Corrigendum: Head and neck cancer treatment outcome prediction: a comparison between machine learning with conventional radiomics features and deep learning radiomics.

[This corrects the article DOI: 10.3389/fmed.2023.1217037.].

A multicentric randomized controlled phase III trial of adaptive and 18F-FDG-PET-guided dose-redistribution in locally advanced head and neck squamous cell carcinoma (ARTFORCE).

BACKGROUND AND PURPOSE: This multicenter randomized phase III trial evaluated whether locoregional control of patients with LAHNSCC could be improved by fluorodeoxyglucose-positron emission tomography (FDG-PET)-guided dose-escalation while minimizing the risk of increasing toxicity using a dose-redistribution and scheduled adaptation strategy. MATERIALS AND METHODS: Patients with T3-4-N0-3-M0 LAHNSCC were randomly assigned (1:1) to either receive a dose distribution ranging from 64-84 Gy/35 fractions with adaptation at the 10thfraction (rRT) or conventional 70 Gy/35 fractions (cRT). Both arms received concurrent three-cycle 100 mg/m2cisplatin. Primary endpoints were 2-year locoregional control (LRC) and toxicity. Primary analysis was based on the intention-to-treat principle. RESULTS: Due to slow accrual, the study was prematurely closed (at 84 %) after randomizing 221 eligible patients between 2012 and 2019 to receive rRT (N = 109) or cRT (N = 112). The 2-year LRC estimate difference of 81 % (95 %CI 74-89 %) vs. 74 % (66-83 %) in the rRT and cRT arm, respectively, was not found statistically significant (HR 0.75, 95 %CI 0.43-1.31,P=.31). Toxicity prevalence and incidence rates were similar between trial arms, with exception for a significant increased grade ≥ 3 pharyngolaryngeal stenoses incidence rate in the rRT arm (0 versus 4 %,P=.05). In post-hoc subgroup analyses, rRT improved LRC for patients with N0-1 disease (HR 0.21, 95 %CI 0.05-0.93) and oropharyngeal cancer (0.31, 0.10-0.95), regardless of HPV. CONCLUSION: Adaptive and dose redistributed radiotherapy enabled dose-escalation with similar toxicity rates compared to conventional radiotherapy. While FDG-PET-guided dose-escalation did overall not lead to significant tumor control or survival improvements, post-hoc results showed improved locoregional control for patients with N0-1 disease or oropharyngeal cancer treated with rRT.

Decisional Conflict in Patients with Advanced Laryngeal Carcinoma: A Multicenter Study.

OBJECTIVES: Decision-making for patients with a locally advanced laryngeal carcinoma (T3 and T4) is challenging due to the treatment choice between organ preservation and laryngectomy, both with different and high impact on function and quality of life (QoL). The complexity of these treatment decisions and their possible consequences might lead to decisional conflict (DC). This study aimed to explore the level of DC in locally advanced laryngeal carcinoma patients facing curative decision-making, and to identify possible associated factors. METHODS: In this multicenter prospective cohort study, participants completed questionnaires on DC, level of shared decision-making (SDM), and a knowledge test directly after counseling and 6 months after treatment. Descriptive statistics and Spearman correlation tests were used to analyze the data. RESULTS: Directly after counseling, almost all participants (44/45; 98%) experienced Clinically Significant DC score (CSDC >25, scale 0-100). On average, patients scored 47% (SD 20%) correct on the knowledge test. Questions related to radiotherapy were answered best (69%, SD 29%), whilst only 35% (SD 29%) of the questions related to laryngectomy were answered correctly. Patients' perceived level of SDM (scale 0-100) was 70 (mean, SD 16.2), and for physicians this was 70 (SD 1.7). CONCLUSION: Most patients with advanced larynx cancer experience high levels of DC. Low knowledge levels regarding treatment aspects indicate a need for better patient counseling. LEVEL OF EVIDENCE: Level IV Laryngoscope, 2024.

The development of a decision aid for patients with operable oropharyngeal carcinoma in the Netherlands - A mixed methods study.

