Proton and photon radiotherapy in stage III NSCLC: Effects on hematological toxicity and adjuvant immune therapy.

BACKGROUND AND PURPOSE: Concurrent chemo-radiotherapy (CCRT) followed by adjuvant durvalumab is standard-of-care for fit patients with unresectable stage III NSCLC. Intensity modulated proton therapy (IMPT) results in different doses to organs than intensity modulated photon therapy (IMRT). We investigated whether IMPT compared to IMRT reduce hematological toxicity and whether it affects durvalumab treatment. MATERIALS AND METHODS: Prospectively collected series of consecutive patients with stage III NSCLC receiving CCRT between 06.16 and 12.22 (staged with FDG-PET-CT and brain imaging) were retrospectively analyzed. The primary endpoint was the incidence of lymphopenia grade ≥ 3 in IMPT vs IMRT treated patients. RESULTS: 271 patients were enrolled (IMPT: n = 71, IMRT: n = 200) in four centers. All patients received platinum-based chemotherapy. Median age: 66 years, 58 % were male, 36 % had squamous NSCLC. The incidence of lymphopenia grade ≥ 3 during CCRT was 67 % and 47 % in the IMRT and IMPT group, respectively (OR 2.2, 95 % CI: 1.0-4.9, P = 0.03). The incidence of anemia grade ≥ 3 during CCRT was 26 % and 9 % in the IMRT and IMPT group respectively (OR = 4.9, 95 % CI: 1.9-12.6, P = 0.001). IMPT was associated with a lower rate of Performance Status (PS) ≥ 2 at day 21 and 42 after CCRT (13 % vs. 26 %, P = 0.04, and 24 % vs. 39 %, P = 0.02). Patients treated with IMPT had a higher probability of receiving adjuvant durvalumab (74 % vs. 52 %, OR 0.35, 95 % CI: 0.16-0.79, P = 0.01). CONCLUSION: IMPT was associated with a lower incidence of severe lymphopenia and anemia, better PS after CCRT and a higher probability of receiving adjuvant durvalumab.

Comparison of photon intensity modulated, hybrid and volumetric modulated arc radiation treatment techniques in locally advanced non-small cell lung cancer.

Background and purpose: There is no consensus on the best photon radiation technique for non-small cell lung cancer (NSCLC). This study quantified the differences between commonly used treatment techniques in NSCLC to find the optimal technique. Materials and methods: Treatment plans were retrospectively generated according to clinical guidelines for 26 stage III NSCLC patients using intensity modulated radiation therapy (IMRT), hybrid, and volumetric modulated arc therapy (VMATC, and VMATV5 optimized for lower lung and heart dose). Plans were evaluated for target coverage, organs at risk dose (including heart substructures) and normal tissue complication probabilities (NTCP). Results: The comparison showed significant and largest median differences (>1 Gy or >5%) in favor of IMRT for the mediastinal envelope and heart (maximum dose), in favor of the hybrid technique for the lungs (V5Gy of the total lungs and V5Gy of the contralateral lung) and in favor of VMATC for the heart (Dmean), most of the substructures of the heart, and the spinal cord (maximum dose). The VMATV5 technique had significantly lower heart dose compared to the hybrid technique and significantly lower lung dose compared to the VMATC, combining both advantages in one technique. The mean ΔNTCP did not exceed the 2 percent point (pp) for grade 5 (mortality), and 10 pp for grade ≥2 toxicities (radiation pneumonitis and acute esophageal toxicity), but ΔNTCP was mostly in favor of VMATC/V5 for individual patients. Conclusion: This planning study showed that VMATV5 was preferred as it achieved low lung and heart doses, as well as low NTCPs, simultaneously.

Geometric and dosimetric analysis of CT- and MR-based automatic contouring for the EPTN contouring atlas in neuro-oncology.

