GPU-based high-performance computing for radiation therapy

Technical note: A GPU-based shared Monte Carlo method for fast photon transport in multi-energy x-ray exposures

BACKGROUND

The Monte Carlo (MC) method is an accurate technique for particle transport calculation due to the precise modeling of physical interactions. Nevertheless, the MC method still suffers from the problem of expensive computational cost, even with graphics processing unit (GPU) acceleration. Our previous works have investigated the acceleration strategies of photon transport simulation for single-energy CT. But for multi-energy CT, conventional individual simulation leads to unnecessary redundant calculation, consuming more time.

PURPOSE

This work proposes a novel GPU-based shared MC scheme (gSMC) to reduce unnecessary repeated simulations of similar photons between different spectra, thereby enhancing the efficiency of scatter estimation in multi-energy x-ray exposures.

METHODS

The shared MC method selects shared photons between different spectra using two strategies. Specifically, we introduce spectral region classification strategy to select photons with the same initial energy from different spectra, thus generating energy-shared photon groups. Subsequently, the multi-directional sampling strategy is utilized to select energy-and-direction-shared photons, which have the same initial direction, from energy-shared photon groups. Energy-and-direction-shared photons perform shared simulations, while others are simulated individually. Finally, all results are integrated to obtain scatter distribution estimations for different spectral cases.

RESULTS

The efficiency and accuracy of the proposed gSMC are evaluated on the digital phantom and clinical case. The experimental results demonstrate that gSMC can speed up the simulation in the digital case by ∼37.8% and the one in the clinical case by ∼20.6%, while keeping the differences in total scatter results within 0.09%, compared to the conventional MC package, which performs an individual simulation.

CONCLUSIONS

The proposed GPU-based shared MC simulation method can achieve fast photon transport calculation for multi-energy x-ray exposures.

Advancing knowledge-based intensity modulated proton planning for adaptive treatment of high-risk prostate cancer

To assess the performance of a knowledge-based planning (KBP) model for generating intensity-modulated proton therapy (IMPT) treatment plans as part of an adaptive radiotherapy (ART) strategy for patients with high-risk prostate cancer. A knowledge-based planning (KBP) model for proton adaptive treatment plan generation was developed based on thirty patient treatment plans utilizing RapidPlanTM PT (Varian Medical Systems, Palo Alto, CA). The model was subsequently validated using an additional eleven patient cases. All patients in the study were administered a prescribed dose of 70.2 Gy to the prostate and seminal vesicle (CTV70.2), along with 46.8 Gy to the pelvic lymph nodes (CTV46.8) through simultaneous integrated boost (SIB) technique. To assess the quality of the validation knowledge-based proton plans (KBPPs), target coverage and organ-at-risk (OAR) dose-volume constraints were compared against those of clinically used expert plans using paired t-tests. The KBP model training statistics (R2) (mean ± SD, 0.763 ± 0.167, range, 0.406 to 0.907) and χ² values (1.162 ± 0.0867, 1.039-1.253) indicate acceptable model training quality. Moreover, the average total treatment planning optimization and calculation time for adaptive plan generation is approximately 10 minutes. The CTV70.2 D98% for the KBPPs (mean ± SD, 69.1 ± 0.08 Gy) and expert plans (69.9 ± 0.04 Gy) shows a significant difference (p < 0.05) but are both within 1.1 Gy of the prescribed dose which is clinically acceptable. While the maximum dose for some organs-at-risk (OARs) such as the bladder and rectum is generally higher in the KBPPs, the doses still fall within clinical constraints. Among all the OARs, most of them received comparable results to the expert plan, except the cauda equina Dmax, which shows statistical significance and was lower in the KBPPs than in expert plans (48.5 ± 0.06 Gy vs 49.3 ± 0.05 Gy). The generated KBPPs were clinically comparable to manually crafted plans by expert treatment planners. The adaptive plan generation process was completed within an acceptable timeframe, offering a quick same-day adaptive treatment option. Our study supports the integration of KBP as a crucial component of an ART strategy, including maintaining plan consistency, improving quality, and enhancing efficiency. This advancement in speed and adaptability promises more precise treatment in proton ART.

DAART: a deep learning platform for deeply accelerated adaptive radiation therapy for lung cancer

Purpose

The study aimed to implement a novel, deeply accelerated adaptive radiation therapy (DAART) approach for lung cancer radiotherapy (RT). Lung cancer is the most common cause of cancer-related death, and RT is the preferred medically inoperable treatment for early stage non-small cell lung cancer (NSCLC). In the current lengthy workflow, it takes a median of four weeks from diagnosis to RT treatment, which can result in complete restaging and loss of local control with delay. We implemented the DAART approach, featuring a novel deepPERFECT system, to address unwanted delays between diagnosis and treatment initiation.

Materials and methods

We developed a deepPERFECT to adapt the initial diagnostic imaging to the treatment setup to allow initial RT planning and verification. We used data from 15 patients with NSCLC treated with RT to train the model and test its performance. We conducted a virtual clinical trial to evaluate the treatment quality of the proposed DAART for lung cancer radiotherapy.

Results

We found that deepPERFECT predicts planning CT with a mean high-intensity fidelity of 83 and 14 HU for the body and lungs, respectively. The shape of the body and lungs on the synthesized CT was highly conformal, with a dice similarity coefficient (DSC) of 0.91, 0.97, and Hausdorff distance (HD) of 7.9 mm, and 4.9 mm, respectively, compared with the planning CT scan. The tumor showed less conformality, which warrants acquisition of treatment Day1 CT and online adaptive RT. An initial plan was designed on synthesized CT and then adapted to treatment Day1 CT using the adapt to position (ATP) and adapt to shape (ATS) method. Non-inferior plan quality was achieved by the ATP scenario, while all ATS-adapted plans showed good plan quality.

Conclusion

DAART reduces the common online ART (ART) treatment course by at least two weeks, resulting in a 50% shorter time to treatment to lower the chance of restaging and loss of local control.

deepPERFECT: Novel Deep Learning CT Synthesis Method for Expeditious Pancreatic Cancer Radiotherapy

Major sources of delay in the standard of care RT workflow are the need for multiple appointments and separate image acquisition. In this work, we addressed the question of how we can expedite the workflow by synthesizing planning CT from diagnostic CT. This idea is based on the theory that diagnostic CT can be used for RT planning, but in practice, due to the differences in patient setup and acquisition techniques, separate planning CT is required. We developed a generative deep learning model, deepPERFECT, that is trained to capture these differences and generate deformation vector fields to transform diagnostic CT into preliminary planning CT. We performed detailed analysis both from an image quality and a dosimetric point of view, and showed that deepPERFECT enabled the preliminary RT planning to be used for preliminary and early plan dosimetric assessment and evaluation.

Same-day adaptive palliative radiotherapy without prior CT simulation: Early outcomes in the FAST-METS study

BACKGROUND AND PURPOSE

Standard palliative radiotherapy workflows involve waiting times or multiple clinic visits. We developed and implemented a rapid palliative workflow using diagnostic imaging (dCT) for pre-planning, with subsequent on-couch target and plan adaptation based on a synthetic computed tomography (CT) obtained from cone-beam CT imaging (CBCT).

MATERIALS AND METHODS

Patients with painful bone metastases and recent diagnostic imaging were eligible for inclusion in this prospective, ethics-approved study. The workflow consisted of 1) telephone consultation with a radiation oncologist (RO); 2) pre-planning on the dCT using planning templates and mostly intensity-modulated radiotherapy; 3) RO consultation on the day of treatment; 4) CBCT scan with on-couch adaptation of the target and treatment plan; 5) delivery of either scheduled or adapted treatment plan. Primary outcomes were dosimetric data and treatment times; secondary outcome was patient satisfaction.