OBJECTIVE: The aim of this project is to create an interactive online patient decision aid (PDA) for oropharyngeal cancer (OPSCC) patients, eligible for transoral (robotic) surgery with an ultimate goal to assist both physicians and patients in making treatment choices. MATERIALS AND METHODS: Following the International Patient Decision Aid Standards, a mixed-methods approach was employed. The study involved semi-structured in-depth interviews with patients and physicians, thinking-out-loud sessions, and study-specific questionnaires. Thematic coding and analysis were conducted on verbatim transcriptions of audio-recorded interviews. RESULTS: The PDA drafts were evaluated by twenty OPSCC survivors and twenty multidisciplinary specialists. Significant revisions were made after phase 1 to enhance readability and reduce text, whilst incorporating videos and graphics. Following all phases, both patients and specialists rated the PDA as comprehensible, feasible, and a valuable addition to regular counseling. CONCLUSION: This study showcases the development of a PDA for early stage oropharyngeal cancer patients considering surgery and radiotherapy options. The decision aid emphasizes the disparities in short- and long-term side effects between the two treatments. Patients and physicians found the decision aid to be understandable, user-friendly, and helpful for future patients. The PDA is available on https://beslissamen.nl/.

Image based prognosis in head and neck cancer using convolutional neural networks: a case study in reproducibility and optimization.

In the past decade, there has been a sharp increase in publications describing applications of convolutional neural networks (CNNs) in medical image analysis. However, recent reviews have warned of the lack of reproducibility of most such studies, which has impeded closer examination of the models and, in turn, their implementation in healthcare. On the other hand, the performance of these models is highly dependent on decisions on architecture and image pre-processing. In this work, we assess the reproducibility of three studies that use CNNs for head and neck cancer outcome prediction by attempting to reproduce the published results. In addition, we propose a new network structure and assess the impact of image pre-processing and model selection criteria on performance. We used two publicly available datasets: one with 298 patients for training and validation and another with 137 patients from a different institute for testing. All three studies failed to report elements required to reproduce their results thoroughly, mainly the image pre-processing steps and the random seed. Our model either outperforms or achieves similar performance to the existing models with considerably fewer parameters. We also observed that the pre-processing efforts significantly impact the model's performance and that some model selection criteria may lead to suboptimal models. Although there have been improvements in the reproducibility of deep learning models, our work suggests that wider implementation of reporting standards is required to avoid a reproducibility crisis.

A clinicogenomic model including GARD predicts outcome for radiation treated patients with HPV+ oropharyngeal squamous cell carcinoma.

Background: Treatment decision-making in oropharyngeal squamous cell carcinoma (OPSCC) includes clinical stage, HPV status, and smoking history. Despite improvements in staging with separation of HPV-positive and -negative OPSCC in AJCC 8th edition (AJCC8), patients are largely treated with a uniform approach, with recent efforts focused on de-intensification in low-risk patients. We have previously shown, in a pooled analysis, that the genomic adjusted radiation dose (GARD) is predictive of radiation treatment benefit and can be used to guide RT dose selection. We hypothesize that GARD can be used to predict overall survival (OS) in HPV-positive OPSCC patients treated with radiotherapy (RT). Methods: Gene expression profiles (Affymetrix Clariom D) were analyzed for 234 formalin-fixed paraffin-embedded samples from HPV-positive OPSCC patients within an international, multi-institutional, prospective/retrospective observational study including patients with AJCC 7th edition stage III-IVb. GARD, a measure of the treatment effect of RT, was calculated for each patient as previously described. In total, 191 patients received primary RT definitive treatment (chemoradiation or RT alone, and 43 patients received post-operative RT. Two RT dose fractionations were utilized for primary RT cases (70 Gy in 35 fractions or 69.96 Gy in 33 fractions). Median RT dose was 70 Gy (range 50.88-74) for primary RT definitive cases and 66 Gy (range 44-70) for post-operative RT cases. The median follow up was 46.2 months (95% CI, 33.5-63.1). Cox proportional hazards analyses were performed with GARD as both a continuous and dichotomous variable and time-dependent ROC analyses compared the performance of GARD with the NRG clinical nomogram for overall survival. Results: Despite uniform radiation dose utilization, GARD showed significant heterogeneity (range 30-110), reflecting the underlying genomic differences in the cohort. On multivariable analysis, each unit increase in GARD was associated with an improvement in OS (HR = 0.951 (0.911, 0.993), p = 0.023) compared to AJCC8 (HR = 1.999 (0.791, 5.047)), p = 0.143). ROC analysis for GARD at 36 months yielded an AUC of 80.6 (69.4, 91.9) compared with an AUC of 73.6 (55.4, 91.7) for the NRG clinical nomogram. GARD≥64.2 was associated with improved OS (HR = 0.280 (0.100, 0.781), p = 0.015). In a virtual trial, GARD predicts that uniform RT dose de-escalation results in overall inferior OS but proposes two separate genomic strategies where selective RT dose de-escalation in GARD-selected populations results in clinical equipoise. Conclusions: In this multi-institutional cohort of patients with HPV-positive OPSCC, GARD predicts OS as a continuous variable, outperforms the NRG nomogram and provides a novel genomic strategy to modern clinical trial design. We propose that GARD, which provides the first opportunity for genomic guided personalization of radiation dose, should be incorporated in the diagnostic workup of HPV-positive OPSCC patients.

