The minimum knowledge base for predicting organ-at-risk dose-volume levels and plan-related complications in IMRT planning.

IMRT treatment planning requires consideration of two competing objectives: achieving the required amount of radiation for the planning target volume and minimizing the amount of radiation delivered to all other tissues. It is important for planners to understand the tradeoff between competing factors so that the time-consuming human interaction loop (plan-evaluate-modify) can be eliminated. Treatment-plan-surface models have been proposed as a decision support tool to aid treatment planners and clinicians in choosing between rival treatment plans in a multi-plan environment. In this paper, an empirical approach is introduced to determine the minimum number of treatment plans (minimum knowledge base) required to build accurate representations of the IMRT plan surface in order to predict organ-at-risk (OAR) dose-volume (DV) levels and complications as a function of input DV constraint settings corresponding to all involved OARs in the plan. We have tested our approach on five head and neck patients and five whole pelvis/prostate patients. Our results suggest that approximately 30 plans were sufficient to predict DV levels with less than 3% relative error in both head and neck and whole pelvis/prostate cases. In addition, approximately 30-60 plans were sufficient to predict saliva flow rate with less than 2% relative error and to classify rectal bleeding with an accuracy of 90%.

A two-stage sequential linear programming approach to IMRT dose optimization.

The conventional IMRT planning process involves two stages in which the first stage consists of fast but approximate idealized pencil beam dose calculations and dose optimization and the second stage consists of discretization of the intensity maps followed by intensity map segmentation and a more accurate final dose calculation corresponding to physical beam apertures. Consequently, there can be differences between the presumed dose distribution corresponding to pencil beam calculations and optimization and a more accurately computed dose distribution corresponding to beam segments that takes into account collimator-specific effects. IMRT optimization is computationally expensive and has therefore led to the use of heuristic (e.g., simulated annealing and genetic algorithms) approaches that do not encompass a global view of the solution space. We modify the traditional two-stage IMRT optimization process by augmenting the second stage via an accurate Monte Carlo-based kernel-superposition dose calculations corresponding to beam apertures combined with an exact mathematical programming-based sequential optimization approach that uses linear programming (SLP). Our approach was tested on three challenging clinical test cases with multileaf collimator constraints corresponding to two vendors. We compared our approach to the conventional IMRT planning approach, a direct-aperture approach and a segment weight optimization approach. Our results in all three cases indicate that the SLP approach outperformed the other approaches, achieving superior critical structure sparing. Convergence of our approach is also demonstrated. Finally, our approach has also been integrated with a commercial treatment planning system and may be utilized clinically.

Moderate predictive value of demographic and behavioral characteristics for a diagnosis of HPV16-positive and HPV16-negative head and neck cancer.

Patients with HPV-positive and HPV-negative head and neck squamous cell carcinoma (HNSCC) are significantly different with regard to sociodemographic and behavioral characteristics that clinicians may use to assume tumor HPV status. Machine learning methods were used to evaluate the predictive value of patient characteristics and laboratory biomarkers of HPV exposure for a diagnosis of HPV16-positive HNSCC compared to in situ hybridization, the current gold-standard. Models that used a combination of demographic characteristics such as age, tobacco use, gender, and race had only moderate predictive value for tumor HPV status among all patients with HNSCC (positive predictive value [PPV]=75%, negative predictive value [NPV]=68%) or when limited to oropharynx cancer patients (PPV=55%, NPV=65%) and thus included a sizeable number of false positive and false negative predictions. Prediction was not improved by the addition of other demographic or behavioral factors (sexual behavior, income, education) or biomarkers of HPV16 exposure (L1, E6/7 antibodies or DNA in oral exfoliated cells). Patient demographic and behavioral characteristics as well as HPV biomarkers are not an accurate substitute for clinical testing of tumor HPV status.

Modeling plan-related clinical complications using machine learning tools in a multiplan IMRT framework.

PURPOSE: To predict organ-at-risk (OAR) complications as a function of dose-volume (DV) constraint settings without explicit plan computation in a multiplan intensity-modulated radiotherapy (IMRT) framework. METHODS AND MATERIALS: Several plans were generated by varying the DV constraints (input features) on the OARs (multiplan framework), and the DV levels achieved by the OARs in the plans (plan properties) were modeled as a function of the imposed DV constraint settings. OAR complications were then predicted for each of the plans by using the imposed DV constraints alone (features) or in combination with modeled DV levels (plan properties) as input to machine learning (ML) algorithms. These ML approaches were used to model two OAR complications after head-and-neck and prostate IMRT: xerostomia, and Grade 2 rectal bleeding. Two-fold cross-validation was used for model verification and mean errors are reported. RESULTS: Errors for modeling the achieved DV values as a function of constraint settings were 0-6%. In the head-and-neck case, the mean absolute prediction error of the saliva flow rate normalized to the pretreatment saliva flow rate was 0.42% with a 95% confidence interval of (0.41-0.43%). In the prostate case, an average prediction accuracy of 97.04% with a 95% confidence interval of (96.67-97.41%) was achieved for Grade 2 rectal bleeding complications. CONCLUSIONS: ML can be used for predicting OAR complications during treatment planning allowing for alternative DV constraint settings to be assessed within the planning framework.

A nested partitions framework for beam angle optimization in intensity-modulated radiation therapy.

