Pareto Optimal Plans Research Articles

Optimizing quality and cost in remanufacturing under uncertainty

AbstractIn the context of growing sustainability demands, businesses are increasingly adapting their production practices by integrating remanufacturing. However, companies often face challenges in profitably implementing remanufacturing due to complexities arising from uncertainties in processes, product quality, and market conditions. This highlights the need for effective decision support in remanufacturing processes. Addressing this challenge, our research introduces an algorithm designed to identify cost-efficient process plans that optimize order fulfillment while considering a company’s specific capabilities and inventory levels. By modeling the remanufacturing planning process as a Markov process, our algorithm comprehensively accounts for both process-related and quality-related uncertainties. This approach enables the evaluation of all Pareto optimal process plans in terms of cost efficiency and reliability. We validate our methodology through a real-world application in the automation industry, specifically focusing on the remanufacturing of variable speed drives. This case study demonstrates the practical relevance of our approach and a potential for significant cost reductions, enhanced process efficiency, and improved labor productivity. Overall, businesses gain critical insights into the financial prospects of their remanufacturing efforts, identifying opportunities for optimization and expansion into new product quality categories. This enhances their economic potential and aligns with consumer preferences for distinct product qualities.

Reducing the lateral dose penumbra in IMPT by incorporating transmission pencil beams

ObjectiveIn intensity-modulated proton therapy (IMPT), Bragg peaks result in steep distal dose fall-offs, while the lateral IMPT dose fall-off is often less steep than in photon therapy. High-energy pristine transmission (‘shoot through’) pencil beams have no Bragg peak in the patient, but show a sharp lateral penumbra at the target level. We investigated whether combining Bragg peaks with Transmission pencil beams (‘IMPT&TPB’) could improve head-and-neck plans by exploiting the steep lateral dose fall-off of transmission pencil beams. ApproachOur system for automated multi-criteria IMPT plan optimisation was extended for combined optimisation of BPs and TPBs. The system generates for each patient a Pareto-optimal plan using a generic ‘wish-list’ with prioritised planning objectives and hard constraints. For eight nasopharynx cancer patients (NPC) and eight oropharynx cancer (OPC) patients, the IMPT&TPB plan was compared to the competing conventional IMPT plan with only Bragg peaks, which was generated with the same optimiser, but without transmission pencil beams. Main resultsClinical OAR and target constraints were met in all plans. By allowing transmission pencil beams in the optimisation, on average 14 of the 25 investigated OAR plan parameters significantly improved for NPC, and 9 of the 17 for OPC, while only one OPC parameter showed small but significant deterioration. Non-significant differences were found in the remaining parameters. In NPC, cochlea Dmean reduced by up to 17.5 Gy and optic nerve D2% by up to 11.1 Gy. ConclusionCompared to IMPT, IMPT&TPB resulted in comparable target coverage with overall superior OAR sparing, the latter originating from steeper dose fall-offs close to OARs.

Bowel bag sparing in palliative radiotherapy (pRT) of rectal cancer (rCa): Tradeoff between organs at risk (OARs) and use of AI to reduce radiation oncologist (RO) workload.

