Search

Purpose: Heart toxicity, such as major acute coronary events (ACE), following breast radiation therapy (RT) is of utmost concern. Thus, many studies have been investigating the effect of mean heart dose (MHD) and dose received in heart sub-structures on toxicity. Most studies focused on the dose thresholds in the heart and its sub-structures, while few studies adopted such computational methods as deep neural networks (DNN) and radiomics. This work aims to construct a feature-driven predictive model for ACE after breast RT., Methods: A recently proposed two-step predictive model that extracts a number of features from a deep auto-segmentation network and processes the selected features for prediction was adopted. This work refined the auto-segmenting network and feature processing algorithms to enhance performance in cardiac toxicity prediction. In the predictive model, the deep convolutional neural network (CNN) extracted features from 3D computed tomography (CT) images and dose distributions in three automatically segmented heart sub-structures, including the left anterior descending artery (LAD), right coronary artery (RCA), and left ventricle (LV). The optimal feature processing workflow for the extracted features was explored to enhance the prediction accuracy. The regions associated with toxicity were visualized using a class activation map (CAM)-based technique. Our proposed model was validated against a conventional DNN (convolutional and fully connected layers) and radiomics with a patient cohort of 84 cases, including 29 and 55 patient cases with and without ACE. Of the entire 84 cases, 12 randomly chosen cases (5 toxicity and 7 non-toxicity cases) were set aside for independent test, and the remaining 72 cases were applied to 4-fold stratified cross-validation., Results: Our predictive model outperformed the conventional DNN by 38% and 10% and radiomics-based predictive models by 9% and 10% in AUC for 4-fold cross-validations and independent test, respectively. The degree of enhancement was greater when incorporating dose information and heart sub-structures into feature extraction. The model whose inputs were CT, dose, and three sub-structures (LV, LAD, and RCA) reached 96% prediction accuracy on average and 0.94 area under the curve (AUC) on average in the cross-validation, and also achieved prediction accuracy of 83% and AUC of 0.83 in the independent test. On 10 correctly predicted cases out of 12 for the independent test, the activation maps implied that for cases of ACE toxicity, the higher intensity was more likely to be observed inside the LV., Conclusions: The proposed model characterized by modifications in model input with dose distributions and cardiac sub-structures, and serial processing of feature extraction and feature selection techniques can improve the predictive performance in ACE following breast RT., (© 2023 American Association of Physicists in Medicine.)

Purpose: The authors developed a video image-guided real-time patient motion monitoring (VGRPM) system using PC-cams, and its clinical utility was evaluated using a motion phantom., Methods: The VGRPM system has three components: (1) an image acquisition device consisting of two PC-cams, (2) a main control computer with a radiation signal controller and warning system, and (3) patient motion analysis software developed in-house. The intelligent patient motion monitoring system was designed for synchronization with a beam on/off trigger signal in order to limit operation to during treatment time only and to enable system automation. During each treatment session, an initial image of the patient is acquired as soon as radiation starts and is compared with subsequent live images, which can be acquired at up to 30 fps by the real-time frame difference-based analysis software. When the error range exceeds the set criteria (δ(movement)) due to patient movement, a warning message is generated in the form of light and sound. The described procedure repeats automatically for each patient. A motion phantom, which operates by moving a distance of 0.1, 0.2, 0.3, 0.5, and 1.0 cm for 1 and 2 s, respectively, was used to evaluate the system performance. The authors measured optimal δ(movement) for clinical use, the minimum distance that can be detected with this system, and the response time of the whole system using a video analysis technique. The stability of the system in a linear accelerator unit was evaluated for a period of 6 months., Results: As a result of the moving phantom test, the δ(movement) for detection of all simulated phantom motion except the 0.1 cm movement was determined to be 0.2% of total number of pixels in the initial image. The system can detect phantom motion as small as 0.2 cm. The measured response time from the detection of phantom movement to generation of the warning signal was 0.1 s. No significant functional disorder of the system was observed during the testing period., Conclusions: The VGRPM system has a convenient design, which synchronizes initiation of the analysis with a beam on/off signal from the treatment machine and may contribute to a reduction in treatment error due to patient motion and increase the accuracy of treatment dose delivery.

Background: 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. Purpose: 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. Methods: 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. Results: 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. Conclusion: 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. [ABSTRACT FROM AUTHOR]

This study evaluated the impact and clinical utility of an auto-contouring system for radiation therapy treatments. The auto-contouring system was implemented in 2019. We evaluated data from 2428 patients who underwent adjuvant breast radiation therapy before and after the system's introduction. We collected the treatment's finalized contours, which were reviewed and revised by a multidisciplinary team. After implementation, the treatment contours underwent a finalization process that involved manual review and adjustment of the initial auto-contours. For the preimplementation group (n = 369), auto-contours were generated retrospectively. We compared the auto-contours and final contours using the Dice similarity coefficient (DSC) and the 95% Hausdorff distance (HD95). We analyzed 22,215 structures from final and corresponding auto-contours. The final contours were generally larger, encompassing more slices in the superior or inferior directions. Among organs at risk (OAR), the heart, esophagus, spinal cord, and contralateral breast demonstrated significantly increased DSC and decreased HD95 postimplementation (all P <.05), except for the lungs, which presented inaccurate segmentation. Among target volumes, CTVn_L2, L3, L4, and the internal mammary node showed increased DSC and decreased HD95 postimplementation (all P <.05), although the increase was less pronounced than the OAR outcomes. The analysis also covered factors contributing to significant differences, pattern identification, and outlier detection. In our study, the adoption of an auto-contouring system was associated with an increased reliance on automated settings, underscoring its utility and the potential risk of automation bias. Given these findings, we underscore the importance of considering the integration of stringent risk assessments and quality management strategies as a precautionary measure for the optimal use of such systems. [ABSTRACT FROM AUTHOR]

