PURPOSE:Aiming for personalization of elective clinical target volumes (CTV), we are reporting on regional lymphatic spread patterns in laryngeal squamous cell carcinoma (SCC), considering not only subsite, T-stage, and lateralization of the primary tumor, but also involvement of adjacent lymph node levels (LNLs). METHODS AND MATERIALS:LNL involvement in 1005 patients with laryngeal SCC treated at University Hospital Zurich between 2013 and 2021 and UMCG Groningen between 2006 and 2023 was analyzed. LNL involvement was assessed based on imaging and, if available, pathology. Patterns of LNL involvement can be visualized on https://lyprox.org/. RESULTS:For T2-glottic tumors (N = 193), involvement was <4% in all LNLs, supporting the hypothesis that ENI could potentially be omitted. In T3/T4-glottic patients without ipsilateral LNL II involvement (N = 198), involvement of LNLs III and IV was 5% and 1%, suggesting that ENI of LNL IV could be omitted in cN0 patients. For T3/T4-glottic tumors (N = 239) almost no contralateral involvement was observed for lateralized tumors (N = 37), suggesting contralateral treatment could potentially be omitted or limited to LNL II in patients with clinically negative contralateral neck. For supraglottic SCC without midline extension of the primary tumor (N = 75), contralateral LNL involvement was below 3%. In patients with midline extension but without contralateral LNL II involvement (N = 193), involvement of downstream levels was rare (LNL III 5%, LNL IV 3%). CONCLUSIONS:We provided detailed information about lymphatic spread patterns of laryngeal SCC, depending on subsite, T-stage, lateralization, and upstream involvement. Subgroups of patients can be identified in whom the elective CTV or surgical approach may be reduced compared to current guidelines.

Importance:Adverse effects of cancer and its treatment may hamper return to work (RTW) among patients with head and neck cancer (HNC). Objectives:To investigate RTW among patients with HNC from end of treatment to 5 years after treatment and associations of RTW with sociodemographic, clinical, work-related, personal, lifestyle, physical, and psychological factors and cancer-related symptoms. Design, Setting and Participants:This prospective, longitudinal, multicenter cohort study of patients with HNC used data from the Netherlands Quality of Life and Biomedical cohort. This study focused on patients younger than 65 years (with a subanalysis of patients younger than 60 years) from time of cancer diagnosis (March 2014 to June 2018) to 5 years after end of treatment (January 2019 to July 2023). Data analysis occurred from April 2023 to August 2024. Exposure:Standard clinical care. Main Outcomes and Measures:Work status was measured at 3 and 6 months, and 1, 2, 3, 4, and 5 years after treatment using an adjusted version of the Productivity Cost Questionnaire. Cox regression analyses were performed to investigate factors (baseline, 3 months, and 6 months) associated with time to RTW. Results:A total of 184 patients with HNC younger than 65 years (mean [SD] age, 55.4 [7.0] years; 146 men [79%]) were included and 77 (42%) had oropharyngeal cancer. RTW increased from 26% (42 of 160 individuals) at 3 months to 65% (89 of 137 individuals) at 1 year, after which it reduced to 52% (51 of 98 individuals) at 5 years. At 5 years after treatment, an additional 28 of 98 participants (29%) were retired. Minor surgery (vs major surgery) was associated with faster RTW from end of treatment onwards (hazard ratio [HR], 2.73; 95% CI, 1.17-6.37). Older age (HR, 0.97; 95% CI, 0.94-0.999) and more fatigue at 3 months (HR, 0.99; 95% CI, 0.98-0.995) were associated with slower RTW from 3 months onwards. Older age was also associated with slower RTW from 6 months onwards (HR, 0.96; 95% CI, 0.93-0.998). Among the 127 patients with HNC younger than 60 years, RTW was 72% (47 individuals) at 5 years after treatment. Advanced tumor stage (HR, 0.59; 95% CI, 0.39-0.90) and more fatigue (HR, 0.99; 95% CI, 0.98-0.999) were associated with slower RTW in this group. Conclusion and relevance:This cohort study found that the majority of patients with HNC in the Netherlands returned to work within 1 year and that certain sociodemographic and clinical factors and cancer-related symptoms were associated with time to RTW. These results may inform patients with HNC and provide insight into potential targets, such as fatigue, to improve RTW.