e15615 Background: We retrospectively studied the potential to reduce bowel toxicity after pRT of rCa using a bowel dose (BD) minimization strategy; also its effect on dose to remaining normal tissues (NT) and pelvic bone marrow (PBM). Finally, we studied the use of AI to reduce the RO workload. Methods: 25 consecutive rCa patients (pts) previously treated with pRT were included. Their treatments were planned without consideration to BD. The following OARs were manually segmented retrospectively: Bowel Bag (BB-M) excluding PTV, PBM (PBM-M), and NT defined as the patient contour excluding PTV and BB-M. The AI-Rad Companion software was used to autosegment: Bowel Loops (BL-AI) and PBM (PBM-AI). For the 25 pts, two Pareto optimal treatment plans (5 Gy x 5) were generated with the Monaco treatment planning system. The first plan (Reference) was optimized aiming to limit dose outside the PTV. The second plan (Opt-BB-M) was optimized aiming firstly to limit BB-M dose and secondly to limit NT dose. A third plan (Opt-BL-AI) was generated for the 10 worst-off pts (in terms of BD) aiming instead to limit BL-AI dose. Two volume-at-dose (VD) metrics (V18Gy, V10Gy) were used as endpoints. Endpoint differences (ΔVD-OAR) were tested using one-sided Wilcoxon signed-rank tests. Spearman (rs) and Pearson (r) correlation coefficients were used to study correlation between variables (ΔVD-BB vs. ΔVD-BM, and ΔVD-BB vs. ΔVD-NT). Dice Similarity Coefficient (DCS) was used to compare PBM-M and PBM-AI. Results: After reoptimization, BB-M VD (V18Gy; V10Gy) was lower (p < 0.001; p < 0.001), PBM-M VD was higher (p = 0.002; p < 0.001), and NT VD was higher (p < 0.001; p < 0.001). For BB-M, ΔV18Gy and ΔV10Gy (median, min, max) were (-4, -46, 0) cm3 and (-33, -254, 0) cm3; for PBM-M: (+2, -4, +56) cm3 and (+33, -6, +189) cm3; for NT: (+10, -43, +194) cm3 and (+146, -18, +614) cm3. Table 1 presents results for the 10 worst-off pts. Medium/strong correlations were found for ΔV18Gy-BB vs. ΔV18Gy-PBM (rs = -0.72, p < 0.001; r = -0.74, p < 0.001), ΔV10Gy-BB vs. ΔV10Gy-PBM (rs = -0.66, p < 0.001; r = -0.32, p = 0.11), ΔV18Gy-BB vs. ΔV18Gy-NT (rs = -0.74, p < 0.001; r = -0.74, p < 0.001), ΔV10Gy-BB vs. ΔV10Gy-NT (rs = -0.74, p < 0.001; r = -0.51, p = 0.009). The DSC (median, min, max) for PBL was (92%, 87%, 94%). Conclusions: Bowel dose in pRT of rCa can be reduced at the expense of increasing dose to PBM and other NT. AI tools can be used effectively to limit RO workload. [Table: see text]

Comparative Study of Eclipse and RayStation Multi-Criteria Optimization-Based Prostate Radiotherapy Treatment Planning Quality.

Multi-criteria optimization (MCO) function has been available on commercial radiotherapy (RT) treatment planning systems to improve plan quality; however, no study has compared Eclipse and RayStation MCO functions for prostate RT planning. The purpose of this study was to compare prostate RT MCO plan qualities in terms of discrepancies between Pareto optimal and final deliverable plans, and dosimetric impact of final deliverable plans. In total, 25 computed tomography datasets of prostate cancer patients were used for Eclipse (version 16.1) and RayStation (version 12A) MCO-based plannings with doses received by 98% of planning target volume having 76 Gy prescription (PTV76D98%) and 50% of rectum (rectum D50%) selected as trade-off criteria. Pareto optimal and final deliverable plan discrepancies were determined based on PTV76D98% and rectum D50% percentage differences. Their final deliverable plans were compared in terms of doses received by PTV76 and other structures including rectum, and PTV76 homogeneity index (HI) and conformity index (CI), using a t-test. Both systems showed discrepancies between Pareto optimal and final deliverable plans (Eclipse: -0.89% (PTV76D98%) and -2.49% (Rectum D50%); RayStation: 3.56% (PTV76D98%) and -1.96% (Rectum D50%)). Statistically significantly different average values of PTV76D98%,HI and CI, and mean dose received by rectum (Eclipse: 76.07 Gy, 0.06, 1.05 and 39.36 Gy; RayStation: 70.43 Gy, 0.11, 0.87 and 51.65 Gy) are noted, respectively (p < 0.001). Eclipse MCO-based prostate RT plan quality appears better than that of RayStation.

A human-cyber-physical system enabled sequential disassembly planning approach for a human-robot collaboration cell in Industry 5.0

Industry 5.0 characterized by human-centricity and sustainability has sparked a new wave of the industrial revolution. Human-cyber-physical system is the cornerstone of human-centric manufacturing while remanufacturing has gained considerable attention in fostering sustainability. Disassembly planning is a vital but challenging task in remanufacturing. In order to accommodate the frequent changes resulting from mass personalization, a human-robot collaboration cell is valued for its ability to achieve flexible disassembly. However, recent studies treated disassembly sequence and task allocation as independent aspects. And tasks are allocated by predefined metrics and thresholds without considering the ergonomics of operators. This paper proposes a human-cyber-physical framework for the human-robot collaboration cell by illustrating human-in-the-loop and human-on-the-loop paradigms. A multi-objective sequential disassembly planning model is presented by simultaneously considering disassembly sequence and task allocation. The task complexity and operator ergonomics are evaluated based on cloud models to handle the fuzziness and randomness in human cognition. Moreover, an improved multi-objective hybrid grey wolf optimization algorithm is proposed to obtain Pareto optimal disassembly plans. A case study on the disassembly planning of a control box is presented to illustrate the feasibility and practicability of the proposed approach. The results underscore the superiority of the proposed approach in handling rigorous constraints inherent in the sequential disassembly planning model, which acquires more convergent, diverse, and uniform disassembly plans along the Pareto front.