We aimed to investigate the deliverability of dynamic conformal arc therapy (DCAT) by gantry wobble owing to the intrinsic inter-segment break of the Elekta linear accelerator (LINAC) and its adverse influence on the dose to the patient. The deliverability of DCAT was evaluated according to the plan parameters, which affect the gantry rotation speed and resultant positional inaccuracies; the deliverability according to the number of control points and dose rates was investigated by using treatment machine log files and dosimetry devices, respectively. A non-negligible degradation in DCAT deliverability due to gantry wobble was observed in both the treatment machine log files and dosimetry devices. The resulting dose-delivery error occurred below a certain number of control points or above a certain dose rate. Dose simulations in the patient domain showed a similar impact on deteriorated deliverability. For targets located primarily in the isocenter, the dose differences were negligible, whereas for organs at risk located mainly off-isocenter, the dose differences were significant up to − 8.77%. To ensure safe and accurate radiotherapy, optimal plan parameters should be selected, and gantry angle-specific validations should be conducted before treatment. [ABSTRACT FROM AUTHOR]

Simple Summary: Vision transformers have been recently spread out to enhance segmentation accuracy, becoming an active area of research and development involved in radiotherapy. We found that the new network architecture did not guarantee improvement. Conventional CNN-based networks struggled with being expanded to the auto-segmentation of tumors from normal organs due to local geometric dependence and difficulty in the hyper-parameter selection. As seen in the development and success of nnU-Net, we emphasized the importance of finding suitable hyper-parameters for the vision transformer. We applied our proposed framework based on VT U-Net v.2 to the prostate target volume segmentation, followed by extensively validating its performance in segmentation accuracy against the other five competing deep neural networks through four-fold cross-validation using CT images. U-Net, based on a deep convolutional network (CNN), has been clinically used to auto-segment normal organs, while still being limited to the planning target volume (PTV) segmentation. This work aims to address the problems in two aspects: 1) apply one of the newest network architectures such as vision transformers other than the CNN-based networks, and 2) find an appropriate combination of network hyper-parameters with reference to recently proposed nnU-Net ("no-new-Net"). VT U-Net was adopted for auto-segmenting the whole pelvis prostate PTV as it consisted of fully transformer architecture. The upgraded version (v.2) applied the nnU-Net-like hyper-parameter optimizations, which did not fully cover the transformer-oriented hyper-parameters. Thus, we tried to find a suitable combination of two key hyper-parameters (patch size and embedded dimension) for 140 CT scans throughout 4-fold cross validation. The VT U-Net v.2 with hyper-parameter tuning yielded the highest dice similarity coefficient (DSC) of 82.5 and the lowest 95% Haussdorff distance (HD95) of 3.5 on average among the seven recently proposed deep learning networks. Importantly, the nnU-Net with hyper-parameter optimization achieved competitive performance, although this was based on the convolution layers. The network hyper-parameter tuning was demonstrated to be necessary even for the newly developed architecture of vision transformers. [ABSTRACT FROM AUTHOR]

• We reviewed the current evidence on radiomics-based hybrid RP prediction models. • Hybrid models combine radiomics features and conventional predictive factors. • Radiomics-based hybrid models are highly effective at predicting RP. • These models can enhance thoracic radiotherapy by mitigating the risks of RP. • A particular emphasis was placed on the effectiveness of GLCM and GLSZM features. This study reviewed and meta -analyzed evidence on radiomics-based hybrid models for predicting radiation pneumonitis (RP). These models are crucial for improving thoracic radiotherapy plans and mitigating RP, a common complication of thoracic radiotherapy. We examined and compared the RP prediction models developed in these studies with the radiomics features employed in RP models. We systematically searched Google Scholar, Embase, PubMed, and MEDLINE for studies published up to April 19, 2024. Sixteen studies met the inclusion criteria. We compared the RP prediction models developed in these studies and the radiomics features employed. Radiomics, as a single-factor evaluation, achieved an area under the receiver operating characteristic curve (AUROC) of 0.73, accuracy of 0.69, sensitivity of 0.64, and specificity of 0.74. Dosiomics achieved an AUROC of 0.70. Clinical and dosimetric factors showed lower performance, with AUROCs of 0.59 and 0.58. Combining clinical and radiomic factors yielded an AUROC of 0.78, while combining dosiomic and radiomics factors produced an AUROC of 0.81. Triple combinations, including clinical, dosimetric, and radiomics factors, achieved an AUROC of 0.81. The study identifies key radiomics features, such as the Gray Level Co-occurrence Matrix (GLCM) and Gray Level Size Zone Matrix (GLSZM), which enhance the predictive accuracy of RP models. Radiomics-based hybrid models are highly effective in predicting RP. These models, combining traditional predictive factors with radiomic features, particularly GLCM and GLSZM, offer a clinically feasible approach for identifying patients at higher RP risk. This approach enhances clinical outcomes and improves patient quality of life. The protocol of this study was registered on PROSPERO (CRD42023426565). [ABSTRACT FROM AUTHOR]