BACKGROUND:In the HECKTOR 2022 challenge set [1], several state-of-the-art (SOTA, achieving best performance) deep learning models were introduced for predicting recurrence-free period (RFP) in head and neck cancer patients using PET and CT images. PURPOSE:This study investigates whether a conventional DenseNet architecture, with optimized numbers of layers and image-fusion strategies, could achieve comparable performance as SOTA models. METHODS:The HECKTOR 2022 dataset comprises 489 oropharyngeal cancer (OPC) patients from seven distinct centers. It was randomly divided into a training set (n = 369) and an independent test set (n = 120). Furthermore, an additional dataset of 400 OPC patients, who underwent chemo(radiotherapy) at our center, was employed for external testing. Each patients' data included pre-treatment CT- and PET-scans, manually generated GTV (Gross tumour volume) contours for primary tumors and lymph nodes, and RFP information. The present study compared the performance of DenseNet against three SOTA models developed on the HECKTOR 2022 dataset. RESULTS:When inputting CT, PET and GTV using the early fusion (considering them as different channels of input) approach, DenseNet81 (with 81 layers) obtained an internal test C-index of 0.69, a performance metric comparable with SOTA models. Notably, the removal of GTV from the input data yielded the same internal test C-index of 0.69 while improving the external test C-index from 0.59 to 0.63. Furthermore, compared to PET-only models, when utilizing the late fusion (concatenation of extracted features) with CT and PET, DenseNet81 demonstrated superior C-index values of 0.68 and 0.66 in both internal and external test sets, while using early fusion was better in only the internal test set. CONCLUSIONS:The basic DenseNet architecture with 81 layers demonstrated a predictive performance on par with SOTA models featuring more intricate architectures in the internal test set, and better performance in the external test. The late fusion of CT and PET imaging data yielded superior performance in the external test.

Background and purpose: Deep learning (DL) models can extract prognostic image features from pre-treatment PET/CT scans. The study objective was to explore the potential benefits of incorporating pathologic lymph node (PL) spatial information in addition to that of the primary tumor (PT) in DL-based models for predicting local control (LC), regional control (RC), distant-metastasis-free survival (DMFS), and overall survival (OS) in oropharyngeal cancer (OPC) patients. Materials and methods: The study included 409 OPC patients treated with definitive (chemo)radiotherapy between 2010 and 2022. Patient data, including PET/CT scans, manually contoured PT (GTVp) and PL (GTVln) structures, clinical variables, and endpoints, were collected. Firstly, a DL-based method was employed to segment tumours in PET/CT, resulting in predicted probability maps for PT (TPMp) and PL (TPMln). Secondly, different combinations of CT, PET, manual contours and probability maps from 300 patients were used to train DL-based outcome prediction models for each endpoint through 5-fold cross validation. Model performance, assessed by concordance index (C-index), was evaluated using a test set of 100 patients. Results: Including PL improved the C-index results for all endpoints except LC. For LC, comparable C-indices (around 0.66) were observed between models trained using only PT and those incorporating PL as additional structure. Models trained using PT and PL combined into a single structure achieved the highest C-index of 0.65 and 0.80 for RC and DMFS prediction, respectively. Models trained using these target structures as separate entities achieved the highest C-index of 0.70 for OS. Conclusion: Incorporating lymph node spatial information improved the prediction performance for RC, DMFS, and OS.

