PET/CT based transformer model for multi-outcome prediction in oropharyngeal cancer.

BACKGROUND AND PURPOSE: To optimize our previously proposed TransRP, a model integrating CNN (convolutional neural network) and ViT (Vision Transformer) designed for recurrence-free survival prediction in oropharyngeal cancer and to extend its application to the prediction of multiple clinical outcomes, including locoregional control (LRC), Distant metastasis-free survival (DMFS) and overall survival (OS). MATERIALS AND METHODS: Data was collected from 400 patients (300 for training and 100 for testing) diagnosed with oropharyngeal squamous cell carcinoma (OPSCC) who underwent (chemo)radiotherapy at University Medical Center Groningen. Each patient's data comprised pre-treatment PET/CT scans, clinical parameters, and clinical outcome endpoints, namely LRC, DMFS and OS. The prediction performance of TransRP was compared with CNNs when inputting image data only. Additionally, three distinct methods (m1-3) of incorporating clinical predictors into TransRP training and one method (m4) that uses TransRP prediction as one parameter in a clinical Cox model were compared. RESULTS: TransRP achieved higher test C-index values of 0.61, 0.84 and 0.70 than CNNs for LRC, DMFS and OS, respectively. Furthermore, when incorporating TransRP's prediction into a clinical Cox model (m4), a higher C-index of 0.77 for OS was obtained. Compared with a clinical routine risk stratification model of OS, our model, using clinical variables, radiomics and TransRP prediction as predictors, achieved larger separations of survival curves between low, intermediate and high risk groups. CONCLUSION: TransRP outperformed CNN models for all endpoints. Combining clinical data and TransRP prediction in a Cox model achieved better OS prediction.

Late-xerostomia prediction model based on 18F-FDG PET image biomarkers of the main salivary glands.

BACKGROUND AND PURPOSE: Recently, a comprehensive xerostomia prediction model was published, based on baseline xerostomia, mean dose to parotid glands (PG) and submandibular glands (SMG). Previously, PET imaging biomarkers (IBMs) of PG were shown to improve xerostomia prediction. Therefore, this study aimed to explore the potential improvement of the additional PET-IBMs from both PG and SMG to the recent comprehensive xerostomia prediction model (i.e., the reference model). MATERIALS AND METHODS: Totally, 540 head and neck cancer patients were split into training and validation cohorts. PET-IBMs from the PG and SMG, were selected using bootstrapped forward selection based on the reference model. The IBMs from both the PG and SMG with the highest selection frequency were added to the reference model, resulting in a PG-IBM model and a SMG-IBM model which were combined into a composite model. Model performance was assessed using the area under the curve (AUC). Likelihood ratio test compared the predictive performance between the reference model and models including IBMs. RESULTS: The final selected PET-IBMs were 90th percentile of the PG SUV and total energy of the SMG SUV. The additional two PET-IBMs in the composite model improved the predictive performance of the reference model significantly. The AUC of the reference model and the composite model were 0.67 and 0.69 in the training cohort, and 0.71 and 0.73 in the validation cohort, respectively. CONCLUSION: The composite model including two additional PET-IBMs from PG and SMG improved the predictive performance of the reference xerostomia model significantly, facilitating a more personalized prediction approach.

Probability maps for deep learning-based head and neck tumor segmentation: Graphical User Interface design and test.

