Total scalp irradiation: A study comparing multiple types of bolus and VMAT optimization techniques.

PURPOSE: To investigate bolus design and VMAT optimization settings for total scalp irradiation. METHODS: Three silicone bolus designs (flat, hat, and custom) from .decimal were evaluated for adherence to five anthropomorphic head phantoms. Flat bolus was cut from a silicone sheet. Generic hat bolus resembles an elongated swim cap while custom bolus is manufactured by injecting silicone into a 3D printed mold. Bolus placement time was recorded. Air gaps between bolus and scalp were quantified on CT images. The dosimetric effect of air gaps on target coverage was evaluated in a treatment planning study where the scalp was planned to 60 Gy in 30 fractions. A noncoplanar VMAT technique based on gEUD penalties was investigated that explored the full range of gEUD alpha values to determine which settings achieve sufficient target coverage while minimizing brain dose. ANOVA and the t-test were used to evaluate statistically significant differences (threshold = 0.05). RESULTS: The flat bolus took 32 ± 5.9 min to construct and place, which was significantly longer (p < 0.001) compared with 0.67 ± 0.2 min for the generic hat bolus or 0.53 ± 0.10 min for the custom bolus. The air gap volumes were 38 ± 9.3 cc, 32 ± 14 cc, and 17 ± 7.0 cc for the flat, hat, and custom boluses, respectively. While the air gap differences between the flat and custom boluses were significant (p = 0.011), there were no significant dosimetric differences in PTV coverage at V57Gy or V60Gy. In the VMAT optimization study, a gEUD alpha of 2 was found to minimize the mean brain dose. CONCLUSIONS: Two challenging aspects of total scalp irradiation were investigated: bolus design and plan optimization. Results from this study show opportunities to shorten bolus fabrication time during simulation and create high quality treatment plans using a straightforward VMAT template with simple optimization settings.

Plan Quality Analysis of Automated Treatment Planning Workflow With Commercial Auto-Segmentation Tools and Clinical Knowledge-Based Planning Models for Prostate Cancer.

This study evaluated the feasibility of using artificial intelligence (AI) segmentation software for volume-modulated arc therapy (VMAT) prostate planning in conjunction with knowledge-based planning to facilitate a fully automated workflow. Two commercially available AI software programs, Radformation AutoContour (Radformation, New York, NY) and Siemens AI-Rad Companion (Siemens Healthineers, Malvern, PA) were used to auto-segment the rectum, bladder, femoral heads, and bowel bag on 30 retrospective clinical cases (10 intact prostate, 10 prostate bed, and 10 prostate and lymph node). Physician-segmented target volumes were transferred to AI structure sets. In-house RapidPlan models were used to generate plans using the original, physician-segmented structure sets as well as Radformation and Siemens AI-generated structure sets. Thus, there were three plans for each of the 30 cases, totaling 90 plans. Following RapidPlan optimization, planning target volume (PTV) coverage was set to 95%. Then, the plans optimized using AI structures were recalculated on the physician structure set with fixed monitor units. In this way, physician contours were used as the gold standard for identifying any clinically relevant differences in dose distributions. One-way analysis of variation (ANOVA) was used for statistical analysis. No statistically significant differences were observed across the three sets of plans for intact prostate, prostate bed, or prostate and lymph nodes. The results indicate that an automated volumetric modulated arc therapy (VMAT) prostate planning workflow can consistently achieve high plan quality. However, our results also show that small but consistent differences in contouring preferences may lead to subtle differences in planning results. Therefore, the clinical implementation of auto-contouring should be carefully validated.

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

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

Lung SBRT treatment planning: a study of VMAT arc selection guided by collision check software.