Simple Summary: With advances in radiotherapy (RT) technique and more frequent use of stereotactic ablative radiotherapy (SABR), precise segmentation of all brain metastases (BM) including a small volume of BM is essential to choose an appropriate treatment modality. However, the process of detecting and manually delineating BM with small volumes often results in missing delineation and requires a great amount of labor. To address this issue, we present a useful deep learning (DL) model for the detection and segmentation of BMwith contrast-enhanced magnetic resonance images. Specifically, we applied effective training techniques to detect and segment a BM of less than 0.04 cc, which is relatively small compared to previous studies. The results of our DL model demonstrated that the proposed methods provide considerable benefit for BM, even small-volume BM, detection, and segmentation for SABR. Recently, several efforts have been made to develop the deep learning (DL) algorithms for automatic detection and segmentation of brain metastases (BM). In this study, we developed an advanced DL model to BM detection and segmentation, especially for small-volume BM. From the institutional cancer registry, contrast-enhanced magnetic resonance images of 65 patients and 603 BM were collected to train and evaluate our DL model. Of the 65 patients, 12 patients with 58 BM were assigned to test-set for performance evaluation. Ground-truth for BM was assigned to one radiation oncologist to manually delineate BM and another one to cross-check. Unlike other previous studies, our study dealt with relatively small BM, so the area occupied by the BM in the high-resolution images were small. Our study applied training techniques such as the overlapping patch technique and 2.5-dimensional (2.5D) training to the well-known U-Net architecture to learn better in smaller BM. As a DL architecture, 2D U-Net was utilized by 2.5D training. For better efficacy and accuracy of a two-dimensional U-Net, we applied effective preprocessing include 2.5D overlapping patch technique. The sensitivity and average false positive rate were measured as detection performance, and their values were 97% and 1.25 per patient, respectively. The dice coefficient with dilation and 95% Hausdorff distance were measured as segmentation performance, and their values were 75% and 2.057 mm, respectively. Our DL model can detect and segment BM with small volume with good performance. Our model provides considerable benefit for clinicians with automatic detection and segmentation of BM for stereotactic ablative radiotherapy. [ABSTRACT FROM AUTHOR]

Purpose: Applications of deep learning (DL) are essential to realizing an effective adaptive radiotherapy (ART) workflow. Despite the promise demonstrated by DL approaches in several critical ART tasks, there remain unsolved challenges to achieve satisfactory generalizability of a trained model in a clinical setting. Foremost among these is the difficulty of collecting a task‐specific training dataset with high‐quality, consistent annotations for supervised learning applications. In this study, we propose a tailored DL framework for patient‐specific performance that leverages the behavior of a model intentionally overfitted to a patient‐specific training dataset augmented from the prior information available in an ART workflow—an approach we term Intentional Deep Overfit Learning (IDOL). Methods: Implementing the IDOL framework in any task in radiotherapy consists of two training stages: (1) training a generalized model with a diverse training dataset of N patients, just as in the conventional DL approach, and (2) intentionally overfitting this general model to a small training dataset‐specific the patient of interest (N+1) generated through perturbations and augmentations of the available task‐ and patient‐specific prior information to establish a personalized IDOL model. The IDOL framework itself is task‐agnostic and is, thus, widely applicable to many components of the ART workflow, three of which we use as a proof of concept here: the autocontouring task on replanning CTs for traditional ART, the MRI super‐resolution (SR) task for MRI‐guided ART, and the synthetic CT (sCT) reconstruction task for MRI‐only ART. Results: In the replanning CT autocontouring task, the accuracy measured by the Dice similarity coefficient improves from 0.847 with the general model to 0.935 by adopting the IDOL model. In the case of MRI SR, the mean absolute error (MAE) is improved by 40% using the IDOL framework over the conventional model. Finally, in the sCT reconstruction task, the MAE is reduced from 68 to 22 HU by utilizing the IDOL framework. Conclusions: In this study, we propose a novel IDOL framework for ART and demonstrate its feasibility using three ART tasks. We expect the IDOL framework to be especially useful in creating personally tailored models in situations with limited availability of training data but existing prior information, which is usually true in the medical setting in general and is especially true in ART. [ABSTRACT FROM AUTHOR]

Purpose: To develop an internal target volume (ITV) margin determination framework (or decision-supporting framework) for treating multiple lung metastases using CyberKnife Synchrony with intraoperatively implanted fiducial markers (IIFMs). The feasibility of using non-ideally implanted fiducial markers (a limited number and/or far from a target) for tracking-based lung stereotactic ablative radiotherapy (SABR) was investigated. Methods: In the developed margin determination framework, an optimal set of IIFMs was determined to minimize a tracking uncertainty-specific ITV (ITVtracking) margin (margin required to cover target-to-marker motion discrepancy), i.e., minimize the motion discrepancies between gross tumor volume (GTV) and the selected set of fiducial markers (FMs). The developed margin determination framework was evaluated in 17 patients with lung metastases. To automatically calculate the respiratory motions of the FMs, a template matching-based FM tracking algorithm was developed, and GTV motion was manually measured. Furthermore, during-treatment motions of the selected FMs were analyzed using log files and compared with those calculated using 4D CTs. Results: For 41 of 42 lesions in 17 patients (97.6%), an optimal set of the IIFMs was successfully determined, requiring an ITVtracking margin less than 5 mm. The template matching-based FM tracking algorithm calculated the FM motions with a sub-millimeter accuracy compared with the manual measurements. The patient respiratory motions during treatment were, on average, significantly smaller than those measured at simulation for the patient cohort considered. Conclusion: Use of the developed margin determination framework employing CyberKnife Synchrony with a limited number of IIFMs is feasible for lung SABR. [ABSTRACT FROM AUTHOR]

