The 3D isodose structure-based method for clinical dose distributions comparison in pretreatment patient-QA

An operator-independent quality assurance system for automatically generated structure sets

Objective. This study describes geometry-based and intensity-based tools for quality assurance (QA) of automatically generated structures for online adaptive radiotherapy, and designs an operator-independent traffic light system that identifies erroneous structure sets.Approach.A cohort of eight head and neck (HN) patients with daily CBCTs was selected for test development. Radiotherapy contours were propagated from planning computed tomography (CT) to daily cone beam CT (CBCT) using deformable image registration. These propagated structures were visually verified for acceptability. For each CBCT, several error scenarios were used to generate what were judged unacceptable structures. Ten additional HN patients with daily CBCTs and different error scenarios were selected for validation. A suite of tests based on image intensity, intensity gradient, and structure geometry was developed using acceptable and unacceptable HN planning structures. Combinations of one test applied to one structure, referred to as structure-test combinations, were selected for inclusion in the QA system based on their discriminatory power. A traffic light system was used to aggregate the structure-test combinations, and the system was evaluated on all fractions of the ten validation HN patients.Results.The QA system distinguished between acceptable and unacceptable fractions with high accuracy, labeling 294/324 acceptable fractions as green or yellow and 19/20 unacceptable fractions as yellow or red.Significance.This study demonstrates a system to supplement manual review of radiotherapy planning structures. Automated QA is performed by aggregating results from multiple intensity- and geometry-based tests.

Invertible and Variable Augmented Network for Pretreatment Patient-Specific Quality Assurance Dose Prediction

Pretreatment patient-specific quality assurance (prePSQA) is conducted to confirm the accuracy of the radiotherapy dose delivered. However, the process of prePSQA measurement is time consuming and exacerbates the workload for medical physicists. The purpose of this work is to propose a novel deep learning (DL) network to improve the accuracy and efficiency of prePSQA. A modified invertible and variable augmented network was developed to predict the three-dimensional (3D) measurement-guided dose (MDose) distribution of 300 cancer patients who underwent volumetric modulated arc therapy (VMAT) between 2018 and 2021, in which 240 cases were randomly selected for training, and 60 for testing. For simplicity, the present approach was termed as "IVPSQA." The input data include CT images, radiotherapy dose exported from the treatment planning system, and MDose distribution extracted from the verification system. Adam algorithm was used for first-order gradient-based optimization of stochastic objective functions. The IVPSQA model obtained high-quality 3D prePSQA dose distribution maps in head and neck, chest, and abdomen cases, and outperformed the existing U-Net-based prediction approaches in terms of dose difference maps and horizontal profiles comparison. Moreover, quantitative evaluation metrics including SSIM, MSE, and MAE demonstrated that the proposed approach achieved a good agreement with ground truth and yield promising gains over other advanced methods. This study presented the first work on predicting 3D prePSQA dose distribution by using the IVPSQA model. The proposed method could be taken as a clinical guidance tool and help medical physicists to reduce the measurement work of prePSQA.

TransQA: deep hybrid transformer network for measurement-guided volumetric dose prediction of pre-treatment patient-specific quality assurance

Objective. Performing pre-treatment patient-specific quality assurance (prePSQA) is considered an essential, time-consuming, and resource-intensive task for volumetric modulated arc radiotherapy (VMAT) which confirms the dose accuracy and ensure patient safety. Most current machine learning and deep learning approaches stack excessive convolutional/pooling operations (CPs) to predict prePSQA with two-dimensional or one-dimensional information input. However, these models generally present limitations in explicitly modeling long-range dependency for volumetric dose prediction due to the loss of spatial dose features and the inherent locality of CPs. The purpose of this work is to construct a deep hybrid network by combining the self-attention mechanism-based Transformer with modified U-Net for predicting measurement-guided volumetric dose (MDose) of prePSQA.Approach. The enrolled 307 cancer patients underwent VMAT were randomly divided into 246 and 61 cases for training and testing the model. The input data included computed tomography images, radiotherapy dose images exported from the treatment planning system, as well as the MDose distribution from the verification system. The output was the predicted high-quality voxel-wise prePSQA dose distribution.Main results: qualitative and quantitative experimental results show that the proposed prediction method could achieve comparable or better performance on MDose prediction over other approaches in terms of spatial dose distribution, dose-volume histogram metrics, gamma passing rates, mean absolute error, root mean square error, and structural similarity.Significance. The preliminary results on multiple cancer sites show that our approach can be taken as a clinical guidance tool and help medical physicists to reduce the measurement work of prePSQA.

