Model-based Algorithm Research Articles

2300: Dosimetric impact of a model-based dose calculation algorithm in skin interventional radiotherapy

2300: Dosimetric impact of a model-based dose calculation algorithm in skin interventional radiotherapy

A novel collision detection method based on current residuals for robots without joint torque sensors: A case study on UR10 robot

Existing model-based collision detection methods rely on accurate torque dynamic parameters identified using measured joint torques. However, for robots lacking joint torque sensors, only joint currents can be measured, and joint torques must be estimated through the linear relationship between joint currents and joint torque constants. This way can lead to cumulative identification errors in torque dynamic parameters, thereby diminishing the performance of model-based collision detection algorithms. To tackle this challenge, this article proposes an innovative collision detection method based on current residuals, which represent the disparities between measured joint currents and predicted joint currents computed by current dynamic parameters. Then, a dynamic threshold method for current residuals is designed to mitigate the impact of modeling errors at zero-speed direction changes on collision detection performance. Additionally, a suppression strategy based on online load identification and compensation is introduced to reduce the interference of non-collision load factors on collision detection signals. The proposed method mitigates the accumulation of errors on torque dynamic identification resulting from inaccuracies in joint torque constants, ultimately enhancing collision detection performance for robots without joint torque sensors. Extensive experiment results validate the correctness and effectiveness of this approach.

Model-Based Algorithm for Flexible Power Point Tracking for Photovoltaic Participation in Primary Frequency Regulation

Grid-connected photovoltaic (PV) systems are commonly designed for maximum energy production. However, as their presence grows, revised grid regulations increasingly require these systems to partially adhere to the primary frequency regulation (PFR) by reducing their power production when the grid frequency exceeds the nominal value. Nevertheless, full participation in PFR of PV systems, without battery storage, would require operating with a dedicated active power reserve to be utilized in the event of underfrequency conditions. This paper presents a model-based (MB) flexible power point tracking (FPPT) algorithm for PV systems. Results of a microgrid simulation show that the proposed algorithm enables a PV system with a nominal power of 100 kW to maintain a 20 kW active power reserve under various irradiation and temperature conditions, with a relative error lower than 3%. Furthermore, a simulation of the PV system assisting in primary frequency regulation is presented. Thanks to the proposed strategy, when employing the algorithm, the frequency deviation is reduced both in the event of underfrequency and overfrequency conditions. By enabling operation with a constant active power reserve, as well as a quick adjustment of the produced active power, in the event of frequency imbalance, the proposed MB algorithm is an interesting candidate for achieving complete PFR capabilities of PV systems.

Decoding genetic diversity and population structure of Brassica species by inter primer binding site (iPBS) retrotransposon markers

AbstractMarker-assisted breeding serves as a potent tool for screening target germplasm, assessing genetic diversity, and determining breeding potential of a crop. Therefore, inter primer binding site (iPBS)-retrotransposons marker system was employed to evaluate a collection of 33 Brassica genotypes, including 10 Brassica juncea, 5 B. oleracea, 7 Sinapis alba, 5 B. nigra, and 6 B. rapa, were utilized to evaluate their genetic diversity and variations 10 polymorphic primers that generated a total of 144 bands. Various diversity indices were calculated in the studied germplasm, including polymorphism information content (0.13–0.30), effective number of alleles (1.217–1.689), Shannon’s information index (0.244–0.531), and gene diversity (0.148–0.370). These indices collectively affirmed substantial genetic variations within the germplasm. Molecular variance analysis revealed that the majority (62%) of genetic variations were present within populations. The Brassica accessions were categorized into three populations utilizing a model-based structure algorithm. Evaluation of diversity indices based on the structure indicated that populations III and II exhibited higher diversity. Principal coordinate analysis and neighbor-joining analysis further corroborated the three distinct populations, confirming the reliability of the STRUCTURE analysis. Notably, the genetic distance assessment identified BN1 and BN3 from B. nigra species and the genotypes BO1 and BO3 from B. oleracea as genetically diverse mustard accessions. The extensive genetic diversity observed within the Brassica germplasm underscores its significance as a valuable genetic resource for comprehensive Brassica breeding programs. Moreover, these accessions hold promise as suitable candidates for heterosis breeding initiatives aimed at improving mustard production.

