Objectives: Human papillomavirus (HPV) positive oropharyngeal cancer (oropharyngeal squamous cell carcinoma, OPSCC) is biologically and clinically different from HPV negative OPSCC. Here, we evaluate the use of a radiomic approach to identify the HPV status of OPSCC. Methods: Four independent cohorts, totaling 778 OPSCC patients with HPV determined by p16 were collected. We randomly assigned 80% of all data for model training (N = 628) and 20% for validation (N = 150). On the pre-treatment CT images, 902 radiomic features were calculated from the gross tumor volume. Multivariable modeling was performed using least absolute shrinkage and selection operator. To assess the impact of CT artifacts in predicting HPV (p16), a model was developed on all training data (Mall) and on the artifact-free subset of training data (Mno art). Models were validated on all validation data (Vall), and the subgroups with (Vart) and without (Vno art) artifacts. Kaplan–Meier survival analysis was performed to compare HPV status based on p16 and radiomic model predictions. Results: The area under the receiver operator curve for Mall and Mno art ranged between 0.70 and 0.80 and was not significantly different for all validation data sets. There was a consistent and significant split between survival curves with HPV status determined by p16 [p = 0.007; hazard ratio (HR): 0.46], Mall (p = 0.036; HR: 0.55) and Mno art (p = 0.027; HR: 0.49). Conclusion: This study provides proof of concept that molecular information can be derived from standard medical images and shows potential for radiomics as imaging biomarker of HPV status. Advances in knowledge: Radiomics has the potential to identify clinically relevant molecular phenotypes.

A major challenge in radiomics is assembling data from multiple centers. Sharing data between hospitals is restricted by legal and ethical regulations. Distributed learning is a technique, enabling training models on multicenter data without data leaving the hospitals (“privacy-preserving” distributed learning). This study tested feasibility of distributed learning of radiomics data for prediction of two year overall survival and HPV status in head and neck cancer (HNC) patients. Pretreatment CT images were collected from 1174 HNC patients in 6 different cohorts. 981 radiomic features were extracted using Z-Rad software implementation. Hierarchical clustering was performed to preselect features. Classification was done using logistic regression. In the validation dataset, the receiver operating characteristics (ROC) were compared between the models trained in the centralized and distributed manner. No difference in ROC was observed with respect to feature selection. The logistic regression coefficients were identical between the methods (absolute difference 0.05). In conclusion, both feature selection and classification are feasible in a distributed manner using radiomics data, which opens new possibility for training more reliable radiomics models.

Background: Chemoradiation or bioradiation treatment (CRT/BRT) of locally advanced head and neck squamous cell carcinoma (LAHNSCC) comes with high toxicity rates, often leading to temporary tube feeding (TF) dependency. Cachexia is a common problem in LAHNSCC. Yet changes in body composition and muscle weakness during CRT/BRT are underexplored. Strong evidence on the effect of TF on body composition during treatment is lacking. The aim of this cohort study was to assess (i) the relationship of fat‐free mass index (FFMI) and handgrip strength (HGS) with CRT/BRT toxicity and outcome, (ii) body composition in patients treated with chemoradiation (cisplatin) vs. bioradiation (cetuximab), and (iii) the effect of the current TF regime on body composition and muscle strength.Methods: Locally advanced head and neck squamous cell carcinoma patients treated with CRT/BRT between January 2013 and December 2016 were included (n = 137). Baseline measurements of body composition (bioelectrical impedance analysis) and HGS were performed. Toxicity grades (Common Terminology Criteria for Adverse Events) were scored. In a subset of 69 patients, weight loss, body composition, and HGS were additionally assessed during and after CRT/BRT. TF was initiated according to the Dutch guidelines for malnutrition.Results: In this cohort (68% male, mean age 59 ± 8 years), the incidence of baseline muscle wasting, defined as FFMI < P₁₀, was 29%. Muscle wasting was present in 23 of 100 (23%) chemoradiation patients and 17 of 37 (46%) bioradiation patients (P = 0.009). Muscle‐wasted patients required more unplanned hospitalizations during CRT (P = 0.035). In the chemoradiation subset, dose‐limiting toxicity was significantly higher in wasted vs. non‐wasted patients (57% vs. 25%, P = 0.004). Median follow‐up was 32 months. Multivariate Cox regression analysis identified muscle wasting as independent unfavourable prognostic factor for overall survival [hazard ratio 2.1 (95% CI 1.1–4.1), P = 0.022] and cisplatin as favourable prognostic factor [hazard ratio 0.3 (95% CI 0.2–0.6), P = 0.001]. Weight and HGS significantly decreased during CRT/BRT, −3.7 ± 3.5 kg (P < 0.001) and −3.1 ± 6.0 kg (P < 0.001), respectively. Sixty‐four per cent of the patients required TF 21 days (range 0–59) after CRT/BRT initiation. Total weight loss during CRT/BRT was significantly (P = 0.007) higher in the total oral diet group (5.5 ± 3.7 kg) compared with the TF group (3.0 ± 3.2 kg). Loss of FFM and HGS was similar in both groups.Conclusions: In LAHNSCC patients undergoing CRT/BRT, FFMI < P₁₀ is an unfavourable prognostic factor for overall survival, treatment toxicity, and tolerance. Patients experience significant weight and FFM loss during treatment. Current TF regime attenuates weight loss but does not overcome loss of muscle mass and function during therapy. Future interventions should consider nutritional intake and additional strategies specifically targeting metabolism, loss of muscle mass, and function.

