Deep learning with uncertainty estimation for automatic tumor segmentation in PET/CT of head and neck cancers: impact of model complexity, image processing and augmentation.

Objective.Target volumes for radiotherapy are usually contoured manually, which can be time-consuming and prone to inter- and intra-observer variability. Automatic contouring by convolutional neural networks (CNN) can be fast and consistent but may produce unrealistic contours or miss relevant structures. We evaluate approaches for increasing the quality and assessing the uncertainty of CNN-generated contours of head and neck cancers with PET/CT as input.Approach.Two patient cohorts with head and neck squamous cell carcinoma and baseline18F-fluorodeoxyglucose positron emission tomography and computed tomography images (FDG-PET/CT) were collected retrospectively from two centers. The union of manual contours of the gross primary tumor and involved nodes was used to train CNN models for generating automatic contours. The impact of image preprocessing, image augmentation, transfer learning and CNN complexity, architecture, and dimension (2D or 3D) on model performance and generalizability across centers was evaluated. A Monte Carlo dropout technique was used to quantify and visualize the uncertainty of the automatic contours.Main results. CNN models provided contours with good overlap with the manually contoured ground truth (median Dice Similarity Coefficient: 0.75-0.77), consistent with reported inter-observer variations and previous auto-contouring studies. Image augmentation and model dimension, rather than model complexity, architecture, or advanced image preprocessing, had the largest impact on model performance and cross-center generalizability. Transfer learning on a limited number of patients from a separate center increased model generalizability without decreasing model performance on the original training cohort. High model uncertainty was associated with false positive and false negative voxels as well as low Dice coefficients.Significance.High quality automatic contours can be obtained using deep learning architectures that are not overly complex. Uncertainty estimation of the predicted contours shows potential for highlighting regions of the contour requiring manual revision or flagging segmentations requiring manual inspection and intervention.

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.].

Chronic fatigue in long-term survivors of head and neck cancer treated with radiotherapy.

BACKGROUND: There is lack of evidence on chronic fatigue (CF) following radiotherapy (RT) in survivors of head and neck cancer (HNC). We aimed to compare CF in HNC survivors > 5 years post-RT with a reference population and investigate factors associated with CF and the possible impact of CF on health-related quality of life (HRQoL). MATERIAL AND METHODS: In this cross-sectional study we included HNC survivors treated in 2007-2013. Participants filled in patient-reported outcome measures and attended a one-day examination. CF was measured with the Fatigue Questionnaire and compared with a matched reference population using t-tests and Cohen's effect size. Associations between CF, clinical and RT-related factors were investigated using logistic regression. HRQoL was measured with the EORTC Quality of Life core questionnaire. RESULTS: The median age of the 227 HNC survivors was 65 years and median time to follow-up was 8.5 years post-RT. CF was twice more prevalent in HNC survivors compared to a reference population. In multivariable analyses, female sex (OR 3.39, 95 % CI 1.82-6.31), comorbidity (OR 2.17, 95 % CI 1.20-3.94) and treatment with intensity-modulated RT (OR 2.13, 95 % CI 1.16-3.91) were associated with CF, while RT dose parameters were not. Survivors with CF compared to those without, had significantly worse HRQoL. CONCLUSIONS: CF in HNC survivors is particularly important for female patients, while specific factors associated with RT appear not to play a role. The high CF prevalence in long-term HNC survivors associated with impaired HRQoL is important information beneficial for clinicians and patients to improve patient follow-up.

Radiation-induced long-term dysphagia in survivors of head and neck cancer and association with dose-volume parameters.

