Unifying gamma passing rates in patient-specific QA for VMAT lung cancer treatment based on data assimilation.

This study aimed to identify systematic errors in measurement-, calculation-, and prediction-based patient-specific quality assurance (PSQA) methods for volumetric modulated arc therapy (VMAT) on lung cancer and to standardize the gamma passing rate (GPR) by considering systematic errors during data assimilation. This study included 150 patients with lung cancer who underwent VMAT. VMAT plans were generated using a collapsed-cone algorithm. For measurement-based PSQA, ArcCHECK was employed. For calculation-based PSQA, Acuros XB was used to recalculate the plans. In prediction-based PSQA, GPR was forecasted using a previously developed GPR prediction model. The representative GPR value was estimated using the least-squares method from the three PSQA methods for each original plan. The unified GPR was computed by adjusting the original GPR to account for systematic errors. The range of limits of agreement (LoA) were assessed for the original and unified GPRs based on the representative GPR using Bland-Altman plots. For GPR (3%/2 mm), original GPRs were 94.4 ± 3.5%, 98.6 ± 2.2% and 93.3 ± 3.4% for measurement-, calculation-, and prediction-based PSQA methods and the representative GPR was 95.5 ± 2.0%. Unified GPRs were 95.3 ± 2.8%, 95.4 ± 3.5% and 95.4 ± 3.1% for measurement-, calculation-, and prediction-based PSQA methods, respectively. The range of LoA decreased from 12.8% for the original GPR to 9.5% for the unified GPR across all three PSQA methods. The study evaluated unified GPRs that corrected for systematic errors. Proposing unified criteria for PSQA can enhance safety regardless of the methods used.

Applications of artificial intelligence for machine- and patient-specific quality assurance in radiation therapy: current status and future directions.

Machine- and patient-specific quality assurance (QA) is essential to ensure the safety and accuracy of radiotherapy. QA methods have become complex, especially in high-precision radiotherapy such as intensity-modulated radiation therapy (IMRT) and volumetric modulated arc therapy (VMAT), and various recommendations have been reported by AAPM Task Groups. With the widespread use of IMRT and VMAT, there is an emerging demand for increased operational efficiency. Artificial intelligence (AI) technology is quickly growing in various fields owing to advancements in computers and technology. In the radiotherapy treatment process, AI has led to the development of various techniques for automated segmentation and planning, thereby significantly enhancing treatment efficiency. Many new applications using AI have been reported for machine- and patient-specific QA, such as predicting machine beam data or gamma passing rates for IMRT or VMAT plans. Additionally, these applied technologies are being developed for multicenter studies. In the current review article, AI application techniques in machine- and patient-specific QA have been organized and future directions are discussed. This review presents the learning process and the latest knowledge on machine- and patient-specific QA. Moreover, it contributes to the understanding of the current status and discusses the future directions of machine- and patient-specific QA.

Protocol of a phase II study to evaluate the efficacy and safety of deep-inspiration breath-hold daily online adaptive radiotherapy for centrally located lung tumours (PUDDING study).

BACKGROUND: Centrally located lung tumours present a challenge because of their tendency to exhibit symptoms such as airway obstruction, atelectasis, and bleeding. Surgical resection of these tumours often requires sacrificing the lungs, making definitive radiotherapy the preferred alternative to avoid pneumonectomy. However, the proximity of these tumours to mediastinal organs at risk increases the potential for severe adverse events. To mitigate this risk, we propose a dual-method approach: deep inspiration breath-hold (DIBH) radiotherapy combined with adaptive radiotherapy. The aim of this single-centre, single-arm phase II study is to investigate the efficacy and safety of DIBH daily online adaptive radiotherapy. METHODS: Patients diagnosed with centrally located lung tumours according to the International Association for the Study of Lung Cancer recommendations, are enrolled and subjected to DIBH daily online adaptive radiotherapy. The primary endpoint is the one-year cumulative incidence of grade 3 or more severe adverse events, as classified by the Common Terminology Criteria for Adverse Events (CTCAE v5.0). DISCUSSION: Delivering definitive radiotherapy for centrally located lung tumours presents a dilemma between ensuring optimal dose coverage for the planning target volume and the associated increased risk of adverse events. DIBH provides measurable dosimetric benefits by increasing the normal lung volume and distancing the tumour from critical mediastinal organs at risk, leading to reduced toxicity. DIBH adaptive radiotherapy has been proposed as an adjunct treatment option for abdominal and pelvic cancers. If the application of DIBH adaptive radiotherapy to centrally located lung tumours proves successful, this approach could shape future phase III trials and offer novel perspectives in lung tumour radiotherapy. TRIAL REGISTRATION: Registered at the Japan Registry of Clinical Trials (jRCT; https://jrct.niph.go.jp/ ); registration number: jRCT1052230085 ( https://jrct.niph.go.jp/en-latest-detail/jRCT1052230085 ).