RESULTS

47 patients were enrolled between December 2021 and October 2022. In all treatments, adapted treatment plans were chosen due to significant improvements in target coverage (PTV/CTV V95%, p-value < 0.005) compared to the original treatment plan calculated on daily anatomy. Most patients were satisfied with the workflow. The average treatment time, including consultation and on-couch adaptive treatment, was 85 minutes. On-couch adaptation took on average 30 min. but was longer in cases where the automated deformable image registration failed to correctly propagate the targets.

CONCLUSION

A fast treatment workflow for patients referred for painful bone metastases was implemented successfully using online adaptive radiotherapy, without a dedicated CT simulation. Patients were generally satisfied with the palliative radiotherapy workflow.

GPU-accelerated Monte Carlo simulation of electron and photon interactions for radiotherapy applications

Objective. The Monte Carlo simulation software is a valuable tool in radiation therapy, in particular to achieve the needed accuracy in the dose evaluation for the treatment plans optimisation. The current challenge in this field is the time reduction to open the way to many clinical applications for which the computational time is an issue. In this manuscript we present an innovative GPU-accelerated Monte Carlo software for dose valuation in electron and photon based radiotherapy, developed as an update of the FRED (Fast paRticle thErapy Dose evaluator) software.Approach. The code transports particles through a 3D voxel grid, while scoring their energy deposition along their trajectory. The models of electromagnetic interactions in the energy region between 1 MeV-1 GeV available in literature have been implemented to efficiently run on GPUs, allowing to combine a fast tracking while keeping high accuracy in dose assessment. The FRED software has been bench-marked against state-of-art full MC (FLUKA, GEANT4) in the realm of two different radiotherapy applications: Intra-Operative Radio Therapy and Very High Electron Energy radiotherapy applications.Results. The single pencil beam dose-depth profiles in water as well as the dose map computed on non-homogeneous phantom agree with full-MCs at 2% level, observing a gain in processing time from 200 to 5000.Significance. Such performance allows for computing a plan with electron beams in few minutes with an accuracy of ∼%, demonstrating the FRED potential to be adopted for fast plan re-calculation in photon or electron radiotherapy applications.

Development of a GPU-superposition Monte Carlo code for fast dose calculation in magnetic fields

Objective. To develop and validate a graphics processing unit (GPU) based superposition Monte Carlo (SMC) code for efficient and accurate dose calculation in magnetic fields. Approach. A series of mono-energy photons ranging from 25 keV to 7.7 MeV were simulated with EGSnrc in a water phantom to generate particle tracks database. SMC physics was extended with charged particle transport in magnetic fields and subsequently programmed on GPU as gSMC. Optimized simulation scheme was designed by combining variance reduction techniques to relieve the thread divergence issue in general GPU-MC codes and improve the calculation efficiency. The gSMC code’s dose calculation accuracy and efficiency were assessed through both phantoms and patient cases. Main results. gSMC accurately calculated the dose in various phantoms for both B = 0 T and B = 1.5 T, and it matched EGSnrc well with a root mean square error of less than 1.0% for the entire depth dose region. Patient cases validation also showed a high dose agreement with EGSnrc with 3D gamma passing rate (2%/2 mm) large than 97% for all tested tumor sites. Combined with photon splitting and particle track repeating techniques, gSMC resolved the thread divergence issue and showed an efficiency gain of 186–304 relative to EGSnrc with 10 CPU threads. Significance. A GPU-superposition Monte Carlo code called gSMC was developed and validated for dose calculation in magnetic fields. The developed code’s high calculation accuracy and efficiency make it suitable for dose calculation tasks in online adaptive radiotherapy with MR-LINAC.

A Data-Driven Fragmentation Model for Carbon Therapy GPU-Accelerated Monte-Carlo Dose Recalculation

The advent of Graphics Processing Units (GPU) has prompted the development of Monte Carlo (MC) algorithms that can significantly reduce the simulation time with respect to standard MC algorithms based on Central Processing Unit (CPU) hardware. The possibility to evaluate a complete treatment plan within minutes, instead of hours, paves the way for many clinical applications where the time-factor is important. FRED (Fast paRticle thErapy Dose evaluator) is a software that exploits the GPU power to recalculate and optimise ion beam treatment plans. The main goal when developing the FRED physics model was to balance accuracy, calculation time and GPU execution guidelines. Nowadays, FRED is already used as a quality assurance tool in Maastricht and Krakow proton clinical centers and as a research tool in several clinical and research centers across Europe. Lately the core software has been updated including a model of carbon ions interactions with matter. The implementation is phenomenological and based on carbon fragmentation data currently available. The model has been tested against the MC FLUKA software, commonly used in particle therapy, and a good agreement was found. In this paper, the new FRED data-driven model for carbon ion fragmentation will be presented together with the validation tests against the FLUKA MC software. The results will be discussed in the context of FRED clinical applications to ¹²C ions treatment planning.

Development of a GPU-accelerated Monte Carlo dose calculation module for nuclear medicine, ARCHER-NM: demonstration for a PET/CT imaging procedure

Objective. This paper describes the development and validation of a GPU-accelerated Monte Carlo (MC) dose computing module dedicated to organ dose calculations of individual patients undergoing nuclear medicine (NM) internal radiation exposures involving PET/CT examination. Approach. This new module extends the more-than-10-years-long ARCHER project that developed a GPU-accelerated MC dose engine by adding dedicated NM source-definition features. To validate the code, we compared dose distributions from the point ion source, including 18F, 11C, 15O, and 68Ga, calculated for a water phantom against a well-tested MC code, GATE. To demonstrate the clinical utility and advantage of ARCHER-NM, one set of 18F-FDG PET/CT data for an adult male NM patient is calculated using the new code. Radiosensitive organs in the CT dataset are segmented using a CNN-based tool called DeepViewer. The PET image intensity maps are converted to radioactivity distributions to allow for MC radiation transport dose calculations at the voxel level. The dose rate maps and corresponding statistical uncertainties were calculated at the acquisition time of PET image. Main results. The water-phantom results show excellent agreement, suggesting that the radiation physics module in the new NM code is adequate. The dose rate results of the 18F-FDG PET imaging patient show that ARCHER-NM’s results agree very well with those of the GATE within −2.45% to 2.58% (for a total of 28 organs considered in this study). Most impressively, ARCHER-NM obtains such results in 22 s while it takes GATE about 180 min for the same number of 5 × 108 simulated decay events. Significance. This is the first study presenting GPU-accelerated patient-specific MC internal radiation dose rate calculations for clinically realistic 18F-FDG PET/CT imaging case involving autosegmentation of whole-body PET/CT images. This study suggests that the proposed computing tools—ARCHER-NM— are accurate and fast enough for routine internal dosimetry in NM clinics.

Machine Learning for Auto-Segmentation in Radiotherapy Planning

Manual segmentation of target structures and organs at risk is a crucial step in the radiotherapy workflow. It has the disadvantages that it can require several hours of clinician time per patient and is prone to inter- and intra-observer variability. Automatic segmentation (auto-segmentation), using computer algorithms, seeks to address these issues. Advances in machine learning and computer vision have led to the development of methods for accurate and efficient auto-segmentation. This review surveys auto-segmentation techniques and applications in radiotherapy planning. It provides an overview of traditional approaches to auto-segmentation, including intensity analysis, shape modelling and atlas-based methods. The focus, though, is on uses of machine learning and deep learning, including convolutional neural networks. Finally, the future of machine-learning-driven auto-segmentation in clinical settings is considered, and the barriers that must be overcome for it to be widely accepted into routine practice are highlighted.

