Dose-volume Metrics Research Articles

Comparison and evaluation of different deep learning models of synthetic CT generation from CBCT for nasopharynx cancer adaptive proton therapy.

Cone-beam computed tomography (CBCT) scanning is used for patient setup in image-guided radiotherapy. However, its inaccurate CT numbers limit its applicability in dose calculation and treatment planning. This study compares four deep learning methods for generating synthetic CT (sCT) to determine which method is more appropriate and offers potential for further clinical exploration in adaptive proton therapy for nasopharynx cancer. CBCTs and deformed planning CT (dCT) from 75 patients (60/5/10 for training, validation and testing) were used to compare cycle-consistent Generative Adversarial Network(cycleGAN), Unet, Unet+cycleGAN and conditionalGenerative Adversarial Network (cGAN) for sCT generation. The sCT images generated by each method were evaluated against dCT images using mean absolute error (MAE), structural similarity (SSIM), peak signal-to-noise ratio (PSNR), spatial non-uniformity (SNU) and radial averaging in the frequency domain. In addition, dosimetric accuracy was assessed through gamma analysis, differences in water equivalent thickness (WET), and dose-volume histogram metrics. The cGAN model has demonstrated optimal performance in the four models across various indicators. In terms of image quality under global condition, the average MAE has been reduced to 16.39HU, SSIM has increased to 95.24%, and PSNR has increased to 28.98. Regarding dosimetric accuracy, the gamma passing rate (2%/2mm) has reached 99.02%, and the WET difference is only 1.28mm. The D95 value of CTVs coverage and Dmax value of spinal cord, brainstem show no significant differences between dCT and sCT generated by cGAN model. The cGAN model has been shown to be a more suitable approach for generating sCT using CBCT, considering its characteristics and concepts. The resulting sCT has the potential for application in adaptive proton therapy.

Statistical Analysis to Determine the Predictors of Liver Segmental Hypertrophy Observed Post-Radiotherapy

Prediction of liver segment hypertrophy based on radiotherapy (RT) dose is crucial for maximizing functional liver volume and avoiding hepatic failure after RT. We determined predictors associated with liver hypertrophy with stratification based on induction chemo (IC) and tumor location. RT planning, CT images, and 3-month-followup CTs were analyzed from 148 patients who underwent RT for primary or metastatic liver cancers. A nnUNet based model was trained (train/test = 160/40 CTs) to contour the liver segments (1, 2, 3, 4, 5-8) with accuracy assessed using Dice Similarity Coefficients (DSC). 52 features corresponding to segments 1, 2, 3, 2+3, 4, 5-8, were collected including equivalent dose to 2Gy fractions metrics-mean dose (Dmean), dose received by 95% of the volume (D95), volume spared from x gy (Vx), cancer type, tumor location, and IC status. Descriptive statistics were reported as percentage of segments showing hypertrophy under all stratification. Predictors were compared with 6 response variables using Chi-squared/Fisher-Exact test (CST/FET) and logistic regression (LR) for categorical and numerical predictors. The nnUNet model had an average DSC of 0.91 across all segments. Overall, segments 1, 4, and 5-8 showed hypertrophy in 35% of cases, and segments 2, 3 and 2+3 showed hypertrophy in 45-49% of patients. Stratification based on tumor location resulted in segment 2+3 hypertrophy in 66% of patients when the tumor was in segments 5-8. For bilobed tumors, segment 2+3 hypertrophy was observed in 34% of patients. CST/FET showed that tumor location, IC, and tumor type were significant predictors of segment 5-8 hypertrophy. Tumor location was also a significant predictor of segments 3 and 2+3 hypertrophy. In LR analysis, all segment-based dose metrics were significant predictors of segment hypertrophy except Dmean in segment 4, and D95 in segment 2 and 4. Overall, the strongest association was obtained for V35 significantly predicting for each segment hypertrophy. The mean dose for segments with hypertrophy was significantly lower (range: 15-30 Gy) than segments with atrophy (p<0.01), except for segment 4 where the mean dose was 10Gy lower but did not reach significance. IC impacts the threshold mean dose that leads to hypertrophy, with more toxic drugs reducing the mean dose threshold. Tumor location and IC significantly impact the response of segments to RT. Dose volume metrics are strong predictors of volumetric response with segment volume spared from 35 Gy being the strongest predictor.

