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.

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.

Measurement of the12C(p,n)12N reaction cross section below 150 MeV.

Objective. Proton therapy currently faces challenges from clinical complications on organs-at-risk due to range uncertainties. To address this issue, positron emission tomography (PET) of the proton-induced11C and15O activity has been used to provide feedback on the proton range. However, this approach is not instantaneous due to the relatively long half-lives of these nuclides. An alternative nuclide,12N (half-life 11 ms), shows promise for real-timein vivoproton range verification. Development of12N imaging requires better knowledge of its production reaction cross section.Approach. The12C(p,n)12N reaction cross section was measured by detecting positron activity of graphite targets irradiated with 66.5, 120, and 150 MeV protons. A pulsed beam delivery with 0.7-2 × 108protons per pulse was used. The positron activity was measured during the beam-off periods using a dual-head Siemens Biograph mCT PET scanner. The12N production was determined from activity time histograms.Main results. The cross section was calculated for 11 energies, ranging from 23.5 to 147 MeV, using information on the experimental setup and beam delivery. Through a comprehensive uncertainty propagation analysis, a statistical uncertainty of 2.6%-5.8% and a systematic uncertainty of 3.3%-4.6% were achieved. Additionally, a comparison between measured and simulated scanner sensitivity showed a scaling factor of 1.25 (±3%). Despite this, there was an improvement in the precision of the cross section measurement compared to values reported by the only previous study.Significance. Short-lived12N imaging is promising for real-timein vivoverification of the proton range to reduce clinical complications in proton therapy. The verification procedure requires experimental knowledge of the12N production cross section for proton energies of clinical importance, to be incorporated in a Monte Carlo framework for12N imaging prediction. This study is the first to achieve a precise measurement of the12C(p,n)12N nuclear cross section for such proton energies.

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.

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.

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.

Case-Matched Outcomes of Proton Beam and Intensity-Modulated Radiation Therapy for Localized Prostate Cancer.

Purpose: Although both intensity-modulated radiation therapy (IMRT) and proton beam therapy (PBT) offer effective long-term disease control for localized prostate cancer (PCa), there are limited data directly comparing the 2 modalities. Methods: The data from 334 patients treated with conventionally fractionated (79.2 GyRBE in 44 fractions) PBT or IMRT were retrospectively analyzed. Propensity score matching was used to balance factors associated with biochemical failure-free survival (BFFS). Age, race, and comorbidities (not BFFS associates) remained imbalanced after matching. Univariable and covariate-adjusted multivariable (MVA) Cox regression models were used to determine if modality affected BFFS. Results: Of 334 patients, 176 (52.7%) were included in the matched cohort with exact matching to National Comprehensive Cancer Network (NCCN) risk group. With a median follow-up time of 9.0 years (interquartile range [IQR]: 7.8-10.2 years), long-term BFFS was similar between the IMRT and PBT matched arms with 8-year estimates of 85% (95% CI: 76%-91%) and 91% (95% CI: 82%-96%, P = .39), respectively. On MVA, modality was not significantly associated with BFFS in both the unmatched (hazard ratio [HR] = 0.75, 95% CI: 0.35-1.63, P = .47) and matched (HR = 0.87, 95% CI: 0.33-2.33, P = .78) cohorts. Prostate cancer-specific survival (PCSS) and overall survival (OS) were also similar (P > .05). However, in an unmatched analysis, the PBT arm had significantly fewer incidences of secondary cancers within the irradiated field (0.6%, 95% CI: 0.0%-3.1% versus 4.5%, 95% CI: 1.8%-9.0%, P = .028). Conclusions: Both PBT and IMRT offer excellent long-term disease control for PCa, with no significant differences between the 2 modalities in BFFS, PCSS, and OS in matched patients. In the unmatched cohort, fewer incidences of secondary malignancy were noted in the PBT group; however, owing to overall low incidence of secondary cancer and imbalanced patient characteristics between the 2 groups, these data are strictly hypothesis generating and require further investigation.

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.

Dose evaluation of inter- and intra-fraction prostate motion in extremely hypofractionated intensity-modulated proton therapy for prostate cancer.