DynaGlaucoDetect: Leveraging Dyna-Q learning for glaucoma detection

Glaucoma is an eye disease that requires early detection and proper diagnosis for timely intervention and treatment which can help slow down further progression and to manage intraocular pressure. This paper aims to address the problem by proposing a novel approach that combines a model-based Reinforcement Learning (RL) approach, called DynaGlaucoDetect, with ocular gaze data. By leveraging the RL algorithms to simulate and predict the dynamics of glaucoma, a model-based approach can improve the accuracy and efficiency of glaucoma detection by enabling better preservation of visual health. The RL agent is trained using real experiences and synthetic experiences which are generated using the model-based algorithm Dyna-Q. Two different Q-table generation methods have been discussed: the Direct Synthesis Method (DSM) and the Indirect Synthesis Method (IdSM). The presence of glaucoma has been detected by comparing the reward score a patient obtains with the threshold values obtained through the performed experimentation. The scores obtained using DSM and IdSM have been compared to understand the learning of the agent in both cases. Finally, hyperparameter tuning has been performed to identify the best set of hyperparameters.

Development and Application of Control Concepts for Twin-Screw Wet Granulation in the ConsiGmaTM-25: Part 1 Granule Composition

Continuous manufacturing of pharmaceuticals offers several benefits, such as increased production efficiency, enhanced product quality control, and lower environmental footprint. To fully exploit these benefits, standard operation mode (production processes with no or minimal disturbance mitigation measures) should be supported by adopting novel quality-by-control (QbC) methodologies. The paper at hand is the first part of a study focused on developing QbC algorithms for optimizing twin-screw wet granulation in the industrial manufacturing line ConsiGmaTM-25, specifically addressing granule composition.This work relies on previously established process-analytical-technology (PAT) equipment for real-time monitoring of the granule composition, i.e., the active pharmaceutical ingredient (API) and liquid content in wet granules. The developed control platform integrates model-based process control algorithms that aim to keep the API- and liquid content at target values through real-time adjustments of the process parameters. Furthermore, the platform integrates a digital operator assistant, which aims to detect and classify granulation disturbances and provides messages and instructions for the plant operator.The present manuscript systematically outlines all design steps from the development phase in the simulation environment to the final real system application and validation. The control platform’s performance is demonstrated through selected test scenarios on the ConsiGmaTM-25 manufacturing line. The obtained results indicate improved disturbance robustness and an increase in intermediate/final product quality (compared to conventional operating modes): The process control algorithms successfully maintained the API- and liquid content at target values despite process disturbances. Furthermore, realistic disturbances (feeder, pump, and material) were accurately detected and classified by the digital assistant algorithm. The information was provided through a user interface, offering real-time support for plant personnel.

Decentralized multi-agent cooperation via adaptive partner modeling

Multi-agent reinforcement learning encounters a non-stationary challenge, where agents concurrently update their policies, leading to changes in the environment. Existing approaches have tackled this challenge through communication among agents to obtain their partners’ actions, but this introduces computational complexity known as partner sample complexity. An alternative approach is to develop partner models that generate samples instead of direct communication to mitigate this complexity. However, a discrepancy arises between the real policies distribution and the policy of partner models, termed as model bias, which can significantly impact performance when heavily relying on partner models. In order to achieve a trade-off between sample complexity and performance, a novel multi-agent model-based reinforcement learning algorithm called decentralized adaptive partner modeling (DAPM) is proposed, which utilizes fictitious self play (FSP) to construct partner models and update policies. Model bias is addressed by establishing an upper bound to restrict the usage of partner models. Coupled with that, an adaptive rollout approach is introduced, enabling real agents to dynamically communicate with partner models based on their quality, ensuring that agent performance can progressively improve with partner model samples. The effectiveness of DAPM is exhibited in two multi-agent tasks, showing that DAPM outperforms existing model-free algorithms in terms of partner sample complexity and training stability. Specifically, DAPM requires 28.5% fewer communications compared to the best baseline and exhibits reduced fluctuations in the learning curve, indicating superior performance.

