A nomogram combining clinical variables and MR imaging features for predicting response in head-neck cancer

Objectives This study aims to develop a multimodal nomogram to predict neoadjuvant chemoimmunotherapy (NCIT) outcomes in head and neck squamous cell carcinoma (HNSCC). Materials and methods Treatment-naive HNSCC patients receiving neoadjuvant NCIT were retrospectively analyzed. Clinical information, conventional MR imaging features, dynamic contrast-enhanced-MRI (DCE-MRI) parameters and ADC values were analyzed in relation to pathological complete response (pCR). The predictive accuracy of clinical and MRI parameters was evaluated using the receiver operating characteristic (ROC) curve, with the area under the curve (AUC) serving as a key metric. Results Following NCIT, 55.0% (67/122) of patients achieved pCR. Significant differences were observed in clinical variables, including tumor location, combined positive score (CPS) and neutrophil-to-lymphocyte ratio (NLR) between pCR and non-pCR groups ( p < 0.05). Imaging features (tumor margin, growth pattern, T2 homogeneity, necrosis, three distinct enhancement patterns, tumor diameter and lymph node short-axis diameter) also differed significantly ( p < 0.05). The enhancement pattern was the most efficient predictor of pCR (AUC = 0.83). A combined model incorporating CPS, tumor diameter, and enhancement pattern achieved an AUC of 0.86. The baseline K trans and ADC values demonstrated an AUC of 0.712 and 0.715 for pCR prediction. The H&E-stained whole-slide analyses revealed significant correlations between specific MRI features and tumor lymphocyte densities/ratios. Conclusions We developed a novel combined model integrating CPS and routine pretreatment MRI features to predict NCIT response in HNSCC. The enhancement pattern was the strongest predictor of pCR, while functional MRI parameters also showed significant predictive value. Critical relevance statement This study demonstrates that systematically integrating combined positive score with routine pretreatment MRI features can effectively predict neoadjuvant chemoimmunotherapy response. These findings may help optimize therapeutic strategies for head and neck squamous cell carcinoma. Key Points Predicting neoadjuvant chemoimmunotherapy response in head and neck cancer remains challenging. A novel clinical-MRI model improves chemoimmunotherapy response prediction in head-neck cancer. The three enhancement patterns emerged as the most robust predictors. Graphical Abstract