BACKGROUND: The different tumor appearance of head and neck cancer across imaging modalities, scanners, and acquisition parameters accounts for the highly subjective nature of the manual tumor segmentation task. The variability of the manual contours is one of the causes of the lack of generalizability and the suboptimal performance of deep learning (DL) based tumor auto-segmentation models. Therefore, a DL-based method was developed that outputs predicted tumor probabilities for each PET-CT voxel in the form of a probability map instead of one fixed contour. The aim of this study was to show that DL-generated probability maps for tumor segmentation are clinically relevant, intuitive, and a more suitable solution to assist radiation oncologists in gross tumor volume segmentation on PET-CT images of head and neck cancer patients. METHOD: A graphical user interface (GUI) was designed, and a prototype was developed to allow the user to interact with tumor probability maps. Furthermore, a user study was conducted where nine experts in tumor delineation interacted with the interface prototype and its functionality. The participants' experience was assessed qualitatively and quantitatively. RESULTS: The interviews with radiation oncologists revealed their preference for using a rainbow colormap to visualize tumor probability maps during contouring, which they found intuitive. They also appreciated the slider feature, which facilitated interaction by allowing the selection of threshold values to create single contours for editing and use as a starting point. Feedback on the prototype highlighted its excellent usability and positive integration into clinical workflows. CONCLUSIONS: This study shows that DL-generated tumor probability maps are explainable, transparent, intuitive and a better alternative to the single output of tumor segmentation models.

Towards a European prospective data registry for particle therapy.

The evidence for the value of particle therapy (PT) is still sparse. While randomized trials remain a cornerstone for robust comparisons with photon-based radiotherapy, data registries collecting real-world data can play a crucial role in building evidence for new developments. This Perspective describes how the European Particle Therapy Network (EPTN) is actively working on establishing a prospective data registry encompassing all patients undergoing PT in European centers. Several obstacles and hurdles are discussed, for instance harmonization of nomenclature and structure of technical and dosimetric data and data protection issues. A preferred approach is the adoption of a federated data registry model with transparent and agile governance to meet European requirements for data protection, transfer, and processing. Funding of the registry, especially for operation after the initial setup process, remains a major challenge.

Radiation-induced Xerostomia is Related to Stem Cell Dose-dependent Reduction of Saliva Production.

PURPOSE: Previous studies have shown that the mean dose to the parotid gland stem cell rich regions (Dmean,SCR) is the strongest dosimetric predictor for the risk of patient-reported daytime xerostomia. This study aimed to test whether the relationship between patient-reported xerostomia and Dmean,SCR is explained by a dose-dependent reduction of saliva production. METHODS AND MATERIALS: In 570 patients with head and neck cancer treated with definitive radiation therapy (RT), flow from the parotid (FLOWPAR) and submandibular/sublingual (FLOWSMSL) glands, and patient-reported daytime (XERDAY) and nighttime (XERNIGHT) xerostomia were prospectively measured before, at 6 months, and 12 months after RT. Using linear mixed effect models, the relationship of the mean dose to the parotid glands (Dmean,par), Dmean,SCR, non-SCR parotid gland tissue (Dmean,non-SCR), submandibular glands (Dmean,sub), and oral cavity (Dmean,oral) with salivary flow and xerostomia was analyzed while correcting for known confounders. RESULTS: Dmean,SCR proved to be responsible for the effect of Dmean,par on FLOWPAR (P ≤ .03), while Dmean,non-SCR did not affect FLOWPAR (P ≥ .11). To illustrate, increasing Dmean,SCR by 10 Gy at a fixed Dmean,non-SCR reduced FLOWPAR by 0.02 mL/min (25%) after RT. However, if the opposite happened, no change in FLOWPAR was observed (0.00 mL/min [4%]). As expected, Dmean,sub was significantly associated with FLOWSMSL (P < .001). For example, increasing Dmean,sub by 10 Gy reduced FLOWSMSL by 0.07 mL/min (26%) after RT. Xerostomia scores were also affected by dose to the salivary glands. Dmean,SCR and Dmean,oral were associated with higher XERDAY scores (P ≤ .05), while Dmean,sub increased XERNIGHT scores (P = .01). For example, an increase of 10 Gy in Dmean,SCR raised XERDAY scores by 2.13 points (5%) after RT, while an additional 10 Gy in Dmean,subs increased XERNIGHT scores by 2.20 points (6%) after RT. Salivary flow was not only associated with radiation dose, but also with xerostomia scores in line with the salivary glands' functions; ie, FLOWPAR only influenced XERDAY (P < .001, 10.92 points lower XERDAY per 1 mL/min saliva), while FLOWSMSL affected XERDAY and XERNIGHT (P ≤ .004, 6.69 and 5.74 points lower XERDAY and XERNIGHT, respectively, per 1 mL/min saliva). Therefore, the observed relationships between dose and xerostomia were corrected for salivary flow. As hypothesized, Dmean,SCR only increased XERDAY scores via reducing FLOWPAR, whereas the effects of Dmean,oral on XERDAY and Dmean,sub on XERNIGHT were independent of salivary flow. CONCLUSIONS: Higher SCR region dose reduced parotid gland saliva production, subsequently resulting in higher daytime xerostomia scores. Consequently, this study supports the clinical implementation of stem cell sparing RT to preserve salivary flow with the aim of reducing the risk of xerostomia.