To evaluate the effects of arc geometry on lung stereotactic body radiation therapy (SBRT) plan quality, using collision check software to select safe beam angles. Thirty lung SBRT cases were replanned 10Gy x 5 using 4 volumetric modulated arc therapy (VMAT) geometries: coplanar lateral (cpLAT), coplanar oblique (cpOBL), noncoplanar lateral (ncpLAT) and noncoplanar oblique (ncpOBL). Lateral arcs spanned 180° on the affected side whereas the 180° oblique arcs crossed midline to spare healthy tissues. Couch angles were separated by 30° on noncoplanar plans. Clearance was verified with Radformation CollisionCheck software. Optimization objectives were the same across the four plans for each case. Planning target volume (PTV) coverage was set to 95% and then plans were evaluated for dose conformity, healthy tissue doses, and monitor units. Clinically treated plans were used to benchmark the results. The volumes of the 25%, 50% and 75% isodoses were smaller with noncoplanar than coplanar arcs. The volume of the 50% isodose line relative to the PTV (CI50%) was as follows: clinical 3.75±0.72, cpLAT 3.39 ± 0.37, cpOBL 3.36 ± 0.34, ncpLAT 3.02 ± 0.21 and ncpOBL 3.02 ± 0.22. The Wilcoxon signed rank test with Bonferroni correction showed p < 0.005 in all CI50% comparisons except between the cpLat and cpObl arcs and between the ncpLat and ncpObl arcs. The best lung sparing was achieved using ncpObl arcs, which was statistically significant (p < 0.001) compared with the other four plans at V12.5Gy, V13.5Gy and V20Gy. Chest wall V30Gy was significantly better using noncoplanar arcs in comparison to the other plan types (p < 0.001). The best heart sparing at V10Gy from the ncpOBL arcs was significant compared with the clinical and cpLat plans (p < 0.005). Arc geometry has a substantial effect on lung SBRT plan quality. Noncoplanar arcs were superior to coplanar arcs at compacting the dose distribution at the 25%, 50% and 75% isodose levels, thereby reducing the dose to healthy tissues. Further healthy tissue sparing was achieved using oblique arcs that minimize the pathlength through healthy tissues and avoid organs at risk. The dosimetric advantages of the noncoplanar and oblique arcs require careful beam angle selection during treatment planning to avoid collisions during treatment, which may be facilitated by commercial software.

Effects of pile fermentation on the physicochemical, functional, and biological properties of tea polysaccharides.

This study investigated the influence of pile fermentation on the physicochemical, functional, and biological properties of tea polysaccharides (TPS). Results indicated that the extraction yield, uronic acid content, and polyphenol content of TPS greatly increased from 1.8, 13.1 and 6.3 % to 4.1, 27.9, and 7.8 %, respectively, but the molecular weight markedly decreased from 153.7 to 76.0 kDa after pile fermentation. Additionally, the interfacial, emulsion formation, and emulsion stabilization properties of TPS were significantly improved after pile fermentation. For instance, 1.0 wt% TPS isolated from dark tea (D-TPS) can fabricate 8.0 wt% MCT oil-in-water nanoemulsion (d32 ≈ 159 nm) with potent storage stability. Moreover, the antioxidant and α-glucosidase inhibitory activities of D-TPS was higher than that of TPS isolated from sun-dried raw tea (R-TPS). Overall, this study indicated that pile fermentation markedly affected the physicochemical and structural characteristics of TPS, thereby improving their functional and biological properties.

Evaluating the plan quality of a general head-and-neck knowledge-based planning model versus separate unilateral/bilateral models.