Purpose: How modern cardiac sparing techniques and beam delivery systems using advanced x-ray and proton beam therapy (PBT) can reduce incidental radiation exposure doses to cardiac and pulmonary organs individually or in any combination is poorly investigated. Methods: Among 15 patients with left-sided breast cancer, partial wide tangential 3D-conformal radiotherapy (3DCRT) delivered in conventional fractionation (CF) or hypofractionated (HF) schedules; PBT delivered in a CF schedule; and volumetric modulated arc therapy (VMAT) delivered in an HF schedule, each under continuous positive airway pressure (CPAP) and free-breathing (FB) conditions, were examined. Target volume coverage and doses to organs-at-risk (OARs) were calculated for each technique. Outcomes were compared with one-way analysis of variance and the Bonferroni test, with p -values <0.05 considered significant. Results: Target volume coverage was within acceptable levels in all interventions, except for the internal mammary lymph node D95 (99% in PBT, 90% in VMAT-CPAP, 84% in VMAT-FB, and 74% in 3DCRT). The mean heart dose (MHD) was the lowest in PBT (<1 Gy) and VMAT-CPAP (2.2 Gy) and the highest in 3DCRT with CF/FB (7.8 Gy), respectively. The mean lung dose (MLD) was the highest in 3DCRT-CF-FB (20 Gy) and the lowest in both VMAT-HF-CPAP and PBT (approximately 5–6 Gy). VMAT-HF-CPAP and PBT delivered a comparable maximum dose to the left ascending artery (7.2 and 6.13 Gy, respectively). Conclusions: Both proton and VMAT in combination with CPAP can minimize the radiation exposure to heart and lung with optimal target coverage in regional RT for left-sided breast cancer. The clinical relevance of these differences is yet to be elucidated. Continued efforts are needed to minimize radiation exposures during RT treatment to maximize its therapeutic index. [ABSTRACT FROM AUTHOR]

Purpose: We evaluated that early metabolic response determined by 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) during radiotherapy (RT), predicts outcomes in non-small cell lung cancer. Material and methods: Twenty-eight patients evaluated using pretreatment 18F-FDG-PET/CT (PETpre) and interim 18F-FDG-PET/CT (PETinterim) after 11 fractions of RT were retrospectively reviewed. Maximum standardized uptake value (SUVmax) was calculated for primary lesion. Predictive value of gross tumor volume (ΔGTV) and SUVmax (ΔSUVmax) changes was evaluated for locoregional control (LRC), distant failure (DF), and overall survival (OS). Metabolic responders were patients with ΔSUVmax >40%. Results: Metabolic responders showed better trends in 1-year LRC (90.9%) than non-responders (47.1%) (p = 0.086). Patients with large GTVpre (≥120 cc) demonstrated poor LRC (hazard ratio 4.14, p = 0.022), while metabolic non-responders with small GTVpre (<120 cc) and metabolic responders with large GTVpre both had 1-year LRC rates of 75.0%. Reduction of 25% in GTV was not associated with LRC; however, metabolic responders without a GTV response showed better 1-year LRC (83.3%) than metabolic non-responders with a reduction in GTV (42.9%). Metabolic responders showed lower 1-year DF (16.7%) than non-responders (50.0%) (p = 0.025). An ΔSUVmax threshold of 40% yielded accuracy of 64% for predicting LRC, 75% for DF, and 54% for OS. However, ΔGTV > 25% demonstrated inferior diagnostic values than metabolic response. Conclusions: Changes in tumor metabolism diagnosed using PETinterim during RT better predicted treatment responses, recurrences, and prognosis than other factors historically used. [ABSTRACT FROM AUTHOR]

Background: Tomotherapy-based total body irradiation (TBI) is performed using the head-first position (HFP) and feet-first position (FFP) due to treatment length exceeding the 135 cm limit. To reduce the dosimetric variation at the match lines, we propose and verify a volumetric gradient matching technique (VGMT) by combining TomoHelical (TH) and TomoDirect (TD) modes.Methods: Two planning CT image sets were acquired with HFP and FFP using 15 × 55 × 18 cm3 of solid water phantom. Planning target volume (PTV) was divided into upper, lower, and gradient volumes. The junction comprised 2-cm thick five and seven gradient volumes (5-GVs and 7-GVs) to create a dose distribution with a gentle slope. TH-IMRT and TD-IMRT plans were generated with 5-GVs and 7-GVs. The setup error in the calculated dose was assessed by shifting dose distribution of the FFP plan by 5, 10, 15, and 20 mm in the longitudinal direction and comparing it with the original. Doses for 95% (D95) and 5% of the PTV (D5) were calculated for all simulated setup error plans. Absolute dose measurements were performed using an ionization chamber in the junction.Results: The TH&TD plan produced a linear gradient in junction volume, comparable to that of the TH&TH plan. D5 of the PTV was 110% of the prescribed dose when the FFP plan was shifted 0.7 cm and 1.2 cm in the superior direction for 5-GVs and 7-GVs. D95 of the PTV decreased to < 90% of the prescribed dose when the FF plan was shifted 1.1 cm and 1.3 cm in the inferior direction for 5-GVs and 7-GVs. The absolute measured dose showed a good correlation with the calculated dose in the gradient junction volume. The average percent difference (±SD) in all measured points was - 0.7 ± 1.6%, and the average dose variations between depths was - 0.18 ± 1.07%.Conclusion: VGMT can create a linear dose gradient across the junction area in both TH&TH and TH&TD and can minimize the dose sensitivity to longitudinal setup errors in tomotherapy-based TBI. [ABSTRACT FROM AUTHOR]

