Plan complexity quantification of dual-layer multi-leaf collimator for volumetric modulated arc therapy with Halcyon linac

Evaluation of the dataset quality in gamma passing rate predictions using machine learning methods

OBJECTIVE

Gamma passing rate (GPR) predictions using machine learning methods have been explored for treatment verification of radiotherapy plans. However, these methods presented datasets with unbalanced number of plans having different treatment conditions (heterogeneous datasets), such as anatomical sites or dose per fractions, leading to lower model interpretability and prediction performance.

METHODS

We investigated the impact of the dataset composition on GPR binary classification (pass/fail) using random forest (RF), XG-boost, and neural network (NN) models. 945 plans were used to create one reference dataset (randomly assembled) and 24 customized datasets that considered four heterogeneity factors independently (anatomical region, number of arcs, dose per fraction, and treatment unit). 309 predictor features were extracted and calculated from plan parameters, modulation complexity metrics, and radiomic analysis (leave-trajectory maps, 3D dose distributions, and portal dosimetry images). The models' performances were measured using the area under the curve from the receiver operating characteristic (ROC-AUC).

RESULTS

Radiomics features for reference models increased ROC-AUC values up to 13%, 15%, and 5% for RF, XG-Boost, and NN, respectively. The datasets with higher heterogeneous conditions presented the lower ROC-AUC values (RF: 0.72 ± 0.11, XG-Boost: 0.67 ± 0.1, NN: 0.89 ± 0.05) compared to models with less heterogeneous treatment conditions (RF: 0.88 ± 0.06, XG-Boost: 0.89 ± 0.07, NN: 0.98 ± 0.01). The ten most important features for each heterogeneity dataset group demonstrated their correlation with the treatments' physical aspects and GPR prediction.

CONCLUSION

Improvements in data generalization and model performances can be associated with datasets having similar treatment conditions. This analysis might be implemented to evaluate the dataset quality and model consistency of further ML applications in radiotherapy.

ADVANCES IN KNOWLEDGE

Dataset heterogeneities decrease ML model performance and reliability.

An effective and optimized patient-specific QA workload reduction for VMAT plans after MLC-modelling optimization

INTRODUCTION

Many complexity metrics characterize modulated plans. First, this study aimed at identify the optimal complexity metrics to reduce workload associated to patient-specific quality assurance (PSQA) for our equipment and processes. Second, it intended to optimize our MLC modelling to improve measurement and calculation agreement with expectation of further reducing PSQA workload.

METHODS

Correlation and sensitivity at specificity equals to 1 were evaluated for PSQA results and different complexity metrics. Thresholds to stop PSQA were determined. After validation of the optimal complexity metric and threshold for our equipment and process, the MLC modelling was reviewed with a recently published methodology. This method is based on measurements with a Farmer-type ionization chamber of synchronous and asynchronous sweeping gap plans. Effect on the PSQA results and the identified threshold was investigated.

RESULTS

In our center, the most appropriate complexity metric for reducing our PSQA workload was the Modulation Complexity Score for VMAT (MCSv). The optimization of the MLC modelling significantly reduced the number of controlled plans, specifically for one of our two Varian Clinac. Any plan with a MCSv >= 0.34 is treated without PSQA.

CONCLUSION

This study rationalized and reduced our PSQA workload by approximately 30%. It is a continuing work with new TPS, machine or PSQA equipment. It encourages centers to re-evaluate their MLC modelling as well as assess the benefit of complexity metrics to streamline their PSQA workflow. An easier access, at least for reporting, at best for optimizing plans, into the TPS would be beneficial for the community.

