Radiotherapy Treatment Planning Research Articles

A feasibility study of using virtual noncontrast images synthesized from dual-energy computed tomography for radiotherapy treatment planning.

In the traditional computed tomography (CT) simulation process, patients need to undergo CT scans before and after injection of iodine-based contrast agent, resulting in a cumbersome workflow and additional imaging dose. Contrast-enhanced spectral CT can synthesize true contrast-enhanced (TCE) images and virtual noncontrast (VNC) images in a single scan without geometric misalignment. To improve work efficiency and reduce patients' imaging dose, we studied the feasibility of using VNC images for radiotherapy treatment planning, with true noncontrast (TNC) images as references and explored its dosimetric advantages compared to using TCE images. Specifically, this study examined tumors near bones, including cases of bone metastasis and myeloma. A total of 54 patients (20 patients with cervical cancer, 15 patients with esophageal cancer, and 15 patients with laryngeal cancer, and 4 patients with bone metastasis or hip replacement) who underwent non-contrast-enhanced and contrast-enhanced spectral CT simulation were retrospectively enrolled between July 2023 and March 2024. The study was approved by the institutional review board. The CT images were acquired using a second-generation fast kilovoltage peak-switching CT. Treatment plans for photon radiotherapy were optimized and calculated using TNC images and recalculated based on TCE and VNC images. To evaluate image and dosimetric equivalent, several metrics, including Hounsfield unit (HU) value differences, gamma pass rates and dose-volume histogram (DVH) parameters of planning target volume (PTV), and organs at risk (OARs), were compared. In terms of HU value difference, for the majority of patients, the HU value differences of the PTV between TCE and TNC images (36.7±23.9 and 27.8±2.1 in esophageal and laryngeal cancer, respectively) were greater than those between VNC and TNC images (10.59±25.8 and 3.55±1.9 in esophageal and laryngeal cancer, respectively). Regarding dosimetry, the gamma pass rates between VNC and TNC were 1 in 2%/2 mm and 3%/3 mm. Most DVH parameter differences were less than 1% between the VNC and TNC plans and between TCE and TNC plans. Meanwhile, in some blood-rich OARs such as heart and small intestine, VNC shows dosimetric potential compared to TCE based on the statistically significant DVH parameters differences. By analyzing radiotherapy treatment plans with target areas located in different locations, including tumors near bones such as bone metastasis, we preliminarily verified the feasibility of using VNC images for photon dose calculation. This approach can effectively improve clinical workflow and reduce the image dose to patients.

Development, characterization and radiation dosimetry evaluation of Bovine gelatin crosslinked with Gum Arabic Aldehyde as brain phantom gel material in radiation therapy

Brain phantom gel materials are of critical importance for accuracy of dosimetry, treatment planning and quality assurance in radiotherapy. Development of reliable and realistic phantoms enhances improved radiotherapy practices. Gel dosimeters have unique property to record radiation dose distribution in three dimensions. Polymer gels also have added advantages for brachytherapy dosimetry. Objective of the study was to develop an alternative polymeric gel material equivalent to human brain for conducting radiation dosimetry studies in radiotherapy. Hydrogel prepared from gelatin and gum arabic aldehyde was used to develop a brain phantom gel material for radiation dosimetry in radiotherapy. The results of comparative studies with G-GAAB gel strongly suggest, the gel can successfully be utilized as a brain equivalent material for radiation dosimetry in place of standard water phantom by measuring (a) CT number values (b) mass attenuation coefficient values at two X-ray energies used in radiation treatment (c) absorbed dose values at different depths for various setup conditions. The midrange CT number values inside gel material and that of human brain measured from CT images were 25.5HU and 25HU respectively with a variation of 2%. The mass attenuation coefficients for brain, water and gel material at 6MV photons were 0.0275cm2/g, 0.0280cm2/g,0.0270cm2/g and for 15MV photons, the attenuation coefficients were 0.0192cm2/g, 0.0190cm2/g and 0.0180cm2/g respectively. The percentage deviation of all measurements of absorbed dose values in gel phantom material, compared with the values of standard water phantom at various radiation dosimetry setup parameters, is less than 2%.