Complexity Metrics and Planning Dose-Based Pretreatment Patient-Specific Quality Assurance Prediction: Classification, Gamma Passing Rates, and DVH Deviation

Patient-specific quality assurance (QA) prediction before treatment is beneficial to the clinical resource allocation and the dosimetric monitoring of the patient plans. The aim of this study is to investigate the potential of complexity metrics of radiotherapy plan and patient planning dose to predict QA result, gamma passing rates and dose-volume indices deviation. Planning dose from treatment planning system (TPS), reconstructed dose from a vendor provided QA phantom and complexity metrics of the 499 radiotherapy plans of patients in our institution from March 2022 to September 2022 were used for methodology verification. Gamma passing rate (3%/2mm,10% threshold) 90% was regarded as criterion of QA pass or fail. A deep learning model ResNet-50 was modified to 3D dose processing and a multilayer perceptron (MLP) with three layers were adopted to extract features from 3D dose and 1D metrics in two parallel ways, then, the features were concatenate together to predict QA results. The dataset was split into 349 for train, 50 for validation and 100 for testing. Evaluation of predictions was based on absolute value deviation and area under the curves (AUC) of receiver operator characteristic (ROC) curve. In this dataset, 71% (355/499) plans pass the pretreatment QA test. For QA passing prediction in 100 testing cases, the AUC of ROC could achieve 0.92. For gamma passing rates prediction, a mean absolute error (MAE) of 1.8% could be observed for cases with gamma passing rates bigger than 90%, and a MAE of 4.5% deviation could be observed for cases with gamma passing rates from 80% to 90%. For PTV ΔD95 (%) and PTV ΔHI (%), the MAE of prediction and ground truth is 1%. The model with only complexity metrics and only 3D dose could achieve the AUC of ROC 0.91 and 0.84, respectively. The complexity metrics and 3D planning dose-based model could predict pretreatment patient specific QA results with high accuracy and the complexity metrics play a leading role in the model. Dose-volume metrics deviations of PTV could be predicted and more clinically useful information could be provided.

Patient-Level and Endpoint-Specific Clinico-Dosimetric Analysis of the Cardiac Base as a Mediator of Radiation Cardiotoxicity in Non-Small Cell Lung Cancer

Cardiac disease is a dose-limiting toxicity in non-small cell lung cancer (NSCLC) radiation therapy. Radiation dose to the cardiac base is associated with poor overall survival in several clinical studies, but has not been validated in a non-dose escalated cohort, or with individual patient delineations. In this study we examined the impact of cardiac base dose on overall survival (OS) and cardiac events (CEs), and interrogated the relationships of the substructures comprising the heart base with OS and CEs. Patients with stage I-III NSCLC treated with curative-intent radiation therapy between 2015 and 2020 at a regional cancer center were identified. Clinical notes were examined for baseline patient, tumor and cardiac details, and both cancer and cardiac outcomes. Three cardiologists verified CEs. Cardiac delineations were completed using a validated deep learning-based autosegmentation tool. Cox and Fine and Gray regressions were undertaken for the risk of death and CEs respectively, accounting for pre-specified evidence-based dose metrics and clinically relevant cardiac covariates. Most patients received 55 Gy/20# (n = 461/478, 96%) without chemotherapy (58%), planned with VMAT (51%) or IMRT (20%). Pre-existing cardiovascular morbidity was common, with 78% having ≥2 risk factors, and 46% having >1 established cardiac disease. The median follow-up was 21.1 months. Dichotomized at the median, higher heart base Dmax was associated with poorer survival on Kaplan-Meier analysis (21.6 months (95% CI 19.3-24.9) versus 29.4 months (95% CI 21.6-36.6), p = 0.021), and remained significant when statistically compared in published multivariate models. In a multivariate analysis for pooled acute CEs, heart base Dmax was associated with CEs (HR 1.75, 95% CI 1.01-1.06, p = 0.04), but this was not the case for individual CEs. Using Fine and Gray models to account for the competing risk of death, left main coronary maximum dose was associated with atrial fibrillation (p = 0.024), proximal right coronary artery V15 (p = 0.023) and mean dose (p = 0.032), and the right atrium mean dose (p = 0.029) were associated with heart failure. No dose-volume metrics were significantly associated with acute coronary syndrome. None of the constituent base substructures dose were significantly associated with death. Dose to the heart base was associated with increased mortality and an increased pooled cardiac event rate. Accounting for endpoint-specific clinical covariates, only select constituent substructures of the heart base were associated with CEs and no substructures were independently associated with survival. Together, these findings are suggestive of possible interplay between the constituent base substructures in their mediation of radiation cardiotoxicity.