The aim of this study was to evaluate the anxiety-reducing effects of virtual reality (VR) on patients with breast cancer undergoing adjuvant radiation therapy (RT). This randomized controlled trial was conducted among patients with breast cancer receiving RT at a single institution. Of 196 enrolled and randomized patients, 97 were assigned to a VR explanation group (intervention) and 99 were assigned to the standard-of-care group (control). Anxiety levels were measured using the Amsterdam Preoperative Anxiety and Information Scale (APAIS) as the primary endpoint and the State-Trait Anxiety Inventory (STAI) and Linear Analogue Scale Assessment (LASA) as secondary endpoints. Knowledge of the RT procedure, patient satisfaction, and time spent for counseling were also assessed. Intervention significantly reduced patient anxiety immediately, not only on the primary endpoint, APAIS, but also on the STAI and LASA anxiety scales. Specifically, in the intervention group, there were immediate reductions of 26.0%, 16.1%, and 55.8% for APAIS, STAI, and LASA, respectively, whereas in the control group, the respective reductions were 8.1%, 8.5%, and 13.7%. Among the 3 anxiety scales, long-term anxiety reduction was observed only when anxiety was measured by LASA. Subgroup analyses showed that the effect on anxiety did not differ based on the physician, baseline anxiety level, use of hormone therapy, or health literacy. The intervention also significantly improved knowledge of the RT procedure (81.9/100 vs 76.8/100; P =.006) and patient satisfaction with the explanation manner (6.56 vs 5.72; P <.001) compared with the control group. Immersive VR applied to the current procedure reduces anxiety during RT planning for patients with breast cancer. Further research is necessary to investigate the long-term effects of VR on anxiety. [Display omitted] [ABSTRACT FROM AUTHOR]

Purpose: Respiration-induced intrafraction target motion is a concern in liver cancer radiotherapy, especially in stereotactic body radiotherapy (SBRT), and therefore, verification of its motion is necessary. An effective means to localize the liver cancer is to insert metal fiducial markers to or near the tumor with simultaneous imaging using cone-beam computed tomography (CBCT). Utilizing the fiducial markers, the authors have demonstrated a method to generate breath-induced motion signal of liver for reconstructing 4D digital tomosynthesis (4DDTS) and 4DCBCT images based on phasewise and/or amplitudewise sorting of projection data. Methods: The marker extraction algorithm is based on template matching of a prior known marker image and has been coded to optimally extract marker positions in CBCT projections from the On-Board Imager (Varian Medical Systems, Palo Alto, CA). To validate the algorithm, multiple projection images of moving thorax phantom and five patient cases were examined. Upon extraction of the motion signals from the markers, 4D image sorting and image reconstructions were subsequently performed. In the case of incomplete signals due to projections with missing markers, the authors have implemented signal profiling to replace the missing portion. Results: The proposed marker extraction algorithm was shown to be very robust and accurate in the phantom and patient cases examined. The maximum discrepancy of the algorithm predicted marker location versus operator selected location was <1.2 mm, with the overall average of 0.51±0.15 mm, for 500 projections. The resulting 4DDTS and 4DCBCT images showed clear reduction in motion-induced blur of the markers and the anatomy for an effective image guidance. The signal profiling method was useful in replacing missing signals. Conclusions: The authors have successfully demonstrated that motion tracking of fiducial markers and the subsequent 4D reconstruction of CBCT and DTS are possible. Due to the significant reduction in motion-induced image blur, it is anticipated that such technology will be useful in image-guided liver SBRT treatments. [ABSTRACT FROM AUTHOR]

Simple Summary: We analyzed the contouring data of 23 organs-at-risk from 100 patients with head and neck cancer who underwent definitive radiation therapy (RT). Deep learning-based segmentation (DLS) with continual training was compared to DLS with conventional training and deformable image registration (DIR) in both quantitative and qualitative (Turing's test) methods. Results indicate the effectiveness of DLS over DIR and that of DLS with continual training over DLS with conventional training in contouring for head and neck region, especially for glandular structures. DLS with continual training might be beneficial for optimizing personalized adaptive RT in head and neck region. This study investigated the feasibility of deep learning-based segmentation (DLS) and continual training for adaptive radiotherapy (RT) of head and neck (H&N) cancer. One-hundred patients treated with definitive RT were included. Based on 23 organs-at-risk (OARs) manually segmented in initial planning computed tomography (CT), modified FC-DenseNet was trained for DLS: (i) using data obtained from 60 patients, with 20 matched patients in the test set (DLSm); (ii) using data obtained from 60 identical patients with 20 unmatched patients in the test set (DLSu). Manually contoured OARs in adaptive planning CT for independent 20 patients were provided as test sets. Deformable image registration (DIR) was also performed. All 23 OARs were compared using quantitative measurements, and nine OARs were also evaluated via subjective assessment from 26 observers using the Turing test. DLSm achieved better performance than both DLSu and DIR (mean Dice similarity coefficient; 0.83 vs. 0.80 vs. 0.70), mainly for glandular structures, whose volume significantly reduced during RT. Based on subjective measurements, DLS is often perceived as a human (49.2%). Furthermore, DLSm is preferred over DLSu (67.2%) and DIR (96.7%), with a similar rate of required revision to that of manual segmentation (28.0% vs. 29.7%). In conclusion, DLS was effective and preferred over DIR. Additionally, continual DLS training is required for an effective optimization and robustness in personalized adaptive RT. [ABSTRACT FROM AUTHOR]