Influence of dose calculation algorithms on the helical diode array using volumetric-modulated arc therapy for small targets.

BACKGROUND: For patient-specific quality assurance (PSQA) for small targets, the dose resolution can change depending on the characteristics of the dose calculation algorithms. PURPOSE: This study aimed to evaluate the influence of the dose calculation algorithms Acuros XB (AXB), anisotropic analytical algorithm (AAA), photon Monte Carlo (pMC), and collapsed cone (CC) on a helical diode array using volumetric-modulated arc therapy (VMAT) for small targets. MATERIALS AND METHODS: ArcCHECK detectors were inserted with a physical depth of 2.9 cm from the surface. To evaluate the influence of the dose calculation algorithms for small targets, rectangular fields of 2×100, 5×100, 10×100, 20×100, 50×100, and 100×100 mm2 were irradiated and measured using ArcCHECK with TrueBeam STx. A total of 20 VMAT plans for small targets, including the clinical sites of 19 brain metastases and one spine, were also evaluated. The gamma passing rates (GPRs) were evaluated for the rectangular fields and the 20 VMAT plans using AXB, AAA, pMC, and CC. RESULTS: For rectangular fields of 2×100 and 5×100 mm2 , the GPR at 3%/2 mm of AXB was < 50% because AXB resulted in a coarser dose resolution with narrow beams. For field sizes > 10×100 mm2, the GPR at 3%/2 mm was > 88.1% and comparable for all dose calculation algorithms. For the 20 VMAT plans, the GPRs at 3%/2 mm were 79.1 ± 15.7%, 93.2 ± 5.8%, 94.9 ± 4.1%, and 94.5 ± 4.1% for AXB, AAA, pMC, and CC, respectively. CONCLUSION: The behavior of the dose distribution on the helical diode array differed depending on the dose calculation algorithm for small targets. Measurements using ArcCHECK for VMAT with small targets can have lower GPRs owing to the coarse dose resolution of AXB around the detector area.

Impact of planning organ at risk volume margins and matching method on late gastrointestinal toxicity in moderately hypofractionated IMRT for locally advanced pancreatic ductal adenocarcinoma.

BACKGROUND: This study examined the differences in late gastrointestinal (GI) toxicities in moderately hypofractionated intensity-modulated radiation therapy (IMRT) for locally advanced pancreatic ductal adenocarcinoma (LA-PDAC) by changing the planning organs at risk volume (PRV) margin and the target matching method and assessed the causes of adverse events. METHODS: We examined 37 patients with LA-PDAC who underwent moderately hypofractionated IMRT between 2016 and 2020 at our institution; 23 patients were treated with wide PRV margins and soft tissue matching (Protocol A) and 14 with narrow PRV margins and fiducial marker matching (Protocol B). The GI toxicities, local control (LC) rate, and overall survival (OS) were assessed for each protocol. The initially planned and daily doses to the gross tumor volume (GTV), stomach, and duodenum, reproduced from cone-beam computed tomography, were evaluated. RESULTS: The late GI toxicity rate of grades 3-4 was higher in Protocol B (42.9%) than in Protocol A (4.3%). Although the 2-year LC rates were significantly higher in Protocol B (90.0%) than in Protocol A (33.3%), no significant difference was observed in OS rates. In the initial plan, no deviations were found for the stomach and duodenum from the dose constraints in either protocol. In contrast, daily dose evaluation for the stomach to duodenal bulb revealed that the frequency of deviation of V3 Gy per session was 44.8% in Protocol B, which was significantly higher than the 24.3% in Protocol A. CONCLUSIONS: Reducing PRV margins with fiducial marker matching increased GI toxicities in exchange for improved LC. Daily dose analysis indicated the trade-off between the GTV dose coverage and the irradiated doses to the GI. This study showed that even with strict matching methods, the PRV margin could not be reduced safely because of GI inter-fractional error, which is expected to be resolved with online adaptive radiotherapy.

Identification of reproducible radiomic features from on-board volumetric images: A multi-institutional phantom study.