A geometry and dose-volume based performance monitoring of artificial intelligence models in radiotherapy treatment planning for prostate cancer

Background and PurposeClinical Artificial Intelligence (AI) implementations lack ground-truth when applied on real-world data. This study investigated how combined geometrical and dose-volume metrics can be used as performance monitoring tools to detect clinically relevant candidates for model retraining. Materials and MethodsFifty patients were analyzed for both AI-segmentation and planning. For AI-segmentation, geometrical (Standard Surface Dice 3 mm and Local Surface Dice 3 mm) and dose-volume based parameters were calculated for two organs (bladder and anorectum) to compare AI output against the clinically corrected structure. A Local Surface Dice was introduced to detect geometrical changes in the vicinity of the target volumes, while an Absolute Dose Difference (ADD) evaluation increased focus on dose-volume related changes. AI-planning performance was evaluated using clinical goal analysis in combination with volume and target overlap metrics. ResultsThe Local Surface Dice reported equal or lower values compared to the Standard Surface Dice (anorectum: (0.93 ± 0.11) vs (0.98 ± 0.04); bladder: (0.97 ± 0.06) vs (0.98 ± 0.04)). The ADD metric showed a difference of (0.9 ± 0.8)Gy for the anorectum D1cm3. The bladder D5cm3 reported a difference of (0.7 ± 1.5)Gy. Mandatory clinical goals were fulfilled in 90 % of the DLP plans. ConclusionsCombining dose-volume and geometrical metrics allowed detection of clinically relevant changes, applied to both auto-segmentation and auto-planning output and the Local Surface Dice was more sensitive to local changes compared to the Standard Surface Dice. This monitoring is able to evaluate AI behavior in clinical practice and allows candidate selection for active learning.

Automated evaluation for rapid implementation of knowledge-based radiotherapy planning models.

Knowledge-based planning (KBP) offers the ability to predict dose-volume metrics based on information extracted from previous plans, reducing plan variability and improving plan quality. As clinical integration of KBP is increasing there is a growing need for quantitative evaluation of KBP models. A .NET-based application, RapidCompare, was created for automated plan creation and analysis of Varian RapidPlan models. RapidCompare was designed to read calculation parameters and a list of reference plans. The tool copies the reference plan field geometry and structure set, applies the RapidPlan model, optimizes the KBP plan, and generates data for quantitative evaluation of dose-volume metrics. A cohort of 85 patients, divided into training (50), testing (10), and validation (25) groups, was used to demonstrate the utility of RapidCompare. After training and tuning, the KBP model was paired with three different optimization templates to compare various planning strategies in the validation cohort. All templates used the same set of constraints for the planning target volume (PTV). For organs-at-risk, the optimization template provided constraints using the whole dose-volume histogram (DVH), fixed-dose/volume points, or generalized equivalent uniform dose (gEUD). The resulting plans from each optimization approach were compared using DVH metrics. RapidCompare allowed for the automated generation of 75 total plans for comparison with limited manual intervention. In comparing optimization techniques, the Dose/Volume and Lines optimization templates generated plans with similar DVH metrics, with a slight preference for the Lines technique with reductions in heart V30Gy and spinal cord max dose. The gEUD model produced high target heterogeneity. Automated evaluation allowed for the exploration of multiple optimization templates in a larger validation cohort than would have been feasible using a manual approach. A final KBP model using line optimization objectives produced the highest quality plans without human intervention.

In silico trial of simulation-free hippocampal-avoidance whole brain adaptive radiotherapy

Background and PurposeHippocampal-avoidance whole brain radiotherapy (HA-WBRT) can be a time-consuming process compared to conventional whole brain techniques, thus potentially limiting widespread utilization. Therefore, we evaluated the in silico clinical feasibility, via dose-volume metrics and timing, by leveraging a computed tomography (CT)-based commercial adaptive radiotherapy (ART) platform and workflow in order to create and deliver patient-specific, simulation-free HA-WBRT. Materials and methodsTen patients previously treated for central nervous system cancers with cone-beam computed tomography (CBCT) imaging were included in this study. The CBCT was the adaptive image-of-the-day to simulate first fraction on-board imaging. Initial contours defined on the MRI were rigidly matched to the CBCT. Online ART was used to create treatment plans at first fraction. Dose-volume metrics of these simulation-free plans were compared to standard-workflow HA-WBRT plans on each patient CT simulation dataset. Timing data for the adaptive planning sessions were recorded. ResultsFor all ten patients, simulation-free HA-WBRT plans were successfully created utilizing the online ART workflow and met all constraints. The median hippocampi D100% was 7.8 Gy (6.6–8.8 Gy) in the adaptive plan vs 8.1 Gy (7.7–8.4 Gy) in the standard workflow plan. All plans required adaptation at first fraction due to both a failing hippocampal constraint (6/10 adaptive fractions) and sub-optimal target coverage (6/10 adaptive fractions). Median time for the adaptive session was 45.2 min (34.0–53.8 min). ConclusionsSimulation-free HA-WBRT, with commercially available systems, was clinically feasible via plan-quality metrics and timing, in silico.