Segmentation of Organs and Tumor within Brain Magnetic Resonance Images Using K-Nearest Neighbor Classification

PURPOSE

To fully exploit the benefits of magnetic resonance imaging (MRI) for radiotherapy, it is desirable to develop segmentation methods to delineate patients' MRI images fast and accurately. The purpose of this work is to develop a semi-automatic method to segment organs and tumor within the brain on standard T1- and T2-weighted MRI images.

METHODS AND MATERIALS

Twelve brain cancer patients were retrospectively included in this study, and a simple rigid registration was used to align all the images to the same spatial coordinates. Regions of interest were created for organs and tumor segmentations. The K-nearest neighbor (KNN) classification algorithm was used to characterize the knowledge of previous segmentations using 15 image features (T1 and T2 image intensity, 4 Gabor filtered images, 6 image gradients, and 3 Cartesian coordinates), and the trained models were used to predict organ and tumor contours. Dice similarity coefficient (DSC), normalized surface dice, sensitivity, specificity, and Hausdorff distance were used to evaluate the performance of segmentations.

RESULTS

Our semi-automatic segmentations matched with the ground truths closely. The mean DSC value was between 0.49 (optical chiasm) and 0.89 (right eye) for organ segmentations and was 0.87 for tumor segmentation. Overall performance of our method is comparable or superior to the previous work, and the accuracy of our semi-automatic segmentation is generally better for large volume objects.

CONCLUSION

The proposed KNN method can accurately segment organs and tumor using standard brain MRI images, provides fast and accurate image processing and planning tools, and paves the way for clinical implementation of MRI-guided radiotherapy and adaptive radiotherapy.

Varian ethos online adaptive radiotherapy for prostate cancer: Early results of contouring accuracy, treatment plan quality, and treatment time

The Varian Ethos system allows for online adaptive treatments through the utilization of artificial intelligence (AI) and deformable image registration which automates large parts of the anatomical contouring and plan optimization process. In this study, treatments of intact prostate and prostate bed, with and without nodes, were simulated for 182 online adaptive fractions, and then a further 184 clinical fractions were delivered on the Ethos system. Frequency and magnitude of contour edits were recorded, as well as a range of plan quality metrics. From the fractions analyzed, 11% of AI generated contours, known as influencer contours, required no change, and 81% required minor edits in any given fraction. The frequency of target and noninfluencer organs at risk (OAR) contour editing varied substantially between different targets and noninfluencer OARs, although across all targets 72% of cases required no edits. The adaptive plan was the preference in 95% of fractions. The adaptive plan met more goals than the scheduled plan in 78% of fractions, while in 15% of fractions the number of goals met was the same. The online adaptive recontouring and replanning process was carried out in 19 min on average. Significant improvements in dosimetry are possible with the Ethos online adaptive system in prostate radiotherapy.

Monte Carlo methods for device simulations in radiation therapy

Monte Carlo (MC) simulations play an important role in radiotherapy, especially as a method to evaluate physical properties that are either impossible or difficult to measure. For example, MC simulations (MCSs) are used to aid in the design of radiotherapy devices or to understand their properties. The aim of this article is to review the MC method for device simulations in radiation therapy. After a brief history of the MC method and popular codes in medical physics, we review applications of the MC method to model treatment heads for neutral and charged particle radiation therapy as well as specific in-room devices for imaging and therapy purposes. We conclude by discussing the impact that MCSs had in this field and the role of MC in future device design.

Monte Carlo methods for device simulations in radiation therapy

Monte Carlo (MC) simulations play an important role in radiotherapy, especially as a method to evaluate physical properties that are either impossible or difficult to measure. For example, MC simulations (MCSs) are used to aid in the design of radiotherapy devices or to understand their properties. The aim of this article is to review the MC method for device simulations in radiation therapy. After a brief history of the MC method and popular codes in medical physics, we review applications of the MC method to model treatment heads for neutral and charged particle radiation therapy as well as specific in-room devices for imaging and therapy purposes. We conclude by discussing the impact that MCSs had in this field and the role of MC in future device design.

Extension and validation of a GPU-Monte Carlo dose engine gDPM for 1.5 T MR-LINAC online independent dose verification

PURPOSE

To extend and validate the accuracy and efficiency of a graphics processing unit (GPU)-Monte Carlo dose engine for Elekta Unity 1.5 T Magnetic Resonance-Linear Accelerator (MR-LINAC) online independent dose verification.

METHODS

Electron/positron propagation physics in a uniform magnetic field was implemented in a previously developed GPU-Monte Carlo dose engine-gDPM. The dose calculation accuracy in the magnetic field was first evaluated in heterogeneous phantom with EGSnrc. The dose engine was then commissioned to a Unity machine with a virtual two photon-source model and compared with the Monaco treatment planning system. Fifteen patient plans from five tumor sites were included for the quantification of online dose verification accuracy and efficiency.

RESULTS

The extended gDPM accurately calculated the dose in a 1.5 T external magnetic field and was well matched with EGSnrc. The relative dose difference along central beam axis was less than 0.5% for the homogeneous region in water-lung phantom. The maximum difference was found at the build-up regions and heterogeneous interfaces, reaching 1.9% and 2.4% for 2 and 6 MeV mono-energy photon beams, respectively. The root mean square errors for depth-dose fall-off region were less than 0.2% for all field sizes and presented a good match between gDPM and Monaco GPUMCD. For in-field profiles, the dose differences were within 1% for cross-plane and in-plane directions for all calculated depths except dmax. For penumbra regions, the distance-to-agreements between two dose profiles were less than 0.1 cm. For patient plan verification, the maximum relative average dose difference was 1.3%. The gamma passing rates with criteria 3% (2 mm) for dose regions above 20% were between 93% and 98%. gDPM can complete the dose calculation for less than 40 s with 5 × 10⁸ photons on a single NVIDIA GTX-1080Ti GPU and achieve a statistical uncertainty of 0.5%-1.1% for all evaluated cases.

CONCLUSIONS

A GPU-Monte Carlo package-gDPM was extended and validated for Elekta Unity online plan verification. Its calculation accuracy and efficiency make it suitable for online independent dose verification for MR-LINAC.

High-throughput, accurate Monte Carlo simulation on CPU hardware for PET applications

Monte Carlo simulations (MCS) represent a fundamental approach to modelling the photon interactions in Positron Emission Tomography (PET). A variety of PET-dedicated MCS tools are available to assist and improve PET imaging applications. Of these, GATE has evolved into one of the most popular software for PET MCS because of its accuracy and flexibility. However, simulations are extremely time-consuming. The use of graphics processing units (GPU) has been proposed as a solution to this, with reported acceleration factors about 400-800. These factors refer to GATE benchmarks performed on a single CPU core. Consequently, CPU-based MCS can also be easily accelerated by one order of magnitude or beyond when exploiting multi-threading on powerful CPUs. Thus, CPU-based implementations become competitive when further optimisations can be achieved. In this context, we have developed a novel, CPU-based software called the PET Physics Simulator (PPS), which combines several efficient methods to significantly boost the performance. PPS flexibly applies GEANT4 cross-sections as a pre-calculated database, thus obtaining results equivalent to GATE. This is demonstrated for an elaborated PET scanner with 3-layer block detectors. All code optimisations yield an acceleration factor of  20 (single core). Multi-threading on a high-end CPU workstation (96 cores) further accelerates the PPS by a factor of 80. This results in a total speed-up factor of 1600, which outperforms comparable GPU-based MCS by a factor of  2. Optionally, the proposed method of coincidence multiplexing can further enhance the throughput by an additonal factor of 15. The combination of all optimisations corresponds to an acceleration factor of  24000. In this way, the PPS can simulate complex PET detector systems with an effective throughput of photon pairs in less than 10 milliseconds.

