AAPM Task Group 334: A guidance document to using radiotherapy immobilization devices and accessories in an MR environment.

Use of magnetic resonance (MR) imaging in radiation therapy has increased substantially in recent years as more radiotherapy centers are having MR simulators installed, requesting more time on clinical diagnostic MR systems, or even treating with combination MR linear accelerator (MR-linac) systems. With this increased use, to ensure the most accurate integration of images into radiotherapy (RT), RT immobilization devices and accessories must be able to be used safely in the MR environment and produce minimal perturbations. The determination of the safety profile and considerations often falls to the medical physicist or other support staff members who at a minimum should be a Level 2 personnel as per the ACR. The purpose of this guidance document will be to help guide the user in making determinations on MR Safety labeling (i.e., MR Safe, Conditional, or Unsafe) including standard testing, and verification of image quality, when using RT immobilization devices and accessories in an MR environment.

NRG Oncology Assessment of Artificial Intelligence Deep Learning-Based Auto-segmentation for Radiation Therapy: Current Developments, Clinical Considerations, and Future Directions.

Deep learning neural networks (DLNN) in Artificial intelligence (AI) have been extensively explored for automatic segmentation in radiotherapy (RT). In contrast to traditional model-based methods, data-driven AI-based models for auto-segmentation have shown high accuracy in early studies in research settings and controlled environment (single institution). Vendor-provided commercial AI models are made available as part of the integrated treatment planning system (TPS) or as a stand-alone tool that provides streamlined workflow interacting with the main TPS. These commercial tools have drawn clinics' attention thanks to their significant benefit in reducing the workload from manual contouring and shortening the duration of treatment planning. However, challenges occur when applying these commercial AI-based segmentation models to diverse clinical scenarios, particularly in uncontrolled environments. Contouring nomenclature and guideline standardization has been the main task undertaken by the NRG Oncology. AI auto-segmentation holds the potential clinical trial participants to reduce interobserver variations, nomenclature non-compliance, and contouring guideline deviations. Meanwhile, trial reviewers could use AI tools to verify contour accuracy and compliance of those submitted datasets. In recognizing the growing clinical utilization and potential of these commercial AI auto-segmentation tools, NRG Oncology has formed a working group to evaluate the clinical utilization and potential of commercial AI auto-segmentation tools. The group will assess in-house and commercially available AI models, evaluation metrics, clinical challenges, and limitations, as well as future developments in addressing these challenges. General recommendations are made in terms of the implementation of these commercial AI models, as well as precautions in recognizing the challenges and limitations.

Radiation-induced acoustic signal denoising using a supervised deep learning framework for imaging and therapy monitoring.

Radiation-induced acoustic (RA) imaging is a promising technique for visualizing the invisible radiation energy deposition in tissues, enabling new imaging modalities and real-time therapy monitoring. However, RA imaging signal often suffers from poor signal-to-noise ratios (SNRs), thus requiring measuring hundreds or even thousands of frames for averaging to achieve satisfactory quality. This repetitive measurement increases ionizing radiation dose and degrades the temporal resolution of RA imaging, limiting its clinical utility. In this study, we developed a general deep inception convolutional neural network (GDI-CNN) to denoise RA signals to substantially reduce the number of frames needed for averaging. The network employs convolutions with multiple dilations in each inception block, allowing it to encode and decode signal features with varying temporal characteristics. This design generalizes GDI-CNN to denoise acoustic signals resulting from different radiation sources. The performance of the proposed method was evaluated using experimental data of x-ray-induced acoustic, protoacoustic, and electroacoustic signals both qualitatively and quantitatively. Results demonstrated the effectiveness of GDI-CNN: it achieved x-ray-induced acoustic image quality comparable to 750-frame-averaged results using only 10-frame-averaged measurements, reducing the imaging dose of x-ray-acoustic computed tomography (XACT) by 98.7%; it realized proton range accuracy parallel to 1500-frame-averaged results using only 20-frame-averaged measurements, improving the range verification frequency in proton therapy from 0.5 to 37.5 Hz; it reached electroacoustic image quality comparable to 750-frame-averaged results using only a single frame signal, increasing the electric field monitoring frequency from 1 fps to 1k fps. Compared to lowpass filter-based denoising, the proposed method demonstrated considerably lower mean-squared-errors, higher peak-SNR, and higher structural similarities with respect to the corresponding high-frame-averaged measurements. The proposed deep learning-based denoising framework is a generalized method for few-frame-averaged acoustic signal denoising, which significantly improves the RA imaging's clinical utilities for low-dose imaging and real-time therapy monitoring.

Radiation-induced Acoustic Signal Denoising using a Supervised Deep Learning Framework for Imaging and Therapy Monitoring.