Proton PBS Planning Techniques, Robustness Evaluation, and OAR Sparing for the Whole-Brain Part of Craniospinal Axis Irradiation.

Proton therapy is a promising modality for craniospinal irradiation (CSI), offering dosimetric advantages over conventional treatments. While significant attention has been paid to spine fields, for the brain fields, only dose reduction to the lens of the eye has been reported. Hence, the objective of this study is to assess the potential gains and feasibility of adopting different treatment planning techniques for the entire brain within the CSI target. To this end, eight previously treated CSI patients underwent retrospective replanning using various techniques: (1) intensity modulated proton therapy (IMPT) optimization, (2) the modification/addition of field directions, and (3) the pre-optimization removal of superficially placed spots. The target coverage robustness was evaluated and dose comparisons for lenses, cochleae, and scalp were conducted, considering potential biological dose increases. The target coverage robustness was maintained across all plans, with minor reductions when superficial spot removal was utilized. Single- and multifield optimization showed comparable target coverage robustness and organ-at-risk sparing. A significant scalp sparing was achieved in adults but only limited in pediatric cases. Superficial spot removal contributed to scalp V30 Gy reduction at the expense of lower coverage robustness in specific cases. Lens sparing benefits from multiple field directions, while cochlear sparing remains impractical. Based on the results, all investigated plan types are deemed clinically adoptable.

Head and neck cancer patients with geriatric deficits are more often non-responders and lost from follow-up in quality of life studies.

OBJECTIVES: To identify associations between frailty and non-response to follow-up questionnaires, in a longitudinal head and neck cancer (HNC) study with patient-reported outcome measures (PROMs). MATERIALS AND METHODS: Patients referred with HNC were included in OncoLifeS, a prospective data-biobank, underwent Geriatric Assessment (GA) and frailty screening ahead of treatment, and were followed up at 3, 6, 12 and 24 months after treatment using the European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire Core 30 and Head and Neck 35. Statistical analysis for factors associated with non-response was done using Generalized Linear Mixed Models. RESULTS: 289 patients were eligible for analysis. Mean age was 68.4 years and 68.5% were male. Restrictions in Activities of Daily Living [OR 4.46 (2.04-9.78)] and Instrumental Activities of Daily Living [OR 4.33 (2.27-8.24)], impaired mobility on Timed Up and Go test [OR 3.95 (1.85-8.45)], cognitive decline [OR 4.85 (2.28-10.35)] and assisted living (OR 5.54 (2.63-11.67)] were significantly associated with non-response. Frailty screening, with Geriatric 8 and Groningen Frailty Indicator, was also associated with non-response [OR, respectively, 2.64 (1.51-4.59) and 2.52 (1.44-4.44)]. All findings remained significant when adjusted for other factors that were significantly associated with non-response, such as higher age, longer study duration and subsequent death. CONCLUSION: Frail HNC patients respond significantly worse to follow-up PROMs. The drop-out and underrepresentation of frail patients in studies may lead to attrition bias, and as a result underestimating the effect sizes of associations. This is of importance when handling and interpreting such data.

Pretrial Quality Assurance for Hypofractionated Salvage Radiation Therapy After Prostatectomy in the Multi-Institutional PERYTON-trial.