Background: Despite detailed instruction for full bladder, patients are unable to maintain consistent bladder filling during a 5-week pelvic radiation therapy (RT) course. We investigated the best bladder volume estimation procedure for verifying consistent bladder volume.Methods: We reviewed 462 patients who underwent pelvic RT. Biofeedback using a bladder scanner was conducted before simulation and during treatment. Exact bladder volume was calculated by bladder inner wall contour based on CT images (Vctsim). Bladder volume was estimated either by bladder scanner (Vscan) or anatomical features from the presacral promontory to the bladder base and dome in the sagittal plane of CT (Vratio). The feasibility of Vratio was validated using daily megavoltage or kV cone-beam CT before treatment.Results: Mean Vctsim was 335.6 ± 147.5 cc. Despite a positive correlation between Vctsim and Vscan (R2 = 0.278) and between Vctsim and Vratio (R2 = 0.424), Vratio yielded more consistent results than Vscan, with a mean percentage error of 26.3 (SD 19.6, p < 0.001). The correlation between Vratio and Vctsim was stronger than that between Vscan and Vctsim (Z-score: - 7.782, p < 0.001). An accuracy of Vratio was consistent in megavoltage or kV cone-beam CT during treatment. In a representative case, we can dichotomize for clinical scenarios with or without bowel displacement, using a ratio of 0.8 resulting in significant changes in bowel volume exposed to low radiation doses.Conclusions: Bladder volume estimation using personalized anatomical features based on pre-treatment verification CT images was useful and more accurate than physician-dependent bladder scanners.Trial Registration: Retrospectively registered. [ABSTRACT FROM AUTHOR]

Background: Rotational beam delivery enables concurrent acquisition of cone-beam CT (CBCT), thereby facilitating further geometric verification of patient setup during radiation treatment. However, it is challenging to acquire CBCT during stereotactic body radiation therapy (SBRT) using flattening-filter free X-ray beams, in which a high radiation dose is delivered. This study presents quantitative evaluation results of the image quality in four-dimensional (4D) in-treatment CBCT acquired during SBRT delivery.Methods: The impact of megavoltage (MV) scatter and acquisition parameters on the image quality was evaluated using Catphan 503 and XSight lung tracking phantoms. The in-treatment CBCT images of the phantoms were acquired while delivering 16 SBRT plans. The uniformity, contrast, and contrast-to-noise ratio (CNR) of the in-treatment CBCT images were calculated and compared to those of CBCT images acquired without SBRT delivery. Furthermore, the localizing accuracy of the moving target in the XSight lung phantom was evaluated for 10 respiratory phases.Results: The CNR of the 3D-reconstucted Catphan CBCT images was reduced from 6.3 to 2.6 due to the effect of MV treatment scatter. Both for the Catphan and XSight phantoms, the CBCT image quality was affected by the tube current and monitor units (MUs) of the treatment plan. The lung target in the XSight tracking phantom was most visible for extreme phases; the mean CNRs of the lung target in the in-treatment CBCT images (with 40 mA tube current) across the SBRT plans were 3.2 for the end-of-exhalation phase and 3.0 for the end-of-inhalation phase. The lung target was localized with sub-millimeter accuracy for the extreme respiratory phases.Conclusions: Full-arc acquisition with an increased tube current (e.g. 40 mA) is recommended to compensate for degradation in the CBCT image quality due to unflattened MV beam scatter. Acquiring in-treatment CBCT with a high-MU treatment beam is also suggested to improve the resulting CBCT image quality. [ABSTRACT FROM AUTHOR]

