This multicenter retrospective study is designed to develop and validate a CT-based multimodal risk stratification approach for postoperative local recurrence after curative-intent resection of non-small cell lung cancer (NSCLC). The approach integrates clinicopathologic variables, intratumoral and peritumoral radiomics, tumor-based 2.5D deep learning features, whole-lung deep learning features, and operative text features to capture complementary information related to tumor phenotype, pulmonary background, and surgical findings. Predictive performance and clinical utility will be evaluated in internal and external validation cohorts using the concordance index, time-dependent area under the receiver operating characteristic curve, decision curve analysis, and risk reclassification analyses. The objective of this study is to assess whether multimodal CT-based risk stratification may improve postoperative risk assessment and support individualized surveillance and management strategies.