Knowledge-based Planning Research Articles

Predicting personalised optimal arc parameter using knowledge-based planning model for inoperable locally advanced lung cancer patients to reduce organ at risk doses

Objectives. Volumetric modulated arc therapy (VMAT) allows for reduction of organs at risk (OAR) volumes receiving higher doses, but increases OAR volumes receiving lower radiation doses and can subsequently increasing associated toxicity. Therefore, reduction of this low-dose-bath is crucial. This study investigates personalizing the optimization of VMAT arc parameters (gantry start and stop angles) to decrease OAR doses. Materials and Methods. Twenty previously treated locally advanced non-small cell lung cancer (NSCLC) patients treated with half-arcs were randomly selected from our database. These plans were re-optimized with seven different arcs parameters; optimization objectives were kept constant for all plans. All resulting plans were reviewed by two clinicians and the optimal plan (lowest OAR doses and adequate target coverage) was selected. Furthermore, knowledge-based planning (KBP) model was developed using these plans as ‘training data’ to predict optimal arc parameters for individual patients based on their anatomy. Treatment plan complexity scores and deliverability measurements were performed for both optimal and original clinical plans. Results. The results show that different arc geometries resulted in different dose distributions to the OAR but target coverage was mostly similar. Different arc geometries were required for different patients to minimize OAR doses. Comparison of the personalized against the standard (2 half-arcs) plans showed a significant reduction in lung V5 (lung volume receiving 5 Gy), mean lung dose and mean heart doses. Reduction in lung V20 and heart V30 were statistically insignificant. Plan complexity and deliverability measurements show the test plans can be delivered as planned. Conclusions. Our study demonstrated that personalizing arc parameters based on an individual patient’s anatomy significantly reduces both lung and heart doses. Dose reduction is expected to reduce toxicity and improve the quality of life for these patients.

Validation of in-house knowledge-based planning model for predicting change in target coverage during VMAT radiotherapy to in-operable advanced-stage NSCLC patients

Objectives. anatomical changes are inevitable during the course of radiotherapy treatments and, if significant, can severely alter expected dose distributions and affect treatment outcome. Adaptive radiotherapy (ART) is employed to maintain the planned distribution and minimise detriment to predicted treatment outcome. Typically, patients who may benefit from adaptive planning are identified via a re-planning process, i.e., re-simulation, re-contouring, re-planning and treatment plan quality assurance (QA). This time-intensive process significantly increases workload, can introduce delays and increases unnecessary stress to those patients who will not actually gain benefit. We consider it crucial to develop efficient models to predict changes to target coverage and trigger ART, without the need for re-planning. Methods. knowledge-based planning (KBP) models were developed using data for 20 patients’ (400 fractions) to predict changes in PTV V95 coverage Initially, this change in coverage was calculated on the synthetic computerised tomography (sCT) images produced using the Velocity adaptive radiotherapy software. Models were developed using patient (cell death bio-marker) and treatment fraction (PTV characteristic) specific parameters to predict and verified using five patients (100 fractions) data. Results. three models were developed using combinations of patient and fraction specific terms. The prediction accuracy of the model developed using biomarker (PD-L1 expression) and the difference in ‘planning’ and ‘fraction’ PTV centre of the mass (characterised by mean square difference, MSD) had the higher prediction accuracy, predicting the within ± 1.0% for 77% of the total fractions; with 59% for the model developed using, PTV size, PD-L1 and MSD and 48% PTV size and MSD respectively. Conclusion. the KBP models can predict very effectively and efficiently for advanced-stage NSCLC patients treated using volumetric modulated arc therapy and to identify patients who may benefit from adaption for a specific fraction.

A comparison of two methodologies for radiotherapy treatment plan optimization and QA for clinical trials.

