Mark Bangert

Purpose: Due to the sharp gradients of intensity-modulated radiotherapy (IMRT) dose distributions, treatment uncertainties may induce substantial deviations from the planned dose during irradiation. Here, we investigate if the planned mean dose to parotid glands in combination with the dose gradient and information about anatomical changes during the treatment improves xerostomia prediction in head and neck cancer patients. Materials and methods: Eighty eight patients were retrospectively analyzed. Three features of the contralateral parotid gland were studied in terms of their association with the outcome, i.e., grade ≥ 2 (G2) xerostomia between 6 months and 2 years after radiotherapy (RT): planned mean dose (MD), average lateral dose gradient (GRADX), and parotid gland migration toward medial (PGM). PGM was estimated using daily megavoltage computed tomography (MVCT) images. Three logistic regression models where analyzed: based on (1) MD only, (2) MD and GRADX, and (3) MD, GRADX, and PGM. Additionally, the cohort was stratified based on the median value of GRADX, and a univariate analysis was performed to study the association of the MD with the outcome for patients in low- and high-GRADX domains. Results: The planned MD failed to recognize G2 xerostomia patients (AUC = 0.57). By adding the information of GRADX (second model), the model performance increased to AUC = 0.72. The addition of PGM (third model) led to further improvement in the recognition of the outcome (AUC = 0.79). Remarkably, xerostomia patients in the low-GRADX domain were successfully identified (AUC = 0.88) by the MD alone. Conclusions: Our results indicate that GRADX and PGM, which together serve as a proxy of dosimetric changes, provide valuable information for xerostomia prediction.

Purpose: The purpose of this study is to investigate whether machine learning with dosiomic, radiomic, and demographic features allows for xerostomia risk assessment more precise than normal tissue complication probability (NTCP) models based on the mean radiation dose to parotid glands. Material and methods: A cohort of 153 head-and-neck cancer patients was used to model xerostomia at 0–6 months (early), 6–15 months (late), 15–24 months (long-term), and at any time (a longitudinal model) after radiotherapy. Predictive power of the features was evaluated by the area under the receiver operating characteristic curve (AUC) of univariate logistic regression models. The multivariate NTCP models were tuned and tested with single and nested cross-validation, respectively. We compared predictive performance of seven classification algorithms, six feature selection methods, and ten data cleaning/class balancing techniques using the Friedman test and the Nemenyi post hoc analysis. Results: NTCP models based on the parotid mean dose failed to predict xerostomia (AUCs < 0.60). The most informative predictors were found for late and long-term xerostomia. Late xerostomia correlated with the contralateral dose gradient in the anterior–posterior (AUC = 0.72) and the right–left (AUC = 0.68) direction, whereas long-term xerostomia was associated with parotid volumes (AUCs > 0.85), dose gradients in the right–left (AUCs > 0.78), and the anterior–posterior (AUCs > 0.72) direction. Multivariate models of long-term xerostomia were typically based on the parotid volume, the parotid eccentricity, and the dose–volume histogram (DVH) spread with the generalization AUCs ranging from 0.74 to 0.88. On average, support vector machines and extra-trees were the top performing classifiers, whereas the algorithms based on logistic regression were the best choice for feature selection. We found no advantage in using data cleaning or class balancing methods. Conclusion: We demonstrated that incorporation of organ- and dose-shape descriptors is beneficial for xerostomia prediction in highly conformal radiotherapy treatments. Due to strong reliance on patient-specific, dose-independent factors, our results underscore the need for development of personalized data-driven risk profiles for NTCP models of xerostomia. The facilitated machine learning pipeline is described in detail and can serve as a valuable reference for future work in radiomic and dosiomic NTCP modeling.