Purpose: The PERYTON trial is a multicenter randomized controlled trial that will investigate whether the treatment outcome of salvage external beam radiation therapy (sEBRT) will be improved with hypofractionated radiation therapy. A pretrial quality assurance (QA) program was undertaken to ensure protocol compliance within the PERYTON trial and to assess variation in sEBRT treatment protocols between the participating centers. Methods and Materials: Completion of the QA program was mandatory for each participating center (N = 8) to start patient inclusion. The pretrial QA program included (1) a questionnaire on the center-specific sEBRT protocol, (2) a delineation exercise of the clinical target volume (CTV) and organs at risk, and (3) a treatment planning exercise. All contours were analyzed using the pairwise dice similarity coefficient (DSC) and the 50th and 95th percentile Hausdorff distance (HD50 and HD95, respectively). The submitted treatment plans were reviewed for protocol compliance. Results: The results of the questionnaire showed that high-quality, state-of-the-art radiation therapy techniques were used in the participating centers and identified variations of the sEBRT protocols used concerning the position verification and preparation techniques. The submitted CTVs showed significant variation, with a range in volume of 29 cm3 to 167 cm3, a mean pairwise DSC of 0.52, and a mean HD50 and HD95 of 2.3 mm and 24.4 mm, respectively. Only in 1 center the treatment plan required adaptation before meeting all constraints of the PERYTON protocol. Conclusions: The pretrial QA of the PERYTON trial demonstrated that high-quality, but variable, radiation techniques were used in the 8 participating centers. The treatment planning exercise confirmed that the dose constraints of the PERYTON protocol were feasible for all participating centers. The observed variation in CTV delineation led to agreement on a new (image-based) delineation guideline to be used by all participating centers within the PERYTON trial.

Optimal timing of re-planning for head and neck adaptive radiotherapy.

BACKGROUND AND PURPOSE: Adaptive radiotherapy (ART) relies on re-planning to correct treatment variations, but the optimal timing of re-planning to account for dose changes in head and neck organs at risk (OARs) is still under investigation. We aimed to find out the optimal timing of re-planning in head and neck ART. MATERIALS AND METHODS: A total of 110 head and neck cancer patients were retrospectively enrolled. A semi auto-segmentation method was applied to obtain the weekly mean dose (Dmean) to OARs. The K-nearest-neighbour method was used for missing data imputation of weekly Dmean. A dose deviation map was built using the planning Dmean and weekly Dmean values and then used to simulate different ART scenarios consisting of 1 to 6 re-plannings. The difference between accumulated Dmean and planning Dmean before re-planning (ΔDmean_acc_noART) and after re-planning (ΔDmean_acc_ART) were evaluated and compared. RESULTS: Among all the OARs, supraglottic showed the largest ΔDmean_acc_noART (1.23 ± 3.13 Gy) and most cases of ΔDmean_acc_noART > 3 Gy (26 patients). The 3rd week is suggested in the optimal timing of re-planning for 10 OARs. For all the organs except arytenoid, 2 re-plannings were able to guarantee the ΔDmean_acc_ART below 3 Gy while the average |ΔDmean_acc_ART| was below 1 Gy. ART scenarios of 2_4, 3_4, 3_5 (week of re-planning separated with "_") were able to guarantee ΔDmean_acc_ART of 99 % of patients below 3 Gy simultaneously for 19 OARs. CONCLUSIONS: The optimal timing of re-planning was suggested for different organs at risk in head and neck adaptive radiotherapy. Generic scenarios of timing and frequency for re-planning can be applied to guarantee the increase of accumulated mean dose within 3 Gy simultaneously for multiple organs.

Nasopharyngeal carcinoma: nationwide trends in subtype-specific incidence and survival over 3 decades in a non-endemic area.

