Prediction of patient-specific quality assurance for volumetric modulated arc therapy using radiomics-based machine learning with dose distribution.

PURPOSE: We sought to develop machine learning models to predict the results of patient-specific quality assurance (QA) for volumetric modulated arc therapy (VMAT), which were represented by several dose-evaluation metrics-including the gamma passing rates (GPRs)-and criteria based on the radiomic features of 3D dose distribution in a phantom. METHODS: A total of 4,250 radiomic features of 3D dose distribution in a cylindrical dummy phantom for 140 arcs from 106 clinical VMAT plans were extracted. We obtained the following dose-evaluation metrics: GPRs with global and local normalization, the dose difference (DD) in 1% and 2% passing rates (DD1% and DD2%) for 10% and 50% dose threshold, and the distance-to-agreement in 1-mm and 2-mm passing rates (DTA1 mm and DTA2 mm) for 0.5%/mm and 1.0%.mm dose gradient threshold determined by measurement using a diode array in patient-specific QA. The machine learning regression models for predicting the values of the dose-evaluation metrics using the radiomic features were developed based on the elastic net (EN) and extra trees (ET) models. The feature selection and tuning of hyperparameters were performed with nested cross-validation in which four-fold cross-validation is used within the inner loop, and the performance of each model was evaluated in terms of the root mean square error (RMSE), the mean absolute error (MAE), and Spearman's rank correlation coefficient. RESULTS: The RMSE and MAE for the developed machine learning models ranged from <1% to nearly <10% depending on the dose-evaluation metric, the criteria, and dose and dose gradient thresholds used for both machine learning models. It was advantageous to focus on high dose region for predicating global GPR, DDs, and DTAs. For certain metrics and criteria, it was possible to create models applicable for patients' heterogeneity by training only with dose distributions in phantom. CONCLUSIONS: The developed machine learning models showed high performance for predicting dose-evaluation metrics especially for high dose region depending on the metric and criteria. Our results demonstrate that the radiomic features of dose distribution can be considered good indicators of the plan complexity and useful in predicting measured dose evaluation metrics.

Deep learning-based detection and classification of multi-leaf collimator modeling errors in volumetric modulated radiation therapy.

PURPOSE: The purpose of this study was to create and evaluate deep learning-based models to detect and classify errors of multi-leaf collimator (MLC) modeling parameters in volumetric modulated radiation therapy (VMAT), namely the transmission factor (TF) and the dosimetric leaf gap (DLG). METHODS: A total of 33 clinical VMAT plans for prostate and head-and-neck cancer were used, assuming a cylindrical and homogeneous phantom, and error plans were created by altering the original value of the TF and the DLG by ± 10, 20, and 30% in the treatment planning system (TPS). The Gaussian filters of σ = 0.5 $\sigma = 0.5$ and 1.0 were applied to the planar dose maps of the error-free plan to mimic the measurement dose map, and thus dose difference maps between the error-free and error plans were obtained. We evaluated 3 deep learning-based models, created to perform the following detections/classifications: (1) error-free versus TF error, (2) error-free versus DLG error, and (3) TF versus DLG error. Models to classify the sign of the errors were also created and evaluated. A gamma analysis was performed for comparison. RESULTS: The detection and classification of TF and DLG error were feasible for σ = 0.5 $\sigma = 0.5$ ; however, a considerable reduction of accuracy was observed for σ = 1.0 $\sigma = 1.0$ depending on the magnitude of error and treatment site. The sign of errors was detectable by the specifically trained models for σ = 0.5 $\sigma = 0.5$ and 1.0. The gamma analysis could not detect errors. CONCLUSIONS: We demonstrated that the deep learning-based models could feasibly detect and classify TF and DLG errors in VMAT dose distributions, depending on the magnitude of the error, treatment site, and the degree of mimicked measurement doses.

Verification of Qfix Encompass™ couch modeling using the Acuros XB algorithm and HypeArc™ using a high-spatial-resolution two-dimensional diode array.

We modeled the Qfix Encompass™ immobilization system and further verified the calculated dose distribution of the AcurosXB (AXB) dose calculation algorithm using SRS MapCHECKⓇ (SRSMC) in the HyperArc™ (HA) clinical plan. An Encompass system with a StereoPHAN™ QA phantom was scanned by SOMATOM go.Sim and imported to an Eclipse™ treatment planning system to create a treatment plan for Encompass modeling. The Encompass modeling was performed in the StereoPHAN with a pinpoint ion chamber for 6 MV and 6 MV flattening filter free (6 MV FFF), and 2 × 2 cm2, 4 × 4 cm2, and 6 × 6 cm2 irradiation field sizes. The dose calculation algorithm used was AXB ver. 15.5 with a 1.0 mm calculation grid size. The Hounsfield unit (HU) values of the Encompass modeling were set to 400, -100, -200, and -300 for Encompass, and -400, -600, -700, and -800 for the Encompass base. We evaluated the dose distribution after Encompass modeling by SRSMC using gamma analysis in 12 patients. We adopted HU values of -200 for Encompass, -800 for Encompass base for 6 MV, and -200 for Encompass and -700 for Encompass. Base for 6 MV FFF was adopted as the HU values for the Encompass modeling based on the measurement results. The proposed Encompass modeling resulted in a mean pass rate evaluation >98% for both 6 MV and 6 MV FFF when the 1%/1 mm criterion was used, demonstrating that the proposed HU value can be adopted to calculate more accurate dose distributions.