Head and neck cancer treatment outcome prediction: a comparison between machine learning with conventional radiomics features and deep learning radiomics.

Background: Radiomics can provide in-depth characterization of cancers for treatment outcome prediction. Conventional radiomics rely on extraction of image features within a pre-defined image region of interest (ROI) which are typically fed to a classification algorithm for prediction of a clinical endpoint. Deep learning radiomics allows for a simpler workflow where images can be used directly as input to a convolutional neural network (CNN) with or without a pre-defined ROI. Purpose: The purpose of this study was to evaluate (i) conventional radiomics and (ii) deep learning radiomics for predicting overall survival (OS) and disease-free survival (DFS) for patients with head and neck squamous cell carcinoma (HNSCC) using pre-treatment 18F-fluorodeoxuglucose positron emission tomography (FDG PET) and computed tomography (CT) images. Materials and methods: FDG PET/CT images and clinical data of patients with HNSCC treated with radio(chemo)therapy at Oslo University Hospital (OUS; n = 139) and Maastricht University Medical Center (MAASTRO; n = 99) were collected retrospectively. OUS data was used for model training and initial evaluation. MAASTRO data was used for external testing to assess cross-institutional generalizability. Models trained on clinical and/or conventional radiomics features, with or without feature selection, were compared to CNNs trained on PET/CT images without or with the gross tumor volume (GTV) included. Model performance was measured using accuracy, area under the receiver operating characteristic curve (AUC), Matthew's correlation coefficient (MCC), and the F1 score calculated for both classes separately. Results: CNNs trained directly on images achieved the highest performance on external data for both endpoints. Adding both clinical and radiomics features to these image-based models increased performance further. Conventional radiomics including clinical data could achieve competitive performance. However, feature selection on clinical and radiomics data lead to overfitting and poor cross-institutional generalizability. CNNs without tumor and node contours achieved close to on-par performance with CNNs including contours. Conclusion: High performance and cross-institutional generalizability can be achieved by combining clinical data, radiomics features and medical images together with deep learning models. However, deep learning models trained on images without contours can achieve competitive performance and could see potential use as an initial screening tool for high-risk patients.

The extent of unnecessary tooth loss due to extractions prior to radiotherapy based on radiation field and dose in patients with head and neck cancer.

BACKGROUND AND PURPOSE: Prior to radiotherapy (RT), teeth with poor prognosis that pose a risk for post-RT osteoradionecrosis (ORN) are removed. To allow enough time for adequate wound healing prior to RT, decisions are made based on the estimated radiation dose. This study aimed to gain insight into (1) the overall number of teeth extracted and (2) the patient and tumor characteristics associated with the number of redundantly extracted teeth. MATERIALS AND METHODS: Patients with head and neck cancer (HNC), treated with RT between 2015 and 2019, were included in this cross-sectional study. For each extracted tooth the radiation dose was calculated retrospectively. The cut-off point for valid extraction was set at ≥ 40 Gy in accordance with the national protocol. Potential factors for doses ≥ 40 Gy were identified, including age, sex, tumor location, tumor (T) and nodal stage (N), overall tumor stage and number of teeth extracted. RESULTS: A total of 1759 teeth were removed from 358 patients. Of these 1759 teeth, 1274 (74%) appeared to have been removed redundantly, based on the mean dose (Dmean) of < 40 Gy. Using the maximum dose (Dmax) of < 40 Gy, 1080 teeth (61%) appeared to have been removed redundantly. Tumor location and N-classification emerged as the most important associative variables in the multivariable regression analysis. CONCLUSION: To our knowledge this is the first study to provide insight into the amount of teeth redundantly extracted prior to RT and represents a step forward in de-escalating the damage to the masticatory system prior to RT.