Recent Developments on gMicroMC: Transport Simulations of Proton and Heavy Ions and Concurrent Transport of Radicals and DNA

Mechanistic Monte Carlo (MC) simulation of radiation interaction with water and DNA is important for the understanding of biological responses induced by ionizing radiation. In our previous work, we employed the Graphical Processing Unit (GPU)-based parallel computing technique to develop a novel, highly efficient, and open-source MC simulation tool, gMicroMC, for simulating electron-induced DNA damages. In this work, we reported two new developments in gMicroMC: the transport simulation of protons and heavy ions and the concurrent transport of radicals in the presence of DNA. We modeled these transports based on electromagnetic interactions between charged particles and water molecules and the chemical reactions between radicals and DNA molecules. Various physical properties, such as Linear Energy Transfer (LET) and particle range, from our simulation agreed with data published by NIST or simulation results from other CPU-based MC packages. The simulation results of DNA damage under the concurrent transport of radicals and DNA agreed with those from nBio-Topas simulation in a comprehensive testing case. GPU parallel computing enabled high computational efficiency. It took 41 s to simultaneously transport 100 protons with an initial kinetic energy of 10 MeV in water and 470 s to transport 105 radicals up to 1 µs in the presence of DNA.

Long short-term memory networks for proton dose calculation in highly heterogeneous tissues

PURPOSE

To investigate the feasibility and accuracy of proton dose calculations with artificial neural networks (ANNs) in challenging three-dimensional (3D) anatomies.

METHODS

A novel proton dose calculation approach was designed based on the application of a long short-term memory (LSTM) network. It processes the 3D geometry as a sequence of two-dimensional (2D) computed tomography slices and outputs a corresponding sequence of 2D slices that forms the 3D dose distribution. The general accuracy of the approach is investigated in comparison to Monte Carlo reference simulations and pencil beam dose calculations. We consider both artificial phantom geometries and clinically realistic lung cases for three different pencil beam energies.

RESULTS

For artificial phantom cases, the trained LSTM model achieved a 98.57% γ-index pass rate ([1%, 3 mm]) in comparison to MC simulations for a pencil beam with initial energy 104.25 MeV. For a lung patient case, we observe pass rates of 98.56%, 97.74%, and 94.51% for an initial energy of 67.85, 104.25, and 134.68 MeV, respectively. Applying the LSTM dose calculation on patient cases that were fully excluded from the training process yields an average γ-index pass rate of 97.85%.

CONCLUSIONS

LSTM networks are well suited for proton dose calculation tasks. Further research, especially regarding model generalization and computational performance in comparison to established dose calculation methods, is warranted.

The Emergence of Artificial Intelligence within Radiation Oncology Treatment Planning

BACKGROUND

The future of artificial intelligence (AI) heralds unprecedented change for the field of radiation oncology. Commercial vendors and academic institutions have created AI tools for radiation oncology, but such tools have not yet been widely adopted into clinical practice. In addition, numerous discussions have prompted careful thoughts about AI's impact upon the future landscape of radiation oncology: How can we preserve innovation, creativity, and patient safety? When will AI-based tools be widely adopted into the clinic? Will the need for clinical staff be reduced? How will these devices and tools be developed and regulated?

SUMMARY

In this work, we examine how deep learning, a rapidly emerging subset of AI, fits into the broader historical context of advancements made in radiation oncology and medical physics. In addition, we examine a representative set of deep learning-based tools that are being made available for use in external beam radiotherapy treatment planning and how these deep learning-based tools and other AI-based tools will impact members of the radiation treatment planning team. Key Messages: Compared to past transformative innovations explored in this article, such as the Monte Carlo method or intensity-modulated radiotherapy, the development and adoption of deep learning-based tools is occurring at faster rates and promises to transform practices of the radiation treatment planning team. However, accessibility to these tools will be determined by each clinic's access to the internet, web-based solutions, or high-performance computing hardware. As seen by the trends exhibited by many technologies, high dependence on new technology can result in harm should the product fail in an unexpected manner, be misused by the operator, or if the mitigation to an expected failure is not adequate. Thus, the need for developers and researchers to rigorously validate deep learning-based tools, for users to understand how to operate tools appropriately, and for professional bodies to develop guidelines for their use and maintenance is essential. Given that members of the radiation treatment planning team perform many tasks that are automatable, the use of deep learning-based tools, in combination with other automated treatment planning tools, may refocus tasks performed by the treatment planning team and may potentially reduce resource-related burdens for clinics with limited resources.

Adaptive Radiation Therapy (ART) Strategies and Technical Considerations: A State of the ART Review From NRG Oncology

The integration of adaptive radiation therapy (ART), or modifying the treatment plan during the treatment course, is becoming more widely available in clinical practice. ART offers strong potential for minimizing treatment-related toxicity while escalating or de-escalating target doses based on the dose to organs at risk. Yet, ART workflows add complexity into the radiation therapy planning and delivery process that may introduce additional uncertainties. This work sought to review presently available ART workflows and technological considerations such as image quality, deformable image registration, and dose accumulation. Quality assurance considerations for ART components and minimum recommendations are described. Personnel and workflow efficiency recommendations are provided, as is a summary of currently available clinical evidence supporting the implementation of ART. Finally, to guide future clinical trial protocols, an example ART physician directive and a physics template following standard NRG Oncology protocol is provided.

Dose rate determination for preclinical total body irradiation

The accuracy of delivered radiation dose and the reproducibility of employed radiotherapy methods are key factors for preclinical radiobiology applications and research studies. In this work, ionization chamber (IC) measurements and Monte Carlo (MC) simulations were used to accurately determine the dose rate for total body irradiation (TBI), a classic radiobiologic and immunologic experimental method. Several phantom configurations, including large solid water slab, small water box and rodentomorphic mouse and rat phantoms were simulated and measured for TBI setup utilizing a preclinical irradiator XRad320. The irradiator calibration and the phantom measurements were performed using an ADCL calibrated IC N31010 following the AAPM TG-61 protocol. The MC simulations were carried out using Geant4/GATE to compute absorbed dose distributions for all phantom configurations. All simulated and measured geometries had favorable agreement. On average, the relative dose rate difference was 2.3%. However, the study indicated large dose rate deviations, if calibration conditions are assumed for a given experimental setup as commonly done for a quick determination of irradiation times utilizing lookup tables and hand calculations. In a TBI setting, the reference calibration geometry at an extended source-to-surface distance and a large reference field size is likely to overestimate true photon scatter. Consequently, the measured and hand calculated dose rates, for TBI geometries in this study, had large discrepancies: 16% for a large solid water slab, 27% for a small water box, and 31%, 36%, and 30% for mouse phantom, rat phantom, and mouse phantom in a pie cage, respectively. Small changes in TBI experimental setup could result in large dose rate variations. MC simulations and the corresponding measurements specific to a designed experimental setup are vital for accurate preclinical dosimetry and reproducibility of radiobiological findings. This study supports the well-recognized need for physics consultation for all radiobiological investigations.