Background: Although there have been many attempts to increase the therapeutic ratio of radiotherapy for gastric mucosa-associated lymphoid tissue lymphoma (MALToma), only a few planning studies have reported the efficacy of the modern radiotherapy technique till date. Therefore, we performed the dosimetric comparison among 3-dimensional conformal radiotherapy (3D-CRT) and intensity-modulated radiotherapy (IMRT) plans, using deep-inspiration breath hold (DIBH) or free-breathing (FB) techniques, to determine the most optimal plan for gastric MALToma.Methods: We evaluated 9 patients with gastric MALToma for whom 3D-CRT, step-and-shoot IMRT (SIMRT), volumetric-modulated arc therapy (VMAT), and tomotherapy plans with identical prescribed doses were generated using DIBH or FB computed tomography (CT). Planning target volume (PTV) coverage and non-target doses were calculated for each plan and compared with plan quality metric (PQM) scores.Results: All 72 plans of 9 patients satisfied our dosimetric goals, and the IMRT plans and 3D-CRT plans had similarly good conformity index values with no differences related to respiratory movement. IMRT plans yielded significantly better doses to the organs-at-risk, and DIBH plans yielded significantly lower liver, heart, and lung Dmean and spinal cord Dmax with smaller irradiated volumes compared to FB plans. For the mean PQM scores, VMAT-DIBH and SIMRT-DIBH yielded the best scores, whereas 3D plans provided reduced beam monitor unit values.Conclusion: Our findings demonstrate that modern RT technologies (DIBH with VMAT or SIMRT) could potentially provide excellent target coverage for gastric MALToma while reducing doses to organs-at-risk. However, the relevance of the most optimal plan considering clinical outcomes should be confirmed further in a larger patient cohort. [ABSTRACT FROM AUTHOR]

Background: To simplify the adaptive treatment planning workflow while achieving the optimal tumor-dose coverage in pancreatic cancer patients undergoing daily adaptive magnetic resonance image guided radiation therapy (MR-IGRT).Methods: In daily adaptive MR-IGRT, the plan objective function constructed during simulation is used for plan re-optimization throughout the course of treatment. In this study, we have constructed the initial objective functions using two methods for 16 pancreatic cancer patients treated with the ViewRay™ MR-IGRT system: 1) the conventional method that handles the stomach, duodenum, small bowel, and large bowel as separate organs at risk (OARs) and 2) the OAR grouping method. Using OAR grouping, a combined OAR structure that encompasses the portions of these four primary OARs within 3 cm of the planning target volume (PTV) is created. OAR grouping simulation plans were optimized such that the target coverage was comparable to the clinical simulation plan constructed in the conventional manner. In both cases, the initial objective function was then applied to each successive treatment fraction and the plan was re-optimized based on the patient's daily anatomy. OAR grouping plans were compared to conventional plans at each fraction in terms of coverage of the PTV and the optimized PTV (PTV OPT), which is the result of the subtraction of overlapping OAR volumes with an additional margin from the PTV.Results: Plan performance was enhanced across a majority of fractions using OAR grouping. The percentage of the volume of the PTV covered by 95% of the prescribed dose (D95) was improved by an average of 3.87 ± 4.29% while D95 coverage of the PTV OPT increased by 3.98 ± 4.97%. Finally, D100 coverage of the PTV demonstrated an average increase of 6.47 ± 7.16% and a maximum improvement of 20.19%.Conclusions: In this study, our proposed OAR grouping plans generally outperformed conventional plans, especially when the conventional simulation plan favored or disregarded an OAR through the assignment of distinct weighting parameters relative to the other critical structures. OAR grouping simplifies the MR-IGRT adaptive treatment planning workflow at simulation while demonstrating improved coverage compared to delivered pancreatic cancer treatment plans in daily adaptive radiation therapy. [ABSTRACT FROM AUTHOR]

Purpose: Utilization of respiratory correlated four-dimensional cone-beam computed tomography (4DCBCT) has enabled verification of internal target motion and volume immediately prior to treatment. However, with current standard CBCT scan, 4DCBCT poses challenge for reconstruction due to the fact that multiple phase binning leads to insufficient number of projection data to reconstruct and thus cause streaking artifacts. The purpose of this study is to develop a novel 4DCBCT reconstruction algorithm framework called motion-map constrained image reconstruction (MCIR), that allows reconstruction of high quality and high phase resolution 4DCBCT images with no more than the imaging dose as well as projections used in a standard free breathing 3DCBCT (FB-3DCBCT) scan. Methods: The unknown 4DCBCT volume at each phase was mathematically modeled as a combination of FB-3DCBCT and phase-specific update vector which has an associated motion-map matrix. The motion-map matrix, which is the key innovation of the MCIR algorithm, was defined as the matrix that distinguishes voxels that are moving from stationary ones. This 4DCBCT model was then reconstructed with compressed sensing (CS) reconstruction framework such that the voxels with high motion would be aggressively updated by the phase-wise sorted projections and the voxels with less motion would be minimally updated to preserve the FB-3DCBCT. To evaluate the performance of our proposed MCIR algorithm, we evaluated both numerical phantoms and a lung cancer patient. The results were then compared with the (1) clinical FB-3DCBCT reconstructed using the FDK, (2) 4DCBCT reconstructed using the FDK, and (3) 4DCBCT reconstructed using the well-known prior image constrained compressed sensing (PICCS). Results: Examination of the MCIR algorithm showed that high phase-resolved 4DCBCT with sets of up to 20 phases using a typical FB-3DCBCT scan could be reconstructed without compromising the image quality. Moreover, in comparison with other published algorithms, the image quality of the MCIR algorithm is shown to be excellent. Conclusions: This work demonstrates the potential for providing high-quality 4DCBCT during on-line image-guided radiation therapy (IGRT), without increasing the imaging dose. The results showed that (at least) 20 phase images could be reconstructed using the same projections data, used to reconstruct a single FB-3DCBCT, without streak artifacts that are caused by insufficient projections. [ABSTRACT FROM AUTHOR]

