Abstract：【Objective】To analyze the diagnostic value of multi-slice spiral CT image texture in pulmonary nodules. 【Methods】A total of 83 patients with pulmonary nodules admitted to our hospital from January 2018 to March 2023 were retrospectively analyzed and divided into the benign group (n=20, benign pulmonary nodules) and the malignant group (n=63, malignant pulmonary nodules) according to pathological diagnosis results. All patients were examined by multi-slice spiral CT. The image features of the two groups were compared, and the influencing factors of the occurrence of malignant pulmonary nodules were analyzed by Logistic regression model. The receiver operating characteristic (ROC) curve was drawn to analyze the value of texture features in the differential diagnosis of pulmonary nodules. 【Results】The mean value of multi-slice spiral CT image textures in the malignant group was higher than that in the benign group (P<0.05), and the skewness of the malignant group was lower than that of the benign group (P<0.05). There was no statistical significance in kurtosis and inhomogeneity between the two groups (P>0.05). Logistic regression analysis showed that both mean value and skewness were influencing factors for distinguishing the occurrence of malignant pulmonary nodules (P<0.05).The ROC curve results showed that the cutoff of the driving influencing factor was 15.34, the sensitivity was 88.89%, the specificity was 75.00%, the area under the curve was 0.798 (95%CI: 0.697-0.878) (P<0.05), and the Youden index was 0.639.【Conclusion】It is valuable to establish a driving factor model based on mean value and skewness in the texture of multi-slice spiral CT images. This method has high clinical value in the diagnosis of malignant pulmonary nodules.
2025, Vol. 42 