Comparison of volumetric modulated arc therapy and helical tomotherapy for prostate cancer using Pareto fronts.

Studies comparing different radiotherapy treatment techniques-such as volumetric modulated arc therapy (VMAT) and helical tomotherapy (HT)-typically compare one treatment plan per technique. Often, some dose metrics favor one plan and others favor the other, so the final plan decision involves subjective preferences. Pareto front comparisons provide a more objective framework for comparing different treatment techniques. A Pareto front is the set of all treatment plans where improvement in one criterion is possible only by worsening another criterion. However, different Pareto fronts can be obtained depending on the chosen machine settings. To compare VMAT and HT using Pareto fronts and blind expert evaluation, to explain the observed differences, and to illustrate limitations of using Pareto fronts. We generated Pareto fronts for twenty-four prostate cancer patients treated at our clinic for VMAT and HT techniques using an in-house script that controlled a commercial treatment planning system. We varied the PTV under-coverage (100%-V95%) and the rectum mean dose, and fixed the mean doses to the bladder and femoral heads. In order to ensure a fair comparison, those fixed mean doses were the same for the two treatment techniques and the sets of objective functions were chosen so that the conformity indexes of the two treatment techniques were also the same. We used the same machine settings as are used in our clinic. Then, we compared the VMAT and HT Pareto fronts using a specific metric (clinical distance measure) and validated the comparison using a blinded expert evaluation of treatment plans on these fronts for all patients in the cohort. Furthermore, we investigated the observed differences between VMAT and HT and pointed out limitations of using Pareto fronts. Both clinical distance and blind treatment plan comparison showed that VMAT Pareto fronts were better than HT fronts. VMAT fronts for 10 and 6MV beam energy were almost identical. HT fronts improved with different machine settings, but were still inferior to VMAT fronts. That VMAT Pareto fronts are better than HT fronts may be explained by the fact that the linear accelerator can rapidly vary the dose rate. This is an advantage in simple geometries that might vanish in more complex geometries. Furthermore, one should be cautious when speaking about Pareto optimal plans as the best possible plans, as their calculation depends on many parameters.

Simultaneous catheter and multicriteria optimization for HDR cervical cancer brachytherapy with a complex intracavity/interstitial applicator.

Complex intracavity and interstitial (IC/IS) applicators, such as the Venezia applicator, can improve the HR-CTV coverage while adequately protecting organs at risk in the treatment of cervical cancer with high-dose-rate (HDR) brachytherapy. Although the Venezia applicator offers more choice for catheter selection, commercially available catheter and dose optimization algorithms are still missing for complex applicators. Moreover, studies on catheter and dose optimization for IC/IS implants in the treatment of cervical cancer are stilllimited. This work aims to combine a GPU-based multi-criteria optimization (gMCO) algorithm with a sparse catheter (SC) optimization algorithm for the Veneziaapplicator. Fifty-eight cervical cancer patients who received 28 Gy in 4 fx of HDR brachytherapy with the Venezia applicator (combination to external beam radiation therapy) are retrospectively revisited. The modelization of the applicator is done by virtually reconstructing all the IS catheters passing through the ring. Template catheters are reconstructed using an in-house python script. To perform simultaneous MCO and SC optimization (SC+MCO), the objective function includes aggregated dose objectives in a weighted sum and a group sparsity term that individually penalizes the contribution of IS catheters. Plans generated with the SC+MCO algorithm are compared with plans generated with MCO using clinical catheters (CC+MCO) and the clinical plans (CP). The EMBRACE II soft constraints (planning aims) and hard constraints (limits for prescribed dose) are used as plan evaluationcriteria. CC+MCO gives the most important gain with an increase up to 20.7% in meeting all EMBRACE II soft constraints compared with CP. The SC+MCO algorithm (adding catheter optimization to MCO) provides a second order increase (up to 12.1% with total acceptance rate of 60.3% or 35/58) in the acceptance rate versus CC+MCO (total increase of 32.8% vs. CP). Acceptance rate in EMBRACE II hard constraints is 98.3% (57/58) for both CC+MCO and SC+MCO versus 91.4% (53/58) for CP. The median SC+MCO optimization time is 11s to generate a total of 5000 Pareto-optimal plans with different catheter configurations (position and number) for eachfraction. Simultaneous catheter and MCO optimization is clinically feasible for HDR cervical cancer brachytherapy using the Venezia applicator. Clinical catheter configurations could be improved and/or the catheter number could be reduced without decreasing plan quality using SC+MCO compared with theCP.