BACKGROUND AND PURPOSE:Accurate delineation of the Gross Tumor Volume (GTV) and the Internal Target Volume (ITV) in early-stage lung tumors is crucial in Stereotactic Body Radiation Therapy (SBRT). Traditionally, the ITVs, which account for breathing motion, are generated by manually contouring GTVs across all breathing phases (BPs), a time-consuming process. This research aims to streamline this workflow by developing a deep learning algorithm to automatically delineate GTVs in all four-dimensional computed tomography (4D-CT) BPs for early-stage Non-Small Cell Lung Cancer Patients (NSCLC). METHODS:A dataset of 214 early-stage NSCLC patients treated with SBRT was used. Each patient had a 4D-CT scan containing ten reconstructed BPs. The data were divided into a training set (75 %) and a testing set (25 %). Three models SwinUNetR and Dynamic UNet (DynUnet), and a hybrid model combining both (Swin + Dyn)were trained and evaluated using the Dice Similarity Coefficient (DSC), 3 mm Surface Dice Similarity Coefficient (SDSC), and the 95th percentile Hausdorff distance (HD95). The best performing model was used to delineate GTVs in all test set BPs, creating the ITVs using two methods: all 10 phases and the maximum inspiration/expiration phases. The ITVs were compared to the ground truth ITVs. RESULTS:The Swin + Dyn model achieved the highest performance, with a test set SDSC of 0.79 ± 0.14 for GTV 50 %. For the ITVs, the SDSC was 0.79 ± 0.16 using all 10 BPs and 0.77 ± 0.14 using 2 BPs. At the voxel level, the Swin + DynNet network achieved a sensitivity of 0.75 ± 0.14 and precision of 0.84 ± 0.10 for the ITV 2 breathing phases, and a sensitivity of 0.79 ± 0.12 and precision of 0.80 ± 0.11 for the 10 breathing phases. CONCLUSION:The Swin + Dyn Net algorithm, trained on the maximum expiration CT-scan effectively delineated gross tumor volumes in all breathing phases and the resulting ITV showed a good agreement with the ground truth (surface DSC = 0.79 ± 0.16 using all 10 BPs and 0.77 ± 0.14 using 2 BPs.). The proposed approach could reduce delineation time and inter-performer variability in the tumor contouring process for NSCLC SBRT workflows.

Objectives. Breast cancer patients treated with proton therapy receive weekly repeat CTs (rCT) for treatment evaluation. However, plan adaptations are rarely necessary in our department. Therefore, the goal of this study was to develop an online method using surface guided radiotherapy (SGRT) to predict the dosimetric impact of changes in breast anatomy to identify patients that require plan adaptations, in order to reduce the number of rCTs. Approach. Seven breast cancer patients, treated with proton therapy with daily 3D surface-images in treatment position used for SGRT, were included. Clinical proton and backup photon plans were available. A novel in-house developed method, Dose Impact Prediction from Surface Imaging (DIPSI), was used to quantify the deformation between the planning CT (pCT) BODY contour, and the daily 3D SGRT surface images. To validate DIPSI, known isotropic deformations of 2, 4, 6, 8, 10 and 15 mm were introduced in the pCT BODY contour surrounding the clinical target volume (CTV). Clinical proton and photon treatment plans were recalculated including this deformation to evaluate the dosimetric impact of known deformations on the CTV D98%, D2% and average dose (Dmean). Deformation thresholds were determined to detect unacceptable dose deviations, from which the corresponding sensitivity, specificity and false negative rate were determined. Main results. DIPSI showed an accuracy of 0.2 mm and perfect correlation with known deformations (R2 = 1.00). Optimal thresholds to trigger treatment plan adaptation were 6.0 mm for the proton plan and 10.0 mm for the photon plan, resulting in sensitivities >95.5%, specificities >93.9% and false negative rates <1.6% in identifying breast deformations that require plan adaptations. Significance. Breast surface deformations could accurately be determined from daily SGRT images, making them suitable in identifying patients that require plan adaptations in photon and proton therapy potentially reducing the need for rCTs.