BACKGROUND: Although dysphagia is a common side effect after radiotherapy (RT) of head and neck cancer (HNC), data on long-term dysphagia is scarce. We aimed to 1) compare radiation dose parameters in HNC survivors with and without dysphagia, 2) investigate factors associated with long-term dysphagia and its possible impact on health-related quality of life (HRQoL), and 3) investigate how our data agree with existing NTCP models. METHODS: This cross-sectional study conducted in 2018-2020, included HNC survivors treated in 2007-2013. Participants attended a one-day examination in hospital and filled in patient questionnaires. Dysphagia was measured with the EORTC QLQ-H&N35 swallowing scale. Toxicity was scored with CTCAE v.4. We contoured swallowing organs at risk (SWOAR) on RT plans, calculated dose-volume histograms (DVHs), performed logistic regression analyses and tested our data in established NTCP models. RESULTS: Of the 239 participants, 75 (31%) reported dysphagia. Compared to survivors without dysphagia, this group had reduced HRQoL and the DVHs for infrahyoid SWOAR were significantly shifted to the right. Long-term dysphagia was associated with age (OR 1.07, 95% CI 1.03-1.10), female sex (OR 2.75, 95% CI 1.45-5.21), and mean dose to middle pharyngeal constrictor muscle (MD-MPCM) (OR 1.06, 95% CI 1.03-1.09). NTCP models overall underestimated the risk of long-term dysphagia. CONCLUSIONS: Long-term dysphagia was associated with higher age, being female, and high MD-MPCM. Doses to distally located SWOAR seemed to be risk factors. Existing NTCP models do not sufficiently predict long-term dysphagia. Further efforts are needed to reduce the prevalence and consequences of this late effect.

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.

Impact of hyperfractionated re-irradiation on quality of life in patients with recurrent or second primary head and neck cancer, a prospective single institutional study.

Purpose: Describe the clinical outcome of hyperfractionated re-irradiation (HFRT) in patients with recurrent or second primary (SP) head and neck cancer (HNC). Methods: This prospective observational study included HNC patients eligible for HFRT. Inclusion criteria: age ≥18 years, recurrent or SP HNC, planned re-irradiation and ability to respond to questionnaires. Patients received 1.5 Gy twice daily, five days a week for three (palliative) or four (curative/local control) weeks, total dose 45/60 Gy. Toxicity was scored with CTCAE v3 at baseline, end of treatment, at three, six, 12 and 36 months follow-up. Health-related quality of life (HRQoL) was measured with EORTC QLQ-C30 and EORTC QLQ-H&N35, pre-treatment and eight times until 36 months. In the main outcome (Global quality of life and H&N Pain), a change score of ≥10 was considered clinically significant, and p-values < 0.05 (two-sided) statistically significant. The Kaplan-Meier method was used for survival analyses. Results: Over four years from 2015, 58 patients were enrolled (37 recurrent and 21 SP). All, but two patients completed treatment as planned. Toxicity (≥grade 3) increased from pre-treatment to end of treatment with improvement in the follow-up period. The mean Global quality of life (QoL) and H&N Pain scores were stable from pre-treatment to three months. Maintained/ improved Global QoL was reported by 60% of patients at three months and 56% of patients at 12 months. For patients with curative, local control and palliative intent, the median survival (range) was 23 (2-53), 10 (1-66) and 14 (3-41) months respectively. Of those alive, the proportion of disease-free patients at 12 and 36 months, were 58% and 48%, respectively. Conclusion: Most HNC patients reported maintained HRQoL at three and 12 months after HFRT despite serious toxicity observed in many patients. Long-term survival can be achieved in a limited proportion of the patients.

Automatic gross tumor segmentation of canine head and neck cancer using deep learning and cross-species transfer learning.

