Can Magnetic Resonance Radiomics Analysis Discriminate Parotid Gland Tumors? A Pilot Study
Michela Gabelloni,
Lorenzo Faggioni,
Simona Attanasio,
Vanina Vani,
Antonio Goddi,
Sara Colantonio,
Danila Germanese,
Claudia Caudai,
Luca Bruschini,
Mariella Scarano,
Veronica Seccia,
Emanuele Neri
Affiliations
Michela Gabelloni
Master in Oncologic Imaging, Diagnostic and Interventional Radiology, Department of Translational Research, University of Pisa, Via Roma, 67, 56126 Pisa, Italy
Lorenzo Faggioni
Master in Oncologic Imaging, Diagnostic and Interventional Radiology, Department of Translational Research, University of Pisa, Via Roma, 67, 56126 Pisa, Italy
Simona Attanasio
Diagnostic and Interventional Radiology, Department of Translational Research, University of Pisa, Via Roma, 67, 56126 Pisa, Italy
Vanina Vani
Diagnostic and Interventional Radiology, Department of Translational Research, University of Pisa, Via Roma, 67, 56126 Pisa, Italy
Antonio Goddi
Diagnostic and Interventional Radiology, Department of Translational Research, University of Pisa, Via Roma, 67, 56126 Pisa, Italy
Sara Colantonio
Institute of Information Science and Technologies “A. Faedo” of the National Research Council of Italy (ISTI-CNR), 56124 Pisa, Italy
Danila Germanese
Institute of Information Science and Technologies “A. Faedo” of the National Research Council of Italy (ISTI-CNR), 56124 Pisa, Italy
Claudia Caudai
Institute of Information Science and Technologies “A. Faedo” of the National Research Council of Italy (ISTI-CNR), 56124 Pisa, Italy
Luca Bruschini
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
Mariella Scarano
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
Veronica Seccia
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
Emanuele Neri
Master in Oncologic Imaging, Diagnostic and Interventional Radiology, Department of Translational Research, University of Pisa, Via Roma, 67, 56126 Pisa, Italy
Our purpose is to evaluate the performance of magnetic resonance (MR) radiomics analysis for differentiating between malignant and benign parotid neoplasms and, among the latter, between pleomorphic adenomas and Warthin tumors. We retrospectively evaluated 75 T2-weighted images of parotid gland lesions, of which 61 were benign tumors (32 pleomorphic adenomas, 23 Warthin tumors and 6 oncocytomas) and 14 were malignant tumors. A receiver operating characteristics (ROC) curve analysis was performed to find the threshold values for the most discriminative features and determine their sensitivity, specificity and area under the ROC curve (AUROC). The most discriminative features were used to train a support vector machine classifier. The best classification performance was obtained by comparing a pleomorphic adenoma with a Warthin tumor (yielding sensitivity, specificity and a diagnostic accuracy as high as 0.8695, 0.9062 and 0.8909, respectively) and a pleomorphic adenoma with malignant tumors (sensitivity, specificity and a diagnostic accuracy of 0.6666, 0.8709 and 0.8043, respectively). Radiomics analysis of parotid tumors on conventional T2-weighted MR images allows the discrimination of pleomorphic adenomas from Warthin tumors and malignant tumors with a high sensitivity, specificity and diagnostic accuracy.