Prior information guided deep-learning model for tumor bed segmentation in breast cancer radiotherapy.

Tumor bed (TB) is the residual cavity of resected tumor after surgery. Delineating TB from CT is crucial in generating clinical target volume for radiotherapy. Due to multiple surgical effects and low image contrast, segmenting TB from soft tissue is challenging. In clinical practice, titanium clips were used as marks to guide the searching of TB. However, this information is limited and may cause large error. To provide more prior location information, the tumor regions on both pre-operative and post-operative CTs are both used by the deep learning model in segmenting TB from surrounding tissues. For breast cancer patient after surgery and going to be treated by radiotherapy, it is important to delineate the target volume for treatment planning. In clinical practice, the target volume is usually generated from TB by adding a certain margin. Therefore, it is crucial to identify TB from soft tissue. To facilitate this process, a deep learning model is developed to segment TB from CT with the guidance of prior tumor location. Initially, the tumor contour on the pre-operative CT is delineated by physician for surgical planning purpose. Then this contour is transformed to the post-operative CT via the deformable image registration between paired pre-operative and post-operative CTs. The original and transformed tumor regions are both used as inputs for predicting the possible region of TB by the deep-learning model. Compared to the one without prior tumor contour information, the dice similarity coefficient of the deep-learning model with the prior tumor contour information is improved significantly (0.812 vs. 0.520, P = 0.001). Compared to the traditional gray-level thresholding method, the dice similarity coefficient of the deep-learning model with the prior tumor contour information is improved significantly (0.812 vs.0.633, P = 0.0005). The prior tumor contours on both pre-operative and post-operative CTs provide valuable information in searching for the precise location of TB on post-operative CT. The proposed method provided a feasible way to assist auto-segmentation of TB in treatment planning of radiotherapy after breast-conserving surgery.

The Segment Anything foundation model achieves favorable brain tumor auto-segmentation accuracy in MRI to support radiotherapy treatment planning.

Promptable foundation auto-segmentation models like Segment Anything (SA, Meta AI, New York, USA) represent anovel class of universal deep learning auto-segmentation models that could be employed for interactive tumor auto-contouring in RT treatment planning. Segment Anything was evaluated in an interactive point-to-mask auto-segmentation task for glioma brain tumor auto-contouring in 16,744 transverse slices from 369 MRI datasets (BraTS 2020 dataset). Up to nine interactive point prompts were automatically placed per slice. Tumor boundaries were auto-segmented on contrast-enhanced T1w sequences. Out of the three auto-contours predicted by SA, accuracy was evaluated for the contour with the highest calculated IoU (Intersection over Union, "oracle mask," simulating interactive model use with selection of the best tumor contour) and for the tumor contour with the highest model confidence ("suggested mask"). Mean best IoU (mbIoU) using the best predicted tumor contour (oracle mask) in full MRI slices was 0.762 (IQR 0.713-0.917). The best 2D mask was achieved after amean of 6.6 interactive point prompts (IQR 5-9). Segmentation accuracy was significantly better for high- compared to low-grade glioma cases (mbIoU 0.789 vs. 0.668). Accuracy was worse using the suggested mask (0.572). Stacking best tumor segmentations from transverse MRI slices, mean 3D Dice score for tumor auto-contouring was 0.872, which was improved to 0.919 by combining axial, sagittal, and coronal contours. The Segment Anything foundation segmentation model can achieve high accuracy for glioma brain tumor segmentation in MRI datasets. The results suggest that foundation segmentation models could facilitate RT treatment planning when properly integrated in aclinical application.