Background and purposeThe efficacy of clinical trials and the outcome of patient treatment are dependent on the quality assurance (QA) of radiation therapy (RT) plans. There are two widely utilized approaches that include plan optimization guidance created based on patient‐specific anatomy. This study examined these two techniques for dose‐volume histogram predictions, RT plan optimizations, and prospective QA processes, namely the knowledge‐based planning (KBP) technique and another first principle (FP) technique.MethodsThis analysis included 60, 44, and 10 RT plans from three Radiation Therapy Oncology Group (RTOG) multi‐institutional trials: RTOG 0631 (Spine SRS), RTOG 1308 (NSCLC), and RTOG 0522 (H&N), respectively. Both approaches were compared in terms of dose prediction and plan optimization. The dose predictions were also compared to the original plan submitted to the trials for the QA procedure.ResultsFor the RTOG 0631 (Spine SRS) and RTOG 0522 (H&N) plans, the dose predictions from both techniques have correlation coefficients of >0.9. The RT plans that were re‐optimized based on the predictions from both techniques showed similar quality, with no statistically significant differences in target coverage or organ‐at‐risk sparing. The predictions of mean lung and heart doses from both methods for RTOG1308 patients, on the other hand, have a discrepancy of up to 14 Gy.ConclusionsBoth methods are valuable tools for optimization guidance of RT plans for Spine SRS and Head and Neck cases, as well as for QA purposes. On the other hand, the findings suggest that KBP may be more feasible in the case of inoperable lung cancer patients who are treated with IMRT plans that have spatially unevenly distributed beam angles.

Deep learning method for prediction of patient-specific dose distribution in breast cancer

BackgroundPatient-specific dose prediction improves the efficiency and quality of radiation treatment planning and reduces the time required to find the optimal plan. In this study, a patient-specific dose prediction model was developed for a left-sided breast clinical case using deep learning, and its performance was compared with that of conventional knowledge-based planning using RapidPlan™.MethodsPatient-specific dose prediction was performed using a contour image of the planning target volume (PTV) and organs at risk (OARs) with a U-net-based modified dose prediction neural network. A database of 50 volumetric modulated arc therapy (VMAT) plans for left-sided breast cancer patients was utilized to produce training and validation datasets. The dose prediction deep neural network (DpNet) feature weights of the previously learned convolution layers were applied to the test on a cohort of 10 test sets. With the same patient data set, dose prediction was performed for the 10 test sets after training in RapidPlan. The 3D dose distribution, absolute dose difference error, dose-volume histogram, 2D gamma index, and iso-dose dice similarity coefficient were used for quantitative evaluation of the dose prediction.ResultsThe mean absolute error (MAE) and one standard deviation (SD) between the clinical and deep learning dose prediction models were 0.02 ± 0.04%, 0.01 ± 0.83%, 0.16 ± 0.82%, 0.52 ± 0.97, − 0.88 ± 1.83%, − 1.16 ± 2.58%, and − 0.97 ± 1.73% for D95%, Dmean in the PTV, and the OARs of the body, left breast, heart, left lung, and right lung, respectively, and those measured between the clinical and RapidPlan dose prediction models were 0.02 ± 0.14%, 0.87 ± 0.63%, − 0.29 ± 0.98%, 1.30 ± 0.86%, − 0.32 ± 1.10%, 0.12 ± 2.13%, and − 1.74 ± 1.79, respectively.ConclusionsIn this study, a deep learning method for dose prediction was developed and was demonstrated to accurately predict patient-specific doses for left-sided breast cancer. Using the deep learning framework, the efficiency and accuracy of the dose prediction were compared to those of RapidPlan. The doses predicted by deep learning were superior to the results of the RapidPlan-generated VMAT plan.

Comprehensive nodal breast VMAT: solving the low-dose wash dilemma using an iterative knowledge-based radiotherapy planning solution.

