Different MRI-based radiomics models for distinguishing misdiagnosed or ambiguous pleomorphic adenoma and Warthin tumor: A multicenter study

Motivation: Enhance the accuracy of distinguishing misdiagnosed or ambiguous cases of pleomorphic adenoma (PA) and Warthin tumor (WT). Goal(s): This study aims to construct various MRI-based radiomics models employing different machine learning classifiers to determine the optimal models for identifying misdiagnosed or ambiguous PA and WT cases. Approach: we evaluate the effectiveness of various MRI-based radiomics models. Results: A nomogram demonstrates exceptional and consistent diagnostic performance. In routine practice, combining clinical parameters is essential for distinguishing between PA and WT. Impact: MRI-based radiomics models can effectively differentiate misdiagnosed or ambiguous cases of PA and WT. The nomogram is a valuable tool for preoperatively and non-invasively distinguishing between PA and WT, a task often challenging for clinicians and radiologists before surgery.