Clinical Implementation of Cone Beam Computed Tomography-Guided Online Adaptive Radiation Therapy in Whole Breast Irradiation

PurposeIn postoperative breast irradiation, changes in the breast contour and arm positioning can result in patient positioning errors and offline re-planning. This can lead to increased treatment burden, and strain on departmental logistics due to the need for additional cone-beam CT images or even a new radiotherapy treatment plan (TP). Online daily adaptive radiotherapy (oART) could provide a solution to these challenges. We have clinically implemented and evaluated the feasibility of oART for whole breast irradiation. Methods and MaterialsTwenty patients treated with postoperative whole breast right irradiation (5 × 5.2 Gy) were included in BREAST-ART, a prospective single-arm trial. Dosimetry of the reference TP calculated on the daily anatomy and adaptive TP were compared. Duration of the oART workflow, in-house satisfaction questionnaires, and acute toxicity (CTCAE v5.0) was collected. The oART workflow was evaluated by investigating the impact of manual corrections of influencer and target contours on treatment time and quality. ResultsIn the first 17 patients (85 fractions), the on-couch time, i.e. time between the end of CBCT1 and CBCT3, was median 13.8 minutes (range=11–25). Retrospective evaluation of the use of the influencer (i.e. breast) in 4 patients (20 fractions) and manual correction of the most cranial and caudal target contours (i.e. 4 mm) in 10 patients (36 fractions) was done. This resulted in a reduced on-couch time in the last 3 clinical patients to a median of 13.0 minutes (range=11–19). No grade 3 or higher toxicity was observed, and 19/20 patients indicated to prefer the same treatment again. Skin marks for patient positioning during treatment were no longer necessary. ConclusionsThis study showed the feasibility, challenges, and practical solutions for the implementation of oART for breast cancer patients. Future work will focus on more complex breast indications such as whole breast including axillary nodes, to further investigate benefits and challenges of oART in breast cancer.

Monte Carlo dose calculation for photon and electron radiotherapy on dynamically deforming anatomy.

Dose calculation in radiotherapy aims to accurately estimate and assess the dose distribution of a treatment plan. Monte Carlo (MC) dose calculation is considered the gold standard owing to its ability to accurately simulate particle transport in inhomogeneous media. However, uncertainties such as the patient's dynamically deforming anatomy can still lead to differences between the delivered and planned dose distribution. Development and validation of a deformable voxel geometry for MC dose calculations (DefVoxMC) to account for dynamic deformation in the dose calculation process of photon- and electron-based radiotherapy treatment plans for clinically motivated cases. DefVoxMC relies on the subdivision of a regular voxel geometry into dodecahedrons. It allows shifting the dodecahedrons' corner points according to the deformation in the patient's anatomy using deformation vector fields (DVF). DefVoxMC is integrated into the Swiss Monte Carlo Plan (SMCP) to allow the MC dose calculation of photon- and electron-based treatment plans on the deformable voxel geometry. DefVoxMC is validated in two steps. A compression test and a Fano test are performed in silico. Delta4 (for photon beams) and EBT4 film measurements in a cubic PMMA phantom (for electron beams) are performed on a TrueBeam in Developer Mode for clinically motivated treatment plans. During these measurements, table motion is used to mimic rigid dynamic patient motion. The measured and calculated dose distributions are compared using gamma passing rate (GPR) (3% / 2mm (global), 10% threshold). DefVoxMC is used to study the impact of patient-recorded breathing motion on the dose distribution for clinically motivated lung and breast cases, each prescribed 50Gy to 50% of the target volume. A volumetric modulated arc therapy (VMAT) and an arc mixed-beam radiotherapy (Arc-MBRT) plan are created for the lung and breast case, respectively. For the dose calculation, the dynamic deformation of the patient's anatomy is described by DVFs obtained from deformable image registration of the different phases of 4DCTs. The resulting dose distributions are compared to the ones of the static situation using dose-volume histograms and dose differences. DefVoxMC is successfully integrated into the SMCP to enable the MC dose calculation of photon- and electron-based treatments on a dynamically deforming patient anatomy. The compression and the Fano test agree within 1.0% and 0.1% with the expected result, respectively. Delta4 and EBT4 film measurements agree with the calculated dose by a GPR>95%. For the clinically motivated cases, breathing motion resulted in areas with a dose increase of up to 26.9Gy (lung) and up to 7.6Gy (breast) compared to the static situation. The largest dose differences are observed in high-dose-gradient regions perpendicular to the beam plane, consequently decreasing the planning target volume coverage (V95%) by 4.2% for the lung case and 2.0% for the breast case. A novel method for MC dose calculation for photon- and electron-based treatments on dynamically deforming anatomy is successfully developed and validated. Applying DefVoxMC to clinically motivated cases, we found that breathing motion has non-negligible impact on the dosimetric plan quality.