Efficient dose-volume histogram-based pretreatment patient-specific quality assurance methodology with combined deep learning and machine learning models for volumetric modulated arc radiotherapy

BACKGROUND

Weak correlation between gamma passing rates and dose differences in target volumes and organs at risk (OARs) has been reported in several studies. Evaluation on the differences between planned dose-volume histogram (DVH) and reconstructed DVH from measurement was adopted and incorporated into patient-specific quality assurance (PSQA). However, it is difficult to develop a methodology allowing the evaluation of errors on DVHs accurately and quickly.

PURPOSE

To develop a DVH-based pretreatment PSQA for volumetric modulated arc therapy (VMAT) with combined deep learning (DL) and machine learning models to overcome the limitation of conventional gamma index (GI) and improve the efficiency of DVH-based PSQA.

METHODS

A DL model with a three-dimensional squeeze-and-excitation residual blocks incorporated into a modified U-net was developed to predict the measured PSQA DVHs of 208 head-and-neck (H&N) cancer patients underwent VMAT between 2018 and 2021 from two hospitals, in which 162 cases was randomly selected for training, 18 for validation, and 28 for testing. After evaluating the differences between treatment planning system (TPS) and PSQA DVHs predicted by DL model with multiple metrics, a pass or fail (PoF) classification model was developed using XGBoost algorithm. Evaluation of domain experts on dose errors between TPS and reconstructed PSQA DVHs was taken as ground truth for PoF classification model training.

RESULTS

The prediction model was able to achieve a good agreement between predicted, measured, and TPS doses. Quantitative evaluation demonstrated no significant difference between predicted PSQA dose and measured dose for target and OARs, except for D_mean of PTV6900 (p = 0.001), D₅₀ of PTV6000 (p = 0.014), D₂ of PTV5400 (p = 0.009), D₅₀ of left parotid (p = 0.015), and D_max of left inner ear (p = 0.007). The XGBoost model achieved an area under curves, accuracy, sensitivity, and specificity of 0.89 versus 0.88, 0.89 versus 0.86, 0. 71 versus 0.71, and 0.95 versus 0.91 with measured and predicted PSQA doses, respectively. The agreement between domain experts and the classification model was 86% for 28 test cases.

CONCLUSIONS

The successful prediction of PSQA doses and classification of PoF for H&N VMAT PSQA indicating that this DVH-based PSQA method is promising to overcome the limitations of GI and to improve the efficiency and accuracy of VMAT delivery.

Investigation of optimum minimum segment width on VMAT plan quality and deliverability: A comprehensive dosimetric and clinical evaluation using DVH analysis

Purpose

Minimum segment width (MSW) plays a fundamental role in the shaping of optimized apertures and creation of segments of varying sizes and shapes in complex radiotherapy treatment plans. The purpose of this work was to study the effect of MSW on dose distribution in patients planned with VMAT for various treatment sites using dose volume histogram (DVH) analysis.

Materials and methods

For the validation of optimum MSW, 125 clinical treatment plans were evaluated. Five groups were identified (brain, head and neck, thorax, pelvis, and extremity), and five cases were chosen from each group. For each case, five plans were created with different MSW (0.5, 0.8, 1.0, 1.25, and 1.5 cm). The quality of treatment plans created using different MSW were compared using dosimetric indicators such as target coverage (D₉₈—dose to 98% of the planning target volume (PTV), maximum dose (D₂—maximum dose to 2% of the PTV), monitor units (MU), and DVH parameters related to organs at risk (OAR). The effect of the MSW on delivery accuracy was quantitatively analyzed using the measured fluence utilizing ionization chamber‐based transmission detector and model‐based dose verification system. Traditional global gamma analysis (2%, 2 mm) and dose volume information was gathered for the PTV and organs at risk and compared for different MSWs.

Results

A total of 125 plans were created and compared across five groups. In terms of treatment plan quality, the plans using MSW of 0.5 cm was found to be superior in all groups. PTV coverage (D₉₈) decreased significantly (p < 0.05) as the MSW increased. Similarly, the maximum dose (D₂) was found to be increased significantly (p < 0.05) as the MSW increased from 0.5 cm, with MSW of 1.5 cm being the least in terms of plan quality for both PTVs and OARs. In terms of plan deliverability using DVH analysis, treatment planning system (TPS) compared to measured fluence, VMAT plans produced with MSW of 0.5 cm showed a better dosimetric index and a smaller deviation for both PTVs and OARs. The deliverability of the plans deteriorated as the MSW increased.