Whole-body voxel-based internal dosimetry using deep learning

Purpose

In the era of precision medicine, patient-specific dose calculation using Monte Carlo (MC) simulations is deemed the gold standard technique for risk-benefit analysis of radiation hazards and correlation with patient outcome. Hence, we propose a novel method to perform whole-body personalized organ-level dosimetry taking into account the heterogeneity of activity distribution, non-uniformity of surrounding medium, and patient-specific anatomy using deep learning algorithms.

Methods

We extended the voxel-scale MIRD approach from single S-value kernel to specific S-value kernels corresponding to patient-specific anatomy to construct 3D dose maps using hybrid emission/transmission image sets. In this context, we employed a Deep Neural Network (DNN) to predict the distribution of deposited energy, representing specific S-values, from a single source in the center of a 3D kernel composed of human body geometry. The training dataset consists of density maps obtained from CT images and the reference voxelwise S-values generated using Monte Carlo simulations. Accordingly, specific S-value kernels are inferred from the trained model and whole-body dose maps constructed in a manner analogous to the voxel-based MIRD formalism, i.e., convolving specific voxel S-values with the activity map. The dose map predicted using the DNN was compared with the reference generated using MC simulations and two MIRD-based methods, including Single and Multiple S-Values (SSV and MSV) and Olinda/EXM software package.

Results

The predicted specific voxel S-value kernels exhibited good agreement with the MC-based kernels serving as reference with a mean relative absolute error (MRAE) of 4.5 ± 1.8 (%). Bland and Altman analysis showed the lowest dose bias (2.6%) and smallest variance (CI: − 6.6, + 1.3) for DNN. The MRAE of estimated absorbed dose between DNN, MSV, and SSV with respect to the MC simulation reference were 2.6%, 3%, and 49%, respectively. In organ-level dosimetry, the MRAE between the proposed method and MSV, SSV, and Olinda/EXM were 5.1%, 21.8%, and 23.5%, respectively.

Conclusion

The proposed DNN-based WB internal dosimetry exhibited comparable performance to the direct Monte Carlo approach while overcoming the limitations of conventional dosimetry techniques in nuclear medicine.

New capabilities of the Monte Carlo dose engine ARCHER-RT: Clinical validation of the Varian TrueBeam machine for VMAT external beam radiotherapy

PURPOSE

The Monte Carlo radiation transport method is considered the most accurate approach for absorbed dose calculations in external beam radiation therapy. In this study, an efficient and accurate source model of the Varian TrueBeam 6X STx Linac is developed and integrated with a fast Monte Carlo photon-electron transport absorbed dose engine, ARCHER-RT, which is capable of being executed on CPUs, NVIDIA GPUs, and AMD GPUs. This capability of fast yet accurate radiation dose calculation is essential for clinical utility of this new technology. This paper describes the software and algorithmic developments made to the ARCHER-RT absorbed dose engine.

METHODS

AMD's Heterogeneous-Compute Interface for Portability (HIP) was implemented in ARCHER-RT to allow for device independent execution on NVIDIA and AMD GPUs. Architecture-specific atomic-add algorithms have been identified and both more accurate single-precision and double-precision computational absorbed dose calculation methods have been added to ARCHER-RT and validated through a test case to evaluate the accuracy and performance of the algorithms. The validity of the source model and the radiation transport physics were benchmarked against Monte Carlo simulations performed with EGSnrc. Secondary dose-check physics plans, and a clinical prostate treatment plan were calculated to demonstrate the applicability of the platform for clinical use. Absorbed dose difference maps and gamma analyses were conducted to establish the accuracy and consistency between the two Monte Carlo models. Timing studies were conducted on a CPU, an NVIDIA GPU, and an AMD GPU to evaluate the computational speed of ARCHER-RT.

RESULTS

Percent depth doses were computed for different field sizes ranging from 1.5 cm²  × 1.5 cm² to 22 cm²  × 40cm² and the two codes agreed for all points outside high gradient regions within 3%. Axial profiles computed for a 10 cm²  × 10 cm² field for multiple depths agreed for all points outside high gradient regions within 2%. The test case investigating the impact of native single-precision compared to double-precision showed differences in voxels as large as 71.47% and the implementation of KAS single-precision reduced the difference to less than 0.01%. The 3%/3mm gamma pass rates for an MPPG5a multileaf collimator (MLC) test case and a clinical VMAT prostate plan were 94.2% and 98.4% respectively. Timing studies demonstrated the calculation of a VMAT plan was completed in 50.3, 187.9, and 216.8 s on an NVIDIA GPU, AMD GPU, and Intel CPU, respectively.

CONCLUSION

ARCHER-RT is capable of patient-specific VMAT external beam photon absorbed dose calculations and its potential has been demonstrated by benchmarking against a well validated EGSnrc model of a Varian TrueBeam. Additionally, the implementation of AMD's HIP has shown the flexibility of the ARCHER-RT platform for device independent calculations. This work demonstrates the significant addition of functionality added to ARCHER-RT framework which has marked utility for both research and clinical applications and demonstrates further that Monte Carlo-based absorbed dose engines like ARCHER-RT have the potential for widespread clinical implementation.

An introduction to deep learning in medical physics: advantages, potential, and challenges

As one of the most popular approaches in artificial intelligence, deep learning (DL) has attracted a lot of attention in the medical physics field over the past few years. The goals of this topical review article are twofold. First, we will provide an overview of the method to medical physics researchers interested in DL to help them start the endeavor. Second, we will give in-depth discussions on the DL technology to make researchers aware of its potential challenges and possible solutions. As such, we divide the article into two major parts. The first part introduces general concepts and principles of DL and summarizes major research resources, such as computational tools and databases. The second part discusses challenges faced by DL, present available methods to mitigate some of these challenges, as well as our recommendations.

Metropolis Monte Carlo simulation scheme for fast scattered X-ray photon calculation in CT

Monte Carlo (MC) method is commonly considered as the most accurate approach for particle transport simulation because of its capability to precisely model physics interactions and simulation geometry. Conventionally, MC simulation is performed in a particle-by-particle fashion. In certain problems such as computing scattered X-ray photon signal at a detector of CT, the conventional simulation scheme suffers from low efficiency mainly due to the fact that abundant photons are simulated but do not reach the detector. The computational resources spent on those photons are therefore wasted. To solve this problem, this study develops a novel GPU-based Metropolis MC (gMMC) with a novel path-by-path simulation scheme and demonstrates its effectiveness in an example problem of scattered X-ray photon calculation in CT. In contrast to the conventional MC approach, gMMC samples an entire photon path extending from the X-ray source to the detector using Metropolis-Hasting algorithm. The path-by-path simulation scheme ensures contribution of every sampled event to the signal of interest, improving overall efficiency. We benchmark gMMC against an in-house developed GPU-based MC tool, gMCDRR, which performs simulations in the conventional particle-by-particle fashion. gMMC reaches speed up factors of 37~48 times in simple phantom cases and 20-34 times in real patient cases. The results calculated by gMCDRR and gMMC agree well with average differences < 3%.

A fast inverse direct aperture optimization algorithm for intensity-modulated radiation therapy

PURPOSE

The goal of this work was to develop and evaluate a fast inverse direct aperture optimization (FIDAO) algorithm for IMRT treatment planning and plan adaptation.