Machine learning-based predictions of gamma passing rates for virtual specific-plan verification based on modulation maps, monitor unit profiles, and composite dose images

Machine learning (ML) methods have been implemented in radiotherapy to aid virtual specific-plan verification protocols, predicting gamma passing rates (GPR) based on calculated modulation complexity metrics because of their direct relation to dose deliverability. Nevertheless, these metrics might not comprehensively represent the modulation complexity, and automatically extracted features from alternative predictors associated with modulation complexity are needed. For this reason, three convolutional neural networks (CNN) based models were trained to predict GPR values (regression and classification), using respectively three predictors: (1) the modulation maps (MM) from the multi-leaf collimator, (2) the relative monitor units per control point profile (MUcp), and (3) the composite dose image (CDI) used for portal dosimetry, from 1024 anonymized prostate plans. The models' performance was assessed for classification and regression by the area under the receiver operator characteristic curve (AUC_ROC) and Spearman's correlation coefficient (r). Finally, four hybrid models were designed using all possible combinations of the three predictors. The prediction performance for the CNN-models using single predictors (MM, MUcp, and CDI) were AUC_ROC = 0.84 ± 0.03, 0.77 ± 0.07, 0.75 ± 0.04, andr= 0.6, 0.5, 0.7. Contrastingly, the hybrid models (MM + MUcp, MM + CDI, MUcp+CDI, MM + MUcp+CDI) performance were AUC_ROC = 0.94 ± 0.03, 0.85 ± 0.06, 0.89 ± 0.06, 0.91 ± 0.03, andr= 0.7, 0.5, 0.6, 0.7. The MP, MUcp, and CDI are suitable predictors for dose deliverability models implementing ML methods. Additionally, hybrid models are susceptible to improving their prediction performance, including two or more input predictors.

Investigation of Halcyon multi-leaf collimator model in Eclipse treatment planning system: A focus on the VMAT dose calculation with the Acuros XB algorithm

Purpose

The dual‐layer multi‐leaf collimator (MLC) in Halcyon involves further complexities in the dose calculation process, because the leaf‐tip transmission varies according to the leaf trailing pattern. For the volumetric modulated arc therapy (VMAT) treatment, the prescribed dose for the target volume can be sensitive to the leaf‐tip transmission change. This report evaluates the dosimetric consequence due to the uncertainty of the dual‐layer MLC model in Eclipse through the dose verifications for clinical VMAT. Additionally, the Halcyon leaf‐tip model is empirically adjusted for the VMAT dose calculation with the Acuros XB.

Materials and methods

For this evaluation, an in‐house program that analyzes the leaf position in each layer was developed. Thirty‐two clinical VMAT plans were edited into three leaf sequences: dual layer (original), proximal single layer, or distal single layer. All leaf sequences were verified using Delta4 according to the dose difference (DD) and the global gamma index (GI). To improve the VMAT dose calculation accuracy, the dosimetric leaf gap (DLG) was adjusted to minimize the DD in single‐layer leaf sequences.

Results

The mean of DD were −1.35%, −1.20%, and −1.34% in the dual‐layer, proximal single‐layer, and distal single‐layer leaf sequences, respectively. The changes in the mean of DD between leaf sequences were within 0.2%. However, the calculated doses differed from the measured doses by approximately 1% in all leaf sequences. The tuned DLG was increased by 0.8 mm from the original DLG in Eclipse. When the tuned DLG was used in the dose calculation, the mean of DD neared 0% and GI with a criterion of 2%/2 mm yielded a pass rate of more than 98%.

Conclusion

No significant change was confirmed in the dose calculation accuracy between the leaf sequences. Therefore, it is suggested that the dosimetric consequence due to the leaf trailing was negligibly small in clinical VMAT plans. The DLG tuning for Halcyon can be useful for reducing the dose calculation uncertainties in Eclipse VMAT and required in the commissioning for Acuros XB.