PO33: Reliability of Vaginal Mucosa Small Volume Dose Metrics in Template Interstitial High-Dose-Rate Brachytherapy

PO33: Reliability of Vaginal Mucosa Small Volume Dose Metrics in Template Interstitial High-Dose-Rate Brachytherapy

Investigating the feasibility of using Ethos generated treatment plans for head and neck cancer patients.

The Varian Ethos treatment platform is designed to automatically create complex RT treatment plans, reducing both workload and operator variability in plan quality. The aim of this study is to evaluate the quality of Ethos-generated head and neck (H&N) treatment plans. Ethos plans were created for ten previous H&N patients and these were compared with the original clinical plans generated in Eclipse. Ethos automatically creates several plans with different field arrangements for each patient. All plans were compared quantitatively using: dose-volume metrics; dose conformity; dose heterogeneity and monitor units (MU). In addition, two H&N Oncologists assessed the clinical acceptability of the Ethos plans. Consultant 1 judged there to be at least three clinically acceptable Ethos plans for 9 out of 10 patients reviewed. Consultant 2 approved of at least two Ethos plans for 5 out of 5 patients reviewed. The Ethos plans' average dose metrics were comparable to the clinical plans. The average plan MU was similar for Eclipse and Ethos VMAT plans. The average plan MU for Ethos IMRT plans was larger with respect to all VMAT plans. The Ethos Treatment Planning system is capable of automatically creating good quality treatment plans for a range of H&N cancer patients.

Feasibility and Clinical Acceptability of Automation-Assisted 3D Conformal Radiotherapy Planning for Patients With Cervical Cancer in a Resource-Constrained Setting.

The Ocean Road Cancer Institute (ORCI) in Tanzania began offering 3D conformal radiation therapy (3DCRT) in 2018. Steep learning curves, high patient volume, and a limited workforce resulted in long radiation therapy (RT) planning workflows. We aimed to establish the feasibility of implementing an automation-assisted cervical cancer 3DCRT planning system. We performed chart abstractions on 30 patients with cervical cancer treated with 3DCRT at ORCI. The Radiation Planning Assistant (RPA) generated a new automated set of contours and plans on the basis of anonymized computed tomography images. Each were assessed for edit time requirements, dose-volume safety metrics, and clinical acceptability by two ORCI physician investigators. Dice similarity coefficient (DSC) agreement analysis was conducted between original and new contour sets. The average time to manually develop treatment plans was 7 days. Applying RPA, automated same-day contours and plans were developed for 29 of 30 patients (97%). Of the 29 evaluable contours, all were approved with <2 minutes of edit time. Agreement between clinical and RPA contours was highest for the rectum (median DSC, 0.72) and bladder (DSC, 0.90). Agreement was lower with the primary tumor clinical target volume (CTVp; DSC, 0.69) and elective nodal clinical target volume (CTVn; DSC, 0.63). All RPA plans were approved with <4 minutes of edit time. RPA target coverage was excellent, covering the CTVp with median V45 Gy 100% and CTVn with median V45 Gy 99.9%. Automation-assisted 3DCRT contouring yielded high levels of agreement for normal structures. The RPA met all planning safety metrics and sustained high levels of clinical acceptability with minimal edit times. This tool offers the potential to significantly decrease RT planning timelines while maintaining high-quality RT delivery in resource-constrained settings.

Dosimetry and acute radiation enteritis comparison between prone and supine position in IMRT for gynecological cancers.

To probe the differences of dosimetry and acute radiation enteritis between prone and supine position in gynecological cancer patients treated with intensity-modulate radiotherapy (IMRT). Gynecologic tumor patients who received IMRT from January 2020 to July 2021 were analyzed. 60 patients were enrolled and divided into the supine or prone position group according to different radiotherapy positions, including 34 patients in prone position and 26 patients in supine position. The dose-volume histogram of organs at risk (OARs) and the incidence of acute radiation enteritis were compared between the two groups. Multivariate logistic regression analysis was conducted to show the clinical characteristics and dose volume metrics to the association of acute radiation enteritis. The percentage of volume receiving 5Gy, 10Gy, 15Gy, 20Gy, 30Gy, 40Gy, and 45Gy doses for the small intestine were 79.0%, 67.4%, 59.6%, 44.3%, 17.0%, 8.9%, and 6.0%, respectively in the prone group, which were lower than those in the supine group (P<0.05). The mean radiation dose (Dmean ) of the small intestine exposure in prone group was decreased (P<0.001). Compared with the supine group, the prone group who suffered from acute radiation enteritis were much less. The probability of indigestion, nausea, vomiting, diarrhea, and abdominal pain in the prone position were 35.29%, 29.41%, 17.65%, 38.24%, and 5.88%, respectively. The differences in indigestion, nausea, and diarrhea between the two groups were statistically significant (P=0.012, P=0.029, and P=0.041). Multivariate logistic regression analysis was shown that prone position was found to be protective against indigestion (P=0.002), nausea (P=0.013), vomiting (P=0.035), and abdominal pain (P=0.021). Prone position in IMRT for gynecological cancers could significantly reduce radiation dose to the small bowel and colon, which would decrease the occurrence and severity of acute intestinal side effects possibly.