Radiation-induced acoustic (RA) imaging is a promising technique for visualizing radiation energy deposition in tissues, enabling new imaging modalities and real-time therapy monitoring. However, it requires measuring hundreds or even thousands of averages to achieve satisfactory signal-to-noise ratios (SNRs). This repetitive measurement increases ionizing radiation dose and degrades the temporal resolution of RA imaging, limiting its clinical utility. In this study, we developed a general deep inception convolutional neural network (GDI-CNN) to denoise RA signals to substantially reduce the number of averages. The multi-dilation convolutions in the network allow for encoding and decoding signal features with varying temporal characteristics, making the network generalizable to signals from different radiation sources. The proposed method was evaluated using experimental data of X-ray-induced acoustic, protoacoustic, and electroacoustic signals, qualitatively and quantitatively. Results demonstrated the effectiveness and generalizability of GDI-CNN: for all the enrolled RA modalities, GDI-CNN achieved comparable SNRs to the fully-averaged signals using less than 2% of the averages, significantly reducing imaging dose and improving temporal resolution. The proposed deep learning framework is a general method for few-frame-averaged acoustic signal denoising, which significantly improves RA imaging's clinical utilities for low-dose imaging and real-time therapy monitoring.

Input feature design and its impact on the performance of deep learning models for predicting fluence maps in intensity-modulated radiation therapy.

Objective. Deep learning (DL) models for fluence map prediction (FMP) have great potential to reduce treatment planning time in intensity-modulated radiation therapy (IMRT) by avoiding the lengthy inverse optimization process. This study aims to improve the rigor of input feature design in a DL-FMP model by examining how different designs of input features influence model prediction performance.Approach. This study included 231 head-and-neck intensity-modulated radiation therapy patients. Three input feature designs were investigated. The first design (D1) assumed that information of all critical structures from all beam angles should be combined to predict fluence maps. The second design (D2) assumed that local anatomical information was sufficient for predicting radiation intensity of a beamlet at a respective beam angle. The third design (D3) assumed the need for both local anatomical information and inter-beam modulation to predict radiation intensity values of the beamlets that intersect at a voxel. For each input design, we tailored the DL model accordingly. All models were trained using the same set of ground truth plans (GT plans). The plans generated by DL models (DL plans) were analyzed using key dose-volume metrics. One-way ANOVA with multiple comparisons correction (Bonferroni method) was performed (significance level = 0.05).Main results. For PTV-related metrics, all DL plans had significantly higher maximum dose (p < 0.001), conformity index (p < 0.001), and heterogeneity index (p < 0.001) compared to GT plans, with D2 being the worst performer. Meanwhile, except for cord+5 mm (p < 0.001), DL plans of all designs resulted in OAR dose metrics that are comparable to those of GT plans.Significance. Local anatomical information contains most of the information that DL models need to predict fluence maps for clinically acceptable OAR sparing. Input features from beam angles are needed to achieve the best PTV coverage. These results provide valuable insights for further improvement of DL-FMP models and DL models in general.

3Din vivodose verification in prostate proton therapy with deep learning-based proton-acoustic imaging.

Dose delivery uncertainty is a major concern in proton therapy, adversely affecting the treatment precision and outcome. Recently, a promising technique, proton-acoustic (PA) imaging, has been developed to provide real-timein vivo3D dose verification. However, its dosimetry accuracy is limited due to the limited-angle view of the ultrasound transducer. In this study, we developed a deep learning-based method to address the limited-view issue in the PA reconstruction. A deep cascaded convolutional neural network (DC-CNN) was proposed to reconstruct 3D high-quality radiation-induced pressures using PA signals detected by a matrix array, and then derive precise 3D dosimetry from pressures for dose verification in proton therapy. To validate its performance, we collected 81 prostate cancer patients' proton therapy treatment plans. Dose was calculated using the commercial software RayStation and was normalized to the maximum dose. The PA simulation was performed using the open-source k-wave package. A matrix ultrasound array with 64 × 64 sensors and 500 kHz central frequency was simulated near the perineum to acquire radiofrequency (RF) signals during dose delivery. For realistic acoustic simulations, tissue heterogeneity and attenuation were considered, and Gaussian white noise was added to the acquired RF signals. The proposed DC-CNN was trained on 204 samples from 69 patients and tested on 26 samples from 12 other patients. Predicted 3D pressures and dose maps were compared against the ground truth qualitatively and quantitatively using root-mean-squared-error (RMSE), gamma-index (GI), and dice coefficient of isodose lines. Results demonstrated that the proposed method considerably improved the limited-view PA image quality, reconstructing pressures with clear and accurate structures and deriving doses with a high agreement with the ground truth. Quantitatively, the pressure accuracy achieved an RMSE of 0.061, and the dose accuracy achieved an RMSE of 0.044, GI (3%/3 mm) of 93.71%, and 90%-isodose line dice of 0.922. The proposed method demonstrates the feasibility of achieving high-quality quantitative 3D dosimetry in PA imaging using a matrix array, which potentially enables the online 3D dose verification for prostate proton therapy.