Purpose: We show that it is possible to explicitly incorporate fractionation effects into closed‐form probabilistic treatment plan analysis and optimization for intensity‐modulated proton therapy with analytical probabilistic modeling (APM). We study the impact of different fractionation schemes on the dosimetric uncertainty induced by random and systematic sources of range and setup uncertainty for treatment plans that were optimized with and without consideration of the number of treatment fractions.Methods: The APM framework is capable of handling arbitrarily correlated uncertainty models including systematic and random errors in the context of fractionation. On this basis, we construct an analytical dose variance computation pipeline that explicitly considers the number of treatment fractions for uncertainty quantitation and minimization during treatment planning. We evaluate the variance computation model in comparison to random sampling of 100 treatments for conventional and probabilistic treatment plans under different fractionation schemes (1, 5, 30 fractions) for an intracranial, a paraspinal and a prostate case. The impact of neglecting the fractionation scheme during treatment planning is investigated by applying treatment plans that were generated with probabilistic optimization for 1 fraction in a higher number of fractions and comparing them to the probabilistic plans optimized under explicit consideration of the number of fractions.Results: APM enables the construction of an analytical variance computation model for dose uncertainty considering fractionation at negligible computational overhead. It is computationally feasible (a) to simultaneously perform a robustness analysis for all possible fraction numbers and (b) to perform a probabilistic treatment plan optimization for a specific fraction number. The incorporation of fractionation assumptions for robustness analysis exposes a dose to uncertainty trade‐off, i.e., the dose in the organs at risk is increased for a reduced fraction number and/or for more robust treatment plans. By explicit consideration of fractionation effects during planning, we demonstrate that it is possible to exploit this trade‐off during optimization. APM optimization considering the fraction number reduced the dose in organs at risk compared to conventional probabilistic optimization neglecting the fraction number.Conclusion: APM enables computationally efficient incorporation of fractionation effects in probabilistic uncertainty analysis and probabilistic treatment plan optimization. The consideration of the fractionation scheme in probabilistic treatment planning reveals the trade‐off between number of fractions, nominal dose, and treatment plan robustness.

Radiation therapy treatment planning requires an incorporation of uncertainties in order to guarantee an adequate irradiation of the tumor volumes. In current clinical practice, uncertainties are accounted for implicitly with an expansion of the target volume according to generic margin recipes. Alternatively, it is possible to account for uncertainties by explicit minimization of objectives that describe worst-case treatment scenarios, the expectation value of the treatment or the coverage probability of the target volumes during treatment planning. In this note we show that approaches relying on objectives to induce a specific coverage of the clinical target volumes are inevitably sensitive to variation of the relative weighting of the objectives. To address this issue, we introduce coverage-based constraints for intensity-modulated radiation therapy (IMRT) treatment planning. Our implementation follows the concept of coverage-optimized planning that considers explicit error scenarios to calculate and optimize patient-specific probabilities q ( d ^ , v ^ ) of covering a specific target volume fraction v ^ with a certain dose d ^ . Using a constraint-based reformulation of coverage-based objectives we eliminate the trade-off between coverage and competing objectives during treatment planning. In-depth convergence tests including 324 treatment plan optimizations demonstrate the reliability of coverage-based constraints for varying levels of probability, dose and volume. General clinical applicability of coverage-based constraints is demonstrated for two cases. A sensitivity analysis regarding penalty variations within this planing study based on IMRT treatment planning using (1) coverage-based constraints, (2) coverage-based objectives, (3) probabilistic optimization, (4) robust optimization and (5) conventional margins illustrates the potential benefit of coverage-based constraints that do not require tedious adjustment of target volume objectives.