Multicomponent mathematical model for tumor volume calculation with setup error using single-isocenter stereotactic radiotherapy for multiple brain metastases.

We evaluated the tumor residual volumes considering six degrees-of-freedom (6DoF) patient setup errors in stereotactic radiotherapy (SRT) with multicomponent mathematical model using single-isocenter irradiation for brain metastases. Simulated spherical gross tumor volumes (GTVs) with 1.0 (GTV 1), 2.0 (GTV 2), and 3.0 (GTV 3)-cm diameters were used. The distance between the GTV center and isocenter (d) was set at 0-10 cm. The GTV was simultaneously translated within 0-1.0 mm (T) and rotated within 0°-1.0° (R) in the three axis directions using affine transformation. We optimized the tumor growth model parameters using measurements of non-small cell lung cancer cell lines' (A549 and NCI-H460) growth. We calculated the GTV residual volume at the irradiation's end using the physical dose to the GTV when the GTV size, d, and 6DoF setup error varied. The d-values that satisfy tolerance values (10%, 35%, and 50%) of the GTV residual volume rate based on the pre-irradiation GTV volume were determined. The larger the tolerance value set for both cell lines, the longer the distance to satisfy the tolerance value. In GTV residual volume evaluations based on the multicomponent mathematical model on SRT with single-isocenter irradiation, the smaller the GTV size and the larger the distance and 6DoF setup error, the shorter the distance that satisfies the tolerance value might need to be.

Evaluation of performance of pelvic CT-MR deformable image registration using two software programs.

We assessed the accuracy of deformable image registration (DIR) accuracy between CT and MR images using an open-source software (Elastix, from Utrecht Medical Center) and a commercial software (Velocity AI Ver. 3.2.0 from Varian Medical Systems, Palo Alto, CA, USA) software. Five male patients' pelvic regions were studied using publicly available CT, T1-weighted (T1w) MR, and T2-weighted (T2w) MR images. In the cost function of the Elastix, we used six DIR parameter settings with different regularization weights (Elastix0, Elastix0.01, Elastix0.1, Elastix1, Elastix10, and Elastix100). We used MR Corrected Deformable algorithm for Velocity AI. The Dice similarity coefficient (DSC) and mean distance to agreement (MDA) for the prostate, bladder, rectum and left and right femoral heads were used to evaluate DIR accuracy. Except for the bladder, most algorithms produced good DSC and MDA results for all organs. In our study, the mean DSCs for the bladder ranged from 0.75 to 0.88 (CT-T1w) and from 0.72 to 0.76 (CT-T2w). Similarly, the mean MDA ranges were 2.4 to 4.9 mm (CT-T1w), 4.6 to 5.3 mm (CT-T2w). For the Elastix, CT-T1w was outperformed CT-T2w for both DSCs and MDAs at Elastix0, Elastix0.01, and Elastix0.1. In the case of Velocity AI, no significant differences in DSC and MDA of all organs were observed. This implied that the DIR accuracy of CT and MR images might differ depending on the sequence used.

Impact of feature selection methods and subgroup factors on prognostic analysis with CT-based radiomics in non-small cell lung cancer patients.

BACKGROUND: Radiomics is a new technology to noninvasively predict survival prognosis with quantitative features extracted from medical images. Most radiomics-based prognostic studies of non-small-cell lung cancer (NSCLC) patients have used mixed datasets of different subgroups. Therefore, we investigated the radiomics-based survival prediction of NSCLC patients by focusing on subgroups with identical characteristics. METHODS: A total of 304 NSCLC (Stages I-IV) patients treated with radiotherapy in our hospital were used. We extracted 107 radiomic features (i.e., 14 shape features, 18 first-order statistical features, and 75 texture features) from the gross tumor volume drawn on the free breathing planning computed tomography image. Three feature selection methods [i.e., test-retest and multiple segmentation (FS1), Pearson's correlation analysis (FS2), and a method that combined FS1 and FS2 (FS3)] were used to clarify how they affect survival prediction performance. Subgroup analysis for each histological subtype and each T stage applied the best selection method for the analysis of All data. We used a least absolute shrinkage and selection operator Cox regression model for all analyses and evaluated prognostic performance using the concordance-index (C-index) and the Kaplan-Meier method. For subgroup analysis, fivefold cross-validation was applied to ensure model reliability. RESULTS: In the analysis of All data, the C-index for the test dataset is 0.62 (FS1), 0.63 (FS2), and 0.62 (FS3). The subgroup analysis indicated that the prediction model based on specific histological subtypes and T stages had a higher C-index for the test dataset than that based on All data (All data, 0.64 vs. SCCall, 060; ADCall, 0.69; T1, 0.68; T2, 0.65; T3, 0.66; T4, 0.70). In addition, the prediction models unified for each T stage in histological subtype showed a different trend in the C-index for the test dataset between ADC-related and SCC-related models (ADCT1-ADCT4, 0.72-0.83; SCCT1-SCCT4, 0.58-0.71). CONCLUSIONS: Our results showed that feature selection methods moderately affected the survival prediction performance. In addition, prediction models based on specific subgroups may improve the prediction performance. These results may prove useful for determining the optimal radiomics-based predication model.