Development and Validation of an Automated Image-Based Deep Learning Platform for Sarcopenia Assessment in Head and Neck Cancer.

Importance: Sarcopenia is an established prognostic factor in patients with head and neck squamous cell carcinoma (HNSCC); the quantification of sarcopenia assessed by imaging is typically achieved through the skeletal muscle index (SMI), which can be derived from cervical skeletal muscle segmentation and cross-sectional area. However, manual muscle segmentation is labor intensive, prone to interobserver variability, and impractical for large-scale clinical use. Objective: To develop and externally validate a fully automated image-based deep learning platform for cervical vertebral muscle segmentation and SMI calculation and evaluate associations with survival and treatment toxicity outcomes. Design, Setting, and Participants: For this prognostic study, a model development data set was curated from publicly available and deidentified data from patients with HNSCC treated at MD Anderson Cancer Center between January 1, 2003, and December 31, 2013. A total of 899 patients undergoing primary radiation for HNSCC with abdominal computed tomography scans and complete clinical information were selected. An external validation data set was retrospectively collected from patients undergoing primary radiation therapy between January 1, 1996, and December 31, 2013, at Brigham and Women's Hospital. The data analysis was performed between May 1, 2022, and March 31, 2023. Exposure: C3 vertebral skeletal muscle segmentation during radiation therapy for HNSCC. Main Outcomes and Measures: Overall survival and treatment toxicity outcomes of HNSCC. Results: The total patient cohort comprised 899 patients with HNSCC (median [range] age, 58 [24-90] years; 140 female [15.6%] and 755 male [84.0%]). Dice similarity coefficients for the validation set (n = 96) and internal test set (n = 48) were 0.90 (95% CI, 0.90-0.91) and 0.90 (95% CI, 0.89-0.91), respectively, with a mean 96.2% acceptable rate between 2 reviewers on external clinical testing (n = 377). Estimated cross-sectional area and SMI values were associated with manually annotated values (Pearson r = 0.99; P < .001) across data sets. On multivariable Cox proportional hazards regression, SMI-derived sarcopenia was associated with worse overall survival (hazard ratio, 2.05; 95% CI, 1.04-4.04; P = .04) and longer feeding tube duration (median [range], 162 [6-1477] vs 134 [15-1255] days; hazard ratio, 0.66; 95% CI, 0.48-0.89; P = .006) than no sarcopenia. Conclusions and Relevance: This prognostic study's findings show external validation of a fully automated deep learning pipeline to accurately measure sarcopenia in HNSCC and an association with important disease outcomes. The pipeline could enable the integration of sarcopenia assessment into clinical decision making for individuals with HNSCC.

Multi-centre radiomics for prediction of recurrence following radical radiotherapy for head and neck cancers: Consequences of feature selection, machine learning classifiers and batch-effect harmonization.

Background and purpose: Radiomics models trained with limited single institution data are often not reproducible and generalisable. We developed radiomics models that predict loco-regional recurrence within two years of radiotherapy with private and public datasets and their combinations, to simulate small and multi-institutional studies and study the responsiveness of the models to feature selection, machine learning algorithms, centre-effect harmonization and increased dataset sizes. Materials and methods: 562 patients histologically confirmed and treated for locally advanced head-and-neck cancer (LA-HNC) from two public and two private datasets; one private dataset exclusively reserved for validation. Clinical contours of primary tumours were not recontoured and were used for Pyradiomics based feature extraction. ComBat harmonization was applied, and LASSO-Logistic Regression (LR) and Support Vector Machine (SVM) models were built. 95% confidence interval (CI) of 1000 bootstrapped area-under-the-Receiver-operating-curves (AUC) provided predictive performance. Responsiveness of the models' performance to the choice of feature selection methods, ComBat harmonization, machine learning classifier, single and pooled data was evaluated. Results: LASSO and SelectKBest selected 14 and 16 features, respectively; three were overlapping. Without ComBat, the LR and SVM models for three institutional data showed AUCs (CI) of 0.513 (0.481-0.559) and 0.632 (0.586-0.665), respectively. Performances following ComBat revealed AUCs of 0.559 (0.536-0.590) and 0.662 (0.606-0.690), respectively. Compared to single cohort AUCs (0.562-0.629), SVM models from pooled data performed significantly better at AUC = 0.680. Conclusions: Multi-institutional retrospective data accentuates the existing variabilities that affect radiomics. Carefully designed prospective, multi-institutional studies and data sharing are necessary for clinically relevant head-and-neck cancer prognostication models.