BACKGROUND: Radiomics analysis using on-board volumetric images has attracted research attention as a method for predicting prognosis during treatment; however, the lack of standardization is still one of the main concerns. PURPOSE: This study investigated the factors that influence the reproducibility of radiomic features extracted from on-board volumetric images using an anthropomorphic radiomics phantom. Furthermore, a phantom experiment was conducted with different treatment machines from multiple institutions as external validation to identify reproducible radiomic features. METHODS: The phantom was designed to be 35 × 20 × 20 cm with eight types of heterogeneous spheres (⌀ = 1, 2, and 3 cm). On-board volumetric images were acquired using 15 treatment machines from eight institutions. Of these, kilovoltage cone-beam computed tomography (kV-CBCT) image data acquired from four treatment machines at one institution were used as an internal evaluation dataset to explore the reproducibility of radiomic features. The remaining image data, including kV-CBCT, megavoltage-CBCT (MV-CBCT), and megavoltage computed tomography (MV-CT) provided by seven different institutions (11 treatment machines), were used as an external validation dataset. A total of 1,302 radiomic features, including 18 first-order, 75 texture, 465 (i.e., 93 × 5) Laplacian of Gaussian (LoG) filter-based, and 744 (i.e., 93 × 8) wavelet filter-based features, were extracted within the spheres. The intraclass correlation coefficient (ICC) was calculated to explore feature repeatability and reproducibility using an internal evaluation dataset. Subsequently, the coefficient of variation (COV) was calculated to validate the feature variability of external institutions. An absolute ICC exceeding 0.85 or COV under 5% was considered indicative of a highly reproducible feature. RESULTS: For internal evaluation, ICC analysis showed that the median percentage of radiomic features with high repeatability was 95.2%. The ICC analysis indicated that the median percentages of highly reproducible features for inter-tube current, reconstruction algorithm, and treatment machine were decreased by 20.8%, 29.2%, and 33.3%, respectively. For external validation, the COV analysis showed that the median percentage of reproducible features was 31.5%. A total of 16 features, including nine LoG filter-based and seven wavelet filter-based features, were indicated as highly reproducible features. The gray-level run-length matrix (GLRLM) was classified as containing the most frequent features (N = 8), followed by the gray-level dependence matrix (N = 7) and gray-level co-occurrence matrix (N = 1) features. CONCLUSIONS: We developed the standard phantom for radiomics analysis of kV-CBCT, MV-CBCT, and MV-CT images. With this phantom, we revealed that the differences in the treatment machine and image reconstruction algorithm reduce the reproducibility of radiomic features from on-board volumetric images. Specifically, the most reproducible features for external validation were LoG or wavelet filter-based GLRLM features. However, the acceptability of the identified features should be examined in advance at each institution before applying the findings to prognosis prediction.

Development of independent dose verification plugin using Eclipse scripting API for brachytherapy.

In this study, an independent dose verification plugin (DVP) using the Eclipse Scripting Application Programming Interface (ESAPI) for brachytherapy was developed. The DVP was based on the general 2D formalism reported in AAPM-TG43U1. The coordinate and orientation of each source position were extracted from the translation matrix acquired from the treatment planning system (TPS), and the distance between the source and verification point (r) was calculated. Moreover, the angles subtended by the center-tip and tip-tip of the hypothetical line source with respect to the verification point (θ and ß) were calculated. With r, θ, ß and the active length of the source acquired from the TPS, the geometry function was calculated. As the TPS calculated the radial dose function, g(r), and 2D anisotropy function, F(r,θ), by interpolating and extrapolating the corresponding table stored in the TPS, the DVP calculated g(r) and F(r,θ) independently from equations fitted with the Monte Carlo data. The relative deviation of the fitted g(r) and F(r,θ) for the GammaMed Plus HDR 192Ir source was 0.5% and 0.9%, respectively. The acceptance range of the relative dose difference was set to ±1.03% based on the relative deviation between the fitted functions and Monte Carlo data, and the linear error propagation law. For 64 verification points from sixteen plans, the mean of absolute values of the relative dose difference was 0.19%. The standard deviation (SD) of the relative dose difference was 0.17%. The DVP maximizes efficiency and minimizes human error for the brachytherapy plan check.

Dosiomic feature comparison between dose-calculation algorithms used for lung stereotactic body radiation therapy.