PURPOSE: To identify trends in incidence and survival of NPC, subdivided by EBV status and histopathological subtype, over a 30-year period in the Netherlands. METHODS: Anonymized data from the Netherlands Cancer Registry and the Dutch Nationwide Pathology Databank (PALGA) for the period 1989-2018 were linked to identify and classify NPC cases. RESULTS: Incidence of NPC remained stable, with an annual percentage change (APC) of - 0.2. (95% CI - 0.9; 0.5). EBV testing became routine only in the last decade, the incidence of EBV-positive tumors remained stable over this period (APC 1.2, 95% CI - 1.3; 3.8). An increase in EBV-negative tumors (APC: 7.1, 95% CI 2.5; 11.9) and a decrease in untested tumors were found (APC: - 10.7, 95% CI - 15.7; - 5.7). The incidence of non-keratinizing, differentiated tumors increased (APC: 3.8, (95% CI 2.2; 5.5) while the incidence of other histological subtypes remained stable. Overall survival was better in patients diagnosed after 1998 (hazard ratio 0.8, 95% CI 0.6; 0.9). EBV status, histology, stage, and age were independently associated with relative excess risk of dying, but period of diagnosis was not. CONCLUSION: Testing for EBV increased over time, and a stable incidence of EBV-positive NPC over the last 10 years. The rising incidence of non-keratinizing, differentiated NPC mirrors data from the US and suggests a shift in non-endemic regions.

Mental healthcare utilization among head and neck cancer patients: A longitudinal cohort study.

OBJECTIVE: To investigate utilization of mental healthcare among head and neck cancer (HNC) patients from diagnosis to 2 years after treatment, in relation to psychological symptoms, mental disorders, need for mental healthcare, and sociodemographic, clinical and personal factors. METHODS: Netherlands Quality of life and Biomedical Cohort study data as measured before treatment, at 3 and 6 months, and at 1 and 2 years after treatment was used (n = 610). Data on mental healthcare utilization (iMCQ), psychological symptoms (Hospital Anxiety and Depression Scale, Cancer Worry Scale), mental disorders (CIDI interview), need for mental healthcare (Supportive Care Needs Survey Short-Form 34, either as continuous outcome indicating the level of need or dichotomized into unmet need (yes/no)) and several sociodemographic, clinical and personal factors were collected. Factors associated with mental healthcare utilization were investigated using generalized estimating equations (p < 0.05). RESULTS: Of all HNC patients, 5%-9% used mental healthcare per timepoint. This was 4%-14% in patients with mild-severe psychological symptoms, 4%-17% in patients with severe psychological symptoms, 15%-35% in patients with a mental disorder and 5%-16% in patients with an unmet need for mental healthcare. Among all patients, higher symptoms of anxiety, a higher need for mental healthcare, lower age, higher disease stage, lower self-efficacy and higher social support seeking were significantly associated with mental healthcare utilization. CONCLUSION: Mental health care utilization among HNC patients is limited, and is related to psychological symptoms, need for mental healthcare, and sociodemographic, clinical and personal factors.

Feasibility of Monte Carlo dropout-based uncertainty maps to evaluate deep learning-based synthetic CTs for adaptive proton therapy.

BACKGROUND: Deep learning has shown promising results to generate MRI-based synthetic CTs and to enable accurate proton dose calculations on MRIs. For clinical implementation of synthetic CTs, quality assurance tools that verify their quality and reliability are required but still lacking. PURPOSE: This study aims to evaluate the predictive value of uncertainty maps generated with Monte Carlo dropout (MCD) for verifying proton dose calculations on deep-learning-based synthetic CTs (sCTs) derived from MRIs in online adaptive proton therapy. METHODS: Two deep-learning models (DCNN and cycleGAN) were trained for CT image synthesis using 101 paired CT-MR images. sCT images were generated using MCD for each model by performing 10 inferences with activated dropout layers. The final sCT was obtained by averaging the inferred sCTs, while the uncertainty map was obtained from the HU variance corresponding to each voxel of 10 sCTs. The resulting uncertainty maps were compared to the observed HU-, range-, WET-, and dose-error maps between the sCT and planning CT. For range and WET errors, the generated uncertainty maps were projected along the 90-degree angle. To evaluate the dose distribution, a mask based on the 5%-isodose curve was applied to only include voxels along the beam paths. Pearson's correlation coefficients were calculated to determine the correlation between the uncertainty maps and HUs, range, WET, and dose errors. To evaluate the dosimetric accuracy of synthetic CTs, clinical proton treatment plans were recalculated and compared to the pCTs RESULTS: Evaluation of the correlation showed an average of r = 0.92 ± 0.03 and r = 0.92 ± 0.03 for errors between uncertainty-HU, r = 0.66 ± 0.09 and r = 0.62 ± 0.06 between uncertainty-range, r = 0.64 ± 0.06 and r = 0.58 ± 0.07 between uncertainty-WET, and r = 0.65 ± 0.09 and r = 0.67 ± 0.07 between uncertainty and dose difference for DCNN and cycleGAN model, respectively. Dosimetric comparison for target volumes showed an average 3%/3 mm gamma pass rate of 99.76 ± 0.43 (DCNN) and 99.10 ± 1.27 (cycleGAN). CONCLUSION: The observed correlations between uncertainty maps and the various metrics (HU, range, WET, and dose errors) demonstrated the potential of MCD-based uncertainty maps as a reliable QA tool to evaluate the accuracy of deep learning-based sCTs.