Purposeful irradiation of the epidural space to enhance local control without compromising cord sparing in spine radiosurgery†.

Purpose: The epidural space is a frequent site of cancer recurrence after spine stereotactic radiosurgery (SSRS). This may be due to microscopic disease in the epidural space which is underdosed to obey strict spinal cord dose constraints. We hypothesized that the epidural space could be purposefully irradiated to prescription dose levels, potentially reducing the risk of recurrence in the epidural space without increasing toxicity. Methods and materials: SSRS clinical treatment plans with spinal cord contours, spinal planning target volumes (PTVspine), and delivered dose distributions were retrospectively identified. An epidural space PTV (PTVepidural) was contoured to avoid the spinal cord and focus on regions near the PTVspine. Clinical plan constraints included PTVspine constraints (D95% and D5%, based on prescription dose) and spinal cord constraints (Dmax < 1300 cGy, D10% < 1000 cGy). Plans were revised with three prescriptions of 1800, 2000 and 2400 cGy in two sets, with one set of revisions (supplemented plans) designed to additionally target the PTVepidural by optimizing PTVepidural D95% in addition to meeting every clinical plan constraint. Clinical and revised plans were compared according to their PTVepidural DVH distributions, and D95% distributions. Results: Seventeen SSRS plans meeting the above criteria were identified. Supplemented plans had higher doses to the epidural low-dose regions at all prescription levels. Epidural PTV D95% values for the supplemented plans were all statistically significantly different from the values of the base plans (p < 10-4). The epidural PTV D95% increases depended on the initial prescription, increasing from 11.52 to 16.90 Gy, 12.23 to 18.85 Gy, and 13.87 to 19.54 Gy for target prescriptions of 1800, 2000 and 2400 cGy, respectively. Conclusions: Purposefully targeting the epidural space in SSRS may increase control in the epidural space without significantly increasing the risk of spinal cord toxicity. A clinical trial of this approach should be considered.

Technical note: Determining the applicability of a clinical knowledge-based learning model via prospective outlier detection.

BACKGROUND: Knowledge-based planning (KBP) is increasingly implemented clinically because of its demonstrated ability to improve treatment planning efficiency and reduce plan quality variations. However, cases with large dose-volume histogram (DVH) prediction uncertainties may still need manual adjustments by the planner to achieve high plan quality. PURPOSE: The purpose of this study is to develop a data-driven method to detect patients with high prediction uncertainties so that intentional effort is directed to these patients. METHODS: We apply an anomaly detection method known as the local outlier factor (LOF) to a dataset consisting of the training set and each of the prospective patients considered, to evaluate their likelihood of being an anomaly when compared with the training cases. Features used in the LOF analysis include anatomical features and the model-generated DVH principal component scores. To test the efficacy of the proposed model, 142 prostate patients were retrieved from the clinical database and split into a training dataset of 100 patients and a test dataset of 42 patients. The outlier identification performance was quantified by the difference between the DVH prediction root-mean-squared errors (RMSE) of the identified outlier cases and that of the remaining inlier cases. RESULTS: With a predefined LOF threshold of 1.4, the inlier cases achieved average RMSEs of 5.0 and 6.7 for bladder and rectum, while the outlier cases have substantially higher RMSEs of 6.7 and 13.0 in comparison. CONCLUSIONS: We propose a method that can determine the prospective patient's outlier status. This method can be integrated into existing automated treatment planning workflows to reduce the risk of generating suboptimal treatment plans while providing an upfront alert to the treatment planner.

A data-driven approach to optimal beam/arc angle selection for liver stereotactic body radiation therapy treatment planning.