IntroductionAimed to develop a simple and robust volumetric modulated arc radiotherapy (VMAT) solution for comprehensive lymph node (CLN) breast cancer without increase in low‐dose wash.MethodsForty CLN‐breast patient data sets were utilised to develop a knowledge‐based planning (KBP) VMAT model, which limits low‐dose wash using iterative learning and base‐tangential methods as benchmark. Another twenty data sets were employed to validate the model comparing KBP‐generated ipsilateral VMAT (ipsi‐VMAT) plans against the benchmarked hybrid (h)‐VMAT (departmental standard) and bowtie‐VMAT (published best practice) methods. Planning target volume (PTV), conformity/homogeneity index (CI/HI), organ‐at‐risk (OAR), remaining‐volume‐at‐risk (RVR) and blinded radiation oncologist (RO) plan preference were evaluated.ResultsIpsi‐ and bowtie‐VMAT plans were dosimetrically equivalent, achieving greater nodal target coverage (P < 0.05) compared to h‐VMAT with minor reduction in breast coverage. CI was enhanced for a small reduction in breast HI with improved dose sparing to ipsilateral‐lung and humeral head (P < 0.05) at immaterial expense to spinal cord. Significantly, low‐dose wash to OARs and RVR were comparable between all plan types demonstrating a simple VMAT class solution robust to patient‐specific anatomic variation can be applied to CLN breast without need for complex beam modification (hybrid plans, avoidance sectors or other). This result was supported by blinded RO review.ConclusionsA simple and robust ipsilateral VMAT class solution for CLN breast generated using iterative KBP modelling can achieve clinically acceptable target coverage and OAR sparing without unwanted increase in low‐dose wash associated with increased second malignancy risk.

Personalising treatment plan quality review with knowledge-based planning in the TROG 15.03 trial for stereotactic ablative body radiotherapy in primary kidney cancer

IntroductionQuality assurance (QA) of treatment plans in clinical trials improves protocol compliance and patient outcomes. Retrospective use of knowledge-based-planning (KBP) in clinical trials has demonstrated improved treatment plan quality and consistency. We report the results of prospective use of KBP for real-time QA of treatment plan quality in the TROG 15.03 FASTRACK II trial, which evaluates efficacy of stereotactic ablative body radiotherapy (SABR) for kidney cancer.MethodsA KBP model was generated based on single institution data. For each patient in the KBP phase (open to the last 31 patients in the trial), the treating centre submitted treatment plans 7 days prior to treatment. A treatment plan was created by using the KBP model, which was compared with the submitted plan for each organ-at-risk (OAR) dose constraint. A report comparing each plan for each OAR constraint was provided to the submitting centre within 24 h of receiving the plan. The centre could then modify the plan based on the KBP report, or continue with the existing plan.ResultsReal-time feedback using KBP was provided in 24/31 cases. Consistent plan quality was in general achieved between KBP and the submitted plan. KBP review resulted in replan and improvement of OAR dosimetry in two patients. All centres indicated that the feedback was a useful QA check of their treatment plan.ConclusionKBP for real-time treatment plan review was feasible for 24/31 cases, and demonstrated ability to improve treatment plan quality in two cases. Challenges include integration of KBP feedback into clinical timelines, interpretation of KBP results with respect to clinical trade-offs, and determination of appropriate plan quality improvement criteria.

An updating approach for knowledge-based planning models to improve plan quality and variability in volumetric-modulated arc therapy for prostate cancer.

PurposeThe purpose of this study was to compare the dose–volume parameters and regression scatter plots of the iteratively improved RapidPlan (RP) models, specific knowledge‐based planning (KBP) models, in volumetric‐modulated arc therapy (VMAT) for prostate cancer over three periods.MethodsA RP1 model was created from 47 clinical intensity‐modulated radiation therapy (IMRT)/VMAT plans. A RP2 model was created to exceed dosimetric goals which set as the mean values +1SD of the dose–volume parameters of RP1 (50 consecutive new clinical VMAT plans). A RP3 model was created with more strict dose constraints for organs at risks (OARs) than RP1 and RP2 models (50 consecutive anew clinical VMAT plans). Each RP model was validated against 30 validation plans (RP1, RP2, and RP3) that were not used for model configuration, and the dose–volume parameters were compared. The Cook's distances of regression scatterplots of each model were also evaluated.ResultsSignificant differences (p < 0.05) between RP1 and RP2 were found in Dmean (101.5% vs. 101.9%), homogeneity index (3.90 vs. 4.44), 95% isodose conformity index (1.22 vs. 1.20) for the target, V40Gy (47.3% vs. 45.7%), V60Gy (27.9% vs. 27.1%), V70Gy (16.4% vs. 15.2%), and V78Gy (0.4% vs. 0.2%) for the rectal wall, and V40Gy (43.8% vs. 41.8%) and V70Gy (21.3% vs. 20.5%) for the bladder wall, whereas only V70Gy (15.2% vs. 15.8%) of the rectal wall differed significantly between RP2 and RP3. The proportions of cases with a Cook's distance of <1.0 (RP1, RP2, and RP3 models) were 55%, 78%, and 84% for the rectal wall, and 77%, 68%, and 76% for the bladder wall, respectively.ConclusionsThe iteratively improved RP models, reflecting the clear dosimetric goals based on the RP feedback (dose–volume parameters) and more strict dose constraints for the OARs, generated superior dose–volume parameters and the regression scatterplots in the model converged. This approach could be used to standardize the inverse planning strategies.