Season of radiotherapy and outcomes of head & neck cancer patients in the MACH-NC & MARCH meta-analyses.

BACKGROUND: A single institution retrospective study suggested that head and neck squamous cell cancer (HNSCC) patients receiving radiotherapy (RT) during "dark" season (fall/winter) may have better outcomes than those treated during "light" season (spring/summer), possibly secondary to seasonal variations in cell cycle progression. We investigated the impact of season of RT in two large, multi-institutional, prospective datasets of randomized trials. METHODS: Individual patient data from the MACH-NC and MARCH meta-analyses were analyzed. Dark season was defined as mid-radiotherapy date during fall or winter and light the reverse, using equinoxes to separate the two periods. Primary endpoint was progression-free survival (PFS) and secondary endpoint was locoregional failure (LRF). The effect of season was estimated with a Cox model stratified by trial and adjusted on sex, tumor site, stage, and treatment. Planned sensitivity analyses were performed on patients treated around solstices, who received "complete radiotherapy", patients treated with concomitant radio-chemotherapy and on trials performed in Northern countries. RESULTS: 11320 patients from 33 trials of MARCH and 6276 patients from 29 trials of MACH-NC were included. RT during dark season had no benefit on PFS in the MARCH (hazard ratio[HR]: 1.01 [95%CI 0.97;1.05],p=0.72) or MACH-NC dataset (HR:1.00 [95%CI 0.94;1.06],p=1.0. No difference in LRF was observed in the MARCH (HR:1.00 [95%CI 0.94;1.06,p=0.95) or MACH-NC dataset (HR:0.99 [95%CI 0.91; 1.07],p=0.77). Sensitivity analyses showed similar results. CONCLUSION: Season of RT had no impact on PFS or LRF in two large databases of HNSCC.

Prostate-Specific Membrane Antigen Positron Emission Tomography/Computed Tomography-Based Clinical Target Volume Delineation Guideline for Postprostatectomy Salvage Radiation Therapy: The PERYTON Guideline.