BACKGROUND: Stereotactic body radiation therapy (SBRT) for liver cancer has shown promising therapeutic effects. Effective treatment relies not only on the precise delivery provided by image-guided radiation therapy (IGRT) but also high dose gradient formed around the treatment volume to spare functional liver tissue, which is highly dependent on the beam/arc angle selection. In this study, we aim to develop a decision support model to learn human planner's beam navigation approach for beam angle/arc angle selection for liver SBRT. METHODS: A total of 27 liver SBRT/HIGRT patients (10 IMRT, 17 VMAT/DCA) were included in this study. A dosimetric budget index was defined for each beam angle/control point considering dose penetration through the patient body and liver tissue. Optimal beam angle setting (beam angles for IMRT and start/terminal angle for VMAT/DCA) was determined by minimizing the loss function defined as the sum of total dosimetric budget index and beam span penalty function. Leave-one-out validation was exercised on all 27 cases while weighting coefficients in the loss function was tuned in nested cross validation. To compare the efficacy of the model, a model plan was generated using automatically generated beam setting while retaining the original optimization constraints in the clinical plan. Model plan was normalized to the same planning target volume (PTV) V100% as the clinical plans. Dosimetric endpoints including PTV D98%, D2%, liver V20Gy and total MU were compared between two plan groups. Wilcoxon Signed-Rank test was performed with the null hypothesis being that no difference exists between two plan groups. RESULTS: Beam setting prediction was instantaneous. Mean PTV D98% was 91.3% and 91.3% (P=0.566), while mean PTV D2% was 107.9% and 108.1% (P=0.164) for clinical plan and model plan respectively. Liver V20Gy showed no significant difference (P=0.590) with 23.3% for clinical plan and 23.4% for the model plan. Total MU is comparable (P=0.256) between the clinical plan (avg. 2,389.6) and model plan (avg. 2,319.6). CONCLUSIONS: The evidence driven beam setting model yielded similar plan quality as hand-crafted clinical plan. It is capable of capturing human's knowledge in beam selection decision making. This model could facilitate decision making for beam angle selection while eliminating lengthy trial-and-error process of adjusting beam setting during liver SBRT treatment planning.

Assessing the robustness of artificial intelligence powered planning tools in radiotherapy clinical settings-a phantom simulation approach.

BACKGROUND: Artificial intelligence (AI) based radiotherapy treatment planning tools have gained interest in automating the treatment planning process. It is essential to understand their overall robustness in various clinical scenarios. This is an existing gap between many AI based tools and their actual clinical deployment. This study works to fill the gap for AI based treatment planning by investigating a clinical robustness assessment (CRA) tool for the AI based planning methods using a phantom simulation approach. METHODS: A cylindrical phantom was created in the treatment planning system (TPS) with the axial dimension of 30 cm by 18 cm. Key structures involved in pancreas stereotactic body radiation therapy (SBRT) including PTV25, PTV33, C-Loop, stomach, bowel and liver were created within the phantom. Several simulation scenarios were created to mimic multiple scenarios of anatomical changes, including displacement, expansion, rotation and combination of three. The goal of treatment planning was to deliver 25 Gy to PTV25 and 33 Gy to PTV33 in 5 fractions in simultaneous integral boost (SIB) manner while limiting luminal organ-at-risk (OAR) max dose to be under 29 Gy. A previously developed deep learning based AI treatment planning tool for pancreas SBRT was identified as the validation object. For each scenario, the anatomy information was fed into the AI tool and the final fluence map associated to the plan was generated, which was subsequently sent to TPS for leaf sequencing and dose calculation. The final auto plan's quality was analyzed against the treatment planning constraint. The final plans' quality was further analyzed to evaluate potential correlation with anatomical changes using the Manhattan plot. RESULTS: A total of 32 scenarios were simulated in this study. For all scenarios, the mean PTV25 V25Gy of the AI based auto plans was 96.7% while mean PTV33 V33Gy was 82.2%. Large variation (16.3%) in PTV33 V33Gy was observed due to anatomical variations, a.k.a. proximity of luminal structure to PTV33. Mean max dose was 28.55, 27.68 and 24.63 Gy for C-Loop, bowel and stomach, respectively. Using D0.03cc as max dose surrogate, the value was 28.03, 27.12 and 23.84 Gy for C-Loop, bowel and stomach, respectively. Max dose constraint of 29 Gy was achieved for 81.3% cases for C-Loop and stomach, and 78.1% for bowel. Using D0.03cc as max dose surrogate, the passing rate was 90.6% for C-Loop, and 81.3% for bowel and stomach. Manhattan plot revealed high correlation between the OAR over dose and the minimal distance between the PTV33 and OAR. CONCLUSIONS: The results showed promising robustness of the pancreas SBRT AI tool, providing important evidence of its readiness for clinical implementation. The established workflow could guide the process of assuring clinical readiness of future AI based treatment planning tools.

Artificial intelligence applications in intensity modulated radiation treatment planning: an overview.