Inter- and intra-fractional prostate motion can deteriorate the dose distribution in extremely hypofractionated intensity-modulated proton therapy. We used verification CTs and prostate motion data calculated from 1024 intra-fractional prostate motion records to develop a voxel-wise based 4-dimensional method, which had a time resolution of 1 s, to assess the dose impact of prostate motion. An example of 100 fractional simulations revealed that motion had minimal impact on planning dose, the accumulated dose in 95 % of the scenarios fulfilled the clinical goals for target coverage (D95 > 37.5 Gy). This method can serve as a complementary measure in clinical setting to guarantee plan quality.

Assessment of residual geometrical errors of clinical target volumes and their impact on dose accumulation for head and neck radiotherapy.

PURPOSE: To assess the residual geometrical errors (dr) and their impact on the clinical target volumes (CTV) dose coverage for head and neck cancer (HNC) proton therapy patients. METHODS: We analysed 28 HNC patients treated with 70 Gy (RBE) and 54.25 Gy (RBE) to the therapeutic CTV70 and prophylactic CTV54.25, respectively. Daily cone beam CTs were converted to high quality synthetic CTs (sCTs). The CTVs from the nominal CT were propagated to the corresponding sCTs using a hybrid deformable image registration (propagated CTVs) in RayStation 11B. For 11 patients, all propagated CTVs were reviewed by our HNC radiation oncologist (physician corrected CTVs). The residual geometrical error dr was quantified as a function of the daily CTVs volume overlap with the nominal plan CTV. The errors dr(propagated CTVs) and dr(physician corrected CTVs) and the difference in dice similarity coefficients (ΔDSC) were determined. Using clinical plans, dose coverage and the tumor control probability (TCP) for the nominal, accumulated and voxel-wise minimum scenarios were determined. RESULTS: The difference in the residual geometrical error dr (propagated CTVs - physician corrected CTVs) and mean DSC (|ΔDSC|mean) were minor: Δdr(CTV70) = 0.16 mm, Δdr(CTV54.25) = 0.26 mm, |ΔDSC|mean < 0.9%. For all 28 patients, dr(CTV70) = 1.91 mm and dr(CTV54.25) = 1.90 mm. However, CTV54.25 above and below the cricoid cartilage differed substantially (1.00 mm c.f. 3.93 mm). The CTV54.25 coverage below the cricoid was then almost always lower, although the TCP of the accumulated dose was higher than the TCP of the voxel-wise minimum dose. CONCLUSIONS: Setup uncertainty setting of 2 mm is possible. The feasibility of using propagated CTVs for error determination is demonstrated.

Simple immobilization for stereotactic radiotherapy aimed at pelvic metastases.

Stereotactic body radiotherapy (SBRT) is increasingly applied for pelvic oligometastases of prostate cancer, and currently no simple immobilization method is available for cone beam computed tomography (CBCT)-guided treatment. We assessed patient set-up and intrafraction motion using simple immobilization during CBCT-guided pelvic SBRT. Forty patients were immobilized with basic arm- head- and knee support and either a thermoplastic cushion or a foam cushion. Analysis of 454 CBCTs showed mean intrafraction translation <3.0 mm in 94% of fractions and mean intrafraction rotation <1.5° in 95% of fractions. Therefore, simple immobilization ensured stable patient positioning during CBCT-guided pelvic SBRT.

Partitioning of discrete proton arcs into interlaced subplans can bring proton arc advances to existing proton facilities.