OSAIRIS: Lessons Learned From the Hospital-Based Implementation and Evaluation of an Open-Source Deep-Learning Model for Radiotherapy Image Segmentation

Several studies report the benefits and accuracy of using autosegmentation for organ at risk (OAR) outlining in radiotherapy treatment planning. Typically, evaluations focus on accuracy metrics, and other parameters such as perceived utility and safety are routinely ignored. Here, we report our finding from the implementation and clinical evaluation of OSAIRIS, an open-source AI model for radiotherapy image segmentation that was carried out as part of its development into a medical device. The device contours OARs in the head and neck and male pelvis (referred to as the prostate model), and is designed to be used as a time-saving workflow device, alongside a clinician. Unlike standard evaluation processes, which heavily rely on accuracy metrics alone, our evaluation sought to demonstrate the tangible benefits, quantify utility and assess risk within a specific clinical workflow. We evaluated the time-saving benefit this device affords to clinicians, and how this time-saving might be linked to accuracy metrics, as well as the clinicians' assessment of the usability of the OSAIRIS contours in comparison to their colleagues' contours and those from other commercial AI contouring devices. Our safety evaluation focused on whether clinicians can notice and correct any errors should they be included in the output of the device.We found that OSAIRIS affords a significant time-saving of 36% (5.4 ± 2.1 minutes) when used for prostate contouring and 67% (30.3 ± 8.7 minutes) for head and neck contouring. Combining editing time data with accuracy metrics, we found the Hausdorff distance best correlated with editing-time, outperforming dice, the industry-standard, with a Spearman correlation coefficient of 0.70, and a Kendall coefficient of 0.52. Our safety and risk-mitigation exercise showed that anchoring bias is present when clinicians edit AI-generated contours, with the effect seemingly more pronounced for some structures over others. Most errors, however, were corrected by clinicians, with 72% of the head and neck errors 81% of the prostate errors removed in the editing step. Notably, our blinded clinician contour rating exercise showed that gold standard clinician contours are not rated more highly than the AI-generated contours.We conclude that evaluations of AI in a clinical setting must consider the clinical workflow in which the device will be used, and not rely on accuracy metrics alone, in order to reliably assess the benefits, utility and safety of the device. The effects of human-AI inter-operation must be evaluated to accurately assess the practical usability and potential uptake of the technology, as demonstrated in our blinded clinical utility review. The clinical risks posed by the use of the device must be studied and mitigated as far as possible, and our ‘Mystery Shopping’ experiment provides a template for future such assessments.

Transformer-Integrated Hybrid Convolutional Neural Network for Dose Prediction in Nasopharyngeal Carcinoma Radiotherapy.

Radiotherapy is recognized as the major treatment of nasopharyngeal carcinoma. Rapid and accurate dose prediction can improve the efficiency of the treatment planning process and the quality of radiotherapy plans. Currently, deep learning-based methods have been widely applied to dose prediction for radiotherapy treatment planning. However, it is important to note that existing models based on Convolutional Neural Networks (CNN) often overlook long-distance information. Although some studies try to use Transformer to solve the problem, it lacks the ability of CNN to process the spatial information inherent in images. Therefore, we propose a novel CNN and Transformer hybrid dose prediction model. To enhance the transmission ability of features between CNN and Transformer, we design a hierarchical dense recurrent encoder with a channel attention mechanism. Additionally, we propose a progressive decoder that preserves richer texture information through layer-wise reconstruction of high-dimensional feature maps. The proposed model also introduces object-driven skip connections, which facilitate the flow of information between the encoder and decoder. Experiments are conducted on in-house datasets, and the results show that the proposed model is superior to baseline methods in most dosimetric criteria. In addition, the image analysis metrics including PSNR, SSIM, and NRMSE demonstrate that the proposed model is consistent with ground truth and produces promising visual effects compared to other advanced methods. The proposed method could be taken as a powerful clinical guidance tool for physicists, significantly enhancing the efficiency of radiotherapy planning. The source code is available at https://github.com/CDUTJ102/THCN-Net .