Artificial intelligence (AI) refers to methods that improve and automate challenging human tasks by systematically capturing and applying relevant knowledge in these tasks. Over the past decades, a number of approaches have been developed to address different types and needs of system intelligence ranging from search strategies to knowledge representation and inference to robotic planning. In the context of radiation treatment planning, multiple AI approaches may be adopted to improve the planning quality and efficiency. For example, knowledge representation and inference methods may improve dose prescription by integrating and reasoning about the domain knowledge described in many clinical guidelines and clinical trials reports. In this review, we will focus on the most studied AI approach in intensity modulated radiation therapy (IMRT)/volumetric modulated arc therapy (VMAT)-machine learning (ML) and describe our recent efforts in applying ML to improve the quality, consistency, and efficiency of IMRT/VMAT planning. With the available high-quality data, we can build models to accurately predict critical variables for each step of the planning process and thus automate and improve its outcomes. Specific to the IMRT/VMAT planning process, we can build models for each of the four critical components in the process: dose-volume histogram (DVH), Dose, Fluence, and Human Planner. These models can be divided into two general groups. The first group focuses on encoding prior experience and knowledge through ML and more recently deep learning (DL) from prior clinical plans and using these models to predict the optimal DVH (DVH prediction model), or 3D dose distribution (dose prediction model), or fluence map (fluence map model). The goal of these models is to reduce or remove the trial-and-error process and guarantee consistently high-quality plans. The second group of models focuses on mimicking human planners' decision-making process (planning strategy model) during the iterative adjustments/guidance of the optimization engine. Each critical step of the IMRT/VMAT treatment planning process can be improved and automated by AI methods. As more training data becomes available and more sophisticated models are developed, we can expect that the AI methods in treatment planning will continue to improve accuracy, efficiency, and robustness.

Insights of an AI agent via analysis of prediction errors: a case study of fluence map prediction for radiation therapy planning.

Purpose.We have previously reported an artificial intelligence (AI) agent that automatically generates intensity-modulated radiation therapy (IMRT) plans via fluence map prediction, by-passing inverse planning. This AI agent achieved clinically comparable quality for prostate cases, but its performance on head-and-neck patients leaves room for improvement. This study aims to collect insights of the deep-learning-based (DL-based) fluence map prediction model by systematically analyzing its prediction errors.Methods.From the modeling perspective, the DL model's output is the fluence maps of IMRT plans. However, from the clinical planning perspective, the plan quality evaluation should be based on the clinical dosimetric criteria such as dose-volume histograms. To account for the complex and non-intuitive relationships between fluence map prediction errors and the corresponding dose distribution changes, we propose a novel error analysis approach that systematically examines plan dosimetric changes that are induced by varying amounts of fluence prediction errors. We investigated four decomposition modes of model prediction errors. The two spatial domain decompositions are based on fluence intensity and fluence gradient. The two frequency domain decompositions are based on Fourier-space banded frequency rings and Fourier-space truncated low-frequency disks. The decomposed error was analyzed for its impact on the resulting plans' dosimetric metrics. The analysis was conducted on 15 test cases spared from the 200 training and 16 validation cases used to train the model.Results.Most planning target volume metrics were significantly correlated with most error decompositions. The Fourier space disk radii had the largest Spearman's coefficients. The low-frequency region within a disk of ∼20% Fourier space contained most of errors that impact overall plan quality.Conclusions.This study demonstrates the feasibility of using fluence map prediction error analysis to understand the AI agent's performance. Such insights will help fine-tune the DL models in architecture design and loss function selection.

Introducing matrix sparsity with kernel truncation into dose calculations for fluence optimization.

Deep learning algorithms for radiation therapy treatment planning automation require large patient datasets and complex architectures that often take hundreds of hours to train. Some of these algorithms require constant dose updating (such as with reinforcement learning) and may take days. When these algorithms rely on commerical treatment planning systems to perform dose calculations, the data pipeline becomes the bottleneck of the entire algorithm's efficiency. Further, uniformly accurate distributions are not always needed for the training and approximations can be introduced to speed up the process without affecting the outcome. These approximations not only speed up the calculation process, but allow for custom algorithms to be written specifically for the purposes of use in AI/ML applications where the dose and fluence must be calculated a multitude of times for a multitude of different situations. Here we present and investigate the effect of introducing matrix sparsity through kernel truncation on the dose calculation for the purposes of fluence optimzation within these AI/ML algorithms. The basis for this algorithm relies on voxel discrimination in which numerous voxels are pruned from the computationally expensive part of the calculation. This results in a significant reduction in computation time and storage. Comparing our dose calculation against calculations in both a water phantom and patient anatomy in Eclipse without heterogenity corrections produced gamma index passing rates around 99% for individual and composite beams with uniform fluence and around 98% for beams with a modulated fluence. The resulting sparsity introduces a reduction in computational time and space proportional to the square of the sparsity tolerance with a potential decrease in cost greater than 10 times that of a dense calculation allowing not only for faster caluclations but for calculations that a dense algorithm could not perform on the same system.

Transfer learning for fluence map prediction in adrenal stereotactic body radiation therapy.