PURPOSE: Atlas-based and deep-learning contouring (DLC) are methods for automatic segmentation of organs-at-risk (OARs). The European Particle Therapy Network (EPTN) published a consensus-based atlas for delineation of OARs in neuro-oncology. In this study, geometric and dosimetric evaluation of automatically-segmented neuro-oncological OARs was performed using CT- and MR-models following the EPTN-contouring atlas. METHODS: Image and contouring data from 76 neuro-oncological patients were included. Two atlas-based models (CT-atlas and MR-atlas) and one DLC-model (MR-DLC) were created. Manual contours on registered CT-MR-images were used as ground-truth. Results were analyzed in terms of geometrical (volumetric Dice similarity coefficient (vDSC), surface DSC (sDSC), added path length (APL), and mean slice-wise Hausdorff distance (MSHD)) and dosimetrical accuracy. Distance-to-tumor analysis was performed to analyze to which extent the location of the OAR relative to planning target volume (PTV) has dosimetric impact, using Wilcoxon rank-sum tests. RESULTS: CT-atlas outperformed MR-atlas for 22/26 OARs. MR-DLC outperformed MR-atlas for all OARs. Highest median (95 %CI) vDSC and sDSC were found for the brainstem in MR-DLC: 0.92 (0.88-0.95) and 0.84 (0.77-0.89) respectively, as well as lowest MSHD: 0.27 (0.22-0.39)cm. Median dose differences (ΔD) were within ± 1 Gy for 24/26(92 %) OARs for all three models. Distance-to-tumor showed a significant correlation for ΔDmax,0.03cc-parameters when splitting the data in ≤ 4 cm and > 4 cm OAR-distance (p < 0.001). CONCLUSION: MR-based DLC and CT-based atlas-contouring enable high-quality segmentation. It was shown that a combination of both CT- and MR-autocontouring models results in the best quality.

Clinical evaluation of synthetic computed tomography methods in adaptive proton therapy of lung cancer patients.

Background and purpose: Efficient workflows for adaptive proton therapy are of high importance. This study evaluated the possibility to replace repeat-CTs (reCTs) with synthetic CTs (sCTs), created based on cone-beam CTs (CBCTs), for flagging the need of plan adaptations in intensity-modulated proton therapy (IMPT) treatment of lung cancer patients. Materials and methods: Forty-two IMPT patients were retrospectively included. For each patient, one CBCT and a same-day reCT were included. Two commercial sCT methods were applied; one based on CBCT number correction (Cor-sCT), and one based on deformable image registration (DIR-sCT). The clinical reCT workflow (deformable contour propagation and robust dose re-computation) was performed on the reCT as well as the two sCTs. The deformed target contours on the reCT/sCTs were checked by radiation oncologists and edited if needed. A dose-volume-histogram triggered plan adaptation method was compared between the reCT and the sCTs; patients needing a plan adaptation on the reCT but not on the sCT were denoted false negatives. As secondary evaluation, dose-volume-histogram comparison and gamma analysis (2%/2mm) were performed between the reCT and sCTs. Results: There were five false negatives, two for Cor-sCT and three for DIR-sCT. However, three of these were only minor, and one was caused by tumour position differences between the reCT and CBCT and not by sCT quality issues. An average gamma pass rate of 93% was obtained for both sCT methods. Conclusion: Both sCT methods were judged to be of clinical quality and valuable for reducing the amount of reCT acquisitions.

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

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

Radiotherapy for mediastinal lymphoma in breath hold using surface monitoring and nasal high flow oxygen: Clinical experiences and breath hold stability.

PURPOSE: In this study we describe the clinical introduction and evaluation of radiotherapy in mediastinal lymphoma in breath hold using surface monitoring combined with nasal high flow therapy (NHFT) to prolong breath hold duration. MATERIALS AND METHODS: 11 Patients with mediastinal lymphoma were evaluated. 6 Patients received NHFT, 5 patients were treated in breath hold without NHFT. Breath hold stability as measured by a surface scanning system was evaluated, as well as internal movement based on cone beam computed tomography (CBCT) before and after treatment. Based on internal movement, margins were determined. In a parallel planning study we compared free breathing plans with breath hold plans using the determined margins. RESULTS: Average inter breath hold stability was 0.6 mm for NHFT treatments, and 0.5 mm for non-NHFT treatments (p > 0.1). Intra breath hold stability was 0.8 vs. 0.6 mm (p > 0.1) on average. Using NHFT, average breath hold duration increased from 34 s to 60 s (p < 0.01). Residual CTV motion derived from CBCTs before and after each fraction was 2.0 mm for NHFT vs 2.2 mm for non-NHFT (p > 0.1). Combined with inter-fraction motion, a uniform mediastinal margin of 5 mm appears to be sufficient. In breath hold, mean lung dose is reduced by 2.6 Gy (p < 0.001), while mean heart dose is reduced by 2.0 Gy (p < 0.001). CONCLUSION: Treatment of mediastinal lymphoma in breath hold is feasible and safe. The addition of NHFT approximately increases breath hold durations with a factor two while stability is maintained. By reducing breathing motion, margins can be decreased to 5 mm. A considerable dose reduction in heart, lungs, esophagus, and breasts can be achieved with this method.