Machine learning for normal tissue complication probability prediction: Predictive power with versatility and easy implementation.

Background and purpose: A popular Normal tissue Complication (NTCP) model deployed to predict radiotherapy (RT) toxicity is the Lyman-Burman Kutcher (LKB) model of tissue complication. Despite the LKB model's popularity, it can suffer from numerical instability and considers only the generalized mean dose (GMD) to an organ. Machine learning (ML) algorithms can potentially offer superior predictive power of the LKB model, and with fewer drawbacks. Here we examine the numerical characteristics and predictive power of the LKB model and compare these with those of ML. Materials and methods: Both an LKB model and ML models were used to predict G2 Xerostomia on patients following RT for head and neck cancer, using the dose volume histogram of parotid glands as the input feature. Model speed, convergence characteristics and predictive power was evaluated on an independent training set. Results: We found that only global optimization algorithms could guarantee a convergent and predictive LKB model. At the same time our results showed that ML models remained unconditionally convergent and predictive, while staying robust to gradient descent optimization. ML models outperform LKB in Brier score and accuracy but compare to LKB in ROC-AUC. Conclusion: We have demonstrated that ML models can quantify NTCP better than or as well as LKB models, even for a toxicity that the LKB model is particularly well suited to predict. ML models can offer this performance while offering fundamental advantages in model convergence, speed, and flexibility, and so could offer an alternative to the LKB model that could potentially be used in clinical RT planning decisions.

Changes in survival in de novo metastatic cancer in an era of new medicines.

BACKGROUND: Over the past decades, the therapeutic landscape has markedly changed for patients with metastatic solid cancer, yet few studies have evaluated its effect on population-based survival. The objective of this study was to evaluate the change in survival of patients with de novo metastatic solid cancers during the last 30 years. METHODS: For this retrospective study, data from almost 2 million patients diagnosed with a solid cancer between January 1, 1989, and December 31, 2018, were obtained from the Netherlands Cancer Registry, with follow-up until January 31, 2021. We classified patients as with or without de novo metastatic disease (M1 or M0, respectively) at diagnosis and determined the proportion with M1 disease over time. Changes in age-standardized net survival were calculated as the difference in the 1- and 5-year survival rates of patients diagnosed in 1989-1993 and 2014-2018. RESULTS: Different cancers showed divergent trends in the proportion of M1 disease and increases in net survival for M1 disease (approximately 0-50 percentage points at both 1 and 5 years). Patients with gastrointestinal stromal tumors saw the largest increases in 5-year survival, but we also observed substantial 5-year survival increases for patients with neuroendocrine tumors, melanoma, prostate cancer, and breast cancer. CONCLUSION: Over 30 years, the survival of patients with de novo M1 disease modestly and unevenly increased among cancers. Metastatic cancer still remains a very lethal disease. Next to better treatment options, we call for better preventive measures and early detection to reduce the incidence of metastatic disease.

Fully-automated sarcopenia assessment in head and neck cancer: development and external validation of a deep learning pipeline.