Background: Radiotherapy (RT) is increasingly being used on dogs with spontaneous head and neck cancer (HNC), which account for a large percentage of veterinary patients treated with RT. Accurate definition of the gross tumor volume (GTV) is a vital part of RT planning, ensuring adequate dose coverage of the tumor while limiting the radiation dose to surrounding tissues. Currently the GTV is contoured manually in medical images, which is a time-consuming and challenging task. Purpose: The purpose of this study was to evaluate the applicability of deep learning-based automatic segmentation of the GTV in canine patients with HNC. Materials and methods: Contrast-enhanced computed tomography (CT) images and corresponding manual GTV contours of 36 canine HNC patients and 197 human HNC patients were included. A 3D U-Net convolutional neural network (CNN) was trained to automatically segment the GTV in canine patients using two main approaches: (i) training models from scratch based solely on canine CT images, and (ii) using cross-species transfer learning where models were pretrained on CT images of human patients and then fine-tuned on CT images of canine patients. For the canine patients, automatic segmentations were assessed using the Dice similarity coefficient (Dice), the positive predictive value, the true positive rate, and surface distance metrics, calculated from a four-fold cross-validation strategy where each fold was used as a validation set and test set once in independent model runs. Results: CNN models trained from scratch on canine data or by using transfer learning obtained mean test set Dice scores of 0.55 and 0.52, respectively, indicating acceptable auto-segmentations, similar to the mean Dice performances reported for CT-based automatic segmentation in human HNC studies. Automatic segmentation of nasal cavity tumors appeared particularly promising, resulting in mean test set Dice scores of 0.69 for both approaches. Conclusion: In conclusion, deep learning-based automatic segmentation of the GTV using CNN models based on canine data only or a cross-species transfer learning approach shows promise for future application in RT of canine HNC patients.

Repeatability of hypoxia dose painting by numbers based on EF5-PET in head and neck cancer.

BACKGROUND: Hypoxia dose painting is a radiotherapy technique to increase the dose to hypoxic regions of the tumour. Still, the clinical effect relies on the reproducibility of the hypoxic region shown in the medical image. 18F-EF5 is a hypoxia tracer for positron emission tomography (PET), and this study investigated the repeatability of 18F-EF5-based dose painting by numbers (DPBN) in head and neck cancer (HNC). MATERIALS AND METHODS: Eight HNC patients undergoing two 18F-EF5-PET/CT sessions (A and B) before radiotherapy were included. A linear conversion of PET signal intensity to radiotherapy dose prescription was employed and DPBN treatment plans were created using the image basis acquired at each PET/CT session. Also, plan A was recalculated on the image basis for session B. Voxel-by-voxel Pearson's correlation and quality factor were calculated to assess the DPBN plan quality and repeatability. RESULTS: The mean (SD) correlation coefficient between DPBN prescription and plan was 0.92 (0.02) and 0.93 (0.02) for sessions A and B, respectively, with corresponding quality factors of 0.02 (0.002) and 0.02 (0.003), respectively. The mean correlation between dose prescriptions at day A and B was 0.72 (0.13), and 0.77 (0.12) for the corresponding plans. A mean correlation of 0.80 (0.08) was found between plan A, recalculated on image basis B, and plan B. CONCLUSION: Hypoxia DPBN planning based on 18F-EF5-PET/CT showed high repeatability. This illustrates that 18F-EF5-PET provides a robust target for dose painting.

A comparison of methods for fully automatic segmentation of tumors and involved nodes in PET/CT of head and neck cancers.

Target volume delineation is a vital but time-consuming and challenging part of radiotherapy, where the goal is to deliver sufficient dose to the target while reducing risks of side effects. For head and neck cancer (HNC) this is complicated by the complex anatomy of the head and neck region and the proximity of target volumes to organs at risk. The purpose of this study was to compare and evaluate conventional PET thresholding methods, six classical machine learning algorithms and a 2D U-Net convolutional neural network (CNN) for automatic gross tumor volume (GTV) segmentation of HNC in PET/CT images. For the latter two approaches the impact of single versus multimodality input on segmentation quality was also assessed. 197 patients were included in the study. The cohort was split into training and test sets (157 and 40 patients, respectively). Five-fold cross-validation was used on the training set for model comparison and selection. Manual GTV delineations represented the ground truth. Tresholding, classical machine learning and CNN segmentation models were ranked separately according to the cross-validation Sørensen-Dice similarity coefficient (Dice). PET thresholding gave a maximum mean Dice of 0.62, whereas classical machine learning resulted in maximum mean Dice scores of 0.24 (CT) and 0.66 (PET; PET/CT). CNN models obtained maximum mean Dice scores of 0.66 (CT), 0.68 (PET) and 0.74 (PET/CT). The difference in cross-validation Dice between multimodality PET/CT and single modality CNN models was significant (p ≤ 0.0001). The top-ranked PET/CT-based CNN model outperformed the best-performing thresholding and classical machine learning models, giving significantly better segmentations in terms of cross-validation and test set Dice, true positive rate, positive predictive value and surface distance-based metrics (p ≤ 0.0001). Thus, deep learning based on multimodality PET/CT input resulted in superior target coverage and less inclusion of surrounding normal tissue.