Automatic quality assurance of radiotherapy treatment plans using Bayesian networks: A multi-institutional study.

Purpose: Artificial intelligence applications in radiation oncology have been the focus of study in the last decade. The introduction of automated and intelligent solutions for routine clinical tasks, such as treatment planning and quality assurance, has the potential to increase safety and efficiency of radiotherapy. In this work, we present a multi-institutional study across three different institutions internationally on a Bayesian network (BN)-based initial plan review assistive tool that alerts radiotherapy professionals for potential erroneous or suboptimal treatment plans. Methods: Clinical data were collected from the oncology information systems in three institutes in Europe (Maastro clinic - 8753 patients treated between 2012 and 2020) and the United States of America (University of Vermont Medical Center [UVMMC] - 2733 patients, University of Washington [UW] - 6180 patients, treated between 2018 and 2021). We trained the BN model to detect potential errors in radiotherapy treatment plans using different combinations of institutional data and performed single-site and cross-site validation with simulated plans with embedded errors. The simulated errors consisted of three different categories: i) patient setup, ii) treatment planning and iii) prescription. We also compared the strategy of using only diagnostic parameters or all variables as evidence for the BN. We evaluated the model performance utilizing the area under the receiver-operating characteristic curve (AUC). Results: The best network performance was observed when the BN model is trained and validated using the dataset in the same center. In particular, the testing and validation using UVMMC data has achieved an AUC of 0.92 with all parameters used as evidence. In cross-validation studies, we observed that the BN model performed better when it was trained and validated in institutes with similar technology and treatment protocols (for instance, when testing on UVMMC data, the model trained on UW data achieved an AUC of 0.84, compared with an AUC of 0.64 for the model trained on Maastro data). Also, combining training data from larger clinics (UW and Maastro clinic) and using it on smaller clinics (UVMMC) leads to satisfactory performance with an AUC of 0.85. Lastly, we found that in general the BN model performed better when all variables are considered as evidence. Conclusion: We have developed and validated a Bayesian network model to assist initial treatment plan review using multi-institutional data with different technology and clinical practices. The model has shown good performance even when trained on data from clinics with divergent profiles, suggesting that the model is able to adapt to different data distributions.

BioXmark® liquid fiducials to enable radiotherapy tumor boosting in rectal cancer, a feasibility trial.

Background and purpose: Dose-escalation in rectal cancer (RCa) may result in an increased complete response rate and thereby enable omission of surgery and organ preservation. In order to implement dose-escalation, it is crucial to develop a technique that allows for accurate image-guided radiotherapy. The aim of the current study was to determine the performance of a novel liquid fiducial marker (BioXmark®) in RCa patients during the radiotherapy course by assessing its positional stability on daily cone-beam CT (CBCT), technical feasibility, visibility on different imaging modalities and safety. Materials and methods: Prospective, non-randomized, single-arm feasibility trial with inclusion of twenty patients referred for neoadjuvant chemoradiotherapy for locally advanced RCa. Primary study endpoint was positional stability on CBCT. Furthermore, technical aspects, safety and clinical performance of the marker, such as visibility on different imaging modalities, were evaluated. Results: Seventy-four markers from twenty patients were available for analysis. The marker was stable in 96% of the cases. One marker showed clinically relevant migration, one marker was lost before start of treatment and one marker was lost during treatment. Marker visibility was good on computed tomography (CT) and CBCT, and moderate on electronic portal imaging (EPI). Marker visibility on magnetic resonance imaging (MRI) was poor during response evaluation. Conclusion: The novel liquid fiducial marker demonstrated positional stability. We provide evidence of the feasibility of the novel fiducial marker for image-guided radiotherapy on daily cone beam CT for RCa patients.

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

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

Plan quality assessment in clinical practice: Results of the 2020 ESTRO survey on plan complexity and robustness.