[Display omitted] • We organized HaN-Seg: The Head and Neck Organ-at-Risk CT and MR Segmentation Challenge. • The task was to automatically segment of 30 OARs of the head and neck region. • The dataset consisted of 42 publicly available training and 14 withheld test cases. • Each case includes one CT and one MR image of the same patient with corresponding OAR reference delineations. • A total of seven teams participated by submitting their deep learning segmentation frameworks. To promote the development of auto-segmentation methods for head and neck (HaN) radiation treatment (RT) planning that exploit the information of computed tomography (CT) and magnetic resonance (MR) imaging modalities, we organized HaN-Seg: The Head and Neck Organ-at-Risk CT and MR Segmentation Challenge. The challenge task was to automatically segment 30 organs-at-risk (OARs) of the HaN region in 14 withheld test cases given the availability of 42 publicly available training cases. Each case consisted of one contrast-enhanced CT and one T1-weighted MR image of the HaN region of the same patient, with up to 30 corresponding reference OAR delineation masks. The performance was evaluated in terms of the Dice similarity coefficient (DSC) and 95-percentile Hausdorff distance (HD 95), and statistical ranking was applied for each metric by pairwise comparison of the submitted methods using the Wilcoxon signed-rank test. While 23 teams registered for the challenge, only seven submitted their methods for the final phase. The top-performing team achieved a DSC of 76.9 % and a HD 95 of 3.5 mm. All participating teams utilized architectures based on U-Net, with the winning team leveraging rigid MR to CT registration combined with network entry-level concatenation of both modalities. This challenge simulated a real-world clinical scenario by providing non-registered MR and CT images with varying fields-of-view and voxel sizes. Remarkably, the top-performing teams achieved segmentation performance surpassing the inter-observer agreement on the same dataset. These results set a benchmark for future research on this publicly available dataset and on paired multi-modal image segmentation in general. [ABSTRACT FROM AUTHOR]

• The DLBAS model performed better for the majority of CTVs and OARs in comparison to ABAS solutions. • ABAS performed relatively well for structures with distinct boundaries. • DLBAS showed more robustness and less dependency on input data. • DLBAS has great potential to help optimise the radiation therapy planning workflow. Manual segmentation is the gold standard method for radiation therapy planning; however, it is time-consuming and prone to inter- and intra-observer variation, giving rise to interests in auto-segmentation methods. We evaluated the feasibility of deep learning-based auto-segmentation (DLBAS) in comparison to commercially available atlas-based segmentation solutions (ABAS) for breast cancer radiation therapy. This study used contrast-enhanced planning computed tomography scans from 62 patients with breast cancer who underwent breast-conservation surgery. Contours of target volumes (CTVs), organs, and heart substructures were generated using two commercial ABAS solutions and DLBAS using fully convolutional DenseNet. The accuracy of the segmentation was assessed using 14 test patients using the Dice Similarity Coefficient and Hausdorff Distance referencing the expert contours. A sensitivity analysis was performed using non-contrast planning CT from 14 additional patients. Compared to ABAS, the proposed DLBAS model yielded more consistent results and the highest average Dice Similarity Coefficient values and lowest Hausdorff Distances, especially for CTVs and the substructures of the heart. ABAS showed limited performance in soft-tissue-based regions, such as the esophagus, cardiac arteries, and smaller CTVs. The results of sensitivity analysis between contrast and non-contrast CT test sets showed little difference in the performance of DLBAS and conversely, a large discrepancy for ABAS. The proposed DLBAS algorithm was more consistent and robust in its performance than ABAS across the majority of structures when examining both CTVs and normal organs. DLBAS has great potential to aid a key process in the radiation therapy workflow, helping optimise and reduce the clinical workload. [ABSTRACT FROM AUTHOR]

In this paper, we propose shielding evaluator actual treatment leaf (SEATTLE), a program that evaluates radiation shielding and calculates the maximum number of treatable patients, using the Digital Imaging and Communications in Medicine Radiation Therapy (DICOM RT) plan files of the actual treated patients. MATLAB App Designer was used for GUI-based program development and DICOM RT plan file analysis. The intensity-modulated radiation therapy (IMRT) factor was calculated based on the monitor unit (MU) value obtained from the DICOM RT plan file; the use factor considering the MU for each gantry angle was obtained. For shielding calculation, the workload and dose were calculated using the formula based on the National Council on Radiation Protection and Measurements (NCRP)-151 report; the maximum number of treatable patients was calculated. For evaluation and validation of the program, an shielding evaluation was performed using anonymized patient data from seven treatment rooms at four institutions for one week of treatment. The average IMRT factor calculated from patient data for the pilot institution was 3.0 ± 0.9, confirming a difference of up to 58.8% compared to the currently used IMRT factor of 5; moreover, the use factor had a difference of up to 33.8% compared to the NCRP-151 value. The measurement data and shielding evaluation result of the transmitted dose at each point in the treatment rooms with SEATTLE showed an error of up to 0.01145 mSv/week. The program was designed with simple operation for user convenience; it was possible to evaluate shielding for the treatment room and the number of patients available for treatment. The program developed in this study performs shielding evaluation considering the clinical environment, and it will be possible to build a real-time shielding management system using actual patient data. • Developed an automatic shielding assessment program for a linear accelerator for treatment that is easy to operate. • Only DICOM RT plan file and shielding information are required when running the program. • Calculated IMRT factor, use factor, and workload based on treated patient data. • Calculate the maximum number of treatable patients according to the actual workload. [ABSTRACT FROM AUTHOR]