Purpose: Sarcopenia is an established prognostic factor in patients diagnosed with head and neck squamous cell carcinoma (HNSCC). The quantification of sarcopenia assessed by imaging is typically achieved through the skeletal muscle index (SMI), which can be derived from cervical neck skeletal muscle (SM) segmentation and cross-sectional area. However, manual SM segmentation is labor-intensive, prone to inter-observer variability, and impractical for large-scale clinical use. To overcome this challenge, we have developed and externally validated a fully-automated image-based deep learning (DL) platform for cervical vertebral SM segmentation and SMI calculation, and evaluated the relevance of this with survival and toxicity outcomes. Materials and Methods: 899 patients diagnosed as having HNSCC with CT scans from multiple institutes were included, with 335 cases utilized for training, 96 for validation, 48 for internal testing and 393 for external testing. Ground truth single-slice segmentations of SM at the C3 vertebra level were manually generated by experienced radiation oncologists. To develop an efficient method of segmenting the SM, a multi-stage DL pipeline was implemented, consisting of a 2D convolutional neural network (CNN) to select the middle slice of C3 section and a 2D U-Net to segment SM areas. The model performance was evaluated using the Dice Similarity Coefficient (DSC) as the primary metric for the internal test set, and for the external test set the quality of automated segmentation was assessed manually by two experienced radiation oncologists. The L3 skeletal muscle area (SMA) and SMI were then calculated from the C3 cross sectional area (CSA) of the auto-segmented SM. Finally, established SMI cut-offs were used to perform further analyses to assess the correlation with survival and toxicity endpoints in the external institution with univariable and multivariable Cox regression. Results: DSCs for validation set (n = 96) and internal test set (n = 48) were 0.90 (95% CI: 0.90 - 0.91) and 0.90 (95% CI: 0.89 - 0.91), respectively. The predicted CSA is highly correlated with the ground-truth CSA in both validation (r = 0.99, p < 0.0001) and test sets (r = 0.96, p < 0.0001). In the external test set (n = 377), 96.2% of the SM segmentations were deemed acceptable by consensus expert review. Predicted SMA and SMI values were highly correlated with the ground-truth values, with Pearson r ß 0.99 (p < 0.0001) for both the female and male patients in all datasets. Sarcopenia was associated with worse OS (HR 2.05 [95% CI 1.04 - 4.04], p = 0.04) and longer PEG tube duration (median 162 days vs. 134 days, HR 1.51 [95% CI 1.12 - 2.08], p = 0.006 in multivariate analysis. Conclusion: We developed and externally validated a fully-automated platform that strongly correlates with imaging-assessed sarcopenia in patients with H&N cancer that correlates with survival and toxicity outcomes. This study constitutes a significant stride towards the integration of sarcopenia assessment into decision-making for individuals diagnosed with HNSCC. SUMMARY STATEMENT: In this study, we developed and externally validated a deep learning model to investigate the impact of sarcopenia, defined as the loss of skeletal muscle mass, on patients with head and neck squamous cell carcinoma (HNSCC) undergoing radiotherapy. We demonstrated an efficient, fullyautomated deep learning pipeline that can accurately segment C3 skeletal muscle area, calculate cross-sectional area, and derive a skeletal muscle index to diagnose sarcopenia from a standard of care CT scan. In multi-institutional data, we found that pre-treatment sarcopenia was associated with significantly reduced overall survival and an increased risk of adverse events. Given the increased vulnerability of patients with HNSCC, the assessment of sarcopenia prior to radiotherapy may aid in informed treatment decision-making and serve as a predictive marker for the necessity of early supportive measures.

The relation between prediction model performance measures and patient selection outcomes for proton therapy in head and neck cancer.

BACKGROUND: Normal-tissue complication probability (NTCP) models predict complication risk in patients receiving radiotherapy, considering radiation dose to healthy tissues, and are used to select patients for proton therapy, based on their expected reduction in risk after proton therapy versus photon radiotherapy (ΔNTCP). Recommended model evaluation measures include area under the receiver operating characteristic curve (AUC), overall calibration (CITL), and calibration slope (CS), whose precise relation to patient selection is still unclear. We investigated how each measure relates to patient selection outcomes. METHODS: The model validation and consequent patient selection process was simulated within empirical head and neck cancer patient data. By manipulating performance measures independently via model perturbations, the relation between model performance and patient selection was studied. RESULTS: Small reductions in AUC (-0.02) yielded mean changes in ΔNTCP between 0.9-3.2 %, and single-model patient selection differences between 2-19 %. Deviations (-0.2 or +0.2) in CITL or CS yielded mean changes in ΔNTCP between 0.3-1.4 %, and single-model patient selection differences between 1-10 %. CONCLUSIONS: Each measure independently impacts ΔNTCP and patient selection and should thus be assessed in a representative sufficiently large external sample. Our suggested practical model selection approach is considering the model with the highest AUC, and recalibrating it if needed.

