Preliminary Study on Differentiating Pleomorphic Adenoma and Malignant Tumors of the Parotid Gland by Texture Analysis of Non-Enhanced CT Images

Objective: To evaluate the possibility of texture analysis on non-enhanced CT images for differentiating pleomorphic adenoma and malignant tumors of the parotid gland. Materials and Methods: 45 cases of parotid pleomorphic adenoma and 12 cases of primary malignant tumor of the parotid gland confirmed by pathology were included in this retrospective study. Texture analysis software was used to delineate region of interest (ROI) on the lesions of these non-enhanced CT images, and obtained 18 texture parameters. Nonparametric test was used to statistically analyze the texture parameters of parotid pleomorphic adenomas and malignant tumors, and the ROC curve was used to evaluate the diagnostic effect of parameters with statistical difference. Results: Among the 18 different CT texture parameters generated on these non-enhanced CT images, 10 texture parameters were statistically significant between the PA group and the MT group (P<0.05). Among them, Median Intensity, Mean Value Voxel Value Sum, RMS, Mean Deviation have higher diagnostic efficacies, the AUCs are all greater than 0.8. Conclusion: Texture analysis of CT plain scan images can be used to identify parotid pleomorphic adenomas and parotid malignancies.