Background: In this prospective study, we hypothesized that magnetic resonance imaging (MRI) may represent not only the tumor but also the microenvironment, reflecting the heterogeneity and microstructural complexity of neoplasms. We investigated the correlation between both diffusion kurtosis imaging (DKI) and dynamic contrast-enhanced (DCE)-MRI with the pathological factors in oral cavity squamous cell carcinomas (OSCCs). Methods: A total of 37 patients with newly diagnosed OSCCs underwent an MR examination on a 3T system. The diffusion coefficient (D), the kurtosis parameter (K), the transfer constants K^trans and K_ep and the volume of extravascular extracellular space v_e were quantified. A histogram-based approach was proposed to investigate the associations between the imaging and the pathological factors based on the histology and immunochemistry. Results: Significant differences in the DCE-MRI and DKI parameters were found in relation to the inflammatory infiltrate, tumor grading, keratinization and desmoplastic reaction. Relevant relationships emerged between tumor-infiltrating lymphocytes (TILs) and DKI, with lower D and higher K values being associated with increased TILs. Conclusion: Although a further investigation is needed, these findings provide a more comprehensive biological characterization of OSCCs and may contribute to a better understanding of DKI-derived parameters, whose biophysical meaning is still not well-defined.

Background: Oropharyngeal squamous cell carcinoma (OPSCC) associated with human papillomavirus (HPV) has higher rates of locoregional control and a better prognosis than HPV-negative OPSCC. These differences are due to some unique biological characteristics that are also visible through advanced imaging modalities. We investigated the ability of a multifactorial model based on both clinical factors and diffusion-weighted imaging (DWI) to determine the HPV status in OPSCC. Methods: The apparent diffusion coefficient (ADC) and the perfusion-free tissue diffusion coefficient D were derived from DWI, both in the primary tumor (PT) and lymph node (LN). First- and second-order radiomic features were extracted from ADC and D maps. Different families of machine learning (ML) algorithms were trained on our dataset using five-fold cross-validation. Results: A cohort of 144 patients was evaluated retrospectively, which was divided into a training set (n = 95) and a validation set (n = 49). The 50th percentile of D_PT, the inverse difference moment of ADCLN, smoke habits, and tumor subsite (tonsil versus base of the tongue) were the most relevant predictors. Conclusions: DWI-based radiomics, together with patient-related parameters, allowed us to obtain good diagnostic accuracies in differentiating HPV-positive from HPV-negative patients. A substantial decrease in predictive power was observed in the validation cohort, underscoring the need for further analyses on a larger sample size.

The prognosis of a subset of patients with locally advanced oropharyngeal cancer (LA-OPC) is still poor despite improvements in patient selection and treatment. Identifying specific patient- and tumor-related factors can help to select those patients who need intensified treatment. We aimed to assess the role of historical risk factors and novel magnetic resonance imaging (MRI) biomarkers in predicting outcomes in these patients. Patients diagnosed with LA-OPC were studied with diffusion-weighted imaging (DWI) and dynamic-contrast enhanced MRI at baseline and at the 10th radiotherapy (RT) fraction. Clinical information was collected as well. The endpoint of the study was the development of disease progression, locally or distantly. Of the 97 patients enrolled, 68 were eligible for analysis. Disease progression was recorded in 21 patients (11 had loco-regional progression, 10 developed distant metastases). We found a correlation between N diameter and disease control (p = 0.02); features such as p16 status and extranodal extension only showed a trend towards statistical significance. Among perfusion MRI features, higher median values of K_ep both in primary tumor (T, p = 0.016) and lymph node (N, p = 0.003) and lower median values of v_e (p = 0.018 in T, p = 0.004 in N) correlated with better disease control. K_ep P90 and N diameter were identified by MRMR algorithm as the best predictors of outcome. In conclusion, the association of non-invasive MRI biomarkers and patients and tumor characteristics may help in predicting disease behavior and patient outcomes in order to ensure a more customized treatment.

(1) Background: Oral tongue squamous cell carcinoma (OTSCC) is a prevalent malignancy with high loco-regional recurrence. Advanced imaging biomarkers are critical for stratifying patients at a high risk of recurrence. This study aimed to develop MRI-based radiomic models to predict loco-regional recurrence in OTSCC patients undergoing surgery. (2) Methods: We retrospectively selected 92 patients with OTSCC who underwent MRI, followed by surgery and cervical lymphadenectomy. A total of 31 patients suffered from a loco-regional recurrence. Radiomic features were extracted from preoperative post-contrast high-resolution MRI and integrated with clinical and pathological data to develop predictive models, including radiomic-only and combined radiomic–clinical approaches, trained and validated with stratified data splitting. (3) Results: Textural features, such as those derived from the Gray-Level Size-Zone Matrix, Gray-Level Dependence Matrix, and Gray-Level Run-Length Matrix, showed significant associations with recurrence. The radiomic-only model achieved an accuracy of 0.79 (95% confidence interval: 0.69, 0.87) and 0.74 (95% CI: 0.54, 0.89) in the training and validation set, respectively. Combined radiomic and clinical models, incorporating features like the pathological depth of invasion and lymph node status, provided comparable diagnostic performances. (4) Conclusions: MRI-based radiomic models demonstrated the potential for predicting loco-regional recurrence, highlighting their increasingly important role in advancing precision oncology for OTSCC.