BACKGROUND: Proton arcs have shown potential to reduce the dose to organs at risks (OARs) by delivering the protons from many different directions. While most previous studies have been focused on dynamic arcs (delivery during rotation), an alternative approach is discrete arcs, where step-and-shoot delivery is used over a large number of beam directions. The major advantage of discrete arcs is that they can be delivered at existing proton facilities. However, this advantage comes at the expense of longer treatment times. PURPOSE: To exploit the dosimetric advantages of proton arcs, while achieving reasonable delivery times, we propose a partitioning approach where discrete arc plans are split into subplans to be delivered over different fractions in the treatment course. METHODS: For three oropharyngeal cancer patients, four different arc plans have been created and compared to the corresponding clinical IMPT plan. The treatment plans are all planned to be delivered in 35 fractions, but with different delivery approaches over the fractions. The first arc plan (1×30) has 30 directions to be delivered every fraction, while the others are partitioned into subplans with 10 and 6 beam directions, each to be delivered every third (3×10), fifth fraction (5×6), or seventh fraction (7×10). All plans are assessed with respect to delivery time, target robustness over the treatment course, doses to OARs and NTCP for dysphagia and xerostomia. RESULTS: The delivery time (including an additional delay of 30 s between the discrete directions to simulate manual interaction with the treatment control system) is reduced from on average 25.2 min for the 1×30 plan to 9.2 min for the 3×10 and 7×10 plans and 5.7 min for the 5×6 plans. The delivery time for the IMPT plan is 7.9 min. When accounting for the combination of delivery time, target robustness, OAR sparing, and NTCP reduction, the plans with 10 directions in each fraction are the preferred choice. Both the 3×10 and 7×10 plans show improved target robustness compared to the 1×30 plans, while keeping OAR doses and NTCP values at almost as low levels as for the 1×30 plans. For all patients the NTCP values for dysphagia are lower for the partitioned plans with 10 directions compared to the IMPT plans. NTCP reduction for xerostomia compared to IMPT is seen in two of the three patients. The best results are seen for the first patient, where the NTCP reductions for the 7×10 plan are 1.6 p.p. (grade 2 xerostomia) and 1.5 p.p. (grade 2 dysphagia). The corresponding NTCP reductions for the 1×30 plan are 2.7 p.p. (xerostomia, grade 2) and 2.0 p.p. (dysphagia, grade 2). CONCLUSIONS: Discrete proton arcs can be implemented at any proton facility with reasonable treatment times using a partitioning approach. The technique also makes the proton arc treatments more robust to changes in the patient anatomy.

PTV-based VMAT vs. robust IMPT for head-and-neck cancer: A probabilistic uncertainty analysis of clinical plan evaluation with the Dutch model-based selection.

BACKGROUND AND PURPOSE: In the Netherlands, head-and-neck cancer (HNC) patients are referred for proton therapy (PT) through model-based selection (MBS). However, treatment errors may compromise adequate CTV dose. Our aims are: (i) to derive probabilistic plan evaluation metrics on the CTV consistent with clinical metrics; (ii) to evaluate plan consistency between photon (VMAT) and proton (IMPT) planning in terms of CTV dose iso-effectiveness and (iii) to assess the robustness of the OAR doses and of the risk toxicities involved in the MBS. MATERIALS AND METHODS: Sixty HNC plans (30 IMPT/30 VMAT) were included. A robustness evaluation with 100,000 treatment scenarios per plan was performed using Polynomial Chaos Expansion (PCE). PCE was applied to determine scenario distributions of clinically relevant dosimetric parameters, which were compared between the 2 modalities. Finally, PCE-based probabilistic dose parameters were derived and compared to clinical PTV-based photon and voxel-wise proton evaluation metrics. RESULTS: Probabilistic dose to near-minimum volume v = 99.8% for the CTV correlated best with clinical PTV-D98% and VWmin-D98%,CTV doses for VMAT and IMPT respectively. IMPT showed slightly higher nominal CTV doses, with an average increase of 0.8 GyRBE in the median of the D99.8%,CTV distribution. Most patients qualified for IMPT through the dysphagia grade II model, for which an average NTCP gain of 10.5 percentages points (%-point) was found. For all complications, uncertainties resulted in moderate NTCP spreads lower than 3 p.p. on average for both modalities. CONCLUSION: Despite the differences between photon and proton planning, the comparison between PTV-based VMAT and robust IMPT is consistent. Treatment errors had a moderate impact on NTCPs, showing that the nominal plans are a good estimator to qualify patients for PT.

SynthRAD2023 Grand Challenge dataset: Generating synthetic CT for radiotherapy.

