Evaluation of Ki-67 expression levels in esophageal squamous cell carcinoma using dual-energy CT quantitative parameters

Abstract

Aim: This study investigates the use of dual-energy computed tomography (DECT) quantitative parameters to assess Ki-67 expression levels in esophageal squamous cell carcinoma (ESCC).

Methods: A total of 57 ESCC patients who underwent dual-phase DECT scans were included. Key parameters measured were iodine concentration (IC), water concentration (WC), normalized iodine concentration (NIC), spectral Hounsfield unit curve slope (λHu), and effective atomic number (Zeff). Univariate and multivariate analyses identified factors associated with Ki-67 expression levels.

Results: Results showed that high Ki-67 expression correlated with significantly higher Zeff and IC values in the venous phase (VP) (P = 0.047 and P = 0.049, respectively; AUC = 0.67 for both), and lower WC in the arterial phase (AP) (P = 0.021; AUC = 0.70). Multivariate analysis revealed that IC in VP and WC in AP were independent predictors of Ki-67 overexpression. The combination of these two parameters yielded an AUC of 0.78 for predicting Ki-67 overexpression, with 68.3% sensitivity, 87.5% specificity, and 73.7% accuracy.

Conclusions: DECT parameters demonstrate potential for non-invasive Ki-67 status detection in ESCC, offering valuable insights for clinical diagnosis and prognosis.

Keywords: Ki-67 expression; dual-energy CT (DECT); esophageal squamous cell carcinoma; nomogram; quantitative parameters.

Figure 1

A 74-year-old male patient with esophageal squamous cell carcinoma (ESCC) exhibiting low Ki-67 expression, grade 2, without neurovascular invasion or lymph node metastasis. Panels (A–D) show the 70-keV monochromatic contrast-enhanced CT image, iodine-based map, effective atomic number (Zeff) map, and spectral curve derived from the arterial phase (AP) scans. Panels (E–H) display the same imaging parameters derived from the venous phase (VP) scans.

Figure 2

ROC curve of the combined parameters for predicting Ki-67 expression in ESCC. IC, Iodine concentration; WC, Water concentrations; Zeff, Effective atomic number; AP, Arterial phase; VP, Venous phase.

Figure 3

The Dual-energy CT (DECT) nomogram for evaluating the Ki-67 expression in ESCC. IC, Iodine concentration; WC, Water concentrations; AP, Arterial phase; VP, Venous phase.

Figure 4

Decision curve analysis of the nomogram model. The nomogram demonstrated good calibration performance and provided the highest clinical net benefit across a wide range of threshold values, particularly demonstrating a positive net benefit within the threshold ranges of 0.12–0.99.

Figure 5

Calibration curve of the nomogram model. The curve was generated using bootstrap resampling (B = 200). The dashed blue line represents the ideal calibration line where predicted probabilities perfectly match observed outcomes. The Hosmer-Lemeshow test showed no significant lack of fit (p = 0.12), indicating good agreement between predicted and observed probabilities.