PO-1856 Minimizing dose to brain structures by knowledge-based planning

PO-1856 Minimizing dose to brain structures by knowledge-based planning

OC-0426 Prospective knowledge-based planning for personalised plan QA in a multi-centre kidney SABR trial

OC-0426 Prospective knowledge-based planning for personalised plan QA in a multi-centre kidney SABR trial

Improving efficiency in the radiation management of multiple brain metastases using a knowledge-based planning solution for single-isocentre volumetric modulated arc therapy (VMAT) technique.

IntroductionThis study aimed to develop a single‐isocentre volumetric modulated arc therapy (si‐VMAT) technique for multiple brain metastases using knowledge‐based planning software, comparing it with a multiple‐isocentre stereotactic radiosurgery (mi‐SRS) planning approach.MethodsTwenty‐six si‐VMAT plans were created and uploaded into RapidPlanTM (RP) to create a si‐VMAT model. Ten patients, with 2 to 6 metastases (mets), were planned with a si‐VMAT technique utilising RP, and a mi‐SRS technique on Brainlab iPlan.Paddick Conformity Index (PCI) was used to compare conformity. The volumes of the brain receiving 15Gy, 12Gy, 10Gy, 7.5Gy and 3Gy were also compared.Retrospective treatment times from the last eight patients treated were averaged for pre‐imaging and beam on time to calculate treatment times for both techniques.ResultsThere was a significant difference in the PCI scores for the mi‐SRS plans (M = 0.667, SD = 0.114) and si‐VMAT plans (M = 0.728, SD = 0.088), with PCI values suggesting better prescription dose conformity with the si‐VMAT technique (P = 0.014). Percentage of total brain volume receiving low‐dose wash at four of the five different dose levels was significantly less (P < 0.05) with mi‐SRS.Average time to treat a single met with current mi‐SRS technique is 25.7 min, with each additional met requiring this same amount of time. The average time to treat 2–3 mets using si‐VMAT would be 25.3 min and 4+ metastases 33.5 min.ConclusionA knowledge‐based si‐VMAT approach was efficient in planning and treating multi metastases while achieving clinically acceptable dosimetry with respect to dose conformity and low‐dose fall off.

Knowledge-based radiation treatment planning: A data-driven method survey.

This paper surveys the data‐driven dose prediction methods investigated for knowledge‐based planning (KBP) in the last decade. These methods were classified into two major categories—traditional KBP methods and deep‐learning (DL) methods—according to their techniques of utilizing previous knowledge. Traditional KBP methods include studies that require geometric or anatomical features to either find the best‐matched case(s) from a repository of prior treatment plans or to build dose prediction models. DL methods include studies that train neural networks to make dose predictions. A comprehensive review of each category is presented, highlighting key features, methods, and their advancements over the years. We separated the cited works according to the framework and cancer site in each category. Finally, we briefly discuss the performance of both traditional KBP methods and DL methods, then discuss future trends of both data‐driven KBP methods to dose prediction.

Wide-Scale Clinical Implementation of Knowledge-Based Planning: An Investigation of Workforce Efficiency, Need for Post-automation Refinement, and Data-Driven Model Maintenance