METHODS

A previously proposed fluence map optimization algorithm called fast inverse dose optimization (FIDO) was extended to optimize the aperture shapes and weights of IMRT beams. FIDO is a very fast fluence map optimization algorithm for IMRT that finds the global minimum using direct matrix inversion without unphysical negative beam weights. In this study, an equivalent second-order Taylor series expansion of the FIDO objective function was used, which allowed for the objective function value and gradient vector to be computed very efficiently during direct aperture optimization, resulting in faster optimization. To evaluate the speed gained with FIDAO, a proof-of-concept algorithm was developed in MATLAB using an interior-point optimization method to solve the reformulated aperture-based FIDO problem. The FIDAO algorithm was used to optimize four step-and-shoot IMRT cases: on the AAPM TG-119 phantom as well as a liver, prostate, and head-and-neck clinical cases. Results were compared with a conventional DAO algorithm that uses the same interior-point method but using the standard formulation of the objective function and its gradient vector.

RESULTS

A substantial gain in optimization speed was obtained with the prototype FIDAO algorithm compared to the conventional DAO algorithm while producing plans of similar quality. The optimization time (number of iterations) for the prototype FIDAO algorithm vs the conventional DAO algorithm was 0.3 s (17) vs 56.7 s (50); 2.0 s (28) vs 134.1 s (57); 2.5 s (26) vs 180.6 s (107); and 6.7 s (20) vs 469.4 s (482) in the TG-119 phantom, liver, prostate, and head-and-neck examples, respectively.

CONCLUSIONS

A new direct aperture optimization algorithm based on FIDO was developed. For the four IMRT test cases examined, this algorithm executed approximately 70-200 times faster without compromising the IMRT plan quality.

Clinical implementations of 4D pencil beam scanned particle therapy: Report on the 4D treatment planning workshop 2016 and 2017

In 2016 and 2017, the 8th and 9th 4D treatment planning workshop took place in Groningen (the Netherlands) and Vienna (Austria), respectively. This annual workshop brings together international experts to discuss research, advances in clinical implementation as well as problems and challenges in 4D treatment planning, mainly in spot scanned proton therapy. In the last two years several aspects like treatment planning, beam delivery, Monte Carlo simulations, motion modeling and monitoring, QA phantoms as well as 4D imaging were thoroughly discussed. This report provides an overview of discussed topics, recent findings and literature review from the last two years. Its main focus is to highlight translation of 4D research into clinical practice and to discuss remaining challenges and pitfalls that still need to be addressed and to be overcome.

Accuracy and efficiency of graphics processing unit (GPU) based Acuros XB dose calculation within the Varian Eclipse treatment planning system

To evaluate, in terms of dosimetric accuracy and calculation efficiency, the implementation of a graphic processing unit (GPU)-based Acuros XB dose calculation engine within version 15.5 of the Varian Eclipse treatment planning system. Initial phantom based calculations and a range of 101 clinical cases were analyzed on a dedicated test system. Dosimetric differences, based on dose-volume histrogram parameters and plan comparison, were compared between central processing unit (CPU) and GPU based calculation. Calculation times were also compared between CPU and GPU, as well as PLAN and FIELD modes. No dosimetric differences were found between CPU and GPU. CPU based calculations ranged from 25 to 533 seconds per plan, reducing to 13 to 70 seconds for GPU. GPU was 4.4 times more efficient than CPU. FIELD mode was up to 1.3 times more efficient than PLAN mode. For the clinical cases and version of Eclipse used, no dosimetric differences were found between CPU and GPU. Based on this, GPU architecture has been safely implemented and is ready for clinical use. GPU based calculation times were superior to CPU, being on average, 4.4 times faster.

Monte Carlo verification of radiotherapy treatments with CloudMC

Background

A new implementation has been made on CloudMC, a cloud-based platform presented in a previous work, in order to provide services for radiotherapy treatment verification by means of Monte Carlo in a fast, easy and economical way. A description of the architecture of the application and the new developments implemented is presented together with the results of the tests carried out to validate its performance.

Methods

CloudMC has been developed over Microsoft Azure cloud. It is based on a map/reduce implementation for Monte Carlo calculations distribution over a dynamic cluster of virtual machines in order to reduce calculation time. CloudMC has been updated with new methods to read and process the information related to radiotherapy treatment verification: CT image set, treatment plan, structures and dose distribution files in DICOM format. Some tests have been designed in order to determine, for the different tasks, the most suitable type of virtual machines from those available in Azure. Finally, the performance of Monte Carlo verification in CloudMC is studied through three real cases that involve different treatment techniques, linac models and Monte Carlo codes.

Results

Considering computational and economic factors, D1_v2 and G1 virtual machines were selected as the default type for the Worker Roles and the Reducer Role respectively. Calculation times up to 33 min and costs of 16 € were achieved for the verification cases presented when a statistical uncertainty below 2% (2σ) was required. The costs were reduced to 3–6 € when uncertainty requirements are relaxed to 4%.

Conclusions

Advantages like high computational power, scalability, easy access and pay-per-usage model, make Monte Carlo cloud-based solutions, like the one presented in this work, an important step forward to solve the long-lived problem of truly introducing the Monte Carlo algorithms in the daily routine of the radiotherapy planning process.

Technical Note: An hybrid parallel implementation for EGSnrc Monte Carlo user codes

PURPOSE

The purpose of this study was to present a parallel solution for the EGSnrc Monte Carlo code system combining MPI and OpenMP programming models as an alternative to the provided implementation, based on the use of a batch-queueing system (BQS).

METHODS

Relying on a previous implementation based on OpenMP by E. Doerner and P. Caprile [Med. Phys. 44, 6672 (2017)], this work incorporates MPI features to efficiently distribute the simulation on current high-performance computing (HPC) systems. These features are introduced through properly defined macros, which are enabled depending on the compilation flags given by the user. The presented solution was benchmarked using the DOSXYZnrc code for a 6 MV clinical photon beam impinging on an homogeneous water phantom.

RESULTS

The platform validation against the serial run results confirmed that the introduction of new features does not modify the final dose distribution. The performance tests indicated that the new implementation was able to handle efficiently the workload distribution among the computing units available. Using all the resources available, the hybrid simulation was 10% faster than the MPI only solution and 30% faster than the BQS implementation.

CONCLUSIONS

The hybrid method presented is a viable solution to parallelize MC simulations using the EGSnrc codes in distributed computing systems in an simple and efficient way, taking advantage of the available resources and giving the user the possibility of choosing between different parallelization schemes (only OpenMP/MPI or a combination of both).

Internal Motion Estimation by Internal-external Motion Modeling for Lung Cancer Radiotherapy

The aim of this study is to develop an internal-external correlation model for internal motion estimation for lung cancer radiotherapy. Deformation vector fields that characterize the internal-external motion are obtained by respectively registering the internal organ meshes and external surface meshes from the 4DCT images via a recently developed local topology preserved non-rigid point matching algorithm. A composite matrix is constructed by combing the estimated internal phasic DVFs with external phasic and directional DVFs. Principle component analysis is then applied to the composite matrix to extract principal motion characteristics, and generate model parameters to correlate the internal-external motion. The proposed model is evaluated on a 4D NURBS-based cardiac-torso (NCAT) synthetic phantom and 4DCT images from five lung cancer patients. For tumor tracking, the center of mass errors of the tracked tumor are 0.8(±0.5)mm/0.8(±0.4)mm for synthetic data, and 1.3(±1.0)mm/1.2(±1.2)mm for patient data in the intra-fraction/inter-fraction tracking, respectively. For lung tracking, the percent errors of the tracked contours are 0.06(±0.02)/0.07(±0.03) for synthetic data, and 0.06(±0.02)/0.06(±0.02) for patient data in the intra-fraction/inter-fraction tracking, respectively. The extensive validations have demonstrated the effectiveness and reliability of the proposed model in motion tracking for both the tumor and the lung in lung cancer radiotherapy.