Random Forest Modeling of Acute Toxicity in Anal Cancer: Effects of Peritoneal Cavity Contouring Approaches on Model Performance

Our purpose was to analyze the effect on gastrointestinal (GI) toxicity models when their dose-volume metrics predictors are derived from segmentations of the peritoneal cavity after different contouring approaches. A random forest machine learning approach was used to predict acute grade ≥3 GI toxicity from dose-volume metrics and clinicopathologic factors for 246 patients (toxicity incidence=9.5%) treated with definitive chemoradiation for squamous cell carcinoma of the anus. Three types of random forest models were constructed based on different bowel bag segmentation approaches: (1) physician-delineated after Radiation Therapy Oncology Group (RTOG) guidelines, (2) autosegmented by a deep learning model (nnU-Net) following RTOG guidelines, and (3) autosegmented but spanning the entire bowel space. Each model type was evaluated using repeated cross-validation (100 iterations; 50%/50% training/test split). The performance of the models was assessed using area under the precision-recall curve (AUPRC) and the receiver operating characteristic curve (AUROCC), as well as optimal F1 score. When following RTOG guidelines, the models based on the nnU-Net auto segmentations (mean values: AUROCC, 0.71 ± 0.07; AUPRC, 0.42 ± 0.09; F1 score, 0.46 ± 0.08) significantly outperformed (P < .001) those based on the physician-delineated contours (mean values: AUROCC, 0.67 ± 0.07; AUPRC, 0.34 ± 0.08; F1 score, 0.36 ± 0.07). When spanning the entire bowel space, the performance of the autosegmentation models improved considerably (mean values: AUROCC, 0.87 ± 0.05; AUPRC, 0.70 ± 0.09; F1 score, 0.68 ± 0.09). Random forest models were superior at predicting acute grade ≥3 GI toxicity when based on RTOG-defined bowel bag autosegmentations rather than physician-delineated contours. Models based on autosegmentations spanning the entire bowel space show further considerable improvement in model performance. The results of this study should be further validated using an external data set.

A deep-learning assisted bioluminescence tomography method to enable radiation targeting in rat glioblastoma

Objective. A novel solution is required for accurate 3D bioluminescence tomography (BLT) based glioblastoma (GBM) targeting. The provided solution should be computationally efficient to support real-time treatment planning, thus reducing the x-ray imaging dose imposed by high-resolution micro cone-beam CT. Approach. A novel deep-learning approach is developed to enable BLT-based tumor targeting and treatment planning for orthotopic rat GBM models. The proposed framework is trained and validated on a set of realistic Monte Carlo simulations. Finally, the trained deep learning model is tested on a limited set of BLI measurements of real rat GBM models. Significance. Bioluminescence imaging (BLI) is a 2D non-invasive optical imaging modality geared toward preclinical cancer research. It can be used to monitor tumor growth in small animal tumor models effectively and without radiation burden. However, the current state-of-the-art does not allow accurate radiation treatment planning using BLI, hence limiting BLI’s value in preclinical radiobiology research. Results. The proposed solution can achieve sub-millimeter targeting accuracy on the simulated dataset, with a median dice similarity coefficient (DSC) of 61%. The provided BLT-based planning volume achieves a median encapsulation of more than 97% of the tumor while keeping the median geometrical brain coverage below 4.2%. For the real BLI measurements, the proposed solution provided median geometrical tumor coverage of 95% and a median DSC of 42%. Dose planning using a dedicated small animal treatment planning system indicated good BLT-based treatment planning accuracy compared to ground-truth CT-based planning, where dose-volume metrics for the tumor fall within the limit of agreement for more than 95% of cases. Conclusion. The combination of flexibility, accuracy, and speed of the deep learning solutions make them a viable option for the BLT reconstruction problem and can provide BLT-based tumor targeting for the rat GBM models.