Our purpose was to investigate the effect of automated knowledge-based planning (KBP) on real-world clinical workflow efficiency, assess whether manual refinement of KBP plans improves plan quality across multiple disease sites, and develop a data-driven method to periodically improve KBP automated planning routines. Using clinical knowledge-based automated planning routines for prostate, prostatic fossa, head and neck, and hypofractionated lung disease sites in a commercial KBP solution, workflow efficiency was compared in terms of planning time in a pre-KBP (n=145 plans) and post-KBP (n=503) patient cohort. Post-KBP, planning was initialized with KBP (KBP-only) and subsequently manually refined (KBP+human). Differences in planning time were tested for significance using a 2-tailed Mann-Whitney U test (P < .05, null hypothesis: planning time unchanged). Post-refinement plan quality was assessed using site-specific dosimetric parameters of the original KBP-only plan versus KBP+human; 2-tailed paired t test quantified statistical significance (Bonferroni-corrected P < .05, null hypothesis: no dosimetric difference after refinement). If KBP+human significantly improved plans across the cohort, optimization objectives were changed to create an updated KBP routine (KBP'). Patients were replanned with KBP' and plan quality was compared with KBP+human as described previously. KBP significantly reduced planning time in all disease sites: prostate (median: 7.6 hrs→2.1 hrs; P < .001), prostatic fossa (11.1 hrs→3.7 hrs; P=.001), lung (9.9 hrs→2.0 hrs; P < .001), and head and neck (12.9 hrs→3.5 hrs; P <.001). In prostate, prostatic fossa, and lung disease sites, organ-at-risk dose changes in KBP+human versus KBP-only were minimal (<1% prescription dose). In head and neck, KBP+human did achieve clinically relevant dose reductions in some parameters. The head and neck routine was updated (KBP'HN) to incorporate dose improvements from manual refinement. The only significant dosimetric differences to KBP+human after replanning with KBP'HN were in favor of the new routine. KBP increased clinical efficiency by significantly reducing planning time. On average, human refinement offered minimal dose improvements over KBP-only plans. In the single disease site where KBP+human was superior to KBP-only, differences were eliminated by adjusting optimization parameters in a revised KBP routine.

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

PurposeHigh 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 MaterialsA 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. ResultsBoth 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. ConclusionsBy 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.

Use of knowledge based DVH predictions to enhance automated re-planning strategies in head and neck adaptive radiotherapy

This study aimed to investigate if a commercial, knowledge-based tool for radiotherapy planning could be used to estimate the amount of sparing in organs at risk (OARs) in the re-planning strategy for adaptive radiotherapy (ART). Eighty head and neck (HN) VMAT Pareto plans from our institute’s database were used to train a knowledge-based planning (KBP) model. An evaluation set of another 20 HN patients was randomly selected. For each patient in the evaluation set, the planning computed tomography (CT) and 2 sets of on-board cone-beam CT, corresponding to the middle and second half of the radiotherapy treatment course, were extracted. The original plan was re-calculated on a daily deformed CT (delivered dose‐volume histogram (DVH)) and compared with the KBP DVH predictions and with the final KBP DVH after optimisation of the plan, which was performed on the same image sets. To evaluate the feasibility of this method, the range of KBP DVH uncertainties was compared with the gains obtained from re-planning. DVH differences and receiver operating characteristic (ROC) curve analysis were used for this purpose. On average, final KBP uncertainties were smaller than the gain in re-planning. Statistical tests confirmed significant differences between the two groups. ROC analysis showed KBP performance in terms of area under the curve values higher than 0.7, which confirmed a good accuracy in predicted values. Overall, for 48% of cases, KBP predicted a desirable outcome from re-planning, and the final dose confirmed an effective gain in 47% of cases. We have established a systematic workflow to identify effective OAR sparing in re-planning based on KBP predictions that can be implemented in an on-line, ART process.

OpenKBP: The open-access knowledge-based planning grand challenge and dataset.