A Comprehensive Evaluation of the Application of the Halcyon(2.0) IMRT Technique in Long-Course Radiotherapy for Rectal Cancer

Objective: To evaluate if the Halcyon(2.0) Intensity Modulation Radiotherapy (IMRT) technique has an advantage in the long-course rectal cancer radiotherapy. Methods: A total of 20 clinical IMRT plans of Halcyon(2.0) for long-course (2Gy in 25 fractions) rectal cancer radiotherapy were randomly selected. Based on the parameters of these plans, 20 TrueBeam (with the Millennium 120 MLC) plans were redesigned, respectively. The dosimetry indexes, field complexity parameters, the Gamma Passing Rates (GPR), and the delivery time of the 2 groups of plans were obtained as measures of the plan quality, the modulation complexity, the delivery accuracy, and the delivery efficiency. The differences between the 2 groups of parameters were analyzed, with P < .05 means statistically significant. Results: In terms of dosimetry, there was no significant or clinical difference between the 2 groups in critical dosimetry parameters. The Monitor Unit of the Halcyon(2.0) fields is lower than the TrueBeam fields by 26.39, while the modulation complexity score (MCS), the mean aperture area variability (AAV), and the mean leaf sequence variability (LSV) of the Halcyon(2.0) fields were 23.8%, 20%, and 2.3% larger than those of the TrueBeam fields, respectively. Neither the ArcCheck-based GPRs nor the portal-dosimetry-based GPRs in both 3%/3 mm and 2%/2 mm criteria showed the difference between the Halcyon(2.0) fields and the TrueBeam fields. The Pearson correlation coefficient between GPR(2%/2 mm) and MCS of the Halcyon(2.0) fields was 0.335, while that of the TrueBeam fields was 0.502. The mean total delivery time of the TrueBeam plans was 195.55 ± 22.86 s, while that of Halcyon(2.0) was 124.25 ± 10.42 s (P < .001), which was reduced approximatively by 36%. Conclusion: For long-course rectal cancer radiotherapy, the Halcyon(2.0) IMRT plans behave almost the same in dosimetry and delivery accuracy as the TrueBeam plans. However, the lower MU and the field modulation complexity, combined with the higher delivery efficiency, make Halcyon(2.0) a feasible and reliable platform in long-course radiotherapy for the rectal cancer.

Feasibility study of volumetric modulated arc therapy with Halcyon™ linac for total body irradiation

Background

The use of total body irradiation (TBI) with linac-based volumetric modulated arc therapy (VMAT) has been steadily increasing. Helical tomotherapy has been applied in TBI and total marrow irradiation to reduce the dose to critical organs, especially the lungs. However, the methodology of TBI with Halcyon™ linac remains unclear. This study aimed to evaluate whether VMAT with Halcyon™ linac can be clinically used for TBI.

Methods

VMAT planning with Halcyon™ linac was conducted using a whole-body computed tomography data set. The planning target volume (PTV) included the body cropped 3 mm from the source. A dose of 12 Gy in six fractions was prescribed for 50% of the PTV. The organs at risk (OARs) included the lens, lungs, kidneys, and testes.

Results

The PTV D_98%, D_95%, D_50%, and D_2% were 8.9 (74.2%), 10.1 (84.2%), 12.6 (105%), and 14.2 Gy (118%), respectively. The homogeneity index was 0.42. For OARs, the D_mean of the lungs, kidneys, lens, and testes were 9.6, 8.5, 8.9, and 4.4 Gy, respectively. The V_12Gy of the lungs and kidneys were 4.5% and 0%, respectively. The D_max of the testes was 5.8 Gy. Contouring took 1–2 h. Dose calculation and optimization was performed for 3–4 h. Quality assurance (QA) took 2–3 h. The treatment duration was 23 min.

Conclusions

A planning study of TBI with Halcyon™ to set up VMAT-TBI, dosimetric evaluation, and pretreatment QA, was established.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-021-01959-3.

Fast generation of lung SBRT plans with a knowledge-based planning model on ring-mounted Halcyon Linac

Purpose

To demonstrate fast treatment planning feasibility of stereotactic body radiation therapy (SBRT) for centrally located lung tumors on Halcyon Linac via a previously validated knowledge‐based planning (KBP) model to support offline adaptive radiotherapy.

Materials/methods

Twenty previously treated non‐coplanar volumetric‐modulated arc therapy (VMAT) lung SBRT plans (c‐Truebeam) on SBRT‐dedicated C‐arm Truebeam Linac were selected. Patients received 50 Gy in five fractions. c‐Truebeam plans were re‐optimized for Halcyon manually (m‐Halcyon) and with KBP model (k‐Halcyon). Both m‐Halcyon and k‐Halcyon plans were normalized for identical or better target coverage than clinical c‐Truebeam plans and compared for target conformity, dose heterogeneity, dose fall‐off, and dose tolerances to the organs‐at‐risk (OAR). Treatment delivery parameters and planning times were evaluated.