A genetic algorithm-based optimal selection and blending ratio of plastic waste for maximizing economic potential

Pyrolysis of plastic waste presents an innovative solution to convert plastics into valuable fuels like oil and gas, thereby contributing to circular economy and sustainability. The efficiency of this process highly depends on the types and compositions of plastics utilized, as each type reacts uniquely during pyrolysis, affecting fuel yield and quality. However, previous studies have not thoroughly examined the impact of plastic selection and blending ratios on the pyrolysis outcome, as this requires extensive experimentation due to the numerous possible combinations. Optimizing these factors, along with operational conditions, is essential for enhancing the economic viability of plastic recycling via pyrolysis. This study introduces an optimal selection and blending ratio for plastic waste in pyrolysis fuel production to enhance economic viability using the surrogate model-based genetic algorithm (GA). The optimization process involves (1) generating data via a process model of the plastic waste pyrolysis reactor, (2) preprocessing data, (3) developing a surrogate model based on deep neural networks (DNNs), and (4) deriving the optimal solution using GA. The results reveal an optimal blending ratio: 4 wt% LDPE, 30 wt% HDPE, 43 wt% PP, and 24 wt% PS. Additionally, the optimal pyrolysis temperature is 607 ℃. By adopting this optimal solution, the net profit could increase by 20% compared to the conventional scenario, resulting in an additional annual net profit of US$ 407,811, thus highlighting the potential this approach offers to attain maximum economic feasibility in industrial applications.

Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games

This paper makes progress toward learning Nash equilibria in two-player, zero-sum Markov games from offline data. Despite a large number of prior works tackling this problem, the state-of-the-art results suffer from the curse of multiple agents in the sense that their sample complexity bounds scale linearly with the total number of joint actions. The current paper proposes a new model-based algorithm, which provably finds an approximate Nash equilibrium with a sample complexity that scales linearly with the total number of individual actions. This work also develops a matching minimax lower bound, demonstrating the minimax optimality of the proposed algorithm for a broad regime of interest. An appealing feature of the result lies in algorithmic simplicity, which reveals the unnecessity of sophisticated variance reduction and sample splitting in achieving sample optimality.

Deep unrolling networks with recurrent momentum acceleration for nonlinear inverse problems

Combining the strengths of model-based iterative algorithms and data-driven deep learning solutions, deep unrolling networks (DuNets) have become a popular tool to solve inverse imaging problems. Although DuNets have been successfully applied to many linear inverse problems, their performance tends to be impaired by nonlinear problems. Inspired by momentum acceleration techniques that are often used in optimization algorithms, we propose a recurrent momentum acceleration (RMA) framework that uses a long short-term memory recurrent neural network (LSTM-RNN) to simulate the momentum acceleration process. The RMA module leverages the ability of the LSTM-RNN to learn and retain knowledge from the previous gradients. We apply RMA to two popular DuNets—the learned proximal gradient descent (LPGD) and the learned primal-dual (LPD) methods, resulting in LPGD-RMA and LPD-RMA, respectively. We provide experimental results on two nonlinear inverse problems: a nonlinear deconvolution problem, and an electrical impedance tomography problem with limited boundary measurements. In the first experiment we have observed that the improvement due to RMA largely increases with respect to the nonlinearity of the problem. The results of the second example further demonstrate that the RMA schemes can significantly improve the performance of DuNets in strongly ill-posed problems.

Resolution analysis of a volumetric coded aperture X-ray diffraction imaging system.

A coded aperture X-ray diffraction (XRD) imaging system can measure the X-ray diffraction form factor from an object in three dimensions -X, Y and Z (depth), broadening the potential application of this technology. However, to optimize XRD systems for specific applications, it is critical to understand how to predict and quantify system performance for each use case. The purpose of this work is to present and validate 3D spatial resolution models for XRD imaging systems with a detector-side coded aperture. A fan beam coded aperture XRD system was used to scan 3D printed resolution phantoms placed at various locations throughout the system's field of view. The multiplexed scatter data were reconstructed using a model-based iterative reconstruction algorithm, and the resulting volumetric images were evaluated using multiple resolution criteria to compare against the known phantom resolution. We considered the full width at half max and Sparrow criterion as measures of the resolution and compared our results against analytical resolution models from the literature as well as a new theory for predicting the system resolution based on geometric arguments. We show that our experimental measurements are bounded by the multitude of theoretical resolution predictions, which accurately predict the observed trends and order of magnitude of the spatial and form factor resolutions. However, we find that the expected and observed resolution can vary by approximately a factor of two depending on the choice of metric and model considered. We observe depth resolutions of 7-16 mm and transverse resolutions of 0.6-2 mm for objects throughout the field of view. Furthermore, we observe tradeoffs between the spatial resolution and XRD form factor resolution as a function of sample location. The theories evaluated in this study provide a useful framework for estimating the 3D spatial resolution of a detector side coded aperture XRD imaging system. The assumptions and simplifications required by these theories can impact the overall accuracy of describing a particular system, but they also can add to the generalizability of their predictions. Furthermore, understanding the implications of the assumptions behind each theory can help predict performance, as shown by our data's placement between the conservative and idealized theories, and better guide future systems for optimized designs.