To advance fair and consistent comparisons of dose prediction methods for knowledge-based planning (KBP) in radiation therapy research. We hosted OpenKBP, a 2020 AAPM Grand Challenge, and challenged participants to develop the best method for predicting the dose of contoured computed tomography (CT) images. The models were evaluated according to two separate scores: (a) dose score, which evaluates the full three-dimensional (3D) dose distributions, and (b) dose-volume histogram (DVH) score, which evaluates a set DVH metrics. We used these scores to quantify the quality of the models based on their out-of-sample predictions. To develop and test their models, participants were given the data of 340 patients who were treated for head-and-neck cancer with radiation therapy. The data were partitioned into training ( ), validation ( ), and testing ( ) datasets. All participants performed training and validation with the corresponding datasets during the first (validation) phase of the Challenge. In the second (testing) phase, the participants used their model on the testing data to quantify the out-of-sample performance, which was hidden from participants and used to determine the final competition ranking. Participants also responded to a survey to summarize their models. The Challenge attracted 195 participants from 28 countries, and 73 of those participants formed 44 teams in the validation phase, which received a total of 1750 submissions. The testing phase garnered submissions from 28 of those teams, which represents 28 unique prediction methods. On average, over the course of the validation phase, participants improved the dose and DVH scores of their models by a factor of 2.7 and 5.7, respectively. In the testing phase one model achieved the best dose score (2.429) and DVH score (1.478), which were both significantly better than the dose score (2.564) and the DVH score (1.529) that was achieved by the runner-up models. Lastly, many of the top performing teams reported that they used generalizable techniques (e.g., ensembles) to achieve higher performance than their competition. OpenKBP is the first competition for knowledge-based planning research. The Challenge helped launch the first platform that enables researchers to compare KBP prediction methods fairly and consistently using a large open-source dataset and standardized metrics. OpenKBP has also democratized KBP research by making it accessible to everyone, which should help accelerate the progress of KBP research. The OpenKBP datasets are available publicly to help benchmark future KBP research.

Technical Note: Dose prediction for head and neck radiotherapy using a three-dimensional dense dilated U-net architecture.

Radiation therapy treatment planning is a time-consuming and iterative manual process. Consequently, plan quality varies greatly between and within institutions. Artificial intelligence shows great promise in improving plan quality and reducing planning times. This technical note describes our participation in the American Association of Physicists in Medicine Open Knowledge-Based Planning Challenge (OpenKBP), a competition to accurately predict radiation therapy dose distributions. A three-dimensional (3D) densely connected U-Net with dilated convolutions was developed to predict 3D dose distributions given contoured CT images of head and neck patients as input. While traditional augmentation techniques such as rotations and translations were explored, it was found that training on random patches alone resulted in the greatest model performance. A custom-weighted mean squared error loss function was employed. Finally, an ensemble of best-performing networks was used to generate the final challenge predictions. Our team (SuperPod) placed second in the dose stream of the OpenKBP challenge. The average mean absolute difference between the predicted and clinical dose distributions of the testing dataset was 2.56Gy. On average, the predicted normalized target DVH metrics were within 3% of the clinical plans, and the predicted organ at risk DVH metrics were within 2Gy of the clinical plans. The developed 3D dense dilated U-Net architecture can accurately predict 3D radiotherapy dose distributions and can be used as part of a fully automated radiation therapy planning pipeline.

Technical Note: Dose prediction for radiation therapy using feature-based losses and One Cycle Learning.

PurposeTo present the technical details of the runner‐up model in the open knowledge‐based planning (OpenKBP) challenge for the dose–volume histogram (DVH) stream. The model was designed to ensure simple and reproducible training, without the necessity of costly advanced generative adversarial network (GAN) techniques.MethodsThe model was developed based on the OpenKBP challenge dataset, consisting of 200 and 40 head‐and‐neck patients for training and validation, respectively. The final model is a U‐Net with additional ResNet blocks between up‐ and down convolutions. The results were obtained by training the model with AdamW with the One Cycle scheduler. The loss function is a combination of the L1 loss with a feature loss, which uses a pretrained video classifier as a feature extractor. The performance was evaluated on another 100 patients in the OpenKBP test dataset. The DVH metrics of the test data were evaluated, where D0.1cc, and Dmean were calculated for the organs at risk (OARs) and D1%, D95%, and D99% were computed for the target structures. DVH metric differences between predicted and true dose are reported in percentage.ResultsThe model achieved 2nd and 4th place in the DVH and dose stream of the OpenKBP challenge, respectively. The dose and DVH score were 2.62 ± 1.10 and 1.52 ± 1.06, respectively. Mean dose differences for the different structures and DVH parameters were within ±1%.ConclusionThis straightforward approach produced excellent results. It incorporated One Cycle Learning, ResNet, and feature‐based losses, which are common computer vision techniques.

Reducing variability among treatment machines using knowledge-based planning for head and neck, pancreatic, and rectal cancer.