BACKGROUND AND PURPOSE:Deformable image registration (DIR) is widely utilized for dose accumulation, but errors in image registration can compromise its accuracy. This study evaluated the precision of DIR in dose accumulation for parotid gland and proposed a method to correct errors induced by DIR. MATERIALS AND METHODS:This retrospective study included 123 patients with head and neck cancer. For each patient, the accumulated mean dose (Dmean) to the parotid gland was obtained by manual segmentation (ground truth) and two DIR strategies: contour propagation and dose mapping. The normal tissue complication probability (NTCP) model predicting xerostomia was employed to translate accumulated Dmean into NTCP values. Comparisons were made between ground truth and DIR for accumulated Dmean and NTCP. RESULTS:The maximum discrepancy of accumulated Dmean and NTCP between DIR and ground truth was 4.87 Gy and 3.94 %, respectively. The discrepancies of accumulated Dmean between DIR and ground truth were significantly correlated with the discrepancies between accumulated Dmean of ground truth and nominal Dmean. Mid-treatment weekly Dmean discrepancies between contour propagation and manual segmentation showed the capability to correct the accumulated Dmean of DIR and decrease the error of NTCP prediction from 2.89 % and 3.81 % to 1.26 % and 2.04 % for baseline xerostomia Grade 0 and Grade 1-2, respectively. CONCLUSIONS:Significant discrepancies were observed in accumulated Dmean of parotid glands between DIR and manual segmentation in candidates for adaptive radiotherapy. Utilizing mid-treatment CT scans offers a practical solution to correct DIR-induced errors, improving the accuracy of dose accumulation.

Objectives: This study aimed to evaluate the prognostic significance of DNA methyltransferases (DNMTs) expression, including DNMT1, DNMT3A, and DNMT3B, in assessing the risk of locoregional recurrence after radiotherapy in patients with locally advanced laryngeal squamous cell carcinoma (LSCC), in order to optimize treatment decision making. Methods: A retrospective analysis was performed on pre-treatment biopsy tissues and clinical data from 58 patients with locally advanced LSCC (stages T3–T4, M0) treated with primary curative radiotherapy. DNMT expression was assessed through immunohistochemistry, and Cox regression analysis was applied to examine associations between methylation marker expression, demographic and clinical data, and both locoregional recurrence and disease-specific mortality. Results: Low expression of DNMT3A (p = 0.045) and the presence of locoregional lymph node metastases at diagnosis (N+-status) (p = 0.002) were associated with disease-specific mortality. Clinical N-status was also associated with locoregional recurrent disease after primary radiotherapy (p < 0.001). Expression of DNMT1 and DNMT3B, age, sex, and clinical T-status were not associated with locoregional recurrences or disease-specific mortality. Conclusions: Low expression of DNMT3A and the presence of regional lymph node metastases were independently associated with disease-specific mortality in patients with locally advanced LSCC treated primarily with definitive, curatively intended radiotherapy.

PURPOSE:He ad and neck cancer (HNC) can trigger a significant mental health burden, including psychoneurological symptoms (PNS). Better insight into the profiling of PNS is important for advancing personalized mental health screening and management. METHODS:Data from 538 newly diagnosed adult HNC patients participating in a prospective multicenter cohort study (NET-QUBIC) were used. Questionnaires were used to assess PNS. Sociodemographic, clinical, lifestyle, and biological variables were collected. Latent class analysis was performed to identify differential classes of PNS. Between-class comparisons and multivariable logistic regression analyses were conducted to characterize each profile in relation to sociodemographic, clinical, lifestyle, and biological variables. RESULTS:Fit indexes supported a three-class solution, with patients distributed in mild (60%), moderate (26%), and severe (14%) PNS classes. Pain and sleep problems were featured in all classes, anxiety and depression in the moderate and severe classes, and fatigue only in the severe class. Patients in the moderate and severe classes were more often women, had oral cavity cancer, showed impaired performance, had a history of anxiety and depression disorders, were daily smokers, had higher CRP, and had a flatter cortisol slope compared to the mild class. CONCLUSION:Newly diagnosed HNC patients can be classified according to the severity of PNS. Several sociodemographic, clinical, lifestyle, and biological variables are proposed as drivers for early detection and treatment of mental health burden.

