Usefulness of MRI-based radiomic features for distinguishing Warthin tumor from pleomorphic adenoma: performance assessment using T2-weighted and post-contrast T1-weighted MR images

Lorenzo Faggioni; Michela Gabelloni; Fabrizio De Vietro; Jessica Frey; Vincenzo Mendola; Diletta Cavallero; Rita Borgheresi; Lorenzo Tumminello; Jorge Shortrede; Riccardo Morganti; Veronica Seccia; Francesca Coppola; Dania Cioni; Emanuele Neri

doi:10.1016/j.ejro.2022.100429

Usefulness of MRI-based radiomic features for distinguishing Warthin tumor from pleomorphic adenoma: performance assessment using T2-weighted and post-contrast T1-weighted MR images

Eur J Radiol Open. 2022 Jun 18:9:100429. doi: 10.1016/j.ejro.2022.100429. eCollection 2022.

Authors

Lorenzo Faggioni¹, Michela Gabelloni¹, Fabrizio De Vietro¹, Jessica Frey¹, Vincenzo Mendola¹, Diletta Cavallero¹, Rita Borgheresi¹, Lorenzo Tumminello¹, Jorge Shortrede¹, Riccardo Morganti², Veronica Seccia³, Francesca Coppola^{4

5}, Dania Cioni^{1

5}, Emanuele Neri^{1

5}

Affiliations

¹ Academic Radiology, Department of Translational Research, University of Pisa, Via Roma 67, 56126, Pisa, Italy.
² Department of Clinical and Experimental Medicine, Section of Statistics, University of Pisa, Via Roma 67, 56126, Pisa, Italy.
³ Otolaryngology, Audiology, and Phoniatric Operative Unit, Department of Surgical, Medical, Molecular Pathology, and Critical Care Medicine, Azienda Ospedaliero Universitaria Pisana, University of Pisa, 56124 Pisa, Italy.
⁴ Department of Radiology, IRCCS Azienda Ospedaliero Universitaria di Bologna, 40138, Bologna, Italy.
⁵ Italian Society of Medical and Interventional Radiology, SIRM Foundation, Via della Signora 2, 20122, Milano, Italy.

Abstract

Purpose: Differentiating Warthin tumor (WT) from pleomorphic adenoma (PA) is of primary importance due to differences in patient management, treatment and outcome. We sought to evaluate the performance of MRI-based radiomic features in discriminating PA from WT in the preoperative setting.

Methods: We retrospectively evaluated 81 parotid gland lesions (48 PA and 33 WT) on T2-weighted (T2w) images and 52 of them on post-contrast fat-suppressed T1-weighted (pcfsT1w) images. All MRI examinations were carried out on a 1.5-Tesla MRI scanner, and images were segmented manually using the software ITK-SNAP (www.itk-snap.org).

Results: The most discriminative feature on pcfsT1w images was GLCM_InverseVariance, yielding area under the curve (AUC), sensitivity and specificity of 0.9, 86 % and 87 %, respectively. Skewness was the feature extracted from T2w images with the highest specificity (88 %) in discriminating WT from PA.

Conclusion: Radiomic analysis could be an important tool to improve diagnostic accuracy in differentiating PA from WT.

Keywords: ADC, apparent diffusion coefficient; AUC, area under the curve; FNAC, fine needle aspiration cytology; GLCM, gray level co-occurrence matrix; GLDM, gray level dependence matrix; GLRLM, gray level run length matrix; GLSZM, gray level size zone matrix; Head and neck cancer; IBSI Image, Biomarker Standardization Initiative; Magnetic resonance imaging; NGTDM, neighboring gray tone difference matrix; PA, pleomorphic adenoma; Parotid neoplasm; PcfsT1W, post-contrast fat-suppressed T1-weighted; Pleomorphic adenoma; ROC, receiver operating characteristics; Radiomics; WT, Warthin tumor; Warthin tumor.