PURPOSE: Prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA PET/CT) scan is the standard imaging procedure for biochemical recurrent prostate cancer postprostatectomy because of its high detection rate at low serum prostate-specific antigen levels. However, existing guidelines for clinical target volume (CTV) in prostate bed salvage external beam radiation therapy (sEBRT) are primarily based on experience-based clinical consensus and have been validated using conventional imaging modalities. Therefore, this study aimed to optimize CTV definition in sEBRT by using PSMA PET/CT-detected local recurrences (LRs). METHODS AND MATERIALS: Patients with suspected LR on PSMA PET/CT postprostatectomy were retrospectively enrolled in 9 Dutch centers. Anonymized scans were centrally reviewed by an expert nuclear medicine physician. Each boundary of the CTV guideline from the Groupe Francophone de Radiothérapie en Urologie (GFRU) was evaluated and adapted to improve the accuracy and coverage of the area at risk of LR (CTV) on PSMA PET/CT. The proposed CTV adaptation was discussed with the radiation oncologists of the participating centers, and final consensus was reached. To assess reproducibility, the participating centers were asked to delineate 3 new cases according to the new PERYTON-CTV, and the submitted contours were evaluated using the Dice similarity coefficient (DSC). RESULTS: After central review, 93 LRs were identified on 83 PSMA PET/CTs. The proposed CTV definition improved the coverage of PSMA PET/CT-detected LRs from 67% to 96% compared with the GFRU-CTV, while reducing the GFRU-CTV by 25%. The new CTV was highly reproducible, with a mean DSC of 0.82 (range, 0.81-0.83). CONCLUSIONS: This study contributes to the optimization of CTV definition in postprostatectomy sEBRT by using the pattern of LR detected on PSMA PET/CT. The PERYTON-CTV is highly reproducible across the participating centers and ensures coverage of 96% LRs while reducing the GFRU-CTV by 25%.

Deep learning-based outcome prediction using PET/CT and automatically predicted probability maps of primary tumor in patients with oropharyngeal cancer.

BACKGROUND AND OBJECTIVE: Recently, deep learning (DL) algorithms showed to be promising in predicting outcomes such as distant metastasis-free survival (DMFS) and overall survival (OS) using pre-treatment imaging in head and neck cancer. Gross Tumor Volume of the primary tumor (GTVp) segmentation is used as an additional channel in the input to DL algorithms to improve model performance. However, the binary segmentation mask of the GTVp directs the focus of the network to the defined tumor region only and uniformly. DL models trained for tumor segmentation have also been used to generate predicted tumor probability maps (TPM) where each pixel value corresponds to the degree of certainty of that pixel to be classified as tumor. The aim of this study was to explore the effect of using TPM as an extra input channel of CT- and PET-based DL prediction models for oropharyngeal cancer (OPC) patients in terms of local control (LC), regional control (RC), DMFS and OS. METHODS: We included 399 OPC patients from our institute that were treated with definitive (chemo)radiation. For each patient, CT and PET scans and GTVp contours, used for radiotherapy treatment planning, were collected. We first trained a previously developed 2.5D DL framework for tumor probability prediction by 5-fold cross validation using 131 patients. Then, a 3D ResNet18 was trained for outcome prediction using the 3D TPM as one of the possible inputs. The endpoints were LC, RC, DMFS, and OS. We performed 3-fold cross validation on 168 patients for each endpoint using different combinations of image modalities as input. The final prediction in the test set (100) was obtained by averaging the predictions of the 3-fold models. The C-index was used to evaluate the discriminative performance of the models. RESULTS: The models trained replacing the GTVp contours with the TPM achieved the highest C-indexes for LC (0.74) and RC (0.60) prediction. For OS, using the TPM or the GTVp as additional image modality resulted in comparable C-indexes (0.72 and 0.74). CONCLUSIONS: Adding predicted TPMs instead of GTVp contours as an additional input channel for DL-based outcome prediction models improved model performance for LC and RC.

Site-specific radiation dosage and implant survival in oral cancer patients: A cohort study.

OBJECTIVES: We assessed the radiation dosages (Dmean ) on implant regions to identify the threshold for implant loss in patients with an intraoral malignancy treated with dental implants to support a mandibular denture during ablative surgery before volumetric-modulated arc therapy (VMAT). MATERIALS AND METHODS: Data was collected prospectively from 28 patients treated surgically for an intraoral malignancy, followed by postoperative radiotherapy (VMAT) and analyzed retrospectively. Patients received 2 implants in the native mandible during ablative surgery. Implant-specific Dmean values were retrieved from the patients' files. Radiographic bone loss was measured 1 year after implant placement and during the last follow-up appointment. Implant survival was analyzed with the Kaplan-Meier method. Univariate logistic regression and Cox-regression analyses were performed to investigate the effect of increasing implant-specific radiation dosages on implant loss. RESULTS: Five out of 56 placed implants were lost during follow-up (median 36.0 months, IQR 39.0). Radiographically, peri-implant bone loss occurred in implants with a Dmean > 40 Gy. Implant loss occurred only in implants with a Dmean > 50 Gy. CONCLUSION: An implant-specific Dmean higher than 50 Gy is related to more peri-implant bone loss and, eventually, implant loss.