The efficacy of radiation therapy treatments for pancreatic cancer is compromised by abdominal motion which limits the spatial accuracy for dose delivery - especially for particles. In this work we investigate the potential of worst case optimization for interfractional offline motion mitigation in carbon ion treatments of pancreatic cancer. We implement a worst case optimization algorithm that explicitly models the relative biological effectiveness of carbon ions during inverse planning. We perform a comparative treatment planning study for seven pancreatic cancer patients. Treatment plans that have been generated using worst case optimization are compared against (1) conventional intensity-modulated carbon ion therapy, (2) single field uniform dose carbon ion therapy, and (3) an ideal yet impractical scenario relying on daily re-planning. The dosimetric quality and robustness of the resulting treatment plans is evaluated using reconstructions of the daily delivered dose distributions on fractional control CTs. Idealized daily re-planning consistently gives the best dosimetric results with regard to both target coverage and organ at risk sparing. The absolute reduction of D 95 within the gross tumor volume during fractional dose reconstruction is most pronounced for conventional intensity-modulated carbon ion therapy. Single field uniform dose optimization exhibits no substantial reduction for six of seven patients and values for D 95 for worst case optimization fall in between. The treated volume (D>95 % prescription dose) outside of the gross tumor volume is reduced by a factor of two by worst case optimization compared to conventional optimization and single field uniform dose optimization. Single field uniform dose optimization comes at an increased radiation exposure of normal tissues, e.g. ≈2 Gy (RBE) in the mean dose in the kidneys compared to conventional and worst case optimization and ≈4 Gy (RBE) in D 1 in the spinal cord compared to worst case optimization. Interfractional motion substantially deteriorates dose distributions for carbon ion treatments of pancreatic cancer patients. Single field uniform dose optimization mitigates the negative influence of motion on target coverage at an increased radiation exposure of normal tissue. Worst case optimization enables an exploration of the trade-off between robust target coverage and organ at risk sparing during inverse treatment planning beyond margin concepts.

Purpose: Iterative methods for beam angle selection (BAS) for intensity‐modulated radiation therapy (IMRT) planning sequentially construct a beneficial ensemble of beam directions. In a naïve implementation, the nth beam is selected by adding beam orientations one‐by‐one from a discrete set of candidates to an existing ensemble of (n − 1) beams. The best beam orientation is identified in a time consuming process by solving the fluence map optimization (FMO) problem for every candidate beam and selecting the beam that yields the largest improvement to the objective function value. This paper evaluates two alternative methods to accelerate iterative BAS based on surrogates for the FMO objective function value.Methods: We suggest to select candidate beams not based on the FMO objective function value after convergence but (1) based on the objective function value after five FMO iterations of a gradient based algorithm and (2) based on a projected gradient of the FMO problem in the first iteration. The performance of the objective function surrogates is evaluated based on the resulting objective function values and dose statistics in a treatment planning study comprising three intracranial, three pancreas, and three prostate cases. Furthermore, iterative BAS is evaluated for an application in which a small number of noncoplanar beams complement a set of coplanar beam orientations. This scenario is of practical interest as noncoplanar setups may require additional attention of the treatment personnel for every couch rotation.Results: Iterative BAS relying on objective function surrogates yields similar results compared to naïve BAS with regard to the objective function values and dose statistics. At the same time, early stopping of the FMO and using the projected gradient during the first iteration enable reductions in computation time by approximately one to two orders of magnitude. With regard to the clinical delivery of noncoplanar IMRT treatments, we could show that optimized beam ensembles using only a few noncoplanar beam orientations often approach the plan quality of fully noncoplanar ensembles.Conclusions: We conclude that iterative BAS in combination with objective function surrogates can be a viable option to implement automated BAS at clinically acceptable computation times.

Background: We provide common datasets (which we call the CORT dataset: common optimization for radiation therapy) that researchers can use when developing and contrasting radiation treatment planning optimization algorithms. The datasets allow researchers to make one-to-one comparisons of algorithms in order to solve various instances of the radiation therapy treatment planning problem in intensity modulated radiation therapy (IMRT), including beam angle optimization, volumetric modulated arc therapy and direct aperture optimization. Results: We provide datasets for a prostate case, a liver case, a head and neck case, and a standard IMRT phantom. We provide the dose-influence matrix from a variety of beam/couch angle pairs for each dataset. The dose-influence matrix is the main entity needed to perform optimizations: it contains the dose to each patient voxel from each pencil beam. In addition, the original Digital Imaging and Communications in Medicine (DICOM) computed tomography (CT) scan, as well as the DICOM structure file, are provided for each case. Conclusions: Here we present an open dataset – the first of its kind – to the radiation oncology community, which will allow researchers to compare methods for optimizing radiation dose delivery.