The implementation of knowledge-based planning (KBP) continues to grow in radiotherapy clinics. KBP guides radiation treatment design by generating clinically acceptable plans in a timely and resource-efficient manner. The role of multiple KBP models tailored for variations within a disease site remains undefined in part because of the substantial effort and number of training cases required to create a high-quality KBP model. In this study, our aim was to explore whether site-specific KBP models lead to clinically meaningful differences in plan quality for head-and-neck (HN) patients when compared to a general model. One KBP model was created from prior volumetric-modulated arc therapy (VMAT) cases that treated unilateral HN lymph nodes while another model was created from VMAT cases that treated bilateral HN nodes. Thirty cases from each model (60 cases total) were randomly selected to create a third, general model. These models were applied to 60 HN test cases - 30 unilateral and 30 bilateral - to generate 180 VMAT plans in Eclipse. Clinically relevant dose metrics were compared between models. Paired-sample t-tests were used for statistical analysis, with the threshold for statistical significance set a priori at 0.007, taking into consideration multiple hypothesis testing to avoid type I error. For unilateral test cases, the unilateral model-generated plans had significantly lower spinal cord maximum doses (12.1 Gy vs 19.3 Gy, p < 0.001) and oral cavity mean doses (20.8 Gy vs 23.0 Gy, p < 0.001), compared with the bilateral model-generated plans. The unilateral and general models generated comparable plans for unilateral HN test cases. For bilateral test cases, the bilateral model created plans had significantly lower brainstem maximum doses (10.8 Gy vs 12.2 Gy, p < 0.001) and parotid mean doses (24.0 Gy vs 25.5 Gy, p < 0.001) when compared to the unilateral model. Right parotid mean doses were lower for bilateral model plans compared to general model plans (23.8 Gy vs 24.4 Gy). The general model created plans with significantly lower brainstem maximum doses (10.3 Gy vs 10.8 Gy) and oral cavity mean doses (35.3 Gy vs 36.7 Gy) when compared with bilateral model-generated plans. The general model outperformed the bilateral model in several dose metrics but they were not deemed clinically significant. For both case sets, the unilateral and general model created plans had higher monitor units when compared to the bilateral model, likely due to more stringent constraint settings. All other dose metrics were comparable. This study demonstrates that a balanced general HN model created using carefully curated treatment plans can produce high quality plans comparable to dedicated unilateral and bilateral models.

Enhanced cardiac substructure sparing through knowledge-based treatment planning for non-small cell lung cancer radiotherapy.

Radiotherapy (RT) doses to cardiac substructures from the definitive treatment of locally advanced non-small cell lung cancers (NSCLC) have been linked to post-RT cardiac toxicities. With modern treatment delivery techniques, it is possible to focus radiation doses to the planning target volume while reducing cardiac substructure doses. However, it is often challenging to design such treatment plans due to complex tradeoffs involving numerous cardiac substructures. Here, we built a cardiac-substructure-based knowledge-based planning (CS-KBP) model and retrospectively evaluated its performance against a cardiac-based KBP (C-KBP) model and manually optimized patient treatment plans. CS-KBP/C-KBP models were built with 27 previously-treated plans that preferentially spare the heart. While the C-KBP training plans were created with whole heart structures, the CS-KBP model training plans each have 15 cardiac substructures (coronary arteries, valves, great vessels, and chambers of the heart). CS-KBP training plans reflect cardiac-substructure sparing preferences. We evaluated both models on 28 additional patients. Three sets of treatment plans were compared: (1) manually optimized, (2) C-KBP model-generated, and (3) CS-KBP model-generated. Plans were normalized to receive the prescribed dose to at least 95% of the PTV. A two-tailed paired-sample t-test was performed for clinically relevant dose-volume metrics to evaluate the performance of the CS-KBP model against the C-KBP model and clinical plans, respectively. Overall results show significantly improved cardiac substructure sparing by CS-KBP in comparison to C-KBP and the clinical plans. For instance, the average left anterior descending artery volume receiving 15 Gy (V15 Gy) was significantly lower (p < 0.01) for CS-KBP (0.69 ± 1.57 cc) compared to the clinical plans (1.23 ± 1.76 cc) and C-KBP plans (1.05 ± 1.68 cc). In conclusion, the CS-KBP model significantly improved cardiac-substructure sparing without exceeding the tolerances of other OARs or compromising PTV coverage.

Oscillatory Motion of Water Droplets Both in Oil and on Superhydrophobic Surface under Corona Discharge.