P13.01.A 11C-METHIONIN PET FOR RADIOTHERAPY TREATMENT PLANNING IN PATIENTS WITH RAPID EARLY PROGRESSION AFTER GLIOBLASTOMA SURGERY: PROSPECTIVE PHASE II TRIAL

Abstract BACKGROUND Radiotherapy (RT) is a standard treatment for nearly all glioblastoma patients following initial surgery. Few retrospective studies indicate negative prognostic instances of progression during the planning magnetic resonance (MR) (up to 1 week before initiating RT), termed Rapid Early Progression (REP). The optimal RT management for REP patients remains uncertain. The objective of this prospective phase II trial (NCT05608395) is to assess impact of 11C-Methionine PET used for RT planning in REP glioblastoma patients. It is one of the first prospective clinical interventional trials focused on this specific cohort of patients. MATERIAL AND METHODS We enrolled glioblastoma, IDHwt, or Astrocytoma, IDHmt, WHO grade IV patients, who developed REP characterized by 1) increase in postoperative residuum by ≥ 25%, 2) appearance of new contras enhancing lesion, 3) unequivocal progression of the unresected satelite. Patients received treatment based on the Stupp or Perry protocol. Treatment response was evaluated using RANO criteria. RT target volumes were delineated as follows: Gross tumor volume included tumor cavity, enhancing lesion and 11C-MET PET (1.3 tumor-to-background ratio). The clinical target volume was GTV plus a modified 2cm margin reflecting surrounding organs at risk. Volumetric analyses of different radiotherapy target volume were performed using EclipseTM software including patterns of failure. RESULTS During 12/2020 - 12/2023, total of 31 patients were enrolled (16 treated via abbreviated RT course); median age 60 years, ECOG 0-1 in 28 patients, median follow up 20 months. No effect of 11C-MET PET - based radiotherapy treatment planning of GBM patients with REP was observed on PFS (median 3.4 months comparing to 4.9 in historical control cohort) and OS (12.3 months comparing to 15.7 months). Median MET volume was 7.3cm3 (43% of MRI volume), MET avidity was presented in 7 patients et least 1cm beyond MRI volume. Central recurrence was presented in 87% patients. CONCLUSION The optimal treatment of patients with REP is unknown and needs to be studied in more details including dose escalation studies with reduced target margins potentialy directed also by aminoacid PET examination. Adjustment of target radiotherapy volumes using 11C-MET PET did not lead to improved PFS or OS. Supported by NU20-03-00148.

Optimization of image reconstruction technique for respiratory-gated lung stereotactic body radiotherapy treatment planning using four-dimensional CT: a phantom study.

Patient respiration is characterized by respiratory parameters, such as cycle, amplitude, and baseline drift. In treatment planning using four-dimensional computed tomography (4DCT) images, the target dose may be affected by variations in image reconstruction techniques and respiratory parameters. This study aimed to optimize 4DCT image reconstruction techniques for the treatment planning of lung stereotactic body radiotherapy (SBRT) based on respiratory parameters using respiratory motion phantom. We quantified respiratory parameters using 30 respiratory motion datasets. The 4DCT images were acquired, and the phase- and amplitude-based reconstruction images (RI) were created. The target dose was calculated based on these reconstructed images. Statistical analysis was performed using Pearson's correlation coefficient (r) to determine the relationship between respiratory parameters and target dose in each reconstructed technique and respiratory region. In the inhalation region of phase-based RI, r of the target dose and baseline drift was -0.52. In particular, the target dose was significantly reduced for respiratory parameters with a baseline drift of 0.8mm/s and above. No other respiratory parameters or respiratory regions were significantly correlated with target dose in phase-based RI. In amplitude-based RI, there were no significant differences in the correlation between all respiratory parameters and target dose in the exhalation or inhalation regions. These results showed that the target dose of the amplitude-based RI did not depend on changes in respiratory parameters or respiratory regions, compared to the phase-based RI. However, it is possible to guarantee the target dose by considering respiratory parameters during the inhalation region of the phase-based RI.