Purpose:: Various strategies to select beneficial beam ensembles for intensity‐modulated radiation therapy (IMRT) have been suggested over the years. These beam angle selection (BAS) strategies are usually evaluated against reference configurations applying equispaced coplanar beams but they are not compared to one another. Here, the authors present a meta analysis of four BAS strategies that incorporates fluence optimization (FO) into BAS by combinatorial optimization (CO) and one BAS strategy that decouples FO from BAS, i.e., spherical cluster analysis (SCA). The underlying parameters of the BAS process are investigated and the dosimetric benefits of the BAS strategies are quantified.Methods:: For three intracranial lesions in proximity to organs at risk (OARs) the authors compare treatment plans applying equispaced coplanar beam ensembles with treatment plans using five different BAS strategies, i.e., four CO techniques and SCA, to establish coplanar and noncoplanar beam ensembles. Treatment plans applying 5, 7, 9, and 11 beams are investigated. For the CO strategies the authors perform BAS runs with a 5°, 10°, 15°, and 20° angular resolution, which corresponds to a minimum of 18 coplanar and a maximum of 1400 noncoplanar candidate beams. In total 272 treatment plans with different BAS settings are generated for every patient. The quality of the treatment plans is compared based on the protection of OARs yet integral dose, target homogeneity, and target conformity are also considered.Results:: It is possible to reduce the average mean and maximum doses in OARs by more than 4 Gy (1 Gy) with optimized noncoplanar (coplanar) beam ensembles found with BAS by CO or SCA. For BAS including FO by CO, the individual algorithm used and the angular resolution in the space of candidate beams does not have a crucial impact on the quality of the resulting treatment plans. All CO algorithms yield similar target conformity and slightly improved target homogeneity in comparison to equispaced coplanar setups. Furthermore, optimized coplanar (noncoplanar) beam ensembles enabled more than a 6% (5%) reduction of the integral dose. For SCA, however, integral dose was increased and target conformity was decreased in comparison to equispaced coplanar setups—especially for a small number of beams.Conclusion:: Both BAS strategies incorporating FO by CO and independent BAS strategies excluding FO provide dose savings in OARs for optimized coplanar and especially noncoplanar beam ensembles; they should not be neglected in the clinic.

An intuitive heuristic to establish beam configurations for intensity-modulated radiation therapy is introduced as an extension of beam ensemble selection strategies applying scalar scoring functions. It is validated by treatment plan comparisons for three intra-cranial, pancreas, and prostate cases each. Based on a patient specific matrix listing the radiological quality of candidate beam directions individually for every target voxel, a set of locally ideal beam angles is generated. The spherical distribution of locally ideal beam angles is characteristic for every treatment site and patient: ideal beam angles typically cluster around distinct orientations. We interpret the cluster centroids, which are identified with a spherical K-means algorithm, as irradiation angles of an intensity-modulated radiation therapy treatment plan. The fluence profiles are subsequently optimized during a conventional inverse planning process. The average computation time for the pre-optimization of a beam ensemble is six minutes on a state-of-the-art work station. The treatment planning study demonstrates the potential benefit of the proposed beam angle optimization strategy. For the three prostate cases under investigation, the standard treatment plans applying nine coplanar equi-spaced beams and treatment plans applying an optimized non-coplanar nine-beam ensemble yield clinically comparable dose distributions. For symmetric patient geometries, the dose distribution formed by nine equi-spaced coplanar beams cannot be improved significantly. For the three pancreas and intra-cranial cases under investigation, the optimized non-coplanar beam ensembles enable better sparing of organs at risk while guaranteeing equivalent target coverage. Beam angle optimization by spherical cluster analysis shows the biggest impact for target volumes located asymmetrically within the patient and close to organs at risk.