Charged droplets driven by Coulomb force are an important part of a droplet-based micro reactor. In this study, we realized the rapid oscillatory motion of droplets both in oil and on superhydrophobic surface by injecting charges through corona discharge. Distinct from the oscillatory motion of water droplets under a DC electric field, charge injection can make the motion of water droplets more flexible. A droplet in the oil layer can move up and down regularly under the action of corona discharge, and the discharge voltage can control the movement period and height of the droplet. In addition, the left-right translation of droplets on a superhydrophobic surface can be achieved by injecting charges into the hydrophobic film surface through corona discharge. Two kinds of droplet motion behaviors are systematically analyzed, and the mechanism of droplet motion is explained. The present results could help establish new approaches to designing efficient machines in microfluidics and micromechanical equipment.

Mutual enhancing learning-based automatic segmentation of CT cardiac substructure.

Objective.Current segmentation practice for thoracic cancer RT considers the whole heart as a single organ despite increased risks of cardiac toxicities from irradiation of specific cardiac substructures. Segmenting up to 15 different cardiac substructures can be a very time-intensive process, especially due to their different volume sizes and anatomical variations amongst different patients. In this work, a new deep learning (DL)-based mutual enhancing strategy is introduced for accurate and automatic segmentation, especially of smaller substructures such as coronary arteries.Approach.Our proposed method consists of three subnetworks: retina U-net, classification module, and segmentation module. Retina U-net is used as a backbone network architecture that aims to learn deep features from the whole heart. Whole heart feature maps from retina U-net are then transferred to four different sets of classification modules to generate classification localization maps of coronary arteries, great vessels, chambers of the heart, and valves of the heart. Each classification module is in sync with its corresponding subsequent segmentation module in a bootstrapping manner, allowing them to share their encoding paths to generate a mutual enhancing strategy. We evaluated our method on three different datasets: institutional CT datasets (55 subjects) 2) publicly available Multi-Modality Whole Heart Segmentation (MM-WHS) challenge datasets (120 subjects), and Automated Cardiac Diagnosis Challenge (ACDC) datasets (100 subjects). For institutional datasets, we performed five-fold cross-validation on training data (45 subjects) and performed inference on separate hold-out data (10 subjects). For each subject, 15 cardiac substructures were manually contoured by a resident physician and evaluated by an attending radiation oncologist. For the MM-WHS dataset, we trained the network on 100 datasets and performed an inference on a separate hold-out dataset with 20 subjects, each with 7 cardiac substructures. For ACDC datasets, we performed five-fold cross-validation on 100 datasets, each with 3 cardiac substructures. We compared the proposed method against four different network architectures: 3D U-net, mask R-CNN, mask scoring R-CNN, and proposed network without classification module. Segmentation accuracies were statistically compared through dice similarity coefficient, Jaccard, 95% Hausdorff distance, mean surface distance, root mean square distance, center of mass distance, and volume difference.Main results.The proposed method generated cardiac substructure segmentations with significantly higher accuracy (P < 0.05) for small substructures, especially for coronary arteries such as left anterior descending artery (CA-LADA) and right coronary artery (CA-RCA) in comparison to four competing methods. For large substructures (i.e. chambers of the heart), our method yielded comparable results to mask scoring R-CNN method, resulting in significantly (P < 0.05) improved segmentation accuracy in comparison to 3D U-net and mask R-CNN.Significance.A new DL-based mutual enhancing strategy was introduced for automatic segmentation of cardiac substructures. Overall results of this work demonstrate the ability of the proposed method to improve segmentation accuracies of smaller substructures such as coronary arteries without largely compromising the segmentation accuracies of larger substructures. Fast and accurate segmentations of up to 15 substructures can possibly be used as a tool to rapidly generate substructure segmentations followed by physicians' reviews to improve clinical workflow.

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.

Automatic inverse treatment planning of Gamma Knife radiosurgery via deep reinforcement learning.

