Optimization Of Radiotherapy Treatment Plans Research Articles

Embedding machine learning based toxicity models within radiotherapy treatment plan optimization

Objective. This study addresses radiation-induced toxicity (RIT) challenges in radiotherapy (RT) by developing a personalized treatment planning framework. It leverages patient-specific data and dosimetric information to create an optimization model that limits adverse side effects using constraints learned from historical data. Approach. The study uses the optimization with constraint learning (OCL) framework, incorporating patient-specific factors into the optimization process. It consists of three steps: optimizing the baseline treatment plan using population-wide dosimetric constraints; training a machine learning (ML) model to estimate the patient’s RIT for the baseline plan; and adapting the treatment plan to minimize RIT using ML-learned patient-specific constraints. Various predictive models, including classification trees, ensembles of trees, and neural networks, are applied to predict the probability of grade 2+ radiation pneumonitis (RP2+) for non-small cell lung (NSCLC) cancer patients three months post-RT. The methodology is assessed with four high RP2+ risk NSCLC patients, with the goal of optimizing the dose distribution to constrain the RP2+ outcome below a pre-specified threshold. Conventional and OCL-enhanced plans are compared based on dosimetric parameters and predicted RP2+ risk. Sensitivity analysis on risk thresholds and data uncertainty is performed using a toy NSCLC case. Main results. Experiments show the methodology’s capacity to directly incorporate all predictive models into RT treatment planning. In the four patients studied, mean lung dose and V20 were reduced by an average of 1.78 Gy and 3.66%, resulting in an average RP2+ risk reduction from 95% to 42%. Notably, this reduction maintains tumor coverage, although in two cases, sparing the lung slightly increased spinal cord max-dose (0.23 and 0.79 Gy). Significance. By integrating patient-specific information into learned constraints, the study significantly reduces adverse side effects like RP2+ without compromising target coverage. This unified framework bridges the gap between predicting toxicities and optimizing treatment plans in personalized RT decision-making.

Creating uniform cluster dose spread-out Bragg peaks for proton and carbon beams.

Preliminary data have shown a close association of the generalized ionization cluster size dose (in short, cluster dose) with cell survival, independent of particle type, and energy, when cluster dose is derived from an ionization detail parameter preferred for its association with cell survival. Such results suggest cluster dose has the potential to replace RBE-weighted dose in proton and ion beam radiotherapy treatment plan optimization, should a uniform cluster dose lead to comparable biological effects. However, further preclinical investigations are warranted to confirm this premise. To present an analytical approach to create uniform cluster dose spread-out Bragg peaks (SOBP) for evaluation of the potential of cluster dose to result in uniform biological effect. We modified the coefficients of the Bortfeld and Schlegel weight formula, an analytical method typically used for the creation of radiation dose SOBP in particle therapy, to produce uniform cluster dose SOBP of different widths (1-5cm) at relevant clinical proton and carbon beam energies. Optimum parameters were found by minimization of the ratio between the maximum and minimum cluster dose in the SOBP region using the Nelder-Mead method. The coefficients of the Bortfeld and Schlegel weight formula leading to uniform cluster dose SOBPs were determined for each combination of beam energy and SOBP width studied. The uniformity of the resulting cluster dose SOBPs, calculated as the relative difference between the maximum and minimum cluster dose within the SOBP, was within 0.3%-3.5% for the evaluated proton beams and 1.3%-3.4% for the evaluated carbon beams. The modifications to the analytical approach to create radiation dose SOBPs resulted in uniform cluster dose proton and carbon SOBPs over a wide range of beam energies and SOBP widths. Such SOBPs should prove valuable in preclinical investigations for the selection of nanodosimetric quantities to be used in proton and ion therapy treatment planning.

Benchmarking daily adaptation using fully automated radiotherapy treatment plan optimization for rectal cancer.

In daily plan adaptation the radiotherapy treatment plan is adjusted just prior to delivery. A simple approach is taking the planning objectives of the reference plan and directly applying these in re-optimization. Here we present a tested method to verify whether daily adaptation without tweaking of the objectives can maintain the plan quality throughout treatment. For fifteen rectal cancer patients, automated treatment planning was used to generate plans mimicking manual reference plans on the planning scans. For 74 fraction scans (4-5 per patient) an automated plan and a daily adapted plan were generated, where the latter re-optimizes the reference plan objectives without any tweaking. To evaluate the robustness of the daily adaptation, the adapted plans were compared to the autoplanning plans. Median differences between the autoplanning plans on the planning scans and the reference plans were between -1 and 0.2Gy. The largest interquartile range (1Gy) was seen for the Lumbar Skin D2%. For the daily scans the PTV D2% and D98% differences between autoplanning and adapted plans were within 0.7Gy, with mean differences within 0.3Gy. Positive differences indicate higher values were obtained using autoplanning. For the Bowelarea+Bladder and the Lumbar Skin the D2% and Dmean differences were all within 2.6Gy, with mean differences between -0.9 and 0.1Gy. Automated treatment planning can be used to benchmark daily adaptation techniques. The investigated adaptation workflow can robustly perform high quality adaptations without daily adjusting of the patient-specific planning objectives for rectal cancer radiotherapy.