Material elemental decomposition in dual and multi-energy CT via a sparsity-dictionary approach for proton stopping power ratio calculation

PURPOSE

Accurate calculation of proton stopping power ratio (SPR) relative to water is crucial to proton therapy treatment planning, since SPR affects prediction of beam range. Current standard practice derives SPR using a single CT scan. Recent studies showed that dual-energy CT (DECT) offers advantages to accurately determine SPR. One method to further improve accuracy is to incorporate prior knowledge on human tissue composition through a dictionary approach. In addition, it is also suggested that using CT images with multiple (more than two) energy channels, i.e., multi-energy CT (MECT), can further improve accuracy. In this paper, we proposed a sparse dictionary-based method to convert CT numbers of DECT or MECT to elemental composition (EC) and relative electron density (rED) for SPR computation.

METHOD

A dictionary was constructed to include materials generated based on human tissues of known compositions. For a voxel with CT numbers of different energy channels, its EC and rED are determined subject to a constraint that the resulting EC is a linear non-negative combination of only a few tissues in the dictionary. We formulated this as a non-convex optimization problem. A novel algorithm was designed to solve the problem. The proposed method has a unified structure to handle both DECT and MECT with different number of channels. We tested our method in both simulation and experimental studies.

RESULTS

Average errors of SPR in experimental studies were 0.70% in DECT, 0.53% in MECT with three energy channels, and 0.45% in MECT with four channels. We also studied the impact of parameter values and established appropriate parameter values for our method.

CONCLUSION

The proposed method can accurately calculate SPR using DECT and MECT. The results suggest that using more energy channels may improve the SPR estimation accuracy.

Multi-GPU configuration of 4D intensity modulated radiation therapy inverse planning using global optimization

We report on the design, implementation and characterization of a multi-graphic processing unit (GPU) computational platform for higher-order optimization in radiotherapy treatment planning. In collaboration with a commercial vendor (Varian Medical Systems, Palo Alto, CA), a research prototype GPU-enabled Eclipse (V13.6) workstation was configured. The hardware consisted of dual 8-core Xeon processors, 256 GB RAM and four NVIDIA Tesla K80 general purpose GPUs. We demonstrate the utility of this platform for large radiotherapy optimization problems through the development and characterization of a parallelized particle swarm optimization (PSO) four dimensional (4D) intensity modulated radiation therapy (IMRT) technique. The PSO engine was coupled to the Eclipse treatment planning system via a vendor-provided scripting interface. Specific challenges addressed in this implementation were (i) data management and (ii) non-uniform memory access (NUMA). For the former, we alternated between parameters over which the computation process was parallelized. For the latter, we reduced the amount of data required to be transferred over the NUMA bridge. The datasets examined in this study were approximately 300 GB in size, including 4D computed tomography images, anatomical structure contours and dose deposition matrices. For evaluation, we created a 4D-IMRT treatment plan for one lung cancer patient and analyzed computation speed while varying several parameters (number of respiratory phases, GPUs, PSO particles, and data matrix sizes). The optimized 4D-IMRT plan enhanced sparing of organs at risk by an average reduction of [Formula: see text] in maximum dose, compared to the clinical optimized IMRT plan, where the internal target volume was used. We validated our computation time analyses in two additional cases. The computation speed in our implementation did not monotonically increase with the number of GPUs. The optimal number of GPUs (five, in our study) is directly related to the hardware specifications. The optimization process took 35 min using 50 PSO particles, 25 iterations and 5 GPUs.

Internet-based computer technology on radiotherapy

Recent rapid development of Internet-based computer technologies has made possible many novel applications in radiation dose delivery. However, translational speed of applying these new technologies in radiotherapy could hardly catch up due to the complex commissioning process and quality assurance protocol. Implementing novel Internet-based technology in radiotherapy requires corresponding design of algorithm and infrastructure of the application, set up of related clinical policies, purchase and development of software and hardware, computer programming and debugging, and national to international collaboration. Although such implementation processes are time consuming, some recent computer advancements in the radiation dose delivery are still noticeable. In this review, we will present the background and concept of some recent Internet-based computer technologies such as cloud computing, big data processing and machine learning, followed by their potential applications in radiotherapy, such as treatment planning and dose delivery. We will also discuss the current progress of these applications and their impacts on radiotherapy. We will explore and evaluate the expected benefits and challenges in implementation as well.

A review of GPU-based medical image reconstruction

Tomographic image reconstruction is a computationally demanding task, even more so when advanced models are used to describe a more complete and accurate picture of the image formation process. Such advanced modeling and reconstruction algorithms can lead to better images, often with less dose, but at the price of long calculation times that are hardly compatible with clinical workflows. Fortunately, reconstruction tasks can often be executed advantageously on Graphics Processing Units (GPUs), which are exploited as massively parallel computational engines. This review paper focuses on recent developments made in GPU-based medical image reconstruction, from a CT, PET, SPECT, MRI and US perspective. Strategies and approaches to get the most out of GPUs in image reconstruction are presented as well as innovative applications arising from an increased computing capacity. The future of GPU-based image reconstruction is also envisioned, based on current trends in high-performance computing.

Monte Carlo dose calculations for high-dose-rate brachytherapy using GPU-accelerated processing

PURPOSE

Current clinical brachytherapy dose calculations are typically based on the Association of American Physicists in Medicine Task Group report 43 (TG-43) guidelines, which approximate patient geometry as an infinitely large water phantom. This ignores patient and applicator geometries and heterogeneities, causing dosimetric errors. Although Monte Carlo (MC) dose calculation is commonly recognized as the most accurate method, its associated long computational time is a major bottleneck for routine clinical applications. This article presents our recent developments of a fast MC dose calculation package for high-dose-rate (HDR) brachytherapy, gBMC, built on a graphics processing unit (GPU) platform.

METHODS AND MATERIALS

gBMC-simulated photon transport in voxelized geometry with physics in (192)Ir HDR brachytherapy energy range considered. A phase-space file was used as a source model. GPU-based parallel computation was used to simultaneously transport multiple photons, one on a GPU thread. We validated gBMC by comparing the dose calculation results in water with that computed TG-43. We also studied heterogeneous phantom cases and a patient case and compared gBMC results with Acuros BV results.

RESULTS

Radial dose function in water calculated by gBMC showed <0.6% relative difference from that of the TG-43 data. Difference in anisotropy function was <1%. In two heterogeneous slab phantoms and one shielded cylinder applicator case, average dose discrepancy between gBMC and Acuros BV was <0.87%. For a tandem and ovoid patient case, good agreement between gBMC and Acruos BV results was observed in both isodose lines and dose-volume histograms. In terms of the efficiency, it took ∼47.5 seconds for gBMC to reach 0.15% statistical uncertainty within the 5% isodose line for the patient case.

CONCLUSIONS

The accuracy and efficiency of a new GPU-based MC dose calculation package, gBMC, for HDR brachytherapy make it attractive for clinical applications.

Fast and Accurate Rat Head Motion Tracking With Point Sources for Awake Brain PET

To avoid the confounding effects of anesthesia and immobilization stress in rat brain positron emission tomography (PET), motion tracking-based unrestrained awake rat brain imaging is being developed. In this paper, we propose a fast and accurate rat headmotion tracking method based on small PET point sources. PET point sources (3-4) attached to the rat's head are tracked in image space using 15-32-ms time frames. Our point source tracking (PST) method was validated using a manually moved microDerenzo phantom that was simultaneously tracked with an optical tracker (OT) for comparison. The PST method was further validated in three awake [¹⁸F]FDG rat brain scans. Compared with the OT, the PST-based correction at the same frame rate (31.2 Hz) reduced the reconstructed FWHM by 0.39-0.66 mm for the different tested rod sizes of the microDerenzo phantom. The FWHM could be further reduced by another 0.07-0.13 mm when increasing the PST frame rate (66.7 Hz). Regional brain [¹⁸F]FDG uptake in the motion corrected scan was strongly correlated ( ) with that of the anesthetized reference scan for all three cases ( ). The proposed PST method allowed excellent and reproducible motion correction in awake in vivo experiments. In addition, there is no need of specialized tracking equipment or additional calibrations to be performed, the point sources are practically imperceptible to the rat, and PST is ideally suitable for small bore scanners, where optical tracking might be challenging.