PURPOSE: Plan complexity and robustness are two essential aspects of treatment plan quality but there is a great variability in their management in clinical practice. This study reports the results of the 2020 ESTRO survey on plan complexity and robustness to identify needs and guide future discussions and consensus. METHODS: A survey was distributed online to ESTRO members. Plan complexity was defined as the modulation of machine parameters and increased uncertainty in dose calculation and delivery. Robustness was defined as a dose distribution's sensitivity towards errors stemming from treatment uncertainties, patient setup, or anatomical changes. RESULTS: A total of 126 radiotherapy centres from 33 countries participated, 95 of them (75%) from Europe and Central Asia. The majority controlled and evaluated plan complexity using monitor units (56 centres) and aperture shapes (38 centres). To control robustness, 98 (97% of question responses) photon and 5 (50%) proton centres used PTV margins for plan optimization while 75 (94%) and 5 (50%), respectively, used margins for plan evaluation. Seventeen (21%) photon and 8 (80%) proton centres used robust optimisation, while 10 (13%) and 8 (80%), respectively, used robust evaluation. Primary uncertainties considered were patient setup (photons and protons) and range calculation uncertainties (protons). Participants expressed the need for improved commercial tools to control and evaluate plan complexity and robustness. CONCLUSION: Clinical implementation of methods to control and evaluate plan complexity and robustness is very heterogeneous. Better tools are needed to manage complexity and robustness in treatment planning systems. International guidelines may promote harmonization.

Real-world analysis of manual editing of deep learning contouring in the thorax region.

Background and purpose: User-adjustments after deep-learning (DL) contouring in radiotherapy were evaluated to get insight in real-world editing during clinical practice. This study assessed the amount, type and spatial regions of editing of auto-contouring for organs-at-risk (OARs) in routine clinical workflow for patients in the thorax region. Materials and methods: A total of 350 lung cancer and 362 breast cancer patients, contoured between March 2020 and March 2021 using a commercial DL-contouring method followed by manual adjustments were retrospectively analyzed. Subsampling was performed for some OARs, using an inter-slice gap of 1-3 slices. Commonly-used whole-organ contouring assessment measures were calculated, and all cases were registered to a common reference shape per OAR to identify regions of manual adjustment. Results were expressed as the median, 10th-90th percentile of adjustment and visualized using 3D renderings. Results: Per OAR, the median amount of editing was below 1 mm. However, large adjustments were found in some locations for most OARs. In general, enlarging of the auto-contours was needed. Subsampling DL-contours showed less adjustments were made in the interpolated slices compared to simulated no-subsampling for these OARs. Conclusion: The real-world performance of automatic DL-contouring software was evaluated and proven useful in clinical practice. Specific regions-of-adjustment were identified per OAR in the thorax region, and separate models were found to be necessary for specific clinical indications different from training data. This analysis showed the need to perform routine clinical analysis especially when procedures or acquisition protocols change to have the best configuration of the workflow.

Treatment planning comparison in the PROTECT-trial randomising proton versus photon beam therapy in oesophageal cancer: Results from eight European centres.

PURPOSE: To compare dose distributions and robustness in treatment plans from eight European centres in preparation for the European randomized phase-III PROTECT-trial investigating the effect of proton therapy (PT) versus photon therapy (XT) for oesophageal cancer. MATERIALS AND METHODS: All centres optimized one PT and one XT nominal plan using delineated 4DCT scans for four patients receiving 50.4 Gy (RBE) in 28 fractions. Target volume receiving 95% of prescribed dose (V95%iCTVtotal) should be >99%. Robustness towards setup, range, and respiration was evaluated. The plans were recalculated on a surveillance 4DCT (sCT) acquired at fraction ten and robustness evaluation was performed to evaluate the effect of respiration and inter-fractional anatomical changes. RESULTS: All PT and XT plans complied with V95%iCTVtotal >99% for the nominal plan and V95%iCTVtotal >97% for all respiratory and robustness scenarios. Lung and heart dose varied considerably between centres for both modalities. The difference in mean lung dose and mean heart dose between each pair of XT and PT plans was in median [range] 4.8 Gy [1.1;7.6] and 8.4 Gy [1.9;24.5], respectively. Patients B and C showed large inter-fractional anatomical changes on sCT. For patient B, the minimum V95%iCTVtotal in the worst-case robustness scenario was 45% and 94% for XT and PT, respectively. For patient C, the minimum V95%iCTVtotal was 57% and 72% for XT and PT, respectively. Patient A and D showed minor inter-fractional changes and the minimum V95%iCTVtotal was >85%. CONCLUSION: Large variability in dose to the lungs and heart was observed for both modalities. Inter-fractional anatomical changes led to larger target dose deterioration for XT than PT plans.

