Radiomic Analysis of Multi-parametric MR Images (MRI) for Classification of Parotid Tumors

Abstract

Background: Characterization of parotid tumors before surgery using multi-parametric magnetic resonance imaging (MRI) scans can support clinical decision making about the best-suited therapeutic strategy for each patient. Objective: This study aims to differentiate benign from malignant parotid tumors through radiomics analysis of multi-parametric MR images, incorporating T2-w images with ADC-map and parametric maps generated from Dynamic Contrast Enhanced MRI (DCE-MRI).Material and Methods: MRI scans of 31 patients with histopathologically-confirmed parotid gland tumors (23 benign, 8 malignant) were included in this retrospective study. For DCE-MRI, semi-quantitative analysis, Tofts pharmacokinetic (PK) modeling, and five-parameter sigmoid modeling were performed and parametric maps were generated. For each patient, borders of the tumors were delineated on whole tumor slices of T2-w image, ADC-map, and the late-enhancement dynamic series of DCE-MRI, creating regions-of-interest (ROIs). Radiomic analysis was performed for the specified ROIs. Results: Among the DCE-MRI-derived parametric maps, wash-in rate (WIR) and PK-derived Ktrans parameters surpassed the accuracy of other parameters based on support vector machine (SVM) classifier. Radiomics analysis of ADC-map outperformed the T2-w and DCE-MRI techniques using the simpler classifier, suggestive of its inherently high sensitivity and specificity. Radiomics analysis of the combination of T2-w image, ADC-map, and DCE-MRI parametric maps resulted in accuracy of 100% with both classifiers with fewer numbers of selected texture features than individual images. Conclusion: In conclusion, radiomics analysis is a reliable quantitative approach for discrimination of parotid tumors and can be employed as a computer-aided approach for pre-operative diagnosis and treatment planning of the patients.

Keywords

• parotid neoplasms
• radiomics
• texture analysis
• magnetic resonance imaging
• machine learning
• diagnosis