Abstract: Objective: We investigated the predictive value of dual-phase quantitative parameters of dual-layer spectral detector computed tomography (DLSCT) combined with Ki-67 expression in non-small-cell lung cancer (NSCLC). Methods: Seventy-seven patients with pathologically confirmed non-small cell lung cancer who underwent dual-phase enhanced scanning at our hospital between August 2022 and December 2024 were retrospectively analyzed. According to immunohistochemical results, they were divided into low (Ki-67≤30%) and high (Ki-67＞30%) Ki-67 expression groups. Spectral CT viewer software was used to measure, calculate, and analyze the quantitative parameters obtained with dual-layer spectral CT in the arterial and venous phases in both groups, including iodine density (IC), standardized iodine density (NIC), effective atomic number (Zeff), and energy spectrum curve slope (K, P < 0.05) (referred to as K and MonoE monochromatic energy spectroscopy) results, and CT40 keV-CT100 keV at 10 keV intervals. An independent samples t-test was used to compare differences between groups. Spearman’s correlation analysis was used to evaluate the correlation between the quantitative parameters of DLSCT and Ki-67 expression. A receiver-operating characteristic (ROC) curve was constructed to obtain the area under the curve (AUC). Youden index, sensitivity, and specificity were used to measure the efficacy of each quantitative parameter of DLSCT in predicting Ki-67 expression. Results: IC, NIC, Zeff, K40-100 keV, CT40 keV-CT70 keV (interval 10 keV) were higher in the low expression group than in the high expression group in venous phase, and K40-100 keV and CT40 keV were higher in the low expression group than in the high expression group in arterial phase. The differences were statistically significant (P＜0.05). IC, NIC, Zeff, K40-100 keV, CT40 keV-CT60 keV (interval 10 keV) in venous phase, and K40-100 keV, CT40 keV in arterial phase correlated negatively with Ki-67 expression level (|r| < 0.40,P < 0.05). The ROC curve showed that K40-100 keV in venous phase was the best parameter for predicting Ki-67 expression in NSCLC (AUC=0.750). Conclusion: Dual-phase quantitative parameters of DLSCT are effective tools for predicting Ki-67 expression in non-small cell lung cancer, and research evidence shows that the slope (K) of the spectral curve in the venous phase is the most valuable index.