The impact of organ-at-risk contour variations on automatically generated treatment plans for NSCLC.

BACKGROUND AND PURPOSE: Quality of automatic contouring is generally assessed by comparison with manual delineations, but the effect of contour differences on the resulting dose distribution remains unknown. This study evaluated dosimetric differences between treatment plans optimized using various organ-at-risk (OAR) contouring methods. MATERIALS AND METHODS: OARs of twenty lung cancer patients were manually and automatically contoured, after which user-adjustments were made. For each contour set, an automated treatment plan was generated. The dosimetric effect of intra-observer contour variation and the influence of contour variations on treatment plan evaluation and generation were studied using dose-volume histogram (DVH)-parameters for thoracic OARs. RESULTS: Dosimetric effect of intra-observer contour variability was highest for Heart Dmax (3.4 ± 6.8 Gy) and lowest for Lungs-GTV Dmean (0.3 ± 0.4 Gy). The effect of contour variation on treatment plan evaluation was highest for Heart Dmax (6.0 ± 13.4 Gy) and Esophagus Dmax (8.7 ± 17.2 Gy). Dose differences for the various treatment plans, evaluated on the reference (manual) contour, were on average below 1 Gy/1%. For Heart Dmean, higher dose differences were found for overlap with PTV (median 0.2 Gy, 95% 1.7 Gy) vs. no PTV overlap (median 0 Gy, 95% 0.5 Gy). For Dmax-parameters, largest dose difference was found between 0-1 cm distance to PTV (median 1.5 Gy, 95% 4.7 Gy). CONCLUSION: Dose differences arising from automatic contour variations were of the same magnitude or lower than intra-observer contour variability. For Heart Dmean, we recommend delineation errors to be corrected when the heart overlaps with the PTV. For Dmax-parameters, we recommend checking contours if the distance is close to PTV (<5 cm). For the lungs, only obvious large errors need to be adjusted.

Treatment planning and 4D robust evaluation strategy for proton therapy of lung tumors with large motion amplitude.

PURPOSE: Intensity-modulated proton therapy (IMPT) for lung tumors with a large tumor movement is challenging due to loss of robustness in the target coverage. Often an upper cut-off at 5-mm tumor movement is used for proton patient selection. In this study, we propose (1) a robust and easily implementable treatment planning strategy for lung tumors with a movement larger than 5 mm, and (2) a four-dimensional computed tomography (4DCT) robust evaluation strategy for evaluating the dose distribution on the breathing phases. MATERIALS AND METHODS: We created a treatment planning strategy based on the internal target volume (ITV) concept (aim 1). The ITV was created as a union of the clinical target volumes (CTVs) on the eight 4DCT phases. The ITV expanded by 2 mm was the target during robust optimization on the average CT (avgCT). The clinical plan acceptability was judged based on a robust evaluation, computing the voxel-wise min and max (VWmin/max) doses over 28 error scenarios (range and setup errors) on the avgCT. The plans were created in RayStation (RaySearch Laboratories, Stockholm, Sweden) using a Monte Carlo dose engine, commissioned for our Mevion S250i Hyperscan system (Mevion Medical Systems, Littleton, MA, USA). We developed a new 4D robust evaluation approach (4DRobAvg; aim 2). The 28 scenario doses were computed on each individual 4DCT phase. For each scenario, the dose distributions on the individual phases were deformed to the reference phase and combined to a weighted sum, resulting in 28 weighted sum scenario dose distributions. From these 28 scenario doses, VWmin/max doses were computed. This new 4D robust evaluation was compared to two simpler 4D evaluation strategies: re-computing the nominal plan on each individual 4DCT phase (4DNom) and computing the robust VWmin/max doses on each individual phase (4DRobInd). The treatment planning and dose evaluation strategies were evaluated for 16 lung cancer patients with tumor movement of 4-26 mm. RESULTS: The ratio of the ITV and CTV volumes increased linearly with the tumor amplitude, with an average ratio of 1.4. Despite large ITV volumes, a clinically acceptable plan fulfilling all target and organ at risk (OAR) constraints was feasible for all patients. The 4DNom and 4DRobInd evaluation strategies were found to under- or overestimate the dosimetric effect of the tumor movement, respectively. 4DRobInd showed target underdosage for five patients, not observed in the robust evaluation on the avgCT or in 4DRobAvg. The accuracy of dose deformation used in 4DRobAvg was quantified and found acceptable, with differences for the dose-volume parameters below 1 Gy in most cases. CONCLUSION: The proposed ITV-based planning strategy on the avgCT was found to be a clinically feasible approach with adequate tumor coverage and no OAR overdosage even for large tumor movement. The new proposed 4D robust evaluation, 4DRobAvg, was shown to give an easily interpretable understanding of the effect of respiratory motion dose distribution, and to give an accurate estimate of the dose delivered in the different breathing phases.