PURPOSE: Several inverse planning algorithms have been developed for Gamma Knife (GK) radiosurgery to determine a large number of plan parameters by solving an optimization problem, which typically consists of multiple objectives. The priorities among these objectives need to be repetitively adjusted to achieve a clinically good plan for each patient. This study aimed to achieve automatic and intelligent priority tuning by developing a deep reinforcement learning (DRL)-based method to model the tuning behaviors of human planners. METHODS: We built a priority-tuning policy network using deep convolutional neural networks. Its input was a vector composed of multiple plan metrics that were used in our institution for GK plan evaluation. The network can determine which tuning action to take based on the observed quality of the intermediate plan. We trained the network using an end-to-end DRL framework to approximate the optimal action-value function. A scoring function was designed to measure the plan quality to calculate the received reward of a tuning action. RESULTS: Vestibular schwannoma was chosen as the test bed in this study. The number of training, validation and testing cases were 5, 5, and 16, respectively. For these three datasets, the average scores of the initial plans obtained with the same initial priority set were 3.63 ± 1.34, 3.83 ± 0.86 and 4.20 ± 0.78, respectively, while they were improved to 5.28 ± 0.23, 4.97 ± 0.44 and 5.22 ± 0.26 through manual priority tuning by human expert planners. Our network achieved competitive results with 5.42 ± 0.11, 5.10 ± 0. 42, 5.28 ± 0.20, respectively. CONCLUSIONS: Our network can generate GK plans of comparable or slightly higher quality than the plans generated by human planners via manual priority tuning for vestibular schwannoma cases. The network can potentially be incorporated into the clinical workflow as planning assistance to improve GK planning efficiency and help to reduce plan quality variation caused by interplanner variability. We also hope that our method can reduce the workload of GK planners and allow them to spend more time on more challenging cases.

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.

Implementation of a Knowledge-Based Treatment Planning Model for Cardiac-Sparing Lung Radiation Therapy.

PURPOSE: High radiation doses to the heart have been correlated with poor overall survival in patients receiving radiation therapy for stage III non-small cell lung cancer (NSCLC). We built a knowledge-based planning (KBP) tool to limit the dose to the heart during creation of volumetric modulated arc therapy (VMAT) treatment plans for patients being treated to 60 Gy in 30 fractions for stage III NSCLC. METHODS AND MATERIALS: A previous study at our institution retrospectively delineated intracardiac volumes and optimized VMAT treatment plans to reduce dose to these substructures and to the whole heart. Two RapidPlan (RP) KBP models were built from this cohort, 1 model using the clinical plans and a separate model using the cardiac-optimized plans. Using target volumes and 6 organs at risk (OARs), models were trained to generate treatment plans in a semiautomated process. The cardiac-sparing KBP model was tested in the same cohort used for training, and both models were tested on an external validation cohort of 30 patients. RESULTS: Both RP models produced clinically acceptable plans in terms of target coverage, dose uniformity, and dose to OARs. Compared with the previously created cardiac-optimized plans, cardiac-sparing RPs showed significant reductions in the mean dose to the esophagus and lungs while performing similarly or better in all evaluated heart dose metrics. When comparing the 2 models, the cardiac-sparing RP showed reduced (P < .05) heart mean and maximum doses as well as volumes receiving 60 Gy, 50 Gy, and 30 Gy. CONCLUSIONS: By using a set of cardiac-optimized treatment plans for training, the proposed KBP model provided a means to reduce the dose to the heart and its substructures without the need to explicitly delineate cardiac substructures. This tool may offer reduced planning time and improved plan quality and might be used to improve patient outcomes.

Learning-based dose prediction for pancreatic stereotactic body radiation therapy using dual pyramid adversarial network.