Dosimetrically triggered adaptive radiotherapy for head and neck cancer: Considerations for the implementation of clinical protocols.

Defining dosimetric rules to automatically detect patients requiring adaptive radiotherapy (ART) is not straightforward, and most centres perform ad-hoc ART with no specific protocol. This study aims to propose and analyse different steps to design a protocol for dosimetrically triggered ART of head and neck (H&N) cancer. As a proof-of-concept, the designed protocol was applied to patients treated in TomoTherapy units, using their available software for daily MVCT image and dose accumulation. An initial protocol was designed by a multidisciplinary team, with a set of flagging criteria based only on dose-volume metrics, including two action levels: (1) surveillance (orange flag), and (2) immediate verification (red flag). This protocol was adapted to the clinical needs following an iterative process. First, the protocol was applied to 38 H&N patients with daily imaging. Automatic software generated the daily contours, recomputed the daily dose and flagged the dosimetric differences with respect to the planning dose. Second, these results were compared, by a sensitivity/specificity test, to the answers of a physician. Third, the physician, supported by the multidisciplinary team, performed a self-analysis of the provided answers and translated them into mathematical rules in order to upgrade the protocol. The upgraded protocol was applied to different definitions of the target volume (i.e. deformed CTV + 0, 2 and 4mm), in order to quantify how the number of flags decreases when reducing the CTV-to-PTV margin. The sensitivity of the initial protocol was very low, specifically for the orange flags. The best values were 0.84 for red and 0.15 for orange flags. After the review and upgrade process, the sensitivity of the upgraded protocol increased to 0.96 for red and 0.84 for orange flags. The number of patients flagged per week with the final (upgraded) protocol decreased in median by 26% and 18% for red and orange flags, respectively, when reducing the CTV-to-PTV margin from 4 to 2mm. This resulted in only one patient flagged at the last fraction for both red and orange flags. Our results demonstrate the value of iterative protocol design with retrospective data, and shows the feasibility of automatically-triggered ART using simple dosimetric rules to mimic the physician's decisions. Using a proper target volume definition is important and influences the flagging rate, particularly when decreasing the CTV-to-PTV margin.

Geometric accuracy in patient positioning for stereotactic radiotherapy of intracranial tumors.

This study determines and compares the geometric setup errors between stereoscopic x-ray and kilo-voltage cone beam CT (CBCT) in phantom tests on a linear accelerator (linac) for image-guided (IG) stereotactic radiotherapy of intracranial tumors. Additionally, dose-volume metrics in the target volumes of the setup errors of CBCT were evaluated. A Winston-Lutz- and an anthropomorphic phantom were used. The mean deviation and root mean square error (RMSE) of CBCT and stereoscopic x-ray were compared. Dose-volume metrics of the planning target volume (PTV) and gross target volume (GTV) for CBCT were calculated. The RMSEs in the tests with the Winston-Lutz-Phantom were 0.3mm, 1.1mm and 0.3mm for CBCT and 0.1mm, 0,1 mm and<0.1mm for stereoscopic x-ray in the translational dimensions (right-left, anterior-posterior and superior-inferior). The RMSEs in the tests with the anthropomorphic phantom were 0.3mm, 0.2mm and 0.1mm for CBCT and 0.1mm, 0,1 mm and<0.1mm for stereoscopic x-ray. The effects on dose-volume metrics of the setup errors of CBCT on the GTV were within 1 % for all considered dose values. The effects on the PTV were within 5 % for all considered dose values. Both IG systems provide high accuracy patient positioning within a submillimeter range. The phantom tests exposed a slightly higher accuracy of stereoscopic x-ray than CBCT. The comparison with other studies with a similar purpose emphasizes the importance of individual IG installation quality assurance.

Detection of suboptimal IMRT treatment plan using machine learning on radiomics features of dose distribution for lung cancers