The impact of bone marrow sparing on organs at risk dose for cervical cancer: a Pareto front analysis.

To quantify the increase in bladder and rectum dose of a bone marrow sparing (BMS) VMAT strategy for primary treatment of locally advanced cervical cancer (LACC). Twenty patients with stage IB-IVA cervical cancer were selected for this study. The whole Pelvic Bones (PB) was taken as substitute for bone marrow. For every patient, Pareto-optimal plans were generated to explore the trade-off between rectum, bladder, and PB mean dose. The PB mean dose was decreased in steps of 1 Gy. For each step, the increase in rectum and bladder mean dose was quantified. The increase in mean dose of other OAR compared to no BMS was constrained to 1 Gy. In total, 931 plans of 19 evaluable patients were analyzed. The average [range] mean dose of PB without BMS was 22.8 [20.7-26.2] Gy. When maximum BMS was applied, the average reduction in mean PB dose was 5.4 [3.0-6.8] Gy resulting in an average mean PB dose of 17.5 [15.8-19.8] Gy. For <1 Gy increase in both the bladder and the rectum mean dose, the PB mean dose could be decreased by >2 Gy, >3 Gy, >4 Gy, and >5 Gy for 19/19, 13/19, 5/19, and 1/19 patients, respectively. Based on the comprehensive three-dimensional Pareto front analysis, we conclude that 2-5 Gy BMS can be implemented without a clinically relevant increase in mean dose to other OAR. If BMS is too dominant, it results in a large increase in mean dose to other OAR. Therefore, we recommend implementing moderate BMS for the treatment of LACC patients with VMAT.

Efficient Bi-objective SQL Optimization for Enclaved Cloud Databases with Differentially Private Padding

Hardware-enabled enclaves have been applied to efficiently enforce data security and privacy protection in cloud database services. Such enclaved systems, however, are reported to suffer from I/O-size (also referred to as communication-volume)-based side-channel attacks. Albeit differentially private padding has been exploited to defend against these attacks as a principle method, it introduces a challenging bi-objective parametric query optimization (BPQO) problem and current solutions are still not satisfactory. Concretely, the goal in BPQO is to find a Pareto-optimal plan that makes a tradeoff between query performance and privacy loss; existing solutions are subjected to poor computational efficiency and high cloud resource waste. In this article, we propose a two-phase optimization algorithm called TPOA to solve the BPQO problem. TPOA incorporates two novel ideas: divide-and-conquer to separately handle parameters according to their types in optimization for dimensionality reduction; on-demand-optimization to progressively build a set of necessary Pareto-optimal plans instead of seeking a complete set for saving resources. Besides, we introduce an acceleration mechanism in TPOA to improve its efficiency, which prunes the non-optimal candidate plans in advance. We theoretically prove the correctness of TPOA, numerically analyze its complexity, and formally give an end-to-end privacy analysis. Through a comprehensive evaluation on its efficiency by running baseline algorithms over synthetic and test-bed benchmarks, we can conclude that TPOA outperforms all benchmarked methods with an overall efficiency improvement of roughly two orders of magnitude; moreover, the acceleration mechanism speeds up TPOA by 10-200×.

MultiOptForest: An interactive multi-objective optimization tool for forest planning and scenario analysis

MultiOptForest is an open-source software designed to simplify building and solving multi-objective optimization problems for forest planning. It aims to find the optimal portfolio of management regimes that balance the objectives regarding multiple forest ecosystem services and biodiversity. The software flexibly imports data, allowing for the use of a variety of forest simulator outputs. The user provides preference information through a user-friendly graphical interface, where the range of possible values for each objective is provided. MultiOptForest solves the optimization problem producing a set of Pareto optimal solutions, i.e., solutions where none of the objectives can be improved without compromising others. MultiOptForest is versatile enough to design a Pareto optimal forest plan for a small holding to assess management and the trade-off between multiple policy objectives impacting the development of forests across regions and countries.