Identification of treatment error types for lung cancer patients using convolutional neural networks and EPID dosimetry.

BACKGROUND/PURPOSE: Electronic portal imaging device (EPID) dosimetry aims to detect treatment errors, potentially leading to treatment adaptation. Clinically used threshold classification methods for detecting errors lead to loss of information (from multi-dimensional EPID data to a few numbers) and cannot be used for identifying causes of errors. Advanced classification methods, such as deep learning, can use all available information. In this study, convolutional neural networks (CNNs) were trained to detect and identify error type and magnitude of simulated treatment errors in lung cancer patients. The purpose of this simulation study is to provide a proof-of-concept of CNNs for error identification using EPID dosimetry in an in vivo scenario. MATERIALS AND METHODS: Clinically realistic ranges of anatomical changes, positioning errors and mechanical errors were simulated for lung cancer patients. Predicted portal dose images (PDIs) containing errors were compared to error-free PDIs using the widely used gamma analysis. CNNs were trained to classify errors using 2D gamma maps. Three classification levels were assessed: Level 1 (main error type, e.g., anatomical change), Level 2 (error subtype, e.g., tumor regression) and Level 3 (error magnitude, e.g., >50% tumor regression). RESULTS: CNNs showed good performance for all classification levels (training/test accuracy 99.5%/96.1%, 92.5%/86.8%, 82.0%/72.9%). For Level 3, overfitting became more apparent. CONCLUSION: This simulation study indicates that deep learning is a promising powerful tool for identifying types and magnitude of treatment errors with EPID dosimetry, providing additional information not currently available from EPID dosimetry. This is a first step towards rapid, automated models for identification of treatment errors using EPID dosimetry.

What is plan quality in radiotherapy? The importance of evaluating dose metrics, complexity, and robustness of treatment plans.

Plan evaluation is a key step in the radiotherapy treatment workflow. Central to this step is the assessment of treatment plan quality. Hence, it is important to agree on what we mean by plan quality and to be fully aware of which parameters it depends on. We understand plan quality in radiotherapy as the clinical suitability of the delivered dose distribution that can be realistically expected from a treatment plan. Plan quality is commonly assessed by evaluating the dose distribution calculated by the treatment planning system (TPS). Evaluating the 3D dose distribution is not easy, however; it is hard to fully evaluate its spatial characteristics and we still lack the knowledge for personalising the prediction of the clinical outcome based on individual patient characteristics. This advocates for standardisation and systematic collection of clinical data and outcomes after radiotherapy. Additionally, the calculated dose distribution is not exactly the dose delivered to the patient due to uncertainties in the dose calculation and the treatment delivery, including variations in the patient set-up and anatomy. Consequently, plan quality also depends on the robustness and complexity of the treatment plan. We believe that future work and consensus on the best metrics for quality indices are required. Better tools are needed in TPSs for the evaluation of dose distributions, for the robust evaluation and optimisation of treatment plans, and for controlling and reporting plan complexity. Implementation of such tools and a better understanding of these concepts will facilitate the handling of these characteristics in clinical practice and be helpful to increase the overall quality of treatment plans in radiotherapy.