Identifying low acuity Emergency Department visits with a machine learning approach: The low acuity visit algorithms (LAVA).

To improve the performance of International Classification of Disease (ICD) code rule-based algorithms for identifying low acuity Emergency Department (ED) visits by using machine learning methods and additional covariates. We used secondary data on ED visits from the National Hospital Ambulatory Medical Survey (NHAMCS), from 2016 to 2020. We established baseline performance metrics with seven published algorithms consisting of International Classification of Disease, Tenth Revision codes used to identify low acuity ED visits. We then trained logistic regression, random forest, and gradient boosting (XGBoost) models to predict low acuity ED visits. Each model was trained on five different covariate sets of demographic and clinical data. Model performance was compared using a separate validation dataset. The primary performance metric was the probability that a visit identified by an algorithm as low acuity did not experience significant testing, treatment, or disposition (positive predictive value, PPV). Subgroup analyses assessed model performance across age, sex, and race/ethnicity. We used 2016-2019 NHAMCS data as the training set and 2020 NHAMCS data for validation. The training and validation data consisted of 53,074 and 9542 observations, respectively. Among seven rule-based algorithms, the highest-performing had a PPV of 0.35 (95% CI [0.33, 0.36]). All model-based algorithms outperformed existing algorithms, with the least effective-random forest using only age and sex-improving PPV by 26% (up to 0.44; 95% CI [0.40, 0.48]). Logistic regression and XGBoost trained on all variables improved PPV by 83% (to 0.64; 95% CI [0.62, 0.66]). Multivariable models also demonstrated higher PPV across all three demographic subgroups. Machine learning models substantially outperform existing algorithms based on ICD codes in predicting low acuity ED visits. Variations in model performance across demographic groups highlight the need for further research to ensure their applicability and fairness across diverse populations.

Model-based compensation of a concave nonlinear hysteresis in the displacement electro-hydraulic servo system

Abstract Nonlinearity exerts a profound influence on the displacement performance of actuators within electro-hydraulic servo systems, particularly in the context of hysteresis. This article analyses a specific hysteresis responsible for control instability, a consequence of the concave-hysteresis loop, giving rise to a notable peak phenomenon in displacement. The behavior of the concave-hysteresis loop is studied in the step load experiment of a triaxial apparatus. Subsequently, an accurately formulated mathematical model utilizing a mathematical function is derived. Notably, the article introduces an efficacious model-based compensation algorithm that integrates nonlinear iteration and fuzzy control. This strategic approach effectively addresses the issue associated with calculating the inverse model when the sensor is located in a nonlinear, hook-shaped domain. Simulation and experimentation verified the concave-hysteresis loop model and the compensation algorithm. The experiment demonstrated the elimination of peak phenomena and a decrease in sensor error from 3.7 mm to below 0.5 mm.

Feature evaluation of accelerometry signals for cough detection.

Cough is a common symptom of multiple respiratory diseases, such as asthma and chronic obstructive pulmonary disorder. Various research works targeted cough detection as a means for continuous monitoring of these respiratory health conditions. This has been mainly achieved using sophisticated machine learning or deep learning algorithms fed with audio recordings. In this work, we explore the use of an alternative detection method, since audio can generate privacy and security concerns related to the use of always-on microphones. This study proposes the use of a non-contact tri-axial accelerometer for motion detection to differentiate between cough and non-cough events/movements. A total of 43 time-domain features were extracted from the acquired tri-axial accelerometry signals. These features were evaluated and ranked for their importance using six methods with adjustable conditions, resulting in a total of 11 feature rankings. The ranking methods included model-based feature importance algorithms, first principal component, leave-one-out, permutation, and recursive features elimination (RFE). The ranking results were further used in the feature selection of the top 10, 20, and 30 for use in cough detection. A total of 68 classification models using a simple logistic regression classifier are reported, using two approaches for data splitting: subject-record-split and leave-one-subject-out (LOSO). The best-performing model out of the 34 using subject-record-split obtained an accuracy of 92.20%, sensitivity of 90.87%, specificity of 93.52%, and F1 score of 92.09% using only 20 features selected by the RFE method. The best-performing model out of the 34 using LOSO obtained an accuracy of 89.57%, sensitivity of 85.71%, specificity of 93.43%, and F1 score of 88.72% using only 10 features selected by the RFE method. These results demonstrate the ability for future implementation of a motion-based wearable cough detector.