Quality assurance in radiotherapy is an important process so that the use of radiation provides maximum benefits. Currently, the implementation of machine learning (ML) in the quality assurance of treatment planning is growing. In this study, 34 optimal intensity-modulated radiation therapy (IMRT) treatment plans and 10 suboptimal IMRT treatment plans obtained from Siloam MRCCC Semanggi Hospital were used to train an ML model of the type autoencoder for anomaly detection developed using PyTorch. There were four stages in this study, namely the preparation stage, development stage, validation stage, and evaluation stage. At the development stage, the raw data was prepared so that it is ready to be used for training. At the development stage, the model was developed and a hyperparameters optimization was performed. The accuracy of the model was analyzed at the validation stage. Finally, at the evaluation stage, the model performance was evaluated along with a Mann-Whitney U test on dose-volume histogram (DVH) parameters, radiomics features, and DVH metrics (conformity index and homogeneity index) to show the difference between treatment plans. The model used 161 radiomics features with an epoch of 1250 iterations, 150-50-17 hidden layers configuration, and a learning rate of 0.2 as the most optimal configuration. The results showed an accuracy of 36% with 7% of radiomics features, 50% of DVH parameters, and the homogeneity index being different significantly. After refinement, that is removing data with conformity index below one, the accuracy became 50% with 12% of radiomics features, 45% of DVH parameters, and both DVH metrics being different significantly. If the radiomics features used are those that were significantly different, the accuracy increased to 93%. From these results, it can be concluded that most radiomics features are noise that need to be removed so the model can detect suboptimal treatment plans. In addition, the planning target volume segment along with the firstorder radiomics features group is the main differentiator between the optimal and suboptimal treatment plans.

Generating deliverable DICOM RT treatment plans for prostate VMAT by predicting MLC motion sequences with an encoder-decoder network.

Deep learning-based auto-planning is an active research field; however, for some tasks a treatment planning system (TPS) is still required. To introduce a deep learning-based model generating deliverable DICOM RT treatment plans that can be directly irradiated by a linear accelerator (LINAC). The model was based on an encoder-decoder network and can predict multileaf collimator (MLC) motion sequences for prostate VMAT radiotherapy. A total of 619 treatment plans from 460 patients treated for prostate cancer with single-arc VMAT were included in this study. An encoder-decoder network was trained using 465 clinical treatment plans and validated on 77 plans. The performance was analyzed on a separate test set of 77 treatment plans. Separate L1 losses were computed for the leaf and jaw positions as well as the monitor units, with the leaf loss being weighted by a factor of 100 before being added to the other losses. The generated treatment plans were recalculated in a treatment planning system and the dose-volume metrics and gamma passing rates were compared to the original dose. All generated treatment plans showed good agreement with the original data, with an average gamma passing rate (3%/3mm) of 91.9±7.1%. However, the coverage of the PTVs. was slightly lower for the generated plans (D98% =92.9±2.6%) in comparison to the original plans (D98% =95.7±2.2%). There was no significant difference in mean dose to the bladder between the predicted and original plan (Dmean of 28.0±13.5vs. 28.1±13.3% of prescribed dose) or rectum (Dmean of 42.3±7.4vs. 42.6±7.5%). The maximum dose to bladder was only slightly higher in the predicted plans (D2% of 100.7±5.3vs. 99.8±4.0%) and for the rectum it was even lower (D2% of 100.5±3.7vs. 100.1±4.3). The deep learning-based model could predict MLC motion sequences in prostate VMAT plans, eliminating the need for sequencing inside a TPS, thus revolutionizing autonomous treatment planning workflows. This research completes the loop in deep learning-based treatment planning processes, enabling more efficient workflows for real-time or online adaptive radiotherapy.

Benchmarking Automated Machine Learning-Enhanced Planning With Ethos Against Manual and Knowledge-Based Planning for Locally Advanced Lung Cancer

Currently, there is insufficient guidance for standard fractionation lung planning using the Varian Ethos adaptive treatment planning system and its unique intelligent optimization engine. Here, we address this gap in knowledge by developing a methodology to automatically generate high-quality Ethos treatment plans for locally advanced lung cancer. Fifty patients previously treated with manually generated Eclipse plans for inoperable stage IIIA-IIIC non-small cell lung cancer were included in this institutional review board-approved retrospective study. Fifteen patient plans were used to iteratively optimize a planning template for the Daily Adaptive vs Non-Adaptive External Beam Radiation Therapy With Concurrent Chemotherapy for Locally Advanced Non-Small Cell Lung Cancer: A Prospective Randomized Trial of an Individualized Approach for Toxicity Reduction (ARTIA-Lung); the remaining 35 patients were automatically replanned without intervention. Ethos plan quality was benchmarked against clinical plans and reoptimized knowledge-based RapidPlan (RP) plans, then judged using standard dose-volume histogram metrics, adherence to clinical trial objectives, and qualitative review. Given equal prescription target coverage, Ethos-generated plans showed improved primary and nodal planning target volume V95% coverage (P < .001) and reduced lung gross tumor volume V5 Gy and esophagus D0.03 cc metrics (P ≤ .003) but increased mean esophagus and brachial plexus D0.03 cc metrics (P < .001) compared with RP plans. Eighty percent, 49%, and 51% of Ethos, clinical, and RP plans, respectively, were "per protocol" or met "variation acceptable" ARTIA-Lung planning metrics. Three radiation oncologists qualitatively scored Ethos plans, and 78% of plans were clinically acceptable to all reviewing physicians, with no plans receiving scores requiring major changes. A standard Ethos template produced lung radiation therapy plans with similar quality to RP plans, elucidating a viable approach for automated plan generation in the Ethos adaptive workspace.

