Research progress in computer-aided diagnosis systems for lung cancer.
review · Level V
Where this comes from
- Record sourced from PubMed, PMID 41299062.
- Also identified by DOI 10.1038/s41746-025-02101-3 and PMC identifier 12658133.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
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.