A novel mathematical model to generate semi-automated optimal IMRT treatment plan based on predicted 3D dose distribution and prescribed dose.

In recent years, with the development of artificial intelligence and deep learning techniques, it has become possible to predict the three-dimensional distribution dose (3D3 ) of a new patient based on the treatment plans of similar recent patients. Therefore, some new questions have arisen for the above issue: how to make use of the predicted 3D3 obtained from deep learning, to facilitate treatment planning? How to convert the predicted 3D3 to a clinical deliverable Pareto optimal plan? Little research has been done and limited software has been developed in this regard. In the current research, an attempt was made to contribute the knowledge-based planning by presenting a new mathematical model, and to take a novel step towards optimizing the treatment plan derived from both predicted 3D3 as well as dose prescription to generate a semi-automated clinically applicable optimal IMRT treatment plan. The presented model has benefited from both prescribed dose as well as predicted dose and its objective function includes both quadratic and linear phrases, so it was called the QuadLin model. The model has been run on the data of 30 patients with head and neck cancer randomly selected from the Open-KBP dataset. There are 19 sets of dose prediction data for each patient in this database. Therefore, a total of 570 problems have been solved in the CVX framework with commercial solver Mosek and the results have been evaluated by two plan quality approaches (1) DVH points differences, and (2) satisfied clinical criteria. The results of the current study indicate a strong significant improvement in almost all plan evaluation indicators compared to the reference plan of the dataset, 3D3 predictions, as well as the results of previous research, based on the Wilcoxon signed ranks test with a significance level of 0.01. Accordingly, for all regions of interest (ROIs) (or structures) of all 570 problems total clinical indicators have improved by more than 21%, 15%, and at least13%, on average, compared to the predicted dose, the reference plan, and previous research, respectively, with 341 s as the average of solving time. Evaluation of the research results indicates the significant effect of the QuadLin model on improving the dose delivery to the target volumes while reducing the dose and preserving organs at risk. Based on the literature, the proposed model has generated the best-known treatment plan from the predicted 3D3 so far.

Evaluating Pareto optimal tradeoffs for hippocampal avoidance whole brain radiotherapy with knowledge-based multicriteria optimization.

The goal of this study is to investigate the Pareto optimal tradeoffs between target coverage and hippocampal sparing using knowledge-based multicriteria optimization (MCO). Ten prior clinical cases were selected that were treated with hippocampal avoidance whole brain radiotherapy (HA-WBRT) using VMAT. A new, balanced plan was generated for each case using an in-house RapidPlan model in the Eclipse V16.1 treatment planning system. The MCO decision support tool was used to create 4 Pareto optimal plans. The Pareto optimal plans were created using PTV Dmin and hippocampus Dmax as tradeoff criteria. The tradeoff plans were generated for each patient by adjusting PTV Dmin from the value achieved by the corresponding balanced plan in fixed intervals as follows: -4 Gy, -2 Gy, +2 Gy, and +4Gy. All plans were normalized so that 95% of the PTV was covered by the prescription dose. A 1-way ANOVA, with Geisser-Greenhouse correction, was used for statistical analysis. When evaluating the achieved PTV Dmin and D98%, the results showed the dose to the hippocampus decreased as coverage lowered and in comparison, D98% was higher when the PTV coverage was increased. When comparing multiple tradeoffs, the p-value for PTV D98% was 0.0026, and the p-values for PTV D2%, PTV Dmin, Hippocampus Dmax, Dmin, and Dmean were all less than 0.0001, indicating that the tradeoff plans achieved statistically significant differences. The results also showed that Pareto optimal plans failed to reduce hippocampal dose beyond a certain point, indicating more limited achievability of the MCO-navigated plans than the interface suggested. This study presents valuable data for planning results for HA-WBRT using MCO. MCO has shown to be mostly effective in adjusting the tradeoff between PTV coverage and hippocampal dose.

