CT-Based Radiomic Nomogram for Preoperative Prediction of Ki-67 in Lung Neuroendocrine Neoplasms: A Multicenter Study

Objective The Lung neuroendocrine neoplasms (L-NENs) are increasingly recognised, yet reliable pre-operative assessment of the Ki-67 proliferation index remains invasive and heterogeneous. We aimed to develop and validate a clinical-radiomics nomogram that uses routine chest CT to estimate Ki-67 status in patients with L-NENs. Methods In this retrospective multicentre study, 199 patients (four hospitals, January 2014–December 2024) with histologically confirmed L-NENs and pre-operative dual-phase contrast-enhanced CT were included. After manual 3D tumour segmentation, 1,874 radiomics features were extracted from fused unenhanced and arterial / venous-phase images. Feature selection combined Pearson correlation (r > 0.8 removed) and LASSO regression. Five classifiers were compared; logistic regression (LR) performed best and was used to build a radiomics signature (Rad-score). Clinical predictors of Ki-67 were identified by multivariable logistic regression and integrated with the Rad-score to construct a nomogram. Discrimination, calibration and clinical utility were assessed by AUC, calibration plot and decision curve analysis in training (n = 116), internal testing (n = 50) and external validation (n = 33) sets. Results High Ki-67 (> 30%) was present in 119 (59.8%) patients. The LR radiomics model yielded AUCs of 0.912 (95% CI 0.858–0.965) and 0.943 (0.887–0.999) in training and testing sets, respectively. Independent clinical predictors were largest tumour diameter, smoking history and age. The combined nomogram achieved AUCs of 0.958 (0.925–0.990), 0.930 (0.865–0.995) and 0.911 (0.867–0.955) in training, testing and external validation sets, with good calibration and superior net benefit on decision-curve analysis. Conclusion The CT-based clinical–radiomics nomogram provides an accurate, non-invasive tool for pre-operative Ki-67 estimation in L-NENs, potentially guiding treatment decisions. Prospective, larger-scale validation is warranted. Clinical trial number: Not applicable.