To evaluate the reproducibility of dose-based radiomic (dosiomic) features between dose-calculation algorithms for lung stereotactic body radiation therapy (SBRT). We analyzed 105 patients with early-stage non-small cell lung cancer who underwent lung SBRT between March 2011 and December 2017. Radiation doses of 48, 60, and 70 Gy were prescribed to the isocenter in 4-8 fractions. Dose calculations were performed using X-ray voxel Monte Carlo (XVMC) on the iPlan radiation treatment planning system (RTPS). Thereafter, the radiation doses were recalculated using the Acuros XB (AXB) and analytical anisotropic algorithm (AAA) on the Eclipse RTPS while maintaining the XVMC-calculated monitor units and beam arrangements. A total of 6808 dosiomic features were extracted without preprocessing (112 shape, 144 first-order, and 600 texture features) or with wavelet filters to eight decompositions (1152 first-order and 4800 texture features). Features with absolute pairwise concordance correlation coefficients-|CCcon|-values exceeding or equaling 0.85 were considered highly reproducible. Subgroup analyses were performed considering the wavelet filters and prescribed doses. The numbers of highly reproducible first-order and texture features were 34.8%, 26.9%, and 31.0% for the XVMC-AXB, XVMC-AAA, and AXB-AAA pairs, respectively. The maximum difference between the mean |CCcon| values was 0.70 and 0.11 for the subgroup analyses of wavelet filters and prescribed dose, respectively. The application of wavelet filter-based dosiomic analyses may be limited when using different types of dose-calculation algorithms for lung SBRT.

Vulnerabilities of radiomic features to respiratory motion on four-dimensional computed tomography-based average intensity projection images: A phantom study.

PURPOSE: To evaluate the influence of respiratory motion on the robustness of radiomic features on four-dimensional computed tomography (4DCT)-based average intensity projection (AIP) images by employing an anthropomorphic chest phantom. METHODS: Three spherical objects (φ30 mm), namely, acrylic (100 Hounsfield unit [HU], homogeneous), rubber (-140 HU, homogeneous), and cork (-630 HU, heterogeneous), were moved with motion amplitudes of 0, 1, 2.5, 4, 6, 8, and 10 mm in the phantom, and 4DCT scans were repeated at four different locations. Thereafter, the AIP images were generated considering the average of the 10 respiratory phases of the 4DCT images. Further, the targets were manually delineated on the AIP images in the lung window setting. A total of 851 radiomic features, including 107 unfiltered features and 744 wavelet filter-based features, were extracted from the region of interest for each material. The feature robustness among the different target motion amplitude (ε) was evaluated by normalizing the feature variability of the target motion relative to the variability of data from 573 patients with early-stage non-small cell lung cancer. The features with absolute ε values ≤0.5 were considered highly robust to target motions. RESULTS: The percentage of robust unfiltered and wavelet filter-based features with a motion amplitude of 1 mm was greater than 83.2% and 93.4%, respectively; however, the percentage decreased by more than 24.3% and 17.6%, respectively, for motion amplitudes greater than 2.5 mm. The movement of cork had a small effect on the feature robustness compared to that of acrylic and rubber, regardless of the target motion amplitudes. CONCLUSIONS: Our phantom study demonstrated that target motion amplitudes ≤1 mm led to the robustness of radiomic features on the 4DCT-based AIP images of thoracic regions. The frequency components and directions of the wavelet filters may be essential factors in 4DCT-based radiomic analysis.

Chk1 suppression leads to a reduction in the enhanced radiation-induced invasive capability on breast cancer cells.

Radiation therapy is generally effective for treating breast cancers. However, approximately 30% of patients with breast cancer experience occasional post-treatment local and distant metastasis. Low-dose (0.5 Gy) irradiation is a risk factor that promotes the invasiveness of breast cancers. Although an inhibitor of checkpoint kinase 1 (Chk1) suppresses the growth and motility of breast cancer cell lines, no study has investigated the effects of the combined use of a Chk1 inhibitor and radiation on cancer metastasis. Here, we addressed this question by treating the human breast cancer cell line MDA-MB-231 (in vitro) and mouse mammary tumor cell line 4 T1 (in vitro and in vivo) with γ-irradiation and the Chk1 inhibitor PD407824. Low-dose γ-irradiation promoted invasiveness, which was suppressed by PD407824. Comprehensive gene expression analysis revealed that low-dose γ-irradiation upregulated the mRNA and protein levels of S100A4, the both of which were downregulated by PD407824. We conclude that PD407824 suppresses the expression of S100A4. As the result, γ-irradiation-induced cell invasiveness were inhibited.

Multi-institutional dose-segmented dosiomic analysis for predicting radiation pneumonitis after lung stereotactic body radiation therapy.