External validation of a hidden Markov model for gamma-based classification of anatomical changes in lung cancer patients using EPID dosimetry.

PURPOSE: To externally validate a hidden Markov model (HMM) for classifying gamma analysis results of in vivo electronic portal imaging device (EPID) measurements into different categories of anatomical change for lung cancer patients. Additionally, the relationship between HMM classification and deviations in dose-volume histogram (DVH) metrics was evaluated. METHODS: The HMM was developed at CHU de Québec (CHUQ), and trained on features extracted from gamma analysis maps of in vivo EPID measurements from 483 fractions (24 patients, treated with three-dimensional 3D-CRT or intensity modulated radiotherapy), using the EPID measurement of the first treatment fraction as reference. The model inputs were the average gamma value, standard deviation, and average value of the highest 1% of gamma values, all averaged over all beams in a fraction. The HMM classified each fraction into one of three categories: no anatomical change (Category 1), some anatomical change (no clinical action needed, Category 2) and severe anatomical change (clinical action needed, Category 3). The external validation dataset consisted of EPID measurements from 263 fractions of 30 patients treated at Maastro with volumetric modulated arc therapy (VMAT) or hybrid plans (containing both static beams and VMAT arcs). Gamma analysis features were extracted in the same way as in the CHUQ dataset, by using the EPID measurement of the first fraction as reference (γQ), and additionally by using an EPID dose prediction as reference (γM). For Maastro patients, cone beam computed tomography (CBCT) scans and image-guided radiotherapy (IGRT) classification of these images were available for each fraction. Contours were propagated from the planning CT to the CBCTs, and the dose was recalculated using a Monte Carlo dose engine. Dose-volume histogram metrics for targets and organs-at-risk (OARs: lungs, heart, mediastinum, spinal cord, brachial plexus) were extracted for each fraction, and compared to the planned dose. HMM classification of the external validation set was compared to threshold classification based on the average gamma value alone (a surrogate for clinical classification at CHUQ), IGRT classification as performed at Maastro, and differences in DVH metrics extracted from 3D dose recalculations on the CBCTs. RESULTS: The HMM achieved 65.4%/65.0% accuracy for γQ and γM, respectively, compared to average gamma threshold classification. When comparing HMM classification with IGRT classification, the overall accuracy was 29.7% for γQ and 23.2% for γM. Hence, HMM classification and IGRT classification of anatomical changes did not correspond. However, there is a trend towards higher deviations in DVH metrics with classification into higher categories by the HMM for large OARs (lungs, heart, mediastinum), but not for the targets and small OARs (spinal cord, brachial plexus). CONCLUSION: The external validation shows that transferring the HMM for anatomical change classification to a different center is challenging, but can still be valuable. The HMM trained at CHUQ cannot be used directly to classify anatomical changes in the Maastro data. However, it may be possible to use the model in a different capacity, as an indicator for changes in the 3D dose based on two-dimensional EPID measurements.

Radiotherapy quality assurance for mesorectum treatment planning within the multi-center phase II STAR-TReC trial: Dutch results.

BACKGROUND: The STAR-TReC trial is an international multi-center, randomized, phase II study assessing the feasibility of short-course radiotherapy or long-course chemoradiotherapy as an alternative to total mesorectal excision surgery. A new target volume is used for both (chemo)radiotherapy arms which includes only the mesorectum. The treatment planning QA revealed substantial variation in dose to organs at risk (OAR) between centers. Therefore, the aim of this study was to determine the treatment plan variability in terms of dose to OAR and assess the effect of a national study group meeting on the quality and variability of treatment plans for mesorectum-only planning for rectal cancer. METHODS: Eight centers produced 25 × 2 Gy treatment plans for five cases. The OAR were the bowel cavity, bladder and femoral heads. A study group meeting for the participating centers was organized to discuss the planning results. At the meeting, the values of the treatment plan DVH parameters were distributed among centers so that results could be compared. Subsequently, the centers were invited to perform replanning if they considered this to be necessary. RESULTS: All treatment plans, both initial planning and replanning, fulfilled the target constraints. Dose to OAR varied considerably for the initial planning, especially for dose levels below 20 Gy, indicating that there was room for trade-offs between the defined OAR. Five centers performed replanning for all cases. One center did not perform replanning at all and two centers performed replanning on two and three cases, respectively. On average, replanning reduced the bowel cavity V20Gy by 12.6%, bowel cavity V10Gy by 22.0%, bladder V35Gy by 14.7% and bladder V10Gy by 10.8%. In 26/30 replanned cases the V10Gy of both the bowel cavity and bladder was lower, indicating an overall lower dose to these OAR instead of a different trade-off. In addition, the bowel cavity V10Gy and V20Gy showed more similarity between centers. CONCLUSIONS: Dose to OAR varied considerably between centers, especially for dose levels below 20 Gy. The study group meeting and the distribution of the initial planning results among centers resulted in lower dose to the defined OAR and reduced variability between centers after replanning. TRIAL REGISTRATION: The STAR-TReC trial, ClinicalTrials.gov Identifier: NCT02945566. Registered 26 October 2016, https://clinicaltrials.gov/ct2/show/NCT02945566).

