Generating 3D images of VMAT plans for predictive models and activation maps associated with plan deliverability.

Intensity modulation with dynamic multi-leaf collimator (MLC) and monitor unit (MU) changes across control points (CPs) characterizes volumetric modulated arc therapy (VMAT). The increased uncertainty in plan deliverability required patient-specific quality assurance (PSQA), which remained inefficient upon Quality Assurance (QA) failure. To prevent waste before QA, plan complexity metrics (PCMs) and machine learning models with the metrics were generated, which were lack of providing CP-specific information upon QA failures. By generating 3D images from digital imaging and comminications in medicine in radiation therapy (DICOM RT) plan, we proposed a predictive model that can estimate the deliverability of VMAT plans and visualize CP-specific regions associated with plan deliverability. The patient cohort consisted of 259 and 190 cases for left- and right-breast VMAT treatments, which were split into 235 and 166 cases for training and 24 cases from each treatment for testing the networks. Three-channel 3D images generated from DICOM RT plans were fed into a DenseNet-based deep learning network. To reflect VMAT plan complexity as an image, the first two channels described MLC and MU variations between two consecutive CPs, while the last channel assigned the beam field size. The network output was defined as binary classified PSQA results, indicating deliverability. The predictive performance was assessed by accuracy, sensitivity, specificity, F1-score, and area under the curve (AUC). The gradient-weighted class activation map (Grad-CAM) highlighted the regions of CPs in VMAT plans associated with deliverability, compared against PCMs by Spearman correlation. The DenseNet-based predictive model yielded AUCs of 92.2% and 93.8%, F1-scores of 97.0% and 93.8% and accuracies of 95.8% and 91.7% for the left- and right-breast VMAT cases. Additionally, the specificity of 87.5% for both cases indicated that the predictive model accurately detected QA failing cases. The activation maps significantly differentiated QA failing-labeled from passing-labeled classes for the non-deliverable cases. The PCM with the highest correlation to the Grad-CAM varied from patient cases, implying that plan deliverability would be considered patient-specific. This work demonstrated that the deep learning-based network based on visualization of dynamic VMAT plan information successfully predicted plan deliverability, which also provided control-point specific planning parameter information associated with plan deliverability in a patient-specific manner.

Cho H ，Lee JS ，Kim JS ，Kim D ，Chang JS ，Byun HK ，Lee IJ ，Kim YB ，Kim C ，Lee H ，Kim H ... -  《-》

Texture analysis on the fluence map to evaluate the degree of modulation for volumetric modulated arc therapy.

Park SY ，Kim IH ，Ye SJ ，Carlson J ，Park JM ... -  《-》

Machine learning-generated decision boundaries for prediction and exploration of patient-specific quality assurance failures in stereotactic radiosurgery plans.

Stereotactic radiosurgery (SRS) is a form of radiotherapy treatment during which high radiation dose is delivered in a single or few fractions. These treatments require highly conformal plans with steep dose gradients, which can result in an increase in plan complexity prompting the need for stringent pretreatment patient-specific quality assurance (QA) measurements to ensure the planned and measured dose distributions agree within clinical standards. Complexity scores and machine learning (ML) techniques may help with prediction of QA outcomes; however interpretability and usability of those results continues to be an area of study. This study investigates the use of plan complexity metrics as input for an ML model to allow for prediction of QA outcomes for SRS plans as measured via three-dimension (3D) phantom dose verification. Explorations into interpretability and predictive ability, as well as a prospective in-clinic implementation using the resulting model were performed. Four hundred ninety-eight plans (1571 volumetric modulated arc therapy arcs) were processed via in-house script to generate several complexity scores. 3D phantom dose verification measurement results were extracted and classified as pass or failure (with failures defined as below 95% voxel agreement passing 3%/1-mm gamma criteria with 10% threshold,) and 1472 of the arcs were split into training and testing sets, with 99 arcs as a sequential holdout set. A z-score scaler was trained on the training set and used to scale all other sets. Variations of multi-leaf collimator (MLC) leaf movement variability, aperture complexity, and leaf size, and monitor unit (MU) at control point weighted target area scores were used as input to a support vector classifier to generate a series of 1D, 2D, and 5D decision boundaries. The best performing 5D model was then used within a prospective in-clinic study providing predictions to physicists prior to ordering 3D phantom dose verification measurements for 38 patient plans (112 arcs). The decision to order 3D phantom dose verification measurements was recorded before and after prediction. Best performing 1D threshold and 2D prediction models with best performance produced a QA failure recall and QA passing recall of 1.00 and 0.55, and 0.82 and 0.82, respectively. Best performing 5D prediction model produced a QA failure recall (sensitivity) of 1.00 and QA passing recall (specificity) of 0.72. This model was then used within a prospective in-clinic study providing predictions to physicists prior to ordering 3D phantom dose verification measurements and achieved a QA failure recall of 1.00 and QA passing recall of 0.58. The decision to order 3D phantom dose verification measurements was recorded before and after measurement. A single initially unidentified failing plan of the prospective cohort was successfully predicted to fail by the model. Implementation of complexity score-based prediction models for SRS would allow for support of a clinician's decision to reduce time spent performing QA measurements and avoid patient treatment delays (i.e., in case of QA failure).

