Artificial intelligence construction: a review of the bridge between CT imaging features of lung ground-glass nodules adenocarcinoma and carcinogenic driver genes

Lung ground-glass nodules (GGNs) represent a critical early imaging manifestation of lung adenocarcinoma, and exploring the relationship between their CT imaging features and oncogenic driver genes holds significant promise for precision diagnosis and personalized treatment. In recent years, artificial intelligence (AI) technologies, particularly deep learning and machine learning methods, have demonstrated remarkable potential in the integrative analysis of radiomic and genomic data. This review summarizes the current advances in AI applications for extracting CT imaging features of lung GGNs, identifying oncogenic driver genes, and analyzing their correlations. Key AI-driven techniques enabling the construction of a bridge between imaging phenotypes and genetic alterations are discussed, alongside challenges such as data heterogeneity, limited annotated datasets, and interpretability. Future research directions emphasize the development of robust, explainable AI models and multi-omics integration to enhance early lung cancer diagnosis and therapeutic strategies. By providing a comprehensive overview of the intersection between AI, radiomics, and genomics in lung GGN adenocarcinoma, this article aims to offer theoretical insights and technical references to advance early detection and precision oncology.