A comparison of two methodologies for radiotherapy treatment plan optimization and QA for clinical trials.

Background and purposeThe efficacy of clinical trials and the outcome of patient treatment are dependent on the quality assurance (QA) of radiation therapy (RT) plans. There are two widely utilized approaches that include plan optimization guidance created based on patient‐specific anatomy. This study examined these two techniques for dose‐volume histogram predictions, RT plan optimizations, and prospective QA processes, namely the knowledge‐based planning (KBP) technique and another first principle (FP) technique.MethodsThis analysis included 60, 44, and 10 RT plans from three Radiation Therapy Oncology Group (RTOG) multi‐institutional trials: RTOG 0631 (Spine SRS), RTOG 1308 (NSCLC), and RTOG 0522 (H&N), respectively. Both approaches were compared in terms of dose prediction and plan optimization. The dose predictions were also compared to the original plan submitted to the trials for the QA procedure.ResultsFor the RTOG 0631 (Spine SRS) and RTOG 0522 (H&N) plans, the dose predictions from both techniques have correlation coefficients of >0.9. The RT plans that were re‐optimized based on the predictions from both techniques showed similar quality, with no statistically significant differences in target coverage or organ‐at‐risk sparing. The predictions of mean lung and heart doses from both methods for RTOG1308 patients, on the other hand, have a discrepancy of up to 14 Gy.ConclusionsBoth methods are valuable tools for optimization guidance of RT plans for Spine SRS and Head and Neck cases, as well as for QA purposes. On the other hand, the findings suggest that KBP may be more feasible in the case of inoperable lung cancer patients who are treated with IMRT plans that have spatially unevenly distributed beam angles.

P168] Volumetric modulated arc therapy using multi-criteria dose plan optimization for anal cancer – Feasibility of selective sparing of organs at risk

Purpose Radiotherapy treatment plan optimization often requires trade-offs between different organs at risk (OARs). This may facilitate individualized plan optimization, where sparing of specific OARs can be incorporated into plan selection. We previously demonstrated this for IMRT using multi-criteria dose plan optimization (MCO). We here present initial results for volumetric modulated arc therapy (VMAT) MCO. Methods VMAT dose plans were generated for ten representative anal cancer patients. Prescribed dose was 53.75 Gy to tumour (simultaneous integrated boost) and 45 Gy to elective nodes in 25 fractions. Plan optimization was done in RayStation® (v5.99.0.16 research build). Dual arc non-MCO VMAT plans were optimized with physician-defined organ-sparing priorities. Three additional VMAT dose distributions were optimized using MCO, representing a span of clinically relevant objectives: 1) minimum acceptable target coverage with physician-defined organ-sparing priorities; 2) maximum bowel sparing without losing target coverage (if needed at expense of the bladder); 3) maximum bladder sparing without losing target coverage (if needed at expense of the bowel). VMAT-MCO dosimetry metrics were compared to non-MCO VMAT plans; and feasibility of selective OAR sparing (bladder or bowel) with VMAT-MCO was compared to previously published findings. Results All plans satisfied constraints for target coverage. Non-MCO and VMAT-MCO plans showed similar conformity indices (CI) and dose volumes to bladder, although with considerable variation between patients. MCO plans had smaller hotspots in elective volumes (ΔV107%: 3.0%-points, interquartile range (IQR) [1.7–3.9]), but higher dose volumes to bowel (median bowel ΔV45 Gy: 57.5 cm[c]; IQR [21.3–298.0]). Compared to IMRT-MCO, VMAT-MCO demonstrated smaller hotspots and similar CI. VMAT-MCO allowed for redistribution of dose between bladder and bowel, but the optimization space was considerably smaller than for IMRT. To illustrate, median bowel ΔV45 Gy: 19.4 cm3; IQR [2.2–31.1] for bowel sparing VMAT-MCO compared to standard VMAT-MCO; while for IMRT-MCO ΔV45 Gy: 47.6 cm3; IQR [18.6–66.4]. Time spent on optimization was longer for VMAT-MCO due to considerable increase in the calculation and conversion time compared to IMRT-MCO. Conclusions Selective sparing of OARs in VMAT-MCO facilitates the same trade-offs as IMRT-MCO, but with significantly less room for dose redistribution. While VMAT-MCO plans are clinically acceptable, further improvement of the research implementation is warranted.