Initial development of goCMC: a GPU-oriented fast cross-platform Monte Carlo engine for carbon ion therapy

Monte Carlo (MC) simulation is considered as the most accurate method for calculation of absorbed dose and fundamental physics quantities related to biological effects in carbon ion therapy. To improve its computational efficiency, we have developed a GPU-oriented fast MC package named goCMC, for carbon therapy. goCMC simulates particle transport in voxelized geometry with kinetic energy up to 450 MeV u-1. Class II condensed history simulation scheme with a continuous slowing down approximation was employed. Energy straggling and multiple scattering were modeled. δ-electrons were terminated with their energy locally deposited. Four types of nuclear interactions were implemented in goCMC, i.e. carbon-hydrogen, carbon-carbon, carbon-oxygen and carbon-calcium inelastic collisions. Total cross section data from Geant4 were used. Secondary particles produced in these interactions were sampled according to particle yield with energy and directional distribution data derived from Geant4 simulation results. Secondary charged particles were transported following the condensed history scheme, whereas secondary neutral particles were ignored. goCMC was developed under OpenCL framework and is executable on different platforms, e.g. GPU and multi-core CPU. We have validated goCMC with Geant4 in cases with different beam energy and phantoms including four homogeneous phantoms, one heterogeneous half-slab phantom, and one patient case. For each case [Formula: see text] carbon ions were simulated, such that in the region with dose greater than 10% of maximum dose, the mean relative statistical uncertainty was less than 1%. Good agreements for dose distributions and range estimations between goCMC and Geant4 were observed. 3D gamma passing rates with 1%/1 mm criterion were over 90% within 10% isodose line except in two extreme cases, and those with 2%/1 mm criterion were all over 96%. Efficiency and code portability were tested with different GPUs and CPUs. Depending on the beam energy and voxel size, the computation time to simulate [Formula: see text] carbons was 9.9-125 s, 2.5-50 s and 60-612 s on an AMD Radeon GPU card, an NVidia GeForce GTX 1080 GPU card and an Intel Xeon E5-2640 CPU, respectively. The combined accuracy, efficiency and portability make goCMC attractive for research and clinical applications in carbon ion therapy.

Accelerated Monte Carlo simulation on the chemical stage in water radiolysis using GPU

The accurate simulation of water radiolysis is an important step to understand the mechanisms of radiobiology and quantitatively test some hypotheses regarding radiobiological effects. However, the simulation of water radiolysis is highly time consuming, taking hours or even days to be completed by a conventional CPU processor. This time limitation hinders cell-level simulations for a number of research studies. We recently initiated efforts to develop gMicroMC, a GPU-based fast microscopic MC simulation package for water radiolysis. The first step of this project focused on accelerating the simulation of the chemical stage, the most time consuming stage in the entire water radiolysis process. A GPU-friendly parallelization strategy was designed to address the highly correlated many-body simulation problem caused by the mutual competitive chemical reactions between the radiolytic molecules. Two cases were tested, using a 750 keV electron and a 5 MeV proton incident in pure water, respectively. The time-dependent yields of all the radiolytic species during the chemical stage were used to evaluate the accuracy of the simulation. The relative differences between our simulation and the Geant4-DNA simulation were on average 5.3% and 4.4% for the two cases. Our package, executed on an Nvidia Titan black GPU card, successfully completed the chemical stage simulation of the two cases within 599.2 s and 489.0 s. As compared with Geant4-DNA that was executed on an Intel i7-5500U CPU processor and needed 28.6 h and 26.8 h for the two cases using a single CPU core, our package achieved a speed-up factor of 171.1-197.2.

Use of proximal operator graph solver for radiation therapy inverse treatment planning

PURPOSE

Most radiation therapy optimization problems can be formulated as an unconstrained problem and solved efficiently by quasi-Newton methods such as the Limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm. However, several next generation planning techniques such as total variation regularization- based optimization and MV+kV optimization, involve constrained or mixed-norm optimization, and cannot be solved by quasi-Newton methods. Using standard optimization algorithms on such problems often leads to prohibitively long optimization times and large memory requirements. This work investigates the use of a recently developed proximal operator graph solver (POGS) in solving such radiation therapy optimization problems.

METHODS

Radiation therapy inverse treatment planning was formulated as a graph form problem, and the proximal operators of POGS for quadratic optimization were derived. POGS was exploited for the first time to impose hard dose constraints along with soft constraints in the objective function. The solver was applied to several clinical treatment sites (TG119, liver, prostate, and head&neck), and the results were compared to the solutions obtained by other commercial and non-commercial optimizers.

RESULTS

For inverse planning optimization with nonnegativity box constraints on beamlet intensity, the speed of POGS can compete with that of LBFGSB in some situations. For constrained and mixed-norm optimization, POGS is about one or two orders of magnitude faster than the other solvers while requiring less computer memory.

CONCLUSIONS

POGS was used for solving inverse treatment planning problems involving constrained or mixed-norm formulation on several example sites. This approach was found to improve upon standard solvers in terms of computation speed and memory usage, and is capable of solving traditionally difficult problems, such as total variation regularization-based optimization and combined MV+kV optimization.

Moving GPU-OpenCL-based Monte Carlo dose calculation toward clinical use: Automatic beam commissioning and source sampling for treatment plan dose calculation

We have previously developed a GPU‐based Monte Carlo (MC) dose engine on the OpenCL platform, named goMC, with a built‐in analytical linear accelerator (linac) beam model. In this paper, we report our recent improvement on goMC to move it toward clinical use. First, we have adapted a previously developed automatic beam commissioning approach to our beam model. The commissioning was conducted through an optimization process, minimizing the discrepancies between calculated dose and measurement. We successfully commissioned six beam models built for Varian TrueBeam linac photon beams, including four beams of different energies (6 MV, 10 MV, 15 MV, and 18 MV) and two flattening‐filter‐free (FFF) beams of 6 MV and 10 MV. Second, to facilitate the use of goMC for treatment plan dose calculations, we have developed an efficient source particle sampling strategy. It uses the pre‐generated fluence maps (FMs) to bias the sampling of the control point for source particles already sampled from our beam model. It could effectively reduce the number of source particles required to reach a statistical uncertainty level in the calculated dose, as compared to the conventional FM weighting method. For a head‐and‐neck patient treated with volumetric modulated arc therapy (VMAT), a reduction factor of ~2.8 was achieved, accelerating dose calculation from 150.9 s to 51.5 s. The overall accuracy of goMC was investigated on a VMAT prostate patient case treated with 10 MV FFF beam. 3D gamma index test was conducted to evaluate the discrepancy between our calculated dose and the dose calculated in Varian Eclipse treatment planning system. The passing rate was 99.82% for 2%/2 mm criterion and 95.71% for 1%/1 mm criterion. Our studies have demonstrated the effectiveness and feasibility of our auto‐commissioning approach and new source sampling strategy for fast and accurate MC dose calculations for treatment plans.