Oropharyngeal dysphagia and cachexia: Intertwined in head and neck cancer.

BACKGROUND: This study aims to investigate the relationship between cancer cachexia and oropharyngeal dysphagia (OD) in patients with head and neck cancer (HNC) prior to chemoradiotherapy or bioradiotherapy (CRT/BRT). METHODS: A prospective cohort study with patients with HNC undergoing CRT/BRT (2018-2021) was conducted. Body composition and skeletal muscle function were evaluated using bioelectrical impedance analysis, handgrip strength, and the short physical performance battery (SPPB). The M. D. Anderson Dysphagia Inventory (MDADI), Eating Assessment Tool (EAT)-10 questionnaire, and patient characteristics were collected. A standardized videofluoroscopic swallowing study was offered to patients. RESULTS: Sixty-six patients were included. Twenty-six patients scored EAT-10 ≥ 3 and seventeen were cachectic. ACE-27 score >1, cachexia, abnormal SPPB-derived repeated chair-stand test, lower MDADI scores, and higher overall stage grouping showed potential predictive value (p ≤ 0.10) for EAT-10 ≥ 3. Using multivariable regression analysis, only cachexia remained a significant predictor of EAT-10 ≥ 3 (HR 9.000 [95%CI 2.483-32.619], p = 0.001). CONCLUSION: Cachexia independently predicted the presence of patient-reported OD.

Immune-based classification of HPV-associated oropharyngeal cancer with implications for biomarker-driven treatment de-intensification.

BACKGROUND: There is significant interest in treatment de-escalation for human papillomavirus-associated (HPV+) oropharyngeal squamous cell carcinoma (OPSCC) patients given the generally favourable prognosis. However, 15-30% of patients recur after primary treatment, reflecting a need for improved risk-stratification tools. We sought to develop a molecular test to risk stratify HPV+ OPSCC patients. METHODS: We created an immune score (UWO3) associated with survival outcomes in six independent cohorts comprising 906 patients, including blinded retrospective and prospective external validations. Two aggressive radiation de-escalation cohorts were used to assess the ability of UWO3 to identify patients who recur. Multivariate Cox models were used to assess the associations between the UWO3 immune class and outcomes. FINDINGS: A three-gene immune score classified patients into three immune classes (immune rich, mixed, or immune desert) and was strongly associated with disease-free survival in six datasets, including large retrospective and prospective datasets. Pooled analysis demonstrated that the immune rich group had superior disease-free survival compared to the immune desert (HR = 9.0, 95% CI: 3.2-25.5, P = 3.6 × 10-5) and mixed (HR = 6.4, 95% CI: 2.2-18.7, P = 0.006) groups after adjusting for age, sex, smoking status, and AJCC8 clinical stage. Finally, UWO3 was able to identify patients from two small treatment de-escalation cohorts who remain disease-free after aggressive de-escalation to 30 Gy radiation. INTERPRETATION: With additional prospective validation, the UWO3 score could enable biomarker-driven clinical decision-making for patients with HPV+ OPSCC based on robust outcome prediction across six independent cohorts. Prospective de-escalation and intensification clinical trials are currently being planned. FUNDING: CIHR, European Union, and the NIH.

Clinical implementation and validation of an automated adaptive workflow for proton therapy.

Background and purpose: Treatment quality of proton therapy can be monitored by repeat-computed tomography scans (reCTs). However, manual re-delineation of target contours can be time-consuming. To improve the workflow, we implemented an automated reCT evaluation, and assessed if automatic target contour propagation would lead to the same clinical decision for plan adaptation as the manual workflow. Materials and methods: This study included 79 consecutive patients with a total of 250 reCTs which had been manually evaluated. To assess the feasibility of automated reCT evaluation, we propagated the clinical target volumes (CTVs) deformably from the planning-CT to the reCTs in a commercial treatment planning system. The dose-volume-histogram parameters were extracted for manually re-delineated (CTVmanual) and deformably mapped target contours (CTVauto). It was compared if CTVmanual and CTVauto both satisfied/failed the clinical constraints. Duration of the reCT workflows was also recorded. Results: In 92% (N = 229) of the reCTs correct flagging was obtained. Only 4% (N = 9) of the reCTs presented with false negatives (i.e., at least one clinical constraint failed for CTVmanual, but all constraints were satisfied for CTVauto), while 5% (N = 12) of the reCTs led to a false positive. Only for one false negative reCT a plan adaption was made in clinical practice, i.e., only one adaptation would have been missed, suggesting that automated reCT evaluation was possible. Clinical introduction hereof led to a time reduction of 49 h (from 65 to 16 h). Conclusion: Deformable target contour propagation was clinically acceptable. A script-based automatic reCT evaluation workflow has been introduced in routine clinical practice.