PURPOSE: To predict radiation pneumonitis (RP) grade 2 or worse after lung stereotactic body radiation therapy (SBRT) using dose-based radiomic (dosiomic) features. METHODS: This multi-institutional study included 247 early-stage nonsmall cell lung cancer patients who underwent SBRT with a prescribed dose of 48-70 Gy at an isocenter between June 2009 and March 2016. Ten dose-volume indices (DVIs) were used, including the mean lung dose, internal target volume size, and percentage of entire lung excluding the internal target volume receiving greater than x Gy (x = 5, 10, 15, 20, 25, 30, 35, and 40). A total of 6,808 dose-segmented dosiomic features, such as shape, first order, and texture features, were extracted from the dose distribution. Patients were randomly partitioned into two groups: model training (70%) and test datasets (30%) over 100 times. Dosiomic features were converted to z-scores (standardized values) with a mean of zero and a standard deviation (SD) of one to put different variables on the same scale. The feature dimension was reduced using the following methods: interfeature correlation based on Spearman's correlation coefficients and feature importance based on a light gradient boosting machine (LightGBM) feature selection function. Three different models were developed using LightGBM as follows: (a) a model with ten DVIs (DVI model), (b) a model with the selected dosiomic features (dosiomic model), and (c) a model with ten DVIs and selected dosiomic features (hybrid model). Suitable hyperparameters were determined by searching the largest average area under the curve (AUC) value in the receiver operating characteristic curve (ROC-AUC) via stratified fivefold cross-validation. Each of the final three models with the closest the ROC-AUC value to the average ROC-AUC value was applied to the test datasets. The classification performance was evaluated by calculating the ROC-AUC, AUC in the precision-recall curve (PR-AUC), accuracy, precision, recall, and f1-score. The entire process was repeated 100 times with randomization, and 100 individual models were developed for each of the three models. Then the mean value and SD for the 100 random iterations were calculated for each performance metric. RESULTS: Thirty-seven (15.0%) patients developed RP after SBRT. The ROC-AUC and PR-AUC values in the DVI, dosiomic, and hybrid models were 0.660 ± 0.054 and 0.272 ± 0.052, 0.837 ± 0.054 and 0.510 ± 0.115, and 0.846 ± 0.049 and 0.531 ± 0.116, respectively. For each performance metric, the dosiomic and hybrid models outperformed the DVI models (P < 0.05). Texture-based dosiomic feature was confirmed as an effective indicator for predicting RP. CONCLUSIONS: Our dose-segmented dosiomic approach improved the prediction of the incidence of RP after SBRT.

Application and limitation of radiomics approach to prognostic prediction for lung stereotactic body radiotherapy using breath-hold CT images with random survival forest: A multi-institutional study.

PURPOSE: To predict local recurrence (LR) and distant metastasis (DM) in early stage non-small cell lung cancer (NSCLC) patients after stereotactic body radiotherapy (SBRT) in multiple institutions using breath-hold computed tomography (CT)-based radiomic features with random survival forest. METHODS: A total of 573 primary early stage NSCLC patients who underwent SBRT between January 2006 and March 2016 and met the eligibility criteria were included in this study. Patients were divided into two datasets: training (464 patients in 10 institutions) and test (109 patients in one institution) datasets. A total of 944 radiomic features were extracted from manually segmented gross tumor volumes (GTVs). Feature selection was performed by analyzing inter-segmentation reproducibility, GTV correlation, and inter-feature redundancy. Nine clinical factors, including histology and GTV size, were also used. Three prognostic models (clinical, radiomic, and combined) for LR and DM were constructed using random survival forest (RSF) to deal with total death as a competing risk in the training dataset. Robust models with optimal hyper-parameters were determined using fivefold cross-validation. The patients were dichotomized into two groups based on the median value of the patient-specific risk scores (high- and low-risk score groups). Gray's test was used to evaluate the statistical significance between the two risk score groups. The prognostic power was evaluated by the concordance index with the 95% confidence intervals (CI) via bootstrapping (2000 iterations). RESULTS: The concordance indices at 3 yr of clinical, radiomic, and combined models for LR were 0.57 [CI: 0.39-0.75], 0.55 [CI: 0.38-0.73], and 0.61 [CI: 0.43-0.78], respectively, whereas those for DM were 0.59 [CI: 0.54-0.79], 0.67 [CI: 0.54-0.79], and 0.68 [CI: 0.55-0.81], respectively, in the test dataset. The combined DM model significantly discriminated its cumulative incidence between high- and low-risk score groups (P < 0.05). The variable importance of RSF in the combined model for DM indicated that two radiomic features were more important than other clinical factors. The feature maps generated on the basis of the most important radiomic feature had visual difference between high- and low-risk score groups. CONCLUSIONS: The radiomics approach with RSF for competing risks using breath-hold CT-based radiomic features might predict DM in early stage NSCLC patients who underwent SBRT although that may not have potential to predict LR.