A Randomized Singular Value Decomposition Based Linear Programming Technique for Robotic Radiation Therapy Treatment Plan Optimization

With highly reliable control of linac positioning, the robotic radiotherapy by CyberKnife significantly increases the freedom in radiation beam placement, but also imposes more challenges on treatment plan optimization. The resampling mechanism in vendor supplied treatment planning system (MultiPlan) could not fully explore the increased beam direction search space. This study proposes a randomized singular value decomposition (RSVD) based linear programming (LP) technique for circular collimator robotic radiotherapy treatment plan optimization (CCRTPO). The RSVDLP algorithm initializes beam angle of each available node is to cover the entire target with equivalent beam taper, which fully explores the complete beam space without redundancy. Beam weight is optimized by LP, which minimizes the deviation of relax constraints (RCs) subjected to hard constraints. Based on the degeneracy of dose influence matrix (DIM), of which the column vector is the dose delivered by one beam to all voxels, a RSVD approach is developed to compress the weight variables, and back project the compressed variables to construct beam weights after optimization. The beams with lower weight are removed, and the weight of remaining beams is further optimized using the same method to reduce number of beams. The technique was demonstrated and compared with the MultiPlan on a lung case with a PTV of 15.5cm3. Both algorithms used the same set of 94 nodes, and circular collimators of 15mm & 20mm diameter. The objectives and constraints used in MultiPlan are switched in RSVDLP model. The switched model is more suitable for SBRT, as it guarantees sufficient dose for PTV and avoids cold spot. For spinal cord (SC) and trachea (Tr), RSVDLP model uses stricter RCs to achieve better protection without triggering infeasibility. RSVD is performed to preserve 90% feature of DIM, the compression rate is 24.4% (1670 compressed variables over 6832 initial beams), and the optimization is sped up 4.8 times (1785s over 370s). The table indicates that RSVDLP plan achieves better homogeneity, conformity and OAR protection with lower MU and fewer beams. Similar results were observed on liver and brain cases.Abstract 3639; Table Comparison of optimization models and results (unit in cGy)Objective (O) & constraint (C)DmaxDmeanCI2HIMUBeam #PTVSCEsTrSCEsTrLLRLRSVDLP>4500 C<4650 O<1200 O<2200 O<1200 O1613304913561173491.281.1735745134MultiPlan>4500 O<4650 C<1500 C<4150 C<4050 O<2200 C1681318016591453621.581.2837820136Abbr: esophagus-Es, left lung-LL, right lung-RL, conformity index-CI, homogeneity index-HI. Open table in a new tab Abbr: esophagus-Es, left lung-LL, right lung-RL, conformity index-CI, homogeneity index-HI. We have developed a RSVDLP technique for CCRTPO. The results demonstrate that RSVD is effective in accelerating the optimization. Due to the use of complete beam space and flexible model, the plan generated by RSVDLP achieves better dose distribution than MultiPlan.

A moment-based approach for DVH-guided radiotherapy treatment plan optimization

The dose–volume histogram (DVH) is a clinically relevant criterion to evaluate the quality of a treatment plan. It is hence desirable to incorporate DVH constraints into treatment plan optimization for intensity modulated radiation therapy. Yet, the direct inclusion of the DVH constraints into a treatment plan optimization model typically leads to great computational difficulties due to the non-convex nature of these constraints. To overcome this critical limitation, we propose a new convex-moment-based optimization approach. Our main idea is to replace the non-convex DVH constraints by a set of convex moment constraints. In turn, the proposed approach is able to generate a Pareto-optimal plan whose DVHs are close to, or if possible even outperform, the desired DVHs. In particular, our experiment on a prostate cancer patient case demonstrates the effectiveness of this approach by employing two and three moment formulations to approximate the desired DVHs.