Treatment planning for pancreatic cancer stereotactic body radiation therapy (SBRT) is very challenging owing to vast spatial variations and close proximity of many organs-at-risk. Recently, deep learning (DL) based methods have been applied in dose prediction tasks of various treatment sites with the aim of relieving planning challenges. However, its effectiveness on pancreatic cancer SBRT is yet to be fully explored due to limited investigations in the literature. This study aims to further current knowledge in DL-based dose prediction tasks by implementing and demonstrating the feasibility of a new dual pyramid networks (DPNs) integrated DL model for predicting dose distributions of pancreatic SBRT. The proposed framework is composed of four parts: CT-only feature pyramid network (FPN), contour-only FPN, late fusion network and an adversarial network. During each phase of the network, combination of mean absolute error, gradient difference error, histogram matching, and adversarial loss is used for supervision. The performance of proposed model was demonstrated for pancreatic cancer SBRT plans with doses prescribed between 33 and 50 Gy across as many as three planning target volumes (PTVs) in five fractions. Five-fold cross validation was performed on 30 patients, and another 20 patients were used as holdout tests of trained model. Predicted plans were compared with clinically approved plans through dose volume parameters and two-paired t-test. For the same sets, our results were compared with three different DL architectures: 3D U-Net, 3D U-Net with adversarial learning, and DPN without adversarial learning. The proposed framework was able to predict 87% and 91% of clinically relevant dose parameters for cross validation sets and holdout sets, respectively, without any significant differences (P > 0.05). Dose distribution predicted by our framework was also able to predict the intentional hotspots as feature characteristics of SBRT plans. Our method achieved higher correlation coefficients with the ground truth in 22/26, 24/26 and 20/26 dose volume parameters compared to the network without adversarial learning, 3D U-Net, and 3D U-Net with adversarial learning, respectively. Overall, the proposed model was able to predict doses to cases with both single and multiple PTVs. In conclusion, the DPN integrated DL model was successfully implemented, and demonstrated good dose prediction accuracy and dosimetric characteristics for pancreatic cancer SBRT.

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.

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.

Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application.

PURPOSE: To develop a deep learning-based AI agent, DDD-PIOP (Dose-Distribution-Driven PET Image Outcome Prediction), for predicting 18FDG-PET image outcomes of oropharyngeal cancer (OPC) in response to intensity-modulated radiation therapy (IMRT). METHODS: DDD-PIOP uses pre-radiotherapy 18FDG-PET/CT images and the planned spatial dose distribution as the inputs, and it predicts the 18FDG-PET image outcomes in response to the planned IMRT delivery. This AI agent centralizes a customized convolutional neural network (CNN) as a deep learning approach, and it incorporates a few designs to enhance prediction accuracy. 66 OPC patients who received IMRT treatment on a sequential boost regime (2 Gy/daily fraction) were studied for DDD-PIOP development. 61 patients were used for AI agent training/validation, and the remaining five were used as independent tests. To evaluate the developed AI agent's performance, the predicted mean standardized uptake values (SUVs) of gross tumor volume (GTV) and clinical target volume (CTV) were compared with the ground truth values. Overall SUV distribution accuracy was evaluated by gamma test passing rates under different criteria. RESULTS: The developed DDD-PIOP successfully generated 18FDG-PET image outcome predictions for five test patients. The predicted mean SUV values of GTV/CTV were 3.50/1.41, which were close to the ground-truth values of 3.57/1.51. In 2D-based gamma tests, the average passing rate was 92.1% using 5%/10 mm criteria, which was improved to 95.9%/93.2% when focusing on GTV/CTV regions. 3D gamma test passing rates were 98.7% using 5%/10 mm criteria, and the corresponding GTV/CTV results were 99.8%/99.4%. CONCLUSION: The reported results suggest that the developed AI agent DDD-PIOP successfully predicted 18FDG-PET image outcomes with high quantitative accuracy. The generated voxel-based image outcome predictions could be used for treatment planning optimization prior to radiation delivery for the best individual-based outcome.

Technical note: Interpolated Pareto surface similarity metrics for multi-criteria optimization in radiation therapy.