Objective:To design a deep transfer learning framework for modeling fluence map predictions for stereotactic body radiation therapy (SBRT) of adrenal cancer and similar sites that usually have a small number of cases.Approach:We developed a transfer learning framework for adrenal SBRT planning that leverages knowledge in a pancreas SBRT planning model. Treatment plans from the two sites had different dose prescriptions and beam settings but both prioritized gastrointestinal sparing. A base framework was first trained with 100 pancreas cases. This framework consists of two convolutional neural networks (CNN), which predict individual beam doses (BD-CNN) and fluence maps (FM-CNN) sequentially for 9-beam intensity-modulated radiation therapy (IMRT) plans. Forty-five adrenal plans were split into training/validation/test sets with the ratio of 20/10/15. The base BD-CNN was re-trained with transfer learning using 5/10/15/20 adrenal training cases to produce multiple candidate adrenal BD-CNN models. The base FM-CNN was directly used for adrenal cases. The deep learning (DL) plans were evaluated by several clinically relevant dosimetric endpoints, producing a percentage score relative to the clinical plans.Main results:Transfer learning significantly reduced the number of training cases and training time needed to train such a DL framework. The adrenal transfer learning model trained with 5/10/15/20 cases achieved validation plan scores of 85.4/91.2/90.7/89.4, suggesting that model performance saturated with 10 training cases. Meanwhile, a model using all 20 adrenal training cases without transfer learning only scored 80.5. For the final test set, the 5/10/15/20-case models achieved scores of 73.5/75.3/78.9/83.3.Significance:It is feasible to use deep transfer learning to train an IMRT fluence prediction framework. This technique could adapt to different dose prescriptions and beam configurations. This framework potentially enables DL modeling for clinical sites that have a limited dataset, either due to few cases or due to rapid technology evolution.

A Novel Machine Learning Model for Dose Prediction in Prostate Volumetric Modulated Arc Therapy Using Output Initialization and Optimization Priorities.

Treatment planning for prostate volumetric modulated arc therapy (VMAT) can take 5-30 min per plan to optimize and calculate, limiting the number of plan options that can be explored before the final plan decision. Inspired by the speed and accuracy of modern machine learning models, such as residual networks, we hypothesized that it was possible to use a machine learning model to bypass the time-intensive dose optimization and dose calculation steps, arriving directly at an estimate of the resulting dose distribution for use in multi-criteria optimization (MCO). In this study, we present a novel machine learning model for predicting the dose distribution for a given patient with a given set of optimization priorities. Our model innovates upon the existing machine learning techniques by utilizing optimization priorities and our understanding of dose map shapes to initialize the dose distribution before dose refinement via a voxel-wise residual network. Each block of the residual network individually updates the initialized dose map before passing to the next block. Our model also utilizes contiguous and atrous patch sampling to effectively increase the receptive fields of each layer in the residual network, decreasing its number of layers, increasing model prediction and training speed, and discouraging overfitting without compromising on the accuracy. For analysis, 100 prostate VMAT cases were used to train and test the model. The model was evaluated by the training and testing errors produced by 50 iterations of 10-fold cross-validation, with 100 cases randomly shuffled into the subsets at each iteration. The error of the model is modest for this data, with average dose map root-mean-square errors (RMSEs) of 2.38 ± 0.47% of prescription dose overall patients and all optimization priority combinations in the patient testing sets. The model was also evaluated at iteratively smaller training set sizes, suggesting that the model requires between 60 and 90 patients for optimal performance. This model may be used for quickly estimating the Pareto set of feasible dose objectives, which may directly accelerate the treatment planning process and indirectly improve final plan quality by allowing more time for plan refinement.

Deep Learning-Based Fluence Map Prediction for Pancreas Stereotactic Body Radiation Therapy With Simultaneous Integrated Boost.

PURPOSE: Treatment planning for pancreas stereotactic body radiation therapy (SBRT) is a challenging task, especially with simultaneous integrated boost treatment approaches. We propose a deep learning (DL) framework to accurately predict fluence maps from patient anatomy and directly generate intensity modulated radiation therapy plans. METHODS AND MATERIALS: The framework employs 2 convolutional neural networks (CNNs) to sequentially generate beam dose prediction and fluence map prediction, creating a deliverable 9-beam intensity modulated radiation therapy plan. Within the beam dose prediction CNN, axial slices of combined structure contour masks are used to predict 3-dimensional (3D) beam doses for each beam. Each 3D beam dose is projected along its beam's-eye-view to form a 2D beam dose map, which is subsequently used by the fluence map prediction CNN to predict its fluence map. Finally, the 9 predicted fluence maps are imported into the treatment planning system to finalize the plan by leaf sequencing and dose calculation. One hundred patients receiving pancreas SBRT were retrospectively collected for this study. Benchmark plans with unified simultaneous integrated boost prescription (25/33 Gy) were manually optimized for each case. The data set was split into 80/20 cases for training and testing. We evaluated the proposed DL framework by assessing both the fluence maps and the final predicted plans. Further, clinical acceptability of the plans was evaluated by a physician specializing in gastrointestinal cancer. RESULTS: The DL-based planning was, on average, completed in under 2 minutes. In testing, the predicted plans achieved similar dose distribution compared with the benchmark plans (-1.5% deviation for planning target volume 33 V33Gy), with slightly higher planning target volume maximum (+1.03 Gy) and organ at risk maximum (+0.95 Gy) doses. After renormalization, the physician rated 19 cases clinically acceptable and 1 case requiring minor improvement. CONCLUSIONS: The DL framework can effectively plan pancreas SBRT cases within 2 minutes. The predicted plans are clinically deliverable, with plan quality approaching that of manual planning.

