Research progress in computer-aided diagnosis systems for lung cancer

Lung cancer remains the top cause of cancer death, demanding consistent decisions. This clinically oriented review synthesizes computer-aided diagnosis across classical imaging, machine learning, and deep learning, emphasizing bedside-proven advances: multimodal CT/PET–clinical fusion; small-data strategies; interpretable AI; and privacy-preserving multi-center learning. Reported systems reach AUC ≥ 0.95 with <0.1 false positives/CT and boost early detection by ~20–30%; prognostic C-index ~0.85–0.90. We outline implementation checkpoints and priorities to convert accuracy into patient benefit.