The application of a nomogram model integrating clinical factors and multimodal MRI radiomics features for predicting cervical lymph node metastasis for patients with oral tongue squamous cell carcinoma in different tumor stages.

The aim of this study was to build and test a nomogram model integrating clinical factors and multimodal MRI radiomics features to predict the risk of cervical lymph node metastasis (CLNM) in oral tongue squamous cell carcinoma (OTSCC) patients in different tumor stages. A total of 326 enrolled patients made up group Ⅰ (including T1WI and FS-T2WI) and group Ⅱ (including T1WI, FS-T2WI, and CE-MRI). Patients were divided into a training set, an internal test set, and an external test set. Radiomics features from the three MRI sequences and clinical factors were extracted and selected. Radiomics models, clinical models, and the combined models (nomogram models) integrating clinical factors and multimodal MRI radiomics features were constructed, respectively, in the two groups. cN0 subgroup and cT1-T2 subgroup analyses were performed. The combined model integrating clinical factors and multimodal MRI radiomics features in group Ⅱ produced a better performance than group Ⅰ. cN0 subgroup and cT1-T2 subgroup analyses also confirmed a superior performance of the combined model in group Ⅱ compared with group Ⅰ. The combined model based on clinical factors and multimodal MRI radiomics features including T1WI, FS-T2WI, and CE-MRI has potential utility in predicting the risk of CLNM in OTSCC patients.