Evaluation of measures for assessing time-saving of automatic organ-at-risk segmentation in radiotherapy.

BACKGROUND AND PURPOSE: In radiotherapy, automatic organ-at-risk segmentation algorithms allow faster delineation times, but clinically relevant contour evaluation remains challenging. Commonly used measures to assess automatic contours, such as volumetric Dice Similarity Coefficient (DSC) or Hausdorff distance, have shown to be good measures for geometric similarity, but do not always correlate with clinical applicability of the contours, or time needed to adjust them. This study aimed to evaluate the correlation of new and commonly used evaluation measures with time-saving during contouring. MATERIALS AND METHODS: Twenty lung cancer patients were used to compare user-adjustments after atlas-based and deep-learning contouring with manual contouring. The absolute time needed (s) of adjusting the auto-contour compared to manual contouring was recorded, from this relative time-saving (%) was calculated. New evaluation measures (surface DSC and added path length, APL) and conventional evaluation measures (volumetric DSC and Hausdorff distance) were correlated with time-recordings and time-savings, quantified with the Pearson correlation coefficient, R. RESULTS: The highest correlation (R = 0.87) was found between APL and absolute adaption time. Lower correlations were found for APL with relative time-saving (R = -0.38), for surface DSC with absolute adaption time (R = -0.69) and relative time-saving (R = 0.57). Volumetric DSC and Hausdorff distance also showed lower correlation coefficients for absolute adaptation time (R = -0.32 and 0.64, respectively) and relative time-saving (R = 0.44 and -0.64, respectively). CONCLUSION: Surface DSC and APL are better indicators for contour adaptation time and time-saving when using auto-segmentation and provide more clinically relevant and better quantitative measures for automatically-generated contour quality, compared to commonly-used geometry-based measures.

Treatment plan quality assessment for radiotherapy of rectal cancer patients using prediction of organ-at-risk dose metrics.

BACKGROUND AND PURPOSE: Radiotherapy centers frequently lack simple tools for periodic treatment plan verification and feedback on current plan quality. It is difficult to measure treatment quality over different years or during the planning process. Here, we implemented plan quality assurance (QA) by developing a database of dose-volume histogram (DVH) metrics and a prediction model. These tools were used to assess automatically optimized treatment plans for rectal cancer patients, based on cohort analysis. MATERIAL AND METHODS: A treatment plan QA framework was established and an overlap volume histogram based model was used to predict DVH parameters for cohorts of patients treated in 2018 and 2019 and grouped according to planning technique. A training cohort of 22 re-optimized treatment plans was used to make the prediction model. The prediction model was validated on 95 automatically generated treatment plans (automatically optimized cohort) and 93 manually optimized plans (manually optimized cohort). RESULTS: For the manually optimized cohort, on average the prediction deviated less than 0.3 ± 1.4 Gy and -4.3 ± 5.5 Gy, for the mean doses to the bowel bag and bladder, respectively; for the automatically optimized cohort a smaller deviation was observed: -0.1 ± 1.1 Gy and -0.2 ± 2.5 Gy, respectively. The interquartile range of DVH parameters was on average smaller for the automatically optimized cohort, indicating less variation within each parameter compared to manual planning. CONCLUSION: An automated framework to monitor treatment quality with a DVH prediction model was successfully implemented clinically and revealed less variation in DVH parameters for automated in comparison to manually optimized plans. The framework also allowed for individual feedback and DVH estimation.