Results

k‐Halcyon plans were dosimetrically similar or better than m‐Halcyon and c‐Truebeam plans. k‐Halcyon and m‐Halcyon plan comparisons are presented with respect to c‐Truebeam. Differences in conformity index were statistically insignificant in k‐Halcyon and on average 0.02 higher (p = 0.04) in m‐Halcyon plans. Gradient index was on average 0.43 (p = 0.006) lower and 0.27 (p = 0.02) higher for k‐Halcyon and m‐Halcyon, respectively. Maximal dose 2 cm away in any direction from target was statistically insignificant. k‐Halcyon increased maximal target dose on average by 2.9 Gy (p < 0.001). Mean lung dose was on average reduced by 0.10 Gy (p = 0.004) in k‐Halcyon and increased by 0.14 Gy (p < 0.001) in m‐Halcyon plans. k‐Halcyon plans lowered bronchial tree dose on average by 1.2 Gy. Beam‐on‐time (BOT) was increased by 2.85 and 1.67 min, on average for k‐Halcyon and m‐Halcyon, respectively. k‐Halcyon plans were generated in under 30 min compared to estimated dedicated 180 ± 30 min for m‐Halcyon or c‐Truebeam plan.

Conclusion

k‐Halcyon plans were generated in under 30 min with excellent plan quality. This adaptable KBP model supports high‐volume clinics in the expansion or transfer of lung SBRT patients to Halcyon.

Effect of treatment planning system parameters on beam modulation complexity for treatment plans with single-layer multi-leaf collimator and dual-layer stacked multi-leaf collimator

OBJECTIVE

High levels of beam modulation complexity (MC) and monitor units (MU) can compromise the plan deliverability of intensity-modulated radiotherapy treatments. Our study evaluates the effect of three treatment planning system (TPS) parameters on MC and MU using different multi-leaf collimator (MLC) architectures.

METHODS

192 volumetric modulated arc therapy plans were calculated using one virtual prostate phantom considering three main settings: (1) three TPS-parameters (Convergence; Aperture Shape Controller, ASC; and Dose Calculation Resolution, DCR) selected from Eclipse v15.6, (2) four levels of dose-sparing priority for organs at risk (OAR), and (3) two treatment units with same nominal conformity resolution and different MLC architectures (Halcyon-v2 dual-layer MLC, DL-MLC & TrueBeam single-layer MLC, SL-MLC). We use seven complexity metrics to evaluate the MC, including two new metrics for DL-MLC, assessed by their correlation with γ passing rate (GPR) analysis.

RESULTS

DL-MLC plans demonstrated lower dose-sparing values than SL-MLC plans (p<0.05). TPS-parameters did not change significantly the complexity metrics for either MLC architectures. However, for SL-MLC, significant variations of MU, target volume dose-homogeneity, and dose spillage were associated with ASC and DCR (p<0.05). MU were found to be correlated (highly or moderately) with all complexity metrics (p<0.05) for both MLC plans. Additionally, our new complexity metrics presented a moderate correlation with GPR (r<0.65). An important correlation was demonstrated between MC (plan deliverability) and dose-sparing priority level for DL-MLC.

CONCLUSIONS

TPS-parameters selected do not change MC for DL-MLC architecture, but they might have a potential use to control the MU, PTV homogeneity or dose spillage for SL-MLC. Our new DL-MLC complexity metrics presented important information to be considered in future pre-treatment quality assurance programs. Finally, the prominent dependence between plan deliverability and priority applied to OAR dose sparing for DL-MLC needs to be analyzed and considered as an additional predictor of GPRs in further studies.

ADVANCES IN KNOWLEDGE

Dose-sparing priority might influence in modulation complexity of DL-MLC.