Bi-criteria Pareto optimization to balance irradiation time and dosimetric objectives in proton arc therapy

Objective. Proton arc therapy (PAT) is a new delivery technique that exploits the continuous rotation of the gantry to distribute the therapeutic dose over many angular windows instead of using a few static fields, as in conventional (intensity-modulated) proton therapy. Although coming along with many potential clinical and dosimetric benefits, PAT has also raised a new optimization challenge. In addition to the dosimetric goals, the beam delivery time (BDT) needs to be considered in the objective function. Considering this bi-objective formulation, the task of finding a good compromise with appropriate weighting factors can turn out to be cumbersome. Approach. We have computed Pareto-optimal plans for three disease sites: a brain, a lung, and a liver, following a method of iteratively choosing weight vectors to approximate the Pareto front with few points. Mixed-integer programming (MIP) was selected to state the bi-criteria PAT problem and to find Pareto optimal points with a suited solver. Main results. The trade-offs between plan quality and beam irradiation time (static BDT) are investigated by inspecting three plans from the Pareto front. The latter are carefully picked to demonstrate significant differences in dose distribution and delivery time depending on their location on the frontier. The results were benchmarked against IMPT and SPArc plans showing the strength of degrees of freedom coming along with MIP optimization. Significance. This paper presents for the first time the application of bi-criteria optimization to the PAT problem, which eventually permits the planners to select the best treatment strategy according to the patient conditions and clinical resources available.

Implications of Including Tumor Presence Probabilities as Weights in Radiotherapy Optimization

<h3>Purpose/Objective(s)</h3> Recently, the fixed nature of the clinical target volume has been challenged in several studies that choose to incorporate microscopic tumor infiltration as a source of uncertainty in radiation therapy treatment planning. The approach to handle this uncertainty typically involves voxel-wise objective function weights that are proportional to each voxel's marginal probability of tumor presence. The main argument for doing so is to balance the probability of target coverage against the increased dose to organs at risk (OARs). We study the implications of basing the optimization on such probability weights, given an isotropic tumor infiltration model used for both optimization and evaluation, in which the infiltration distance is taken from a truncated gaussian probability distribution. We hypothesize that the low voxel weights far from the gross tumor volume (GTV) will cause the dose to fall off unevenly between directions that have high and low conflict with OARs, leading to a suboptimal trade-off between the probability of target coverage and OAR sparing. <h3>Materials/Methods</h3> We implement the probability weight method on a phantom geometry where suspected target voxels are weighted with probabilities from the tumor infiltration model, decreasing away from the GTV. This probability weighted plan is then compared against plans that are optimized using target volumes from an enumeration over a discrete set of scenarios from the tumor infiltration model. For both methods, plans are optimized using a range of scaling factors which scale the (uniform dose) objectives on the target in relation to those on OARs (max EUD), allowing comparison of the approximate Pareto fronts of the plans in the enumeration scheme to that of the probability weighted plan. The plans are evaluated on target samples from the tumor infiltration model which are used to compute target dose statistics. For each plan, the probability of satisfying a target coverage criterion (D98 > 0.95*D_pres.) is then plotted against the OAR objective to evaluate whether the probability weight method can produce Pareto optimal plans with respect to these criteria. In evaluation, we also include a tumor control probability (TCP) model to investigate how the methods compare on a smooth target coverage criterion. <h3>Results</h3> For a given scaling factor, the probability weighted plan is usually close to the corresponding set of plans from the enumeration scheme. However, the non-dominated subset of all generated plans consists almost entirely of plans from the enumeration scheme. Although the result holds also for TCP, there is less difference between the non-dominated subset of plans and the set of probability weighted plans. <h3>Conclusion</h3> The results indicate that finding the right combination of scaling factor and target expansion distance gives a better trade-off than the probability weight method, although efficiently doing so remains a future challenge. Meanwhile, using probability weights may serve as a practical alternative.

Automated and Clinical-Criteria-Driven Planning for Lung Cancer Using the Expedited Constrained Hierarchical Optimization (ECHO) System