Deep learning-based auto-delineation of gross tumour volumes and involved nodes in PET/CT images of head and neck cancer patients.

PURPOSE: Identification and delineation of the gross tumour and malignant nodal volume (GTV) in medical images are vital in radiotherapy. We assessed the applicability of convolutional neural networks (CNNs) for fully automatic delineation of the GTV from FDG-PET/CT images of patients with head and neck cancer (HNC). CNN models were compared to manual GTV delineations made by experienced specialists. New structure-based performance metrics were introduced to enable in-depth assessment of auto-delineation of multiple malignant structures in individual patients. METHODS: U-Net CNN models were trained and evaluated on images and manual GTV delineations from 197 HNC patients. The dataset was split into training, validation and test cohorts (n= 142, n = 15 and n = 40, respectively). The Dice score, surface distance metrics and the new structure-based metrics were used for model evaluation. Additionally, auto-delineations were manually assessed by an oncologist for 15 randomly selected patients in the test cohort. RESULTS: The mean Dice scores of the auto-delineations were 55%, 69% and 71% for the CT-based, PET-based and PET/CT-based CNN models, respectively. The PET signal was essential for delineating all structures. Models based on PET/CT images identified 86% of the true GTV structures, whereas models built solely on CT images identified only 55% of the true structures. The oncologist reported very high-quality auto-delineations for 14 out of the 15 randomly selected patients. CONCLUSIONS: CNNs provided high-quality auto-delineations for HNC using multimodality PET/CT. The introduced structure-wise evaluation metrics provided valuable information on CNN model strengths and weaknesses for multi-structure auto-delineation.

A Nordic-Baltic perspective on indications for proton therapy with strategies for identification of proper patients.

The beneficial effects of protons are primarily based on reduction of low to intermediate radiation dose bath to normal tissue surrounding the radiotherapy target volume. Despite promise for reduced long-term toxicity, the percentage of cancer patients treated with proton therapy remains low. This is probably caused by technical improvements in planning and delivery of photon therapy, and by high cost, low availability and lack of high-level evidence on proton therapy. A number of proton treatment facilities are under construction or have recently opened; there are now two operational Scandinavian proton centres and two more are under construction, thereby eliminating the availability hurdle. Even with the advantageous physical properties of protons, there is still substantial ambiguity and no established criteria related to which patients should receive proton therapy. This topic was discussed in a session at the Nordic Collaborative Workshop on Particle Therapy, held in Uppsala 14-15 November 2019. This paper resumes the Nordic-Baltic perspective on proton therapy indications and discusses strategies to identify patients for proton therapy. As for indications, neoplastic entities, target volume localisation, size, internal motion, age, second cancer predisposition, dose escalation and treatment plan comparison based on the as low as reasonably achievable (ALARA) principle or normal tissue complication probability (NTCP) models were discussed. Importantly, the patient selection process should be integrated into the radiotherapy community and emphasis on collaboration across medical specialties, involvement of key decision makers and knowledge dissemination in general are important factors. An active Nordic-Baltic proton therapy organisation would also serve this purpose.

The prognostic role of 18F-fluorodeoxyglucose PET in head and neck cancer depends on HPV status.

