Background: Oropharyngeal squamous cell carcinoma (OPSCC) not associated with the human papillomavirus (HPV) have a poor prognosis compared to their HPV-associated counterpart. In literature diffusion-weighted imaging (DWI) shows great potential as a biomarker for treatment response in HPV-associates OPSCC. For this study the possibility of using DWI parameters as biomarker for treatment response during treatment of HPV-negative OPSCC is investigated. Tumor size and shrinkage have also been investigated.
Methods: In this study sixteen patients with HPV-negative OPSCC who underwent (chemo-)radiotherapy have been included. All are current and/or former smokers. At two time point an DWI-MRI scan took place, before and 2 weeks into treatment. The mean apparent diffusion coefficient (ADC) and Non-Gaussian Intravoxel Incoherent Motion Imaging (NG-IVIM) parameters based on the gross tumor volume (GTV) have been calculated. The parameters and differences in parameters have been compared between patients that responded well to treatment and patients with progressive disease.
Results: At pre- and midtreatment no significant differences have been found between the Complete Response (CR) and Progressive Disease(PD) patient groups. Diffusion coefficient D showed a significant change between pre- and midtreatment, with an increase for PD and decrease for CR. When comparing the residual region to the region that had disappeared after two weeks based on pretreatment data significant differences have been found in ADC, D and f for CR, as well as f for PD.
Conclusion: Changes in D during treatment have shown to be a significant predictor for treatment response. However this study is limited by a small patient group and more research with larger cohorts and additional biomarkers is needed to develop reliable clinical decision-making tools.

Background: Oropharyngeal squamous cell carcinoma (OPSCC) not associated with the human papillomavirus (HPV) have a poor prognosis compared to their HPV-associated counterpart. In literature diffusion-weighted imaging (DWI) shows great potential as a biomarker for treatment response in HPV-associates OPSCC. For this study the possibility of using DWI parameters as biomarker for treatment response during treatment of HPV-negative OPSCC is investigated. Tumor size and shrinkage have also been investigated.
Methods: In this study sixteen patients with HPV-negative OPSCC who underwent (chemo-)radiotherapy have been included. All are current and/or former smokers. At two time point an DWI-MRI scan took place, before and 2 weeks into treatment. The mean apparent diffusion coefficient (ADC) and Non-Gaussian Intravoxel Incoherent Motion Imaging (NG-IVIM) parameters based on the gross tumor volume (GTV) have been calculated. The parameters and differences in parameters have been compared between patients that responded well to treatment and patients with progressive disease.
Results: At pre- and midtreatment no significant differences have been found between the Complete Response (CR) and Progressive Disease(PD) patient groups. Diffusion coefficient D showed a significant change between pre- and midtreatment, with an increase for PD and decrease for CR. When comparing the residual region to the region that had disappeared after two weeks based on pretreatment data significant differences have been found in ADC, D and f for CR, as well as f for PD.
Conclusion: Changes in D during treatment have shown to be a significant predictor for treatment response. However this study is limited by a small patient group and more research with larger cohorts and additional biomarkers is needed to develop reliable clinical decision-making tools.

Background: Histopathological examination in the diagnostic workflow of oropharyngeal squamous cell carcinoma (OPSCC) is essential. We aimed to develop a machine learning pipeline to predict human papillomavirus (HPV) status in OPSCC patients based on clinical variables and multiparametric magnetic resonance imaging (MRI).
Methods: In a dataset of OPSCC patients (n=59), we extracted features from three categories: clinical variables; histogram parameters from diffusion weighted imaging (DWI)-MRI model; radiomics based on T2-weighted and DWI-MRI. We performed ten-times repeated stratified five-fold cross-validation and divided each outer training set (80%) into an inner training set (80% of outer training set) and validation set (20% of outer training set) using five-fold stratified cross-validation. We performed three types of feature selection methods (LASSO, statistical analysis and manual selection), tuned and trained seven classifiers (logistic regression, k-nearest-neighbours, naive bayes, random forest, support vector machine, XGBoost and LightGBM) to find the optimal combination of features, hyperparameters and classifier on each inner training set. We ensembled the inner fold models to fit on the outer training set and tested on the outer test set (20%). We constructed additional models with subsets of the features.
Results: the combined model area under the curve was 0.793±0.136. Models including clinical features outperformed models without clinical features (p<0.001). Features from all feature categories were selected for the combined model.
Conclusion: we were able to predict HPV status in OPSCC patients using multiparametric MRI and clinical variables with reasonable accuracy, though retraining and validating on larger, external datasets is needed before implementation in clinic.