PURPOSE: Medical imaging has become increasingly important in diagnosing and treating oncological patients, particularly in radiotherapy. Recent advances in synthetic computed tomography (sCT) generation have increased interest in public challenges to provide data and evaluation metrics for comparing different approaches openly. This paper describes a dataset of brain and pelvis computed tomography (CT) images with rigidly registered cone-beam CT (CBCT) and magnetic resonance imaging (MRI) images to facilitate the development and evaluation of sCT generation for radiotherapy planning. ACQUISITION AND VALIDATION METHODS: The dataset consists of CT, CBCT, and MRI of 540 brains and 540 pelvic radiotherapy patients from three Dutch university medical centers. Subjects' ages ranged from 3 to 93 years, with a mean age of 60. Various scanner models and acquisition settings were used across patients from the three data-providing centers. Details are available in a comma separated value files provided with the datasets. DATA FORMAT AND USAGE NOTES: The data is available on Zenodo (https://doi.org/10.5281/zenodo.7260704, https://doi.org/10.5281/zenodo.7868168) under the SynthRAD2023 collection. The images for each subject are available in nifti format. POTENTIAL APPLICATIONS: This dataset will enable the evaluation and development of image synthesis algorithms for radiotherapy purposes on a realistic multi-center dataset with varying acquisition protocols. Synthetic CT generation has numerous applications in radiation therapy, including diagnosis, treatment planning, treatment monitoring, and surgical planning.

An efficient strategy to select head and neck cancer patients for adaptive radiotherapy.

BACKGROUND AND PURPOSE: Adaptive radiotherapy (ART) is workload intensive but only benefits a subgroup of patients. We aimed to develop an efficient strategy to select candidates for ART in the first two weeks of head and neck cancer (HNC) radiotherapy. MATERIALS AND METHODS: This study retrospectively enrolled 110 HNC patients who underwent modern photon radiotherapy with at least 5 weekly in-treatment re-scan CTs. A semi auto-segmentation method was applied to obtain the weekly mean dose (Dmean) to OARs. A comprehensive NTCP-profile was applied to obtain NTCP's. The difference between planning and actual values of Dmean (ΔDmean) and dichotomized difference of clinical relevance (BIOΔNTCP) were used for modelling to determine the cut-off maximum ΔDmean of OARs in week 1 and 2 (maxΔDmean_1 and maxΔDmean_2). Four strategies to select candidates for ART, using cut-off maxΔDmean were compared. RESULTS: The Spearman's rank correlation test showed significant positive correlation between maxΔDmean and BIOΔNTCP (p-value <0.001). For major BIOΔNTCP (>5%) of acute and late toxicity, 10.9% and 4.5% of the patients were true candidates for ART. Strategy C using both cut-off maxΔDmean_1 (3.01 and 5.14 Gy) and cut-off maxΔDmean_2 (3.41 and 5.30 Gy) showed the best sensitivity, specificity, positive and negative predictive values (0.92, 0.82, 0.38, 0.99 for acute toxicity and 1.00, 0.92, 0.38, 1.00 for late toxicity, respectively). CONCLUSIONS: We propose an efficient selection strategy for ART that is able to classify the subgroup of patients with >5% BIOΔNTCP for late toxicity using imaging in the first two treatment weeks.

CT-based deep multi-label learning prediction model for outcome in patients with oropharyngeal squamous cell carcinoma.