<h3>Purpose/Objective(s)</h3> Treatment planning for locally advanced non-small cell lung cancer (NSCLC) has always been challenging due to the variabilities of the planning target volume (PTV) and competing constraints of organs at risk such as lung, cord, esophagus, and heart. We share our experience in developing a fully automatic treatment planning solution for NSCLC. <h3>Materials/Methods</h3> Automated plans for NSCLC radiotherapy patients with static IMRT fields were designed using an in-house-developed automated planning system named Expedited Constrained Hierarchical Optimization (ECHO) which is integrated into the treatment planning system (TPS) using API scripting. ECHO does not use TPS optimization algorithms, but utilizes TPS leaf sequencing and final dose calculation. ECHO applies advanced optimization tools (such as hierarchical constrained optimization, convex approximations and Lagrangian methods) to produce Pareto optimal plans that meet clinical constraints and improve desired clinical objectives as much as possible. ECHO optimization parameters were tuned with 29 NSCLC patients and validated retrospectively using 113 NSCLC patients treated with prescription doses including conventional (1.8Gy-2Gy x 25-35 fractions) and hypofractionation (2.75Gy-4Gy x 10-20 fractions). Clinically treated plans were created manually using either static IMRT or VMAT. Automated plans were created using static IMRT fields with beam templates based on the location of PTV within the lung. Dosimetric metrics were evaluated with respect to tumor coverage and normal tissue sparing. <h3>Results</h3> PTV sizes ranged from 64cc to 2297cc (median 292cc). Median planning time for ECHO was 23 minutes (range: 8min-78min). Both manual and ECHO plans met all established clinical criteria. Compared with manual plans, ECHO plans produced significantly improved and more consistent PTV coverage and better sparing of esophagus, heart and cord while maintaining similar lung doses (Table 1). <h3>Conclusion</h3> An automated and clinical-criteria-driven treatment planning system has been validated and clinically implemented in our institution for NSCLC radiotherapy. Use of automation improves efficiency, plan consistency and quality for NSCLC treatment planning.

Вычислительный эксперимент в оптимизационном моделировании процесса мультимодальных грузоперевозок на основе эгалитарных принципов

Purpose: To build an optimization model of multimodal cargo transportations in a port-side transport and technological system with the participation of rail and sea kinds of transport based on egalitarian principles, the model allows manipulating the values of parameters characterizing a transportation process and taking into account interests of transportation process participants within the frames of being considered cost indicators. Methods: An algorithm has been developed for planning the shipment and delivery of cargo flows to port station address in view of routing, time and cost parameters of transportation process which under, cost optimal values of being transported cargo and complex time indicators of transportation process are provided. One of the limitations in the optimization task is the volume of a ship batch that’s expected at any port unloading stations. The built mathematical model is a multi-criteria and multi-extreme task of nonlinear stochastic integer programming. The research theoretical and economic basis is the synthesis of the classical concepts of utilitarian and egalitarian approaches in a welfare theory that makes it possible to build sounded theoretically and demanded in practice the optimization models of multimodal freight transportation railway component. Results: Developed in analytical computing system environment the optimization algorithm provides opportunities along with Pareto optimal transportation plans for to find plans embodying “just in time” logistic concept, so at these plans, it is also achieved the balance of interests of transportation considered participants. Practical importance: An approach is proposed for to study freight transportation organization on a railway landfill wherein transportations are pursued within the framework of multimodal port-side transport and technological system. The developed models and algorithms can be recommended for practical use during the formation and analysis of logistic supply chains with rail and sea transport kind participation.

Inter-observer evaluation of a GPU-based multicriteria optimization algorithm combined with plan navigation tools for HDR brachytherapy

PURPOSERecently, a GPU-based multicriteria optimization (gMCO) algorithm was integrated in a graphical user interface (gMCO-GUI) that allowed real-time plan navigation through a set of Pareto-optimal plans for high-dose-rate (HDR) brachytherapy. This work reports on the inter-observer evaluation of the gMCO algorithm into the clinical workflow. METHODS AND MATERIALSTwenty HDR brachytherapy prostate cancer patients were retrospectively replanned with the gMCO algorithm. The reference clinical plans were each generated by experienced physicists using inverse planning followed by graphical optimization and approved by a radiation oncologist (RO). Each case was replanned with the gMCO algorithm by generating 2000 Pareto-optimal plans with four different objective functions. Two physicists were asked to rank the objective functions according to their preferences by choosing one preferred plan for each plans pool and ranking them using gMCO-GUI. The optimized dwell positions and dwell times of the gMCO plans that were ranked first were exported to Oncentra Prostate where a blinded comparison of the gMCO plans with the clinical plans was conducted by three ROs. RESULTSThe median planning time of the two physicists was 9 min. Both physicists preferred the objective function with target sub-regions to cover specific target regions. Regarding the blinded comparison, the gMCO plans were preferred 19, 17, and 12 times by the three ROs, in which eight gMCO plans were unanimously preferred compared with the clinical plans. CONCLUSIONSThe plan quality and the planning time were similar between the two physicists and within what is observed in the clinic. Moreover, the gMCO plans evaluated favorably by ROs compared to the reference clinical plans.