Independent validation of a dysphagia dose response model for the selection of head and neck cancer patients to proton therapy.

Background and purpose: The model based approach involves the use of normal tissue complication models for selection of head and neck cancer patients to proton therapy. Our goal was to validate the clinical utility of the related dysphagia model using an independent patient cohort. Materials and Methods: A dataset of 277 head and neck cancer (pharynx and larynx) patients treated with (chemo)radiotherapy between 2019 and 2021 was acquired. For the evaluation of the model discrimination we used statistical metrics such as the sensitivity, specificity and the area under the receiver operating characteristic curve. After the validation we evaluated if the dysphagia model can be improved using the closed testing procedure, the Brier and the Hosmer-Lemeshow score. Results: The performance of the original normal tissue complication probability model for dysphagia grade II-IV at 6 months was good (AUC = 0.80). According to the graphical calibration assessment, the original model showed underestimated dysphagia risk predictions. The closed testing procedure indicated that the model had to be updated and selected a revised model with new predictor coefficients as an optimal model. The revised model had also satisfactory discrimination (AUC = 0.83) with improved calibration. Conclusion: The validation of the normal tissue complication probability model for grade II-IV dysphagia was successful in our independent validation cohort. However, the closed testing procedure indicated that the model should be updated with new coefficients.

Disease outcome and associated factors after definitive platinum based chemoradiotherapy for advanced stage HPV-negative head and neck cancer.

BACKGROUND: Definitive concomitant cisplatin-based chemoradiotherapy (CRT) is the current gold standard for most patients with advanced stage head and neck squamous cell carcinoma (HNSCC) of the pharynx and larynx. Since previous meta-analysis on CRT outcomes in HNSCC have been reported, advances have been made in radiotherapy techniques and clinical management, while HPV-status has been identified as a strong confounding prognostic factor in oropharyngeal cancer. Here, we present real-world outcome data from a large multicenter cohort of HPV-negative advanced stage HNSCC treated with CRT using contemporary IMRT-based techniques. METHOD: Retrospective data were collected from a multicenter cohort of 513 patients treated with definitive concurrent platinum-based CRT with curative intent between January 2009 and August 2017. Only patients with HPV-negative advanced stage (III-IV) HNSCC were included. A prognostic model for outcome was developed based on clinical parameters and compared to TNM. RESULTS: Nearly half of the 513 patients (49%) had an oropharyngeal tumor, often locally advanced (73.3% T3-T4b) and with involvement of the regional lymph nodes (84%). Most patients (84%) received cisplatin as single agent. In total 66% received the planned number of cycles and 75% reached a cumulative cisplatin dose of ≥200 mg/m2. Locoregional control was achieved in 324 (63%) patients during follow-up, and no association with tumor sites was observed (p = 0.48). Overall survival at 5 year follow-up was 47%, with a better survival for laryngeal cancer (p = 0.02) compared to other sites. A model with clinical variables (gender, high pre-treatment weight loss, N2c/N3-stage and <200 mg/m2 dose of cisplatin) provided a noticeably stronger association with overall survival than TNM-staging (C- index 0.68 vs 0.55). Simultaneous Integrated Boosting (SIB) significantly outperformed Sequential Boosting (SEQ) to reduce the development of distant metastasis (SEQ vs SIB: OR 1.91 (1.11-3.26; p = 0.02). CONCLUSION: Despite advances in clinical management, more than a third of patients with HPV-negative HNSCC do not complete CRT treatment protocols due to cisplatin toxicity. A model that consists of clinical variables and treatment parameters including cisplatin dose provided the strongest association with overall survival. Since cisplatin toxicity is a major obstacle in completing definitive CRT, the development of alternative and less toxic radiosensitizers is therefore warranted to improve treatment results. The association of RT-boost technique with distant metastasis is an important finding and requires further study.