Clinical Experience With Machine Learning-Based Automated Treatment Planning for Whole Breast Radiation Therapy.

PURPOSE: The machine learning-based automated treatment planning (MLAP) tool has been developed and evaluated for breast radiation therapy planning at our institution. We implemented MLAP for patient treatment and assessed our clinical experience for its performance. METHODS AND MATERIALS: A total of 102 patients of breast or chest wall treatment plans were prospectively evaluated with institutional review board approval. A human planner executed MLAP to create an auto-plan via automation of fluence maps generation. If judged necessary, a planner further fine-tuned the fluence maps to reach a final plan. Planners recorded the time required for auto-planning and manual modification. Target (ie, breast or chest wall and nodes) coverage and dose homogeneity were compared between the auto-plan and final plan. RESULTS: Cases without nodes (n = 71) showed negligible (<1%) differences for target coverage and dose homogeneity between the auto-plan and final plan. Cases with nodes (n = 31) also showed negligible difference for target coverage. However, mean ± standard deviation of volume receiving 105% of the prescribed dose and maximum dose were reduced from 43.0% ± 26.3% to 39.4% ± 23.7% and 119.7% ± 9.5% to 114.4% ± 8.8% from auto-plan to final plan, respectively, all with P ≤ .01 for cases with nodes (n = 31). Mean ± standard deviation time spent for auto-plans and additional fluence modification for final plans were 12.1 ± 9.3 and 13.1 ± 12.9 minutes, respectively, for cases without nodes, and 16.4 ± 9.7 and 26.4 ± 16.4 minutes, respectively, for cases with nodes. CONCLUSIONS: The MLAP tool has been successfully implemented for routine clinical practice and has significantly improved planning efficiency. Clinical experience indicates that auto-plans are sufficient for target coverage, but improvement is warranted to reduce high dose volume for cases with nodal irradiation. This study demonstrates the clinical implementation of auto-planning for patient treatment and the significant importance of integrating human experience and feedback to improve MLAP for better clinical translation.

An artificial intelligence-driven agent for real-time head-and-neck IMRT plan generation using conditional generative adversarial network (cGAN).

PURPOSE: To develop an artificial intelligence (AI) agent for fully automated rapid head-and-neck intensity-modulated radiation therapy (IMRT) plan generation without time-consuming dose-volume-based inverse planning. METHODS: This AI agent was trained via implementing a conditional generative adversarial network (cGAN) architecture. The generator, PyraNet, is a novel deep learning network that implements 28 classic ResNet blocks in pyramid-like concatenations. The discriminator is a customized four-layer DenseNet. The AI agent first generates multiple customized two-dimensional projections at nine template beam angles from a patient's three-dimensional computed tomography (CT) volume and structures. These projections are then stacked as four-dimensional inputs of PyraNet, from which nine radiation fluence maps of the corresponding template beam angles are generated simultaneously. Finally, the predicted fluence maps are automatically postprocessed by Gaussian deconvolution operations and imported into a commercial treatment planning system (TPS) for plan integrity check and visualization. The AI agent was built and tested upon 231 oropharyngeal IMRT plans from a TPS plan library. 200/16/15 plans were assigned for training/validation/testing, respectively. Only the primary plans in the sequential boost regime were studied. All plans were normalized to 44 Gy prescription (2 Gy/fx). A customized Harr wavelet loss was adopted for fluence map comparison during the training of the PyraNet. For test cases, isodose distributions in AI plans and TPS plans were qualitatively evaluated for overall dose distributions. Key dosimetric metrics were compared by Wilcoxon signed-rank tests with a significance level of 0.05. RESULTS: All 15 AI plans were successfully generated. Isodose gradients outside of PTV in AI plans were comparable to those of the TPS plans. After PTV coverage normalization, Dmean of left parotid (DAI  = 23.1 ± 2.4 Gy; DTPS  = 23.1 ± 2.0 Gy), right parotid (DAI  = 23.8 ± 3.0 Gy; DTPS  = 23.9 ± 2.3 Gy), and oral cavity (DAI  = 24.7 ± 6.0 Gy; DTPS  = 23.9 ± 4.3 Gy) in the AI plans and the TPS plans were comparable without statistical significance. AI plans achieved comparable results for maximum dose at 0.01cc of brainstem (DAI  = 15.0 ± 2.1 Gy; DTPS  = 15.5 ± 2.7 Gy) and cord + 5mm (DAI  = 27.5 ± 2.3 Gy; DTPS  = 25.8 ± 1.9 Gy) without clinically relevant differences, but body Dmax results (DAI  = 121.1 ± 3.9 Gy; DTPS  = 109.0 ± 0.9 Gy) were higher than the TPS plan results. The AI agent needed ~3 s for predicting fluence maps of an IMRT plan. CONCLUSIONS: With rapid and fully automated execution, the developed AI agent can generate complex head-and-neck IMRT plans with acceptable dosimetry quality. This approach holds great potential for clinical applications in preplanning decision-making and real-time planning.