Braun J ，Quirk S ，Tchistiakova E 《-》

Dosimetric quality, accuracy, and deliverability of modulated radiotherapy treatments for spinal metastases.

Cancer often metastasizes to the vertebra, and such metastases can be treated successfully using simple, static posterior or opposed-pair radiation fields. However, in some cases, including when re-irradiation is required, spinal cord avoidance becomes necessary and more complex treatment plans must be used. This study evaluated 16 sample intensity-modulated radiation therapy (IMRT) and volumetric-modulated arc therapy (VMAT) treatment plans designed to treat 6 typical vertebral and paraspinal volumes using a standard prescription, with the aim of investigating the advantages and limitations of these treatment techniques and providing recommendations for their optimal use in vertebral treatments. Treatment plan quality and beam complexity metrics were evaluated using the Treatment And Dose Assessor (TADA) code. A portal-imaging-based quality assurance (QA) system was used to evaluate treatment delivery accuracy, and radiochromic film measurements were used to provide high-resolution verification of treatment plan dose accuracy, especially in the steep dose gradient regions between each vertebral target and spinal cord. All treatment modalities delivered approximately the same doses and the same levels of dose heterogeneity to each planning target volume (PTV), although the minimum PTV doses in the vertebral plans were substantially lower than the prescription, because of the requirement that the plans meet a strict constraint on the dose to the spinal cord and cord planning risk volume (PRV). All plans met required dose constraints on all organs at risk, and all measured PTV-cord dose gradients were steeper than planned. Beam complexity analysis suggested that the IMRT treatment plans were more deliverable (less complex, leading to greater QA success) than the VMAT treatment plans, although the IMRT plans also took more time to deliver. The accuracy and deliverability of VMAT treatment plans were found to be substantially increased by limiting the number of monitor units (MU) per beam at the optimization stage, and thereby limiting beam modulation complexity. The VMAT arcs that were optimized with MU limitation had higher QA pass rates as well as higher modulation complexity scores (less complexity), lower modulation indices (less modulation), lower MU per beam, larger beam segments, and fewer small apertures than the VMAT arcs that were optimized without MU limitation. It is recommended that VMAT treatments for vertebral volumes, where the PTV abuts or surrounds the spinal cord, should be optimized with MU limitation. IMRT treatments may be preferable to the VMAT treatments, for dosimetry and deliverability reasons, but may be inappropriate for some patients because of their increased treatment delivery time.

Kairn T ，Papworth D ，Crowe SB ，Anderson J ，Christie DR ... -  《-》

Plan complexity metrics for head and neck VMAT competition plans.

Previous plan competitions have largely focused on dose metric assessments. However, whether the submitted plans were realistic and reasonable from a quality assurance (QA) perspective remains unclear. This study aimed to investigate the relationship between aperture-based plan complexity metrics (PCM) in volumetric modulated arc therapy (VMAT) competition plans and clinical treatment plans verified through patient-specific QA (PSQA). In addition, the association of PCMs with plan quality was examined. A head and neck (HN) plan competition was held for Japanese institutions from June 2019 to July 2019, in which 210 competition plans were submitted. Dose distribution quality was quantified based on dose-volume histogram (DVH) metrics by calculating the dose distribution plan score (DDPS). Differences in PCMs between the two VMAT treatment plan groups (HN plan competitions held in Japan and clinically accepted HN VMAT plans through PSQA) were investigated. The mean (± standard deviation) DDPS for the 98 HN competition plans was 158.5 ± 20.6 (maximum DDPS: 200). DDPS showed a weak correlation with PCMs with a maximum r of 0.45 for monitor unit (MU); its correlation with some PCMs was "very weak." Significant differences were found in some PCMs between plans with the highest 20% DDPSs and the remaining plans. The clinical VMAT and competition plans revealed similar distributions for some PCMs. Deviations in PCMs for the two groups were comparable, indicating considerable variability among planners regarding planning skills. The plan complexity for HN VMAT competition plans increased for high-quality plans, as shown by the dose distribution. Direct comparison of PCMs between competition plans and clinically accepted plans showed that the submitted HN VMAT competition plans were realistic and reasonable from the QA perspective. This evaluation may provide a set of criteria for evaluating plan quality in plan competitions.

Okamoto H ，Wakita A ，Tani K ，Kito S ，Kurooka M ，Kodama T ，Tohyama N ，Fujita Y ，Nakamura S ，Iijima K ，Chiba T ，Nakayama H ，Murata M ，Goka T ，Igaki H ... -  《-》