BACKGROUND AND PURPOSE: Standardized uptake value (SUV) and related parameters derived from 2-deoxy-2-[18F]-fluoro-d-glucose (FDG) PET/CT prior to radiochemotherapy of head and neck cancer (HNC) were significantly associated with survival in a number of studies. The aim of this study was to validate these findings and to evaluate the prognostic role of PET parameters also including clinical factors and HPV status. MATERIALS AND METHODS: We reviewed 166 HNC cases with a radiotherapy planning FDG PET/CT scan. All patients received radiotherapy, 68-70 Gy with or without concomitant cisplatin. Primary endpoint was disease-free survival (DFS). Twelve clinical factors, including HPV, performance status, stage and treatment parameters and ten PET/CT image parameters including gross tumor volume (GTV), metastatic lymph node volume, SUVmax, metabolic tumor volume (MTV) and total lesion glycolysis (TLG), were collected. Univariate and multivariate Cox regression analyses were employed. RESULTS: Of the 166 patients included, 48 had locoregional and 23 had metastatic recurrence. None of the FDG PET parameters were significant in the univariate analysis using DFS as endpoint. HPV status, ECOG status and GTV-U (primary tumor and lymph node volume from CT) were statistically significant (p < 0.01). Only in the subgroup of HPV-unrelated HNC (HPV negative oropharyngeal cancer [OPC] and non-OPC; n = 73), the multivariate model could be improved by including MTV (p < 0.001). DFS events were 29 (31%) in HPV-related and 53 (73%) in HPV-unrelated HNC. CONCLUSION: FDG PET parameters appear less important for overall prognostication of radiochemotherapy outcome for HNC. Still, the association between the FDG PET parameters and survival is strong for HNC not related to HPV. Tumor volume from CT is generally more closely related to outcome than parameters derived from FDG PET/CT.

Dose painting for re-irradiation of head and neck cancer.

BACKGROUND: For patients with recurrent or second primary disease, re-irradiation can be challenging due to overlap with previously irradiated volumes. Dose painting may be attractive for these patients, as the focus is on delivering maximal dose to areas of high tumor activity. Here, we compare dose painting by contours (DPBC) treatment plans based on 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) with conventional plans. MATERIAL AND METHODS: We included 10 patients with recurrent or second primary head and neck cancer (HNC) eligible for re-irradiation. Our conventional re-irradiation regimen is hyperfractionated radiotherapy 1.5 Gy twice daily over 4 weeks, giving a total dose of 60 Gy. For DPBC, we defined two prescription volumes, PV33 and PV66, corresponding to 33 and 66% of the highest FDG uptake in the tumor. The clinical target volume (CTV) prescription dose was 60 Gy, PV33; 65-67 Gy and PV66; 70-73 Gy. The DPBC plan is to be given the first 20 fractions and the conventional plan the last 20 fractions. Dose to organs at risk (OARs) were compared for DPBC and conventional treatment. By summation of the initial curative plan and the re-irradiation plan, we also evaluated differences in dose to the 2 ccm hot spot (D2cc). RESULTS: We achieved DPBC plans with adequate target coverage for all 10 patients. There were no significant differences in OAR doses between the standard plans and the DPBC plans (p=.7). Summation of the initial curative plan and the re-irradiation plan showed that the median D2cc increased from 130 Gy (range 113-132 Gy; conventional) to 140 Gy (range 115-145 Gy; DPBC). CONCLUSIONS: Our proposed DPBC could be straightforwardly implemented and all plans met the objectives. Re-irradiation of HNC with DPBC may increase tumor control without more side effects compared to conventional radiotherapy.

Patterns of local-regional recurrence after conformal and intensity-modulated radiotherapy for head and neck cancer.