Radiation Therapy for Rectal Cancer: Executive Summary of an ASTRO Clinical Practice Guideline.

PURPOSE: This guideline reviews the evidence and provides recommendations for the indications and appropriate technique and dose of neoadjuvant radiation therapy (RT) in the treatment of localized rectal cancer. METHODS: The American Society for Radiation Oncology convened a task force to address 4 key questions focused on the use of RT in preoperative management of operable rectal cancer. These questions included the indications for neoadjuvant RT, identification of appropriate neoadjuvant regimens, indications for consideration of a nonoperative or local excision approach after chemoradiation, and appropriate treatment volumes and techniques. Recommendations were based on a systematic literature review and created using a predefined consensus-building methodology and system for grading evidence quality and recommendation strength. RESULTS: Neoadjuvant RT is recommended for patients with stage II-III rectal cancer, with either conventional fractionation with concurrent 5-FU or capecitabine or short-course RT. RT should be performed preoperatively rather than postoperatively. Omission of preoperative RT is conditionally recommended in selected patients with lower risk of locoregional recurrence. Addition of chemotherapy before or after chemoradiation or after short-course RT is conditionally recommended. Nonoperative management is conditionally recommended if a clinical complete response is achieved after neoadjuvant treatment in selected patients. Inclusion of the rectum and mesorectal, presacral, internal iliac, and obturator nodes in the clinical treatment volume is recommended. In addition, inclusion of external iliac nodes is conditionally recommended in patients with tumors invading an anterior organ or structure, and inclusion of inguinal and external iliac nodes is conditionally recommended in patients with tumors involving the anal canal. CONCLUSIONS: Based on currently published data, the American Society for Radiation Oncology task force has proposed evidence-based recommendations regarding the use of RT for rectal cancer. Future studies will look to further personalize treatment recommendations to optimize treatment outcomes and quality of life.

An Interpretable Planning Bot for Pancreas Stereotactic Body Radiation Therapy.

PURPOSE: Pancreas stereotactic body radiation therapy (SBRT) treatment planning requires planners to make sequential, time-consuming interactions with the treatment planning system to reach the optimal dose distribution. We sought to develop a reinforcement learning (RL)-based planning bot to systematically address complex tradeoffs and achieve high plan quality consistently and efficiently. METHODS AND MATERIALS: The focus of pancreas SBRT planning is finding a balance between organ-at-risk sparing and planning target volume (PTV) coverage. Planners evaluate dose distributions and make planning adjustments to optimize PTV coverage while adhering to organ-at-risk dose constraints. We formulated such interactions between the planner and treatment planning system into a finite-horizon RL model. First, planning status features were evaluated based on human planners' experience and defined as planning states. Second, planning actions were defined to represent steps that planners would commonly implement to address different planning needs. Finally, we derived a reward system based on an objective function guided by physician-assigned constraints. The planning bot trained itself with 48 plans augmented from 16 previously treated patients, and generated plans for 24 cases in a separate validation set. RESULTS: All 24 bot-generated plans achieved similar PTV coverages compared with clinical plans while satisfying all clinical planning constraints. Moreover, the knowledge learned by the bot could be visualized and interpreted as consistent with human planning knowledge, and the knowledge maps learned in separate training sessions were consistent, indicating reproducibility of the learning process. CONCLUSIONS: We developed a planning bot that generates high-quality treatment plans for pancreas SBRT. We demonstrated that the training phase of the bot is tractable and reproducible, and the knowledge acquired is interpretable. As a result, the RL planning bot can potentially be incorporated into the clinical workflow and reduce planning inefficiencies.