The Role of MRI Radiomics Using T2-Weighted Images and the Apparent Diffusion Coefficient Map for Discriminating Between Warthin's Tumors and Malignant Parotid Gland Tumors

Abstract

Background/objectives: Differentiating between benign and malignant parotid gland tumors (PGT) is essential for establishing the treatment strategy, which is greatly influenced by the tumor's histology. The objective of this study was to evaluate the role of MRI-based radiomics in the differentiation between Warthin's tumors (WT) and malignant tumors (MT), two entities that proved to present overlapping imaging features on conventional and functional MRI sequences.

Methods: In this retrospective study, a total of 106 PGT (66 WT, 40 MT) with confirmed histology were eligible for radiomic analysis, which were randomly split into a training group (79 PGT; 49 WT; 30 MT) and a testing group (27 PGT; 17 WT, 10 MT). The radiomic features were extracted from 3D segmentations of PGT performed on the following sequences: PROPELLER T2-weighted images and the ADC map, using a dedicated software. First- and second-order features were derived for each lesion, using original and filtered images.

Results: After employing several feature reduction techniques, including LASSO regression, three final radiomic parameters were identified to be the most significant in distinguishing between the two studied groups, with fair AUC values that ranged between 0.703 and 0.767. All three radiomic features were used to construct a Radiomic Score that presented the highest diagnostic performance in distinguishing between WT and MT, achieving an AUC of 0.785 in the training set, and 0.741 in the testing set.

Conclusions: MRI-based radiomic features have the potential to serve as promising novel imaging biomarkers for discriminating between Warthin's tumors and malignant tumors in the parotid gland. Nevertheless, it is still to prove how radiomic features can consistently achieve higher diagnostic performance, and if they can outperform alternative imaging methods, ideally in larger, multicentric studies.

Keywords: MRI; Warthin’s tumors; malignant tumors; parotid gland tumors; radiomics; textural analysis.

Figure 1

Three-dimensional segmentation of a malignant parotid gland tumor (histopathologically confirmed acinic cell carcinoma) performed on the T2-weighted image (A) and the ADC map (B).

Figure 2

Three-dimensional segmentation exemplification of a histopathologically confirmed Warthin’s tumor performed on the T2-weighted image (A) and the ADC map (B).

Figure 3

The radiomic pipeline. WT = Warthin’s tumors; MT = malignant tumors; ICC = intraclass correlation coefficient; BHC = Benjamani–Hochberg Correction; LASSO = least absolute shrinkage and selection operator; ROC = receiver-operating characteristic.

Figure 4

LASSO regression. (A) Cross-validation curve: X-axis represents the logarithm of the regularization parameter lambda (λ); Y-axis represents the binomial deviance as a measure of model fit; the red dots represent the mean binomial deviance calculated for each value of λ during cross-validation; the error bars show the standard error of the binomial deviance at each λ; the first vertical line corresponds to the λ value that minimizes the deviance (the optimal λ; the second vertical line represents the largest λ within one standard error of the minimum deviance. (B) Coefficient path: The X-axis shows the logarithm of the regularization parameter λ; the Y-axis represents the magnitude of the regression coefficients; the colored lines represent the paths of individual coefficients as λ changes; the vertical dotted line corresponds to the optimal λ selected by cross-validation.

Figure 5

Receiver operating characteristic (ROC) curve of the Radiomic Score for differentiating between Warthin’s tumors and malignant tumors of the parotid gland in the training set (A) and testing set (B).