Modeling the Risk of Secondary Malignancies after Radiotherapy

In developed countries, more than half of all cancer patients receive radiotherapy at some stage in the management of their disease. However, a radiation-induced secondary malignancy can be the price of success if the primary cancer is cured or at least controlled. Therefore, there is increasing concern regarding radiation-related second cancer risks in long-term radiotherapy survivors and a corresponding need to be able to predict cancer risks at high radiation doses. Of particular interest are second cancer risk estimates for new radiation treatment modalities such as intensity modulated radiotherapy, intensity modulated arc-therapy, proton and heavy ion radiotherapy. The long term risks from such modern radiotherapy treatment techniques have not yet been determined and are unlikely to become apparent for many years, due to the long latency time for solid tumor induction. Most information on the dose-response of radiation-induced cancer is derived from data on the A-bomb survivors who were exposed to γ-rays and neutrons. Since, for radiation protection purposes, the dose span of main interest is between zero and one Gy, the analysis of the A-bomb survivors is usually focused on this range. With increasing cure rates, estimates of cancer risk for doses larger than one Gy are becoming more important for radiotherapy patients. Therefore in this review, emphasis was placed on doses relevant for radiotherapy with respect to radiation induced solid cancer. Simple radiation protection models should be used only with extreme care for risk estimates in radiotherapy, since they are developed exclusively for low dose. When applied to scatter radiation, such models can predict only a fraction of observed second malignancies. Better semi-empirical models include the effect of dose fractionation and represent the dose-response relationships more accurately. The involved uncertainties are still huge for most of the organs and tissues. A major reason for this is that the underlying processes of the induction of carcinoma and sarcoma are not well known. Most uncertainties are related to the time patterns of cancer induction, the population specific dependencies and to the organ specific cancer induction rates. For radiotherapy treatment plan optimization these factors are irrelevant, as a treatment plan comparison is performed for a patient of specific age, sex, etc. If a treatment plan is compared relative to another one only the shape of the dose-response curve (the so called risk-equivalent dose) is of importance and errors can be minimized.

CalcNTCP: A simple tool for computation of normal tissue complication probability (NTCP) associated with cancer radiotherapy

Purpose: This study was aimed to develop a simple and user-friendly software for fast and accurate computation of normal tissue complication probability (NTCP) in accordance with the Lyman model.Materials and methods: The software CalcNTCP has been developed in Visual Basic and is equipped with two functional modes. Mode 1 is based on pre-stored values of various parameters for 27 different organ systems and the user has only to input the values of volume fraction (v) and radiation dose (D), whereas Mode 2 is designed for the customized entries.Results: The results of software validation have demonstrated that CalcNTCP is more efficient and time-saving as compared to manual or semi-manual procedures. The shapes and locations of representative survival curves generated by CalcNTCP-based computations for various radiation doses (10 – 100 Gy) and reference volumes (0.33 – 1.00) absolutely matched with optimal curves.Conclusion: CalcNTCP is a simple, fast and accurate tool for the computation of NTCP with a direct implication in the evaluation or optimization of radiotherapy treatment plans.

Pulmonary Radiation Injury: Identification of Risk Factors Associated with Regional Hypersensitivity

Effective radiation treatment of thoracic tumors is often limited by radiosensitivity of surrounding tissues. Several experimental studies have suggested variations in radiosensitivity of different pulmonary regions. Mice and rat studies in part contradict each other and urge for a more detailed analysis. This study was designed to obtain a more comprehensive insight in radiation injury development, expression, and its regional heterogeneity in lung. The latter is obviously highly critical for optimization of radiotherapy treatment plans and may shed light on the mechanisms of lung dysfunction after irradiation. Six different but volume-equal regions in rat lung were irradiated. Whereas the severity of damage, as seen in histologic analysis, was comparable in all regions, the degree of lung dysfunction, measured as breathing rates, largely varied. During the pneumonitic phase (early: 6-12 weeks), the most sensitive regions contained a substantial part of alveolar lung parenchyma. Also, a trend for hypersensitivity was observed when the heart lay in the irradiation field. In the fibrotic phase (late: 34-38 weeks), lung parenchyma and heart-encompassing regions were the most sensitive. No impact of the heart was observed during the intermediate phase (16-28 weeks). The severity of respiratory dysfunction after partial thoracic irradiation is likely governed by an interaction between pulmonary and cardiac functional deficits. As a repercussion, more severe acute and delayed toxicity should be expected after combined lung and heart irradiation. This should be considered in the process of radiotherapy treatment planning of thoracic malignancies.

Estimation theory and model parameter selection for therapeutic treatment plan optimization.

Treatment optimization is usually formulated as an inverse problem, which starts with a prescribed dose distribution and obtains an optimized solution under the guidance of an objective function. The solution is a compromise between the conflicting requirements of the target and sensitive structures. In this paper, the treatment plan optimization is formulated as an estimation problem of a discrete and possibly nonconvex system. The concept of preference function is introduced. Instead of prescribing a dose to a structure (or a set of voxels), the approach prioritizes the doses with different preference levels and reduces the problem into selecting a solution with a suitable estimator. The preference function provides a foundation for statistical analysis of the system and allows us to apply various techniques developed in statistical analysis to plan optimization. It is shown that an optimization based on a quadratic objective function is a special case of the formalism. A general two-step method for using a computer to determine the values of the model parameters is proposed. The approach provides an efficient way to include prior knowledge into the optimization process. The method is illustrated using a simplified two-pixel system as well as two clinical cases. The generality of the approach, coupled with promising demonstrations, indicates that the method has broad implications for radiotherapy treatment plan optimization.