PurposeThis study aimed to assess dosimetric indices of RapidPlan model‐based plans for different energies (6, 8, 10, and 15 MV; 6‐ and 10‐MV flattening filter‐free), multileaf collimator (MLC) types (Millennium 120, High Definition 120, dual‐layer MLC), and disease sites (head and neck, pancreatic, and rectal cancer) and compare these parameters with those of clinical plans.MethodsRapidPlan models in the Eclipse version 15.6 were used with the data of 28, 42, and 20 patients with head and neck, pancreatic, and rectal cancer, respectively. RapidPlan models of head and neck, pancreatic, and rectal cancer were created for TrueBeam STx (High Definition 120) with 6 MV, TrueBeam STx with 10‐MV flattening filter‐free, and Clinac iX (Millennium 120) with 15 MV, respectively. The models were used to create volumetric‐modulated arc therapy plans for a 10‐patient test dataset using all energy and MLC types at all disease sites. The Holm test was used to compare multiple dosimetric indices in different treatment machines and energy types.ResultsThe dosimetric indices for planning target volume and organs at risk in RapidPlan model‐based plans were comparable to those in the clinical plan. Furthermore, no dose difference was observed among the RapidPlan models. The variability among RapidPlan models was consistent regardless of the treatment machines, MLC types, and energy.ConclusionsDosimetric indices of RapidPlan model‐based plans appear to be comparable to the ones based on clinical plans regardless of energies, MLC types, and disease sites. The results suggest that the RapidPlan model can generate treatment plans independent of the type of treatment machine.

Plan Complexity and Delivery Accuracy of Knowledge-based Volumetric Modulated Arc Therapy Plans with Single Optimization for Oropharyngeal Cancer.

We investigated the plan complexity of volumetric modulated arc therapy (VMAT) with knowledge-based plan (KBP) for oropharyngeal cancer (OPC) with a single optimization and whether it could be used clinically. KBP model was configured using 55 consecutive OPC and nasopharyngeal cancer plans. Plan complexity as a characteristic of multileaf collimator (MLC) motion and γ pass rate (2%/2 mm criterion) were compared between clinical manual plan (CMP) and KBP for other 10 plans. Plan complexity metrics that had significant differences (p<0.05) (CMP vs. KBP), were mean lateral displacement of MLC from central axis (15.82 mm vs. 18.90 mm), proportions of MLC aperture sizes of ≤5 mm (0.14 vs. 0.11), ≤10 mm (0.24 vs. 0.19), and ≤20 mm (0.41 vs. 0.34), and monitor units (578.68 vs. 505.04). The γ pass rate was 91.3% vs. 93.3%. Single optimized KBP for OPC had simple plan complexity features and comparable delivery accuracy to CMP, and could be clinically applied.

Assessment of a conventional volumetric-modulated arc therapy knowledge-based planning model applied to the new Halcyon© O-ring linac in locoregional breast cancer radiotherapy.

The aim of this study was to evaluate the performance of a knowledge-based planning (KBP) model for breast cancer trained on plans performed on a conventional linac with 6 MV FF (flattening filter) beams and volumetric-modulated arc therapy (VMAT) for plans performed on the new jawless Halcyon© system with 6 MV FFF (flattening filter-free) beams. Based on the RapidPlan© (RP) KBP optimization engine, a DVH Estimation Model was first trained using 56 VMAT left-sided breast cancer treatment plans performed on a conventional linac, and validated on another 20 similar cases (without manual intervention). To determine the capacity of the model for Halcyon©, an additional cohort of 20 left-sided breast cancer plans was generated with RP and analyzed for both TrueBeam© and Halcyon© machines. Plan qualities between manual vs RP (followed by manual intervention) Halcyon© plans set were compared qualitatively by blinded review by radiation oncologists for 10 new independent plans. Halcyon© plans generated with the VMAT model trained with conventional linac plans showed comparable target dose distribution compared to TrueBeam© plans. Organ sparingwas comparable between the 2 devices with a slight decrease in heart dose for Halcyon© plans. Nine out of ten automatically generated Halcyon© plans were preferentially chosen by the radiation oncologists over the manually generated Halcyon© plans. A VMAT KBP model driven by plans performed on a conventional linac with 6 MV FF beams provides high quality plans performed with 6 MV FFF beams on the new Halcyon© linac.