Optimal control for continuous-time Markov jump singularly perturbed systems : A hybrid reinforcement learning scheme

This article discusses the adaptive optimal control problem for continuous-time Markov jump singularly perturbed systems with unknown system dynamics. First, the subsystems transformation technique is introduced to reconstruct the system with stochastic jump characteristics, yielding a set of parallel subsystems. Next, under the framework of reinforcement learning, an offline model-based hybrid iteration algorithm is developed to approximate the solution of the full-order coupled algebraic Riccati equations. Following this, to escape from the system model constraints, an online model-free hybrid iteration algorithm is introduced and relevant convergence proof is given. Compared to traditional value iteration and policy iteration algorithms, the hybrid iteration algorithm has ideal convergence rate and eliminates the requirement of initial stabilizing control policy. At the end, the availability of the online algorithm is demonstrated by means of an operational amplifier circuit model as a simulation example.

Meta model-based and cross entropy-based importance sampling algorithms for efficiently solving system failure probability function

The multi-mode system failure probability function (SFPF) can quantify how the distribution parameters of the random input vector affect the system safety and decouple the system reliability-based design optimization model. However, for a problem with a time-consuming implicit performance function and rare failure domain, efficiently solving the SFPF remains significantly challenging. Therefore, in this study, two efficient algorithms are proposed, namely, the meta model-based importance sampling and cross entropy-based importance sampling. The contributions of this study are twofold. The first is constructing a single-loop optimal importance sampling density (SL-OISD) method to decouple the double-loop framework for analyzing the SFPF. The second is establishing two methods to efficiently approximate the SL-OISD and complete the SFPF estimation. The first method is based on the meta model of the system performance function, which is abbreviated as SL-Meta-IS. The second method is based on minimizing the cross entropy between the Gaussian mixture density model and SL-OISD, which is abbreviated as SL-CE-IS. To reduce the number of evaluating the system performance function when approximating the SL-OISD, sampling the SL-OISD, and identifying the state of the samples for completing the SFPF estimation, an adaptive Kriging model of the system performance function is introduced into SL-Meta-IS and SL-CE-IS. Owing to decoupling the double-loop framework into a single-loop framework, replacing the time-consuming system performance function with the economic Kriging model, and employing importance sampling variance reduction techniques to address issues related to the rare failure domain, the proposed SL-Meta-IS and SL-CE-IS methods greatly enhance the efficiency of SFPF estimations. The numerical and practical examples demonstrate that the two proposed methods are superior to the existing algorithms; moreover, the efficiency of SL-CE-IS is higher than that of SL-Meta-IS.

Inverse Calculation and Regularization Process for the Solar Aspect System (SAS) of HXI Payload on ASO-S Spacecraft

For the ASO-S/HXI payload, the accuracy of the flare reconstruction is reliant on important factors such as the alignment of the dual grating and the precise measurement of observation orientation. To guarantee optimal functionality of the instrument throughout its life cycle, the Solar Aspect System (SAS) is imperative to ensure that measurements are accurate and reliable. This is achieved by capturing the target motion and utilizing a physical model-based inversion algorithm. However, the SAS optical system’s inversion model is a typical ill-posed inverse problem due to its optical parameters, which results in small target sampling errors triggering unacceptable shifts in the solution. To enhance inversion accuracy and make it more robust against observation errors, we suggest dividing the inversion operation into two stages based on the SAS spot motion model. First, the as-rigid-as-possible (ARAP) transformation algorithm calculates the relative rotations and an intermediate variable between the substrates. Second, we solve an inversion linear equation for the relative translation of the substrates, the offset of the optical axes, and the observation orientation. To address the ill-posed challenge, the Tikhonov method grounded on the discrepancy criterion and the maximum a posteriori (MAP) method founded on the Bayesian framework are utilized. The simulation results exhibit that the ARAP method achieves a solution with a rotational error of roughly ±3.″5 (1/2-quantile); both regularization techniques are successful in enhancing the stability of the solution, the variance of error in the MAP method is even smaller—it achieves a translational error of approximately ±18 μm (1/2-quantile) in comparison to the Tikhonov method’s error of around ±24 μm (1/2-quantile). Furthermore, the SAS practical application data indicates the method’s usability in this study. Lastly, this paper discusses the intrinsic interconnections between the regularization methods.