AIM: To evaluate the patterns of loco-regional recurrences in head and neck cancer patients METHODS: Twenty-six out of 112 patients treated with primary or postoperative 3D CRT or IMRT for their primary and recurrent disease between 2007 and 2013 were included. The CT images of recurrent disease were rigidly registered with the primary CT images for each patient. To assess overlaps and overlap localization, the recurrence volume overlapping with the primary target volume was identified. For relapses occurring in the regional lymph nodes, the epicenter distance in recurrences and primary volumes and dose in recurrences were also identified. The recurrences were defined as in-field, marginal or out-of-field. RESULTS: The majority of the failures occurred within 1 year after completed primary treatment. The dose differences in recurrence volume were not statistically significant when patients were treated with IMRT or 3D CRT. Recurrence in 15/26 of the included patients occurred in the regional lymph nodes located fully or partly inside the primary target volume or the elective lymph node region. The majority of recurrences were recognized as in-field, independent of the primary treatment. CONCLUSION: Recurrence in the majority of the patients occurred in the regional lymph nodes located in high dose area. The cause of recurrence may be due to inadequate total dose in the primary treatment and/or lack of optimal primary diagnosis leading to inadequate primary target delineation.

Cervical lymph node metastases of squamous cell carcinoma of unknown origin: the diagnostic value of FDG PET/CT and clinical outcome.

FDG PET/CT is perceived as a valuable diagnostic tool in addition to the standard diagnostic workup for patients with isolated neck lymph nodes of squamous cell carcinoma of unknown primary (SCCUP). For patients with SCCUP intended for primary radiotherapy, we hypothesize that the previously reported FDG PET/CT detection rates are too high. From 2008 to 2015, 30 SCCUP patients were examined with FDG PET/CT. The objective of the FDG PET/CT examination was twofold: (1) improve the radiotherapy target definition, and (2) identify the primary cancer. Before the FDG PET/CT, the patients had been through a standard workup consisting of CT of the neck and chest, examination with flexible endoscopy with patient awake, panendoscopy and examination under general anesthesia, tonsillectomy and sometimes blind sampling biopsies, and MRI (floor of the mouth). All FDG PET/CTs were performed applying a flat table, head support and fixation mask as part of the radiotherapy treatment planning. Diagnostic CT with contrast was an integrated part of the PET/CT examination. Only 1/30 patients (cancer of the vallecula) had their primary cancer detected by FDG PET/CT. In addition, a non-biopsied patient with high uptake in the ipsilateral palatine tonsil was included, giving a detection rate of ≤7 % (95 % CI 2-21 %). In this retrospective study, we found that the FDG PET/CT detection rate of the primary for SCCUP patients is lower than previously reported. It is questionable whether FDG PET/CT is necessary for these patients when improved, advanced workup is available.

Dose painting by numbers in a standard treatment planning system using inverted dose prescription maps.

BACKGROUND: Dose painting by numbers (DPBN) is a method to deliver an inhomogeneous tumor dose voxel-by-voxel with a prescription based on biological medical images. However, planning of DPBN is not supported by commercial treatment planning systems (TPS) today. Here, a straightforward method for DPBN with a standard TPS is presented. MATERIAL AND METHODS: DPBN tumor dose prescription maps were generated from (18)F-FDG-PET images applying a linear relationship between image voxel value and dose. An inverted DPBN prescription map was created and imported into a standard TPS where it was defined as a mock pre-treated dose. Using inverse optimization for the summed dose, a planned DPBN dose distribution was created. The procedure was tested in standard TPS for three different tumor cases; cervix, lung and head and neck. The treatment plans were compared to the prescribed DPBN dose distribution by three-dimensional (3D) gamma analysis and quality factors (QFs). Delivery of the DPBN plans was assessed with portal dosimetry (PD). RESULTS: Maximum tumor doses of 149%, 140% and 151% relative to the minimum tumor dose were prescribed for the cervix, lung and head and neck case, respectively. DPBN distributions were well achieved within the tumor whilst normal tissue doses were within constraints. Generally, high gamma pass rates (> 89% at 2%/2 mm) and low QFs (< 2.6%) were found. PD showed that all DPBN plans could be successfully delivered. CONCLUSIONS: The presented methodology enables the use of currently available TPSs for DPBN planning and delivery and may therefore pave the way for clinical implementation.