PURPOSE:Medical imaging is crucial in modern radiotherapy, aiding diagnosis, treatment planning, and monitoring. The development of synthetic imaging techniques, particularly synthetic computed tomography (sCT), continues to attract interest in radiotherapy. The SynthRAD2025 dataset and the accompanying SynthRAD2025 Grand Challenge aim to stimulate advancements in synthetic CT generation algorithms by providing a platform for comprehensive evaluation and benchmarking of synthetic CT generation algorithms based on cone-beam CTs (CBCT) and magnetic resonance images (MRI). ACQUISITION AND VALIDATION METHODS:The dataset comprises 2362 cases, including 890 MRI-CT pairs and 1472 CBCT-CT pairs of head-and-neck, thoracic, and abdominal cancer patients treated at five European university medical centers [UMC Groningen, UMC Utrecht, Radboud UMC (Netherlands), LMU University Hospital Munich, and University Hospital of Cologne (Germany)]. Images were acquired using a wide range of acquisition protocols and scanners. Pre-processing, including rigid and deformable image registration methods, was performed to ensure high-quality image datasets and alignment between modalities. Extensive quality assurance was performed to validate image consistency and usability. DATA FORMAT AND USAGE NOTES:All imaging data is provided using the MetaImage (.mha) file format, ensuring compatibility with common medical image processing tools. Metadata, including acquisition parameters and registration details, is available in structured comma-separated value (CSV) files. To ensure dataset integrity, SynthRAD2025 is split into training (65%), validation (10%), and test (25%) sets. The dataset is accessible through https://doi.org/10.5281/zenodo.14918088 under the SynthRAD2025 collection. POTENTIAL APPLICATIONS:This dataset enables benchmarking and development of synthetic imaging techniques for radiotherapy applications. Potential use cases include sCT generation for MRI-only and MR-guided photon and proton radiotherapy, CBCT-based dose calculations, and adaptive radiotherapy workflows. By incorporating data from diverse acquisition settings, SynthRAD2025 supports the advancement of robust and generalizable image synthesis algorithms for clinical implementation, ultimately promoting personalized cancer care and improving adaptive radiotherapy workflows.

Background/Purpose Taste impairment is a common yet complex toxicity of head and neck cancer (HNC) radiotherapy treatment that may affect quality of life of survivors. This study aimed to predict acute and late taste impairment using taste bud bearing tongue mucosa as a new taste-specific organ-at-risk compared to full oral cavity as identified in previous studies. Materials/Methods Included HNC patients were treated with curative radiotherapy between 2007 and 2022. The endpoint was patient-rated moderate-to-severe taste loss scored with the EORTC QLQ-H&N35. The new tongue mucosa structure was derived from the existing oral cavity structure in accordance with published guidelines. An auto-segmentation tool was developed and verified by comparison to manually delineated structures. The performance of the mean dose admitted to this new structure was evaluated with both univariable analysis and a refit of a reference NTCP model substituting the oral cavity with the tongue mucosa. Results A total of 691 HNC patients were included. Good conformity between manually delineated and auto-segmented structures was observed with no significant differences in mean dose (22.2 Gy vs. 22.1 Gy) or volume (20.7 cm3 vs. 20.3 cm3). Full oral cavity mean dose showed comparable effect size in univariable analysis compared to tongue mucosa mean dose. The NTCP model with tongue mucosa did not outperform the reference model with oral cavity for any evaluated time points. Conclusion The tongue mucosa mean dose did not outperform the oral cavity mean dose in the logistic regression NTCP model predicting acute and late taste impairment.