BACKGROUND: Personalized treatment is increasingly required for oropharyngeal squamous cell carcinoma (OPSCC) patients due to emerging new cancer subtypes and treatment options. Outcome prediction model can help identify low or high-risk patients who may be suitable to receive de-escalation or intensified treatment approaches. PURPOSE: To develop a deep learning (DL)-based model for predicting multiple and associated efficacy endpoints in OPSCC patients based on computed tomography (CT). METHODS: Two patient cohorts were used in this study: a development cohort consisting of 524 OPSCC patients (70% for training and 30% for independent testing) and an external test cohort of 396 patients. Pre-treatment CT-scans with the gross primary tumor volume contours (GTVt) and clinical parameters were available to predict endpoints, including 2-year local control (LC), regional control (RC), locoregional control (LRC), distant metastasis-free survival (DMFS), disease-specific survival (DSS), overall survival (OS), and disease-free survival (DFS). We proposed DL outcome prediction models with the multi-label learning (MLL) strategy that integrates the associations of different endpoints based on clinical factors and CT-scans. RESULTS: The multi-label learning models outperformed the models that were developed based on a single endpoint for all endpoints especially with high AUCs ≥ 0.80 for 2-year RC, DMFS, DSS, OS, and DFS in the internal independent test set and for all endpoints except 2-year LRC in the external test set. Furthermore, with the models developed, patients could be stratified into high and low-risk groups that were significantly different for all endpoints in the internal test set and for all endpoints except DMFS in the external test set. CONCLUSION: MLL models demonstrated better discriminative ability for all 2-year efficacy endpoints than single outcome models in the internal test and for all endpoints except LRC in the external set.

Proton arc therapy increases the benefit of proton therapy for oropharyngeal cancer patients in the model based clinic.

BACKGROUND AND PURPOSE: In the model-based approach, patients qualify for proton therapy when the reduction in risk of toxicity (ΔNTCP) obtained with IMPT relative to VMAT is larger than predefined thresholds as defined by the Dutch National Indication Protocol (NIPP). Proton arc therapy (PAT) is an emerging technology which has the potential to further decrease NTCPs compared to IMPT. The aim of this study was to investigate the potential impact of PAT on the number of oropharyngeal cancer (OPC) patients that qualify for proton therapy. MATERIALS AND METHODS: A prospective cohort of 223 OPC patients subjected to the model-based selection procedure was investigated. 33 (15%) patients were considered unsuitable for proton treatment before plan comparison. When IMPT was compared to VMAT for the remaining 190 patients, 148 (66%) patients qualified for protons and 42 (19%) patients did not. For these 42 patients treated with VMAT, robust PAT plans were generated. RESULTS: PAT plans provided better or similar target coverage compared to IMPT plans. In the PAT plans, integral dose was significantly reduced by 18% relative to IMPT plans and by 54% relative to VMAT plans. PAT decreased the mean dose to numerous organs-at-risk (OARs), further reducing NTCPs. The ΔNTCP for PAT relative to VMAT passed the NIPP thresholds for 32 out of the 42 patients treated with VMAT, resulting in 180 patients (81%) of the complete cohort qualifying for protons. CONCLUSION: PAT outperforms IMPT and VMAT, leading to a further reduction of NTCP-values and higher ΔNTCP-values, significantly increasing the percentage of OPC patients selected for proton therapy.

Clinical 3D/4D cumulative proton dose assessment methods for thoracic tumours with large motion.

PURPOSE: Despite the anticipated clinical benefits of intensity-modulated proton therapy (IMPT), plan robustness may be compromised due to its sensitivity to patient treatment uncertainties, especially for tumours with large motion. In this study, we investigated treatment course-wise plan robustness for intra-thoracic tumours with large motion comparing a 4D pre-clinical evaluation method (4DREM) to our clinical 3D/4D dose reconstruction and accumulation methods. MATERIALS AND METHODS: Twenty patients with large target motion (>10 mm) were treated with five times layered rescanned IMPT. The 3D-robust optimised plans were generated on the averaged planning 4DCT. Using multiple 4DCTs, treatment plan robustness was assessed on a weekly and treatment course-wise basis through the 3D robustness evaluation method (3DREM, based on averaged 4DCTs), the 4D robustness evaluation method (4DREM, including the time structure of treatment delivery and 4DCT phases) and 4D dose reconstruction and accumulation (4DREAL, based on fraction-wise information). RESULTS: Baseline target motion for all patients ranged from 11-17 mm. For the offline adapted course-wise dose assessment, adequate target dose coverage was found for all patients. The target volume receiving 95% of the prescription dose was consistent between methods with 16/20 patients showing differences < 1%. 4DREAL showed the highest target coverage (99.8 ± 0.6%, p < 0.001), while no differences were observed between 3DREM and 4DREM (99.3 ± 1.3% and 99.4 ± 1.1%, respectively). CONCLUSION: Our results show that intra-thoracic tumours can be adequately treated with IMPT in free breathing for target motion amplitudes up to 17 mm employing any of the accumulation methods. Anatomical changes, setup and range errors demonstrated a more severe impact on target coverage than motion in these patients treated with fractionated proton radiotherapy.