Conclusion

Dose volume histogram (DVH) analysis demonstrated that treatment plans with minimal MSW showed better plan quality and deliverability and provided clinical relevance as compared to gamma index analysis.

Validation of a secondary dose check tool against Monte Carlo and analytical clinical dose calculation algorithms in VMAT

PURPOSE

Patient-specific quality assurance (QA) is very important in radiotherapy, especially for patients with highly conformed treatment plans like VMAT plans. Traditional QA protocols for these plans are time-consuming reducing considerably the time available for patient treatments. In this work, a new MC-based secondary dose check software (SciMoCa) is evaluated and benchmarked against well-established TPS (Monaco and Pinnacle3 ) by means of treatment plans and dose measurements.

METHODS

Fifty VMAT plans have been computed using same calculation parameters with SciMoCa and the two primary TPSs. Plans were validated with measurements performed with a 3D diode detector (ArcCHECK) by translating patient plans to phantom geometry. Calculation accuracy was assessed by measuring point dose differences and gamma passing rates (GPR) from a 3D gamma analysis with 3%-2 mm criteria. Comparison between SciMoCa and primary TPS calculations was made using the same estimators and using both patient and phantom geometry plans.

RESULTS

TPS and SciMoCa calculations were found to be in very good agreement with validation measurements with average point dose differences of 0.7 ± 1.7% and -0.2 ± 1.6% for SciMoCa and two TPSs, respectively. Comparison between SciMoCa calculations and the two primary TPS plans did not show any statistically significant difference with average point dose differences compatible with zero within error for both patient and phantom geometry plans and GPR (98.0 ± 3.0% and 99.0 ± 3.0% respectively) well in excess of the typical 95 % clinical tolerance threshold.

CONCLUSION

This work presents results obtained with a significantly larger sample than other similar analyses and, to the authors' knowledge, compares SciMoCa with a MC-based TPS for the first time. Results show that a MC-based secondary patient-specific QA is a clinically viable, reliable, and promising technique, that potentially allows significant time saving that can be used for patient treatment and a per-plan basis QA that effectively complements traditional commissioning and calibration protocols.

DVH analysis using a transmission detector and model-based dose verification system as a comprehensive pretreatment QA tool for VMAT plans: Clinical experience and results

Purpose

Dose volume histogram (DVH)‐based analysis is utilized as a pretreatment quality assurance tool to determine clinical relevance from measured dose which is difficult in conventional gamma‐based analysis. In this study, we report our clinical experience with an ionization‐based transmission detector and model‐based verification system, using DVH analysis, as a comprehensive pretreatment QA tool for complex volumetric modulated arc therapy plans.

Methods and Materials

Seventy‐three subsequent treatment plans categorized into four clinical sites (Head and Neck, Thorax, Abdomen, and Pelvis) were evaluated. The average dose (D_mean) and dose received by 1% (D₁) of the planning target volumes (PTVs) and organs at risks (OARs) calculated using the treatment planning system (TPS) were compared to a computed (model‐based) and reconstructed dose, from the measured fluence, using DVH analysis. The correlation between gamma (3% 3 mm) and DVH‐based analysis for targets was evaluated. Furthermore, confidence and action limits for detector and verification systems were established.

Results

Linear regression confirmed an excellent correlation between TPS planned and computed dose using a model‐based verification system (r² = 1). The average percentage difference between TPS calculated and reconstructed dose for PTVs achieved using DVH analysis for each site is as follows: Head and Neck — 0.57 ± 2.8% (D_mean) and 2.6 ± 2.7% (D₁), Abdomen — 0.19 ± 2.8% and 1.64 ± 2.2%, Thorax — 0.24 ± 2.1% and 3.12 ± 2.8%, Pelvis 0.37 ± 2.4% and 1.16 ± 2.3%, respectively. The average percentage of passed gamma values achieved was above 95% for all cases. However, no correlation was observed between gamma passing rates and DVH difference (%) for PTVs (r² = 0.11). The results demonstrate a confidence limit of 5% (D_mean and D₁) for PTVs using DVH analysis for both computed and reconstructed dose distribution.

Conclusion

DVH analysis of treatment plan using a model‐based verification system and transmission detector provided useful information on clinical relevance for all cases and could be used as a comprehensive pretreatment patient‐specific QA tool.