Co-Optimization of Design and Fabrication Plans for Carpentry

Past work on optimizing fabrication plans given a carpentry design can provide Pareto-optimal plans trading off between material waste, fabrication time, precision, and other considerations. However, when developing fabrication plans, experts rarely restrict to a single design , instead considering families of design variations , sometimes adjusting designs to simplify fabrication. Jointly exploring the design and fabrication plan spaces for each design is intractable using current techniques. We present a new approach to jointly optimize design and fabrication plans for carpentered objects. To make this bi-level optimization tractable, we adapt recent work from program synthesis based on equality graphs (e-graphs), which encode sets of equivalent programs. Our insight is that subproblems within our bi-level problem share significant substructures. By representing both designs and fabrication plans in a new bag of parts (BOP) e-graph, we amortize the cost of optimizing design components shared among multiple candidates. Even using BOP e-graphs, the optimization space grows quickly in practice. Hence, we also show how a feedback-guided search strategy dubbed Iterative Contraction and Expansion on E-graphs (ICEE) can keep the size of the e-graph manageable and direct the search towards promising candidates. We illustrate the advantages of our pipeline through examples from the carpentry domain.

Probabilistic Pareto plan generation for semiautomated multicriteria radiation therapy treatment planning

Objective. We propose a semiautomatic pipeline for radiation therapy treatment planning, combining ideas from machine learning–automated planning and multicriteria optimization (MCO). Approach. Using knowledge extracted from historically delivered plans, prediction models for spatial dose and dose statistics are trained and furthermore systematically modified to simulate changes in tradeoff priorities, creating a set of differently biased predictions. Based on the predictions, an MCO problem is subsequently constructed using previously developed dose mimicking functions, designed in such a way that its Pareto surface spans the range of clinically acceptable yet realistically achievable plans as exactly as possible. The result is an algorithm outputting a set of Pareto optimal plans, either fluence-based or machine parameter–based, which the user can navigate between in real time to make adjustments before a final deliverable plan is created. Main results. Numerical experiments performed on a dataset of prostate cancer patients show that one may often navigate to a better plan than one produced by a single-plan-output algorithm. Significance. We demonstrate the potential of merging MCO and a data-driven workflow to automate labor-intensive parts of the treatment planning process while maintaining a certain extent of manual control for the user.

Commissioning of GPU-based multi-criteria optimizer combined with plan navigation tools for high-dose-rate brachytherapy.

PurposeRecently, our GPU-based multi-criteria optimization (gMCO) algorithm has been integrated in a graphical user interface (gMCO-GUI) that allows real-time plan navigation through a gMCO-generated set of Pareto-optimal plans for high-dose-rate (HDR) brachytherapy. This work reports on the commissioning of the gMCO algorithm into clinical workflow.Material and methodsOur MCO workflow was validated against Oncentra Prostate v. 4.2.2 (OcP) and Oncentra Brachy v. 4.6.0 (OcB). 40 HDR prostate brachytherapy patients (20 with OcP and 20 with OcB) were retrospectively re-planned with gMCO algorithm by generating 2,000 Pareto-optimal plans. A single gMCO treatment plan was exported using gMCO-GUI plan navigation tools. The optimized dwell positions and dwell times of gMCO plans were exported via DICOM RTPLAN files to OcP/OcB, where final dosimetry was calculated. TG43 implementation in gMCO was validated against the consensus data of flexisource. Five analytical shapes were used as the ground truth for volume calculations. Dose-volume histogram (DVH) curves generated by gMCO were compared with the ones generated by OcP/OcB. 3D dose distributions (and isodose lines) were validated against OcP/OcB using dice similarity coefficient (DSC), 95% undirected Hausdorff distance (95% HD), and γ analysis.ResultsDifferences between –0.4% and 0.3% were observed between gMCO calculated dose rates and the flexisource consensus data. gMCO volumes were within ±2% agreement in 3/5 volumes (deviations within –2.9% and 0.1%). For 9 key DVH indices, the differences between gMCO and OcP/OcB were within ±1.2%. Regarding the accuracy of key isodose lines, the mean DSC was greater than 0.98, and the mean 95% HD was below 0.4 mm. The fraction of voxels with γ ≤ 1 was greater than 99% for all cases with 1%/1 mm threshold.ConclusionsThe GPU-based MCO workflow was successfully integrated into the clinical workflow and validated against OcP and OcB.