Survival prediction for stage I-IIIA non-small cell lung cancer using deep learning.

BACKGROUND AND PURPOSE: The aim of this study was to develop and evaluate a prediction model for 2-year overall survival (OS) in stage I-IIIA non-small cell lung cancer (NSCLC) patients who received definitive radiotherapy by considering clinical variables and image features from pre-treatment CT-scans. MATERIALS AND METHODS: NSCLC patients who received stereotactic radiotherapy were prospectively collected at the UMCG and split into a training and a hold out test set including 189 and 81 patients, respectively. External validation was performed on 228 NSCLC patients who were treated with radiation or concurrent chemoradiation at the Maastro clinic (Lung1 dataset). A hybrid model that integrated both image and clinical features was implemented using deep learning. Image features were learned from cubic patches containing lung tumours extracted from pre-treatment CT scans. Relevant clinical variables were selected by univariable and multivariable analyses. RESULTS: Multivariable analysis showed that age and clinical stage were significant prognostic clinical factors for 2-year OS. Using these two clinical variables in combination with image features from pre-treatment CT scans, the hybrid model achieved a median AUC of 0.76 [95 % CI: 0.65-0.86] and 0.64 [95 % CI: 0.58-0.70] on the complete UMCG and Maastro test sets, respectively. The Kaplan-Meier survival curves showed significant separation between low and high mortality risk groups on these two test sets (log-rank test: p-value < 0.001, p-value = 0.012, respectively) CONCLUSION: We demonstrated that a hybrid model could achieve reasonable performance by utilizing both clinical and image features for 2-year OS prediction. Such a model has the potential to identify patients with high mortality risk and guide clinical decision making.

Technical note: Flat panel proton radiography with a patient specific imaging field for accurate WEPL assessment.

BACKGROUND: Proton radiography (PR) uses highly energetic proton beams to create images where energy loss is the main contrast mechanism. Water-equivalent path length (WEPL) measurements using flat panel PR (FP-PR) have potential for in vivo range verification. However, an accurate WEPL measurement via FP-PR requires irradiation with multiple energy layers, imposing high imaging doses. PURPOSE: A FP-PR method is proposed for accurate WEPL determination based on a patient-specific imaging field with a reduced number of energies (n) to minimize imaging dose. METHODS: Patient-specific FP-PRs were simulated and measured for a head and neck (HN) phantom. An energy selection algorithm estimated spot-wise the lowest energy required to cross the anatomy (Emin) using a water-equivalent thickness map. Starting from Emin, n was restricted to certain values (n = 26, 24, 22, …, 2 for simulations, n = 10 for measurements), resulting in patient-specific FP-PRs. A reference FP-PR with a complete set of energies was compared against patient-specific FP-PRs covering the whole anatomy via mean absolute WEPL differences (MAD), to evaluate the impact of the developed algorithm. WEPL accuracy of patient-specific FP-PRs was assessed using mean relative WEPL errors (MRE) with respect to measured multi-layer ionization chamber PRs (MLIC-PR) in the base of skull, brain, and neck regions. RESULTS: MADs ranged from 2.1 mm (n = 26) to 21.0 mm (n = 2) for simulated FP-PRs, and 7.2 mm for measured FP-PRs (n = 10). WEPL differences below 1 mm were observed across the whole anatomy, except at the phantom surfaces. Measured patient-specific FP-PRs showed good agreement against MLIC-PRs, with MREs of 1.3 ± 2.0%, -0.1 ± 1.0%, and -0.1 ± 0.4% in the three regions of the phantom. CONCLUSION: A method to obtain accurate WEPL measurements using FP-PR with a reduced number of energies selected for the individual patient anatomy was established in silico and validated experimentally. Patient-specific FP-PRs could provide means of in vivo range verification.