Radiation-induced circulating microRNAs linked to echocardiography parameters after radiotherapy.

Patients treated with radiotherapy to the chest region are at risk of cardiac sequelae, however, identification of those with greatest risk of complications remains difficult. Here, we sought to determine whether short-term changes in circulating miRNA expression are related to measures of cardiac dysfunction in follow-up. Two parallel patient cohorts were enrolled and followed up for 3 years after completion of RT to treat left-sided breast cancer. In the primary group (N=28) we used a a panel of 752 miRNAs to identify miRNAs associated with radiation and cardiac indices at follow up. In the second, independent cohort (N=56) we validated those candidate miRNAs with a targeted qPCR panel. In both cohorts. serum samples were collected before RT, 24h after the last dose and 1 month after RT; cardiac echocardiography was performed 2.5-3 year after RT. Seven miRNAs in the primary group showed marked changes in serum miRNAs immediately after RT compared to baseline and associations with cardiopulmonary dose-volume histogram metrics. Among those miRNAs: miR-15b-5p, miR-22-3p, miR-424-5p and miR-451a were confirmed to show significant decrease of expression 24 hours post-RT in the validation cohort. Moreover, miR-29c, miR-451 and miR-424 were correlated with the end-diastolic diameter of the left ventricle, which was also confirmed in multivariable analysis adjusting for RT-associated factors. We identified a subset of circulating miRNAs predictive for cardiac function impairment in patients treated for left-sided breast cancer, although longer clinical observation could determine if these can be used to predict major clinical endpoints.

Skin/mucosa avoidance radiotherapy (SMART) versus conventional volumetric arc-based radiotherapy (VMAT) for the treatment of head and neck cancer: Dosimetric feasibility study.

Intensity modulated radiotherapy (IMRT) for head and neck cancer has led to a reduction in radiotherapy doses to normal tissues, like the salivary glands, while maintaining high rates of local control. Oral mucosal and skin toxicity is still a major source of treatment-related morbidity, occurring in most patients. We conducted a dosimetric feasibility study with the goal of creating a methodology that could theoretically reduce the dose of radiation to skin and oral mucosa, while maintaining comparable avoidance of other organs at risk, and planning target volume (PTV) coverage. The clinical plans of patients treated previously were replanned using coplanar VMAT arcs on a TrueBeam STx using the photon optimizer (PO) version 15.6 and the Acuros XB dose calculation algorithm. Comparisons were made between three methodologies: "Conventional," "Skin Sparing" and a skin/mucosa avoiding ("SMART") technique, with dose metrics being compared using analysis of variance, with a Bonferroni correction to account for multiple pairwise comparisons. The maximum grade of mucositis and radiation dermatitis during treatment was correlated to different dose-volume metrics to predict what could be clinically meaningful. Sixteen patients met the study criteria and were replanned using the skin sparing and SMART techniques. Maximum doses to the skin sparing structure were reduced from 64.2Gy to 56.6 and 55.9Gy, in the skin sparing and SMART plans (p<0.0001), and mean doses reduced from 26.7Gy to 20.0 and 20.2Gy, respectively (p<0.0001). Maximum doses to the oral cavity structure were not reduced by either technique, however mean dose to the oral cavity structure was reduced from 39.03Gy to 33.5Gy by the SMART technique (p<0.0001). There was a slight reduction in PTV_High coverage by the V95% in the SMART plans (99.52%vs. 98.79%, p=0.0073), and a similar slight reduction in PTV_Low coverage by the V95% by both the skin sparing and SMART plans (99.74%vs. 97.89%vs. 97.42%, p<0.0001). Maximum doses to organs at risk were not statistically different between techniques. Dose to oral cavity and maximum grade experienced during radiotherapy correlated. The Spearman correlation coefficient for dose to 20%, 50%, and 80% of the volume of oral cavity was 0.5 (p=0.048), 0.64 (p=0.007), and 0.62 (p=0.010), respectively. Skin toxicity grade was only found to be correlated with the D20% of the skin sparing structure (Spearman correlation coefficient of 0.58, p=0.0177). The SMART technique appears to be able to reduce maximum and mean skin dose, as well as mean oral cavity doses, while only slightly reducing PTV coverage, with acceptable OAR doses. We feel the improvements warrant investigation in a clinical trial.