Comparison of computed tomography image features extracted by radiomics, self-supervised learning and end-to-end deep learning for outcome prediction of oropharyngeal cancer.

Background and purpose: To compare the prediction performance of image features of computed tomography (CT) images extracted by radiomics, self-supervised learning and end-to-end deep learning for local control (LC), regional control (RC), locoregional control (LRC), distant metastasis-free survival (DMFS), tumor-specific survival (TSS), overall survival (OS) and disease-free survival (DFS) of oropharyngeal squamous cell carcinoma (OPSCC) patients after (chemo)radiotherapy. Methods and materials: The OPC-Radiomics dataset was used for model development and independent internal testing and the UMCG-OPC set for external testing. Image features were extracted from the Gross Tumor Volume contours of the primary tumor (GTVt) regions in CT scans when using radiomics or a self-supervised learning-based method (autoencoder). Clinical and combined (radiomics, autoencoder or end-to-end) models were built using multivariable Cox proportional-hazard analysis with clinical features only and both clinical and image features for LC, RC, LRC, DMFS, TSS, OS and DFS prediction, respectively. Results: In the internal test set, combined autoencoder models performed better than clinical models and combined radiomics models for LC, RC, LRC, DMFS, TSS and DFS prediction (largest improvements in C-index: 0.91 vs. 0.76 in RC and 0.74 vs. 0.60 in DMFS). In the external test set, combined radiomics models performed better than clinical and combined autoencoder models for all endpoints (largest improvements in LC, 0.82 vs. 0.71). Furthermore, combined models performed better in risk stratification than clinical models and showed good calibration for most endpoints. Conclusions: Image features extracted using self-supervised learning showed best internal prediction performance while radiomics features have better external generalizability.

Technical note: Evaluation of deep learning based synthetic CTs clinical readiness for dose and NTCP driven head and neck adaptive proton therapy.

BACKGROUND: Adaptive proton therapy workflows rely on accurate imaging throughout the treatment course. Our centre currently utilizes weekly repeat CTs (rCTs) for treatment monitoring and plan adaptations. However, deep learning-based methods have recently shown to successfully correct CBCT images, which suffer from severe imaging artifacts, and generate high quality synthetic CT (sCT) images which enable CBCT-based proton dose calculations. PURPOSE: To compare daily CBCT-based sCT images to planning CTs (pCT) and rCTs of head and neck (HN) cancer patients to investigate the dosimetric accuracy of CBCT-based sCTs in a scenario mimicking actual clinical practice. METHODS: Data of 56 HN cancer patients, previously treated with proton therapy was used to generate 1.962 sCT images, using a previously developed and trained deep convolutional neural network. Clinical IMPT treatment plans were recalculated on the pCT, weekly rCTs and daily sCTs. The dosimetric accuracy of sCTs was compared to same day rCTs and the initial planning CT. As a reference, rCTs were also compared to pCTs. The dose difference between sCTs and rCTs/pCT was quantified by calculating the D98 difference for target volumes and Dmean difference for organs-at-risk. To investigate the clinical relevancy of possible dose differences, NTCP values were calculated for dysphagia and xerostomia. RESULTS: For target volumes, only minor dose differences were found for sCT versus rCT and sCT versus pCT, with dose differences mostly within ±1.5%. Larger dose differences were observed in OARs, where a general shift towards positive differences was found, with the largest difference in the left parotid gland. Delta NTCP values for grade 2 dysphagia and xerostomia were within ±2.5% for 90% of the sCTs. CONCLUSIONS: Target doses showed high similarity between rCTs and sCTs. Further investigations are required to identify the origin of the dose differences at OAR levels and its relevance in clinical decision making.