PURPOSE: There is a strong clinical need to evaluate different multi-criteria optimization (MCO) algorithms, including inverse optimization sampling algorithms and machine learning-based predictions. This study aims to develop and compare several interpolated Pareto surface similarity metrics. MATERIALS AND METHODS: The first metric is the root-mean-square error (RMSE) evaluated between vertices on the interpolated surfaces, augmented by intra-simplex sampling of the barycentric coordinates of the surfaces' simplicial complexes. The second metric is the average projected distance (APD), which evaluates the displacements between the vertices and computes their projections along the mean displacement. The third metric is the average nearest-point distance (ANPD), which numerically integrates point-to-simplex distances over the sampled simplices of the interpolated surfaces. These metrics were compared by their convergence rates, the times required to achieve convergence, and their representation of the underlying surface interpolations. For analysis, several interpolated Pareto surface pairs were constructed abstractly, with one pair from a nasopharyngeal treatment planning case using MCO. RESULTS: Convergence within 1% is typically achieved at approximately 50 and 80 samples per barycentric dimension for the RMSE and the ANPD, respectively. Calculation requires approximately 1 and 10 ms to achieve convergence for the RMSE and the ANPD in two dimensions, respectively, while the APD always requires < 1 ms. These time costs are much higher in higher dimensions for just the RMSE and ANPD. The APD values more closely approximated the ANPD limits than the RMSE limits. CONCLUSION: The ANPD's formulation and generality make it likely more meaningful than the RMSE and APD for representing the similarity between the underlying interpolated surfaces rather than the sampling points on the surfaces. However, in situations requiring high-speed evaluations, the APD may be more desirable due to its speed, independence from a subjectively chosen sampling rate, and similarity to the ANPD limits.

Automatic IMRT planning via static field fluence prediction (AIP-SFFP): a deep learning algorithm for real-time prostate treatment planning.

The purpose of this work was to develop a deep learning (DL) based algorithm, Automatic intensity-modulated radiotherapy (IMRT) Planning via Static Field Fluence Prediction (AIP-SFFP), for automated prostate IMRT planning with real-time planning efficiency. The following method was adopted: AIP-SFFP generates a prostate IMRT plan through predictions of fluence maps using patient anatomy. No inverse planning is required. AIP-SFFP is centered on a custom-built deep learning (DL) neural network for fluence map prediction. Predictions are imported to a commercial treatment-planning system for dose calculation and plan generation. AIP-SFFP was demonstrated for prostate IMRT simultaneously-integrated-boost planning (58.8 Gy/70 Gy to PTV58.8 Gy/PTV70 Gy in 28 fx, PTV = Planning Target Volume). Training data was generated from 106 patients using a knowledge-based planning (KBP) plan generator. Two types of 2D projection images were designed to represent structures' sizes and locations, and a total of eight projections were utilized to describe targets and organs-at-risk. Projections at nine template beam angles were stacked as inputs for artificial intelligence (AI) training. 14 patients were used as independent tests. The generated test plans were compared with the plans from the KBP training plan generator and clinic practice. The following results were obtained: After normalization (PTV70 Gy V70 Gy = 95%), all 14 AI plans met institutional criteria. The coverage of PTV58.8 Gy in the AI plans was comparable to KBP and clinic plans without statistical significance. The whole body (BODY) D1cc and rectum D0.1cc of AI plans were slightly higher (<1 Gy) compared to KBP and clinic plans; in contrast, the bladder D1cc and other rectum and bladder low doses in the AI plans were slightly improved without clinical relevance. The overall isodose distribution in the AI plans was comparable with KBP plans and clinical plans. AIP-SFFP generated each test plan within 20s including the prediction and the dose calculation. In conclusion, AIP-SFFP was successfully developed for prostate IMRT planning. AIP-SFFP demonstrated good overall plan quality and real-time efficiency. Showing great promise, AIP-SFFP will be investigated for immediate clinical application.