Development of a dynamic deformable thorax phantom for the quality management of deformable image registration.

The purpose of this study was to develop a novel dynamic deformable thorax phantom for deformable image registration (DIR) quality assurance (QA) and to verify as a tool for commissioning and DIR QA. The phantom consists of a base phantom, an inner phantom, and a motor-derived piston. The base phantom is an acrylic cylinder phantom with a diameter of 180 mm. The inner phantom consists of deformable, 20 mm thick disk-shaped sponges. To evaluate the physical characteristics of the phantom, we evaluated its image quality and deformation. DIR accuracies were evaluated using the three types of commercially DIR software (MIM, RayStation, and Velocity AI) to test the feasibility of this phantom. We used different DIR parameters to test the impact of parameters on DIR accuracy in various phantom settings. To evaluate DIR accuracy, a target registration error (TRE) was calculated using the anatomical landmark points. The three locations (i.e., distal, middle, and proximal positions) had different displacement amounts. This result indicated that the inner phantom was not moved but deformed. In cases with different phantom settings and marker settings, the ranges of the average TRE were 0.63-15.60 mm (MIM). In cases with different DIR parameters settings, the ranges of the average TRE were as follows: 0.73-7.10 mm (MIM), 8.25-8.66 mm (RayStation), and 8.26-8.43 mm (Velocity). These results suggest that our phantom could evaluate the detailed DIR behaviors with TRE. Therefore, this is indicative of the potential usefulness of our phantom in DIR commissioning and QA.

Homology-based radiomic features for prediction of the prognosis of lung cancer based on CT-based radiomics.

PURPOSE: Radiomics is a new technique that enables noninvasive prognostic prediction by extracting features from medical images. Homology is a concept used in many branches of algebra and topology that can quantify the contact degree. In the present study, we developed homology-based radiomic features to predict the prognosis of non-small-cell lung cancer (NSCLC) patients and then evaluated the accuracy of this prediction method. METHODS: Four datasets were used: two to provide training and test data and two for the selection of robust radiomic features. All the datasets were downloaded from The Cancer Imaging Archive (TCIA). In two-dimensional cases, the Betti numbers consist of two values: b0 (zero-dimensional Betti number), which is the number of isolated components, and b1 (one-dimensional Betti number), which is the number of one-dimensional or "circular" holes. For homology-based evaluation, computed tomography (CT) images must be converted to binarized images in which each pixel has two possible values: 0 or 1. All CT slices of the gross tumor volume were used for calculating the homology histogram. First, by changing the threshold of the CT value (range: -150 to 300 HU) for all its slices, we developed homology-based histograms for b0 , b1 , and b1 /b0 using binarized images. All histograms were then summed, and the summed histogram was normalized by the number of slices. 144 homology-based radiomic features were defined from the histogram. To compare the standard radiomic features, 107 radiomic features were calculated using the standard radiomics technique. To clarify the prognostic power, the relationship between the values of the homology-based radiomic features and overall survival was evaluated using LASSO Cox regression model and the Kaplan-Meier method. The retained features with nonzero coefficients calculated by the LASSO Cox regression model were used for fitting the regression model. Moreover, these features were then integrated into a radiomics signature. An individualized rad score was calculated from a linear combination of the selected features, which were weighted by their respective coefficients. RESULTS: When the patients in the training and test datasets were stratified into high-risk and low-risk groups according to the rad scores, the overall survival of the groups was significantly different. The C-index values for the homology-based features (rad score), standard features (rad score), and tumor size were 0.625, 0.603, and 0.607, respectively, for the training datasets and 0.689, 0.668, and 0.667 for the test datasets. This result showed that homology-based radiomic features had slightly higher prediction power than the standard radiomic features. CONCLUSIONS: Prediction performance using homology-based radiomic features had a comparable or slightly higher prediction power than standard radiomic features. These findings suggest that homology-based radiomic features may have great potential for improving the prognostic prediction accuracy of CT-based radiomics. In this result, it is noteworthy that there are some limitations.