sybil

Low-dose computed tomography (LDCT) is effective for lung cancer screening, but many eligible individuals are not being screened. To address this, a deep learning model called Sybil was developed to predict individual lung cancer risk using only one LDCT scan, without needing additional demographic or clinical data. Sybil was validated on three independent datasets and demonstrated high accuracy in predicting lung cancer risk, offering potential for more personalized screening approaches.