Enhancing accident cause analysis through text classification and accident causation theory: A case study of coal mine gas explosion accidents

Accident analysis is a crucial aspect of accident prevention, and natural language processing (NLP) techniques can efficiently be applied to analyze the causes of accidents. However, existing analysis methods primarily rely on text clustering and lack the application of accident causation theories, leading to a lack of specific accident cause analysis results. Combining text classification techniques with accident causation theories is an effective approach to address this issue. In this study, we integrated text classification techniques with accident causation theories and utilized coal mine gas explosion accidents as an example. We constructed a corpus, trained a BERT model, and evaluated its performance to obtain a text classification model for accident cause analysis. The results indicated that the BERT model-based text classification algorithm had an accuracy and macro-average F1 value of 0.9878 and 0.7792, respectively, significantly outperforming the control model. The application of this approach demonstrated that combining accident causation theories with text classification techniques for accident cause analysis can improve the efficiency of accident analysis while ensuring the richness of details in analyzing accident causes. By efficiently analyzing a large number of accident cases, this approach can provide a data foundation for data-driven accident prevention and technical support for integrated accident prevention.

Ultrasound-induced reorientation for multi-angle optical coherence tomography

Organoid and spheroid technology provide valuable insights into developmental biology and oncology. Optical coherence tomography (OCT) is a label-free technique that has emerged as an excellent tool for monitoring the structure and function of these samples. However, mature organoids are often too opaque for OCT. Access to multi-angle views is highly desirable to overcome this limitation, preferably with non-contact sample handling. To fulfil these requirements, we present an ultrasound-induced reorientation method for multi-angle-OCT, which employs a 3D-printed acoustic trap inserted into an OCT imaging system, to levitate and reorient zebrafish larvae and tumor spheroids in a controlled and reproducible manner. A model-based algorithm was developed for the physically consistent fusion of multi-angle data from a priori unknown angles. We demonstrate enhanced penetration depth in the joint 3D-recovery of reflectivity, attenuation, refractive index, and position registration for zebrafish larvae, creating an enabling tool for future applications in volumetric imaging.

A kV–MV approach to CBCT metal artifact reduction using multi-layer MV-CBCT

Objective. To demonstrate that complete cone beam CT (CBCT) scans from both MV-energy and kV-energy LINAC sources can reduce metal artifacts in radiotherapy guidance, while maintaining standard-of-care x-ray doses levels. Approach. MV-CBCT and kV-CBCT scans are acquired at half normal dose. The impact of lowered dose on MV-CBCT data quality is mitigated by the use of a 4-layer MV-imager prototype and reduced LINAC energy settings (2.5 MV) to improve photon capture. Additionally, the MV-CBCT is used to determine the 3D position and pose of metal implants, which in turn is used to guide model-based poly-energetic correction and interleaving of the kV-CBCT and MV-CBCT data. Certain edge-preserving regularization steps incorporated into the model-based correction algorithm further reduce MV data noise. Main results. The method was tested in digital phantoms and a real pelvis phantom with large 2.5″ spherical inserts, emulating hip replacements of different materials. The proposed method demonstrated an appealing compromise between the high contrast of kV-CBCT and low artifact content of MV-CBCT. Contrast-to-noise improved 3-fold compared to MV-CBCT with a clinical 1-layer architecture at matched dose (37 mGy) and edge blur levels. Visual delineation of the bladder and prostate improved noteably over kV- or MV-CBCT alone. Significance. The proposed method demonstrates that a full MV-CBCT scan can be combined with kV-CBCT to reduce metal artifacts without resorting to complicated beam collimation strategies to limit the MV-CBCT dose contribution. Additionally, significant improvements in CNR can be achieved as compared to metal artifact reduction through current clinical MV-CBCT practices.