In this study, we investigate the role of radiomics for prediction of overall survival (OS), locoregional recurrence (LRR) and distant metastases (DM) in stage III and IV HNSCC patients treated by chemoradiotherapy. We hypothesize that radiomic analysis of (peri-)tumoral tissue may detect invasion of surrounding tissues indicating a higher chance of locoregional recurrence and distant metastasis. Two comprehensive data sources were used: the Dutch Cancer Society Database (Alp 7072, DESIGN) and “Big Data To Decide” (BD2Decide). The gross tumor volumes (GTV) were delineated on contrast-enhanced CT. Radiomic features were extracted using the RadiomiX Discovery Toolbox (OncoRadiomics, Liege, Belgium). Clinical patient features such as age, gender, performance status etc. were collected. Two machine learning methods were chosen for their ability to handle censored data: Cox proportional hazards regression and random survival forest (RSF). Multivariable clinical and radiomic Cox/ RSF models were generated based on significance in univariable cox regression/ RSF analyses on the held out data in the training dataset. Features were selected according to a decreasing hazard ratio for Cox and relative importance for RSF. A total of 444 patients with radiotherapy planning CT-scans were included in this study: 301 head and neck squamous cell carcinoma (HNSCC) patients in the training cohort (DESIGN) and 143 patients in the validation cohort (BD2DECIDE). We found that the highest performing model was a clinical model that was able to predict distant metastasis in oropharyngeal cancer cases with an external validation C-index of 0.74 and 0.65 with the RSF and Cox models respectively. Peritumoral radiomics based prediction models performed poorly in the external validation, with C-index values ranging from 0.32 to 0.61 utilizing both feature selection and model generation methods. Our results suggest that radiomic features from the peritumoral regions are not useful for the prediction of time to OS, LR and DM.

Background: Locoregionally advanced head and neck squamous cell carcinoma (HNSCC) patients have high relapse and mortality rates. Imaging-based decision support may improve outcomes by optimising personalised treatment, and support patient risk stratification. We propose a multifactorial prognostic model including radiomics features to improve risk stratification for advanced HNSCC, compared to TNM eighth edition, the gold standard. Patient and methods: Data of 666 retrospective- and 143 prospective-stage III-IVA/B HNSCC patients were collected. A multivariable Cox proportional-hazards model was trained to predict overall survival (OS) using diagnostic CT-based radiomics features extracted from the primary tumour. Separate analyses were performed using TNM8, tumour volume, clinical and biological variables, and combinations thereof with radiomics features. Patient risk stratification in three groups was assessed through Kaplan–Meier (KM) curves. A log-rank test was performed for significance (p-value < 0.05). The prognostic accuracy was reported through the concordance index (CI). Results: A model combining an 11-feature radiomics signature, clinical and biological variables, TNM8, and volume could significantly stratify the validation cohort into three risk groups (p < 0∙01, CI of 0.79 as validation). Conclusion: A combination of radiomics features with other predictors can predict OS very accurately for advanced HNSCC patients and improves on the current gold standard of TNM8.