Coupling beam angle optimization with dose optimization in intensity-modulated radiation therapy (IMRT) increases the size and complexity of an already large-scale combinatorial optimization problem. We have developed a novel algorithm, nested partitions (NP), that is capable of finding suitable beam angle sets by guiding the dose optimization process. NP is a metaheuristic that is flexible enough to guide the search of a heuristic or deterministic dose optimization algorithm. The NP method adaptively samples from the entire feasible region, or search space, and coordinates the sampling effort with a systematic partitioning of the feasible region at successive iterations, concentrating the search in promising subsets. We used a 'warm-start' approach by initiating NP with beam angle samples derived from an integer programming (IP) model. In this study, we describe our implementation of the NP framework with a commercial optimization algorithm. We compared the NP framework with equi-spaced beam angle selection, the IP method, greedy heuristic and random sampling heuristic methods. The results of the NP approach were evaluated using two clinical cases (head and neck and whole pelvis) involving the primary tumor and nodal volumes. Our results show that NP produces better quality solutions than the alternative considered methods.

A multiplan treatment-planning framework: a paradigm shift for intensity-modulated radiotherapy.

PURPOSE: To describe a multiplan intensity-modulated radiotherapy (IMRT) planning framework, and to describe a decision support system (DSS) for ranking multiple plans and modeling the planning surface. METHODS AND MATERIALS: One hundred twenty-five plans were generated sequentially for a head-and-neck case and a pelvic case by varying the dose-volume constraints on each of the organs at risk (OARs). A DSS was used to rank plans according to dose-volume histogram (DVH) values, as well as equivalent uniform dose (EUD) values. Two methods for ranking treatment plans were evaluated: composite criteria and pre-emptive selection. The planning surface determined by the results was modeled using quadratic functions. RESULTS: The DSS provided an easy-to-use interface for the comparison of multiple plan features. Plan ranking resulted in the identification of one to three "optimal" plans. The planning surface models had good predictive capability with respect to both DVH values and EUD values and generally, errors of <6%. Models generated by minimizing the maximum relative error had significantly lower relative errors than models obtained by minimizing the sum of squared errors. Using the quadratic model, plan properties for one OAR were determined as a function of the other OAR constraint settings. The modeled plan surface can then be used to understand the interdependence of competing planning objectives. CONCLUSION: The DSS can be used to aid the planner in the selection of the most desirable plan. The collection of quadratic models constructed from the plan data to predict DVH and EUD values generally showed excellent agreement with the actual plan values.

A difference-matrix metaheuristic for intensity map segmentation in step-and-shoot IMRT delivery.

At an intermediate stage of radiation treatment planning for IMRT, most commercial treatment planning systems for IMRT generate intensity maps that describe the grid of beamlet intensities for each beam angle. Intensity map segmentation of the matrix of individual beamlet intensities into a set of MLC apertures and corresponding intensities is then required in order to produce an actual radiation delivery plan for clinical use. Mathematically, this is a very difficult combinatorial optimization problem, especially when mechanical limitations of the MLC lead to many constraints on aperture shape, and setup times for apertures make the number of apertures an important factor in overall treatment time. We have developed, implemented and tested on clinical cases a metaheuristic (that is, a method that provides a framework to guide the repeated application of another heuristic) that efficiently generates very high-quality (low aperture number) segmentations. Our computational results demonstrate that the number of beam apertures and monitor units in the treatment plans resulting from our approach is significantly smaller than the corresponding values for treatment plans generated by the heuristics embedded in a widely use commercial system. We also contrast the excellent results of our fast and robust metaheuristic with results from an 'exact' method, branch-and-cut, which attempts to construct optimal solutions, but, within clinically acceptable time limits, generally fails to produce good solutions, especially for intensity maps with more than five intensity levels. Finally, we show that in no instance is there a clinically significant change of quality associated with our more efficient plans.

Selection of beam orientations in intensity-modulated radiation therapy using single-beam indices and integer programming.

While the process of IMRT planning involves optimization of the dose distribution, the procedure for selecting the beam inputs for this process continues to be largely trial-and-error. We have developed an integer programming (IP) optimization method to optimize beam orientation using mean organ-at-risk (MOD) data from single-beam plans. Two test cases were selected in which one organ-at-risk (OAR) and four OARs were simulated, respectively, along with a PTV. Beam orientation space was discretized in 10 degrees increments. For each beam orientation, a single-beam plan without intensity modulation and without constraints on OAR dose was generated and normalized to yield a mean PTV dose of 2 Gy and the corresponding MOD was calculated. The degree of OAR sparing was related to the average OAR MODs resulting from the beam orientations utilized with improvements of up to 10% at some dose levels. On the other hand, OAR DVHs in the IMRT plans were insensitive to beam numbers (in the 6-9 range) for similar average single-beam MODs. These MOD data were input to an IP optimization process, which then selected specified numbers of beam angles as inputs to a treatment planning system. Our results show that sets of beam angles with lower average single-beam MODs produce IMRT plans with better OAR sparing than manually selected beam angles. To optimize beam orientations, weights were assigned to each OAR following MOD input to the IP which was subsequently solved using the branch-and-cut algorithm. Seven-beam orientations obtained from solving the IP were applied to the test case with four OARs and the resulting plan with a dose prescription of 63 Gy was compared with an equi-spaced beam plan. The IP selected beams produced dose-volume improvements of up to 40% for OARs proximal to the PTV. Further improvement in the DVH can be obtained by increasing the weights assigned to these OARs but at the expense of the remaining OARs.