Definition of a framework for volumetric modulated arc therapy plan quality assessment with integration of dose-, complexity-, and robustness metrics

Background and purposeConventionally, the quality of radiotherapy treatment plans is assessed through visual inspection of dose distributions and dose-volume histograms. This study developed a framework to evaluate plan quality using dose, complexity, and robustness metrics. Additionally, a method for predicting plan robustness metrics using dose and complexity metrics was introduced for cases where plan robustness evaluation is unavailable or impractical. Materials and methodsThe framework and prediction models were developed and validated using 103-bronchial Volumetric Modulated Arc Therapy (VMAT)-plans. The application of the framework was demonstrated using 25-VMAT-plans. To identify significant metrics for plan evaluation, 122-metrics were analysed and narrowed down using multivariate Spearman correlation. Metric limits were set with Statistical process control (SPC). Robustness metrics were predicted using multivariable or single linear regression models based on dose-and complexity-metrics. ResultsTwenty-five-metrics were selected based on the amount and strength of correlations. R95(dose coverage) and HI95/5(homogeneity index) stood out among the dose-metrics, while the complexity-metrics showed similar correlations. Average scenarios dose at 95 % Clinical Target Volume D95mean(CTV) and Errorbar-based Volume-Histograms (EVH) were notable for robustness metrics. Approximately 99 % of evaluated metrics fell within established SPC limits. The prediction model for D95mean(CTV) showed good performance (adjusted R2 = 0.88, mean squared error (MSE) = 3.84 × 10−6), while the model for EVH demonstrated moderate reliability (adjusted R2 = 0.52, MSE = 0.2). No statistically significant differences were found between the predicted (using dose-and complexity-metrics) and calculated robustness metrics (EVH (p-value = 0.9) and D95mean(CTV) (p-value = 1)). ConclusionsThe developed framework enables early detection of sub-optimal, complex and non-robust treatment plans. The predictive model can be used when robustness evaluations are impractical.

Artificial Intelligence-Supported Applications in Radiotherapy Treatment Planning and Dose Optimization

The Article Abstract is not available.

Deep learning-based prediction of the dose-volume histograms for volumetric modulated arc therapy of left-sided breast cancer.

The advancements in artificial intelligence and computational power have made deep learning an attractive tool for radiotherapy treatment planning. Deep learning has the potential to significantly simplify the trial-and-error process involved in inverse planning required by modern treatment techniques such as volumetric modulated arc therapy (VMAT). In this study, we explore the ability of deep learning to predict organ-at-risk (OAR) dose-volume histograms (DVHs) of left-sided breast cancer patients undergoing VMAT treatment based solely on their anatomical characteristics. The predicted DVHs could be used to derive patient-specific dose constraints and dose objectives, streamlining the treatment planning process, standardizing the quality of the plans, and personalizing the treatment planning. This study aimed to develop a deep learning-based framework for the prediction of organ-specific dose-volume histograms (DVH) based on structures delineated for left-sided breast cancer treatment. We used a dataset of 249 left-sided breast cancer patients treated with tangential VMAT fields. We extracted delineated structures and dose distributions for each patient and derived slice-by-slice DVHs for planning target volume (PTV) and organs-at-risk. The patients were divided into training (70%, n=174), validation (10%, n=24), and test (20%, n=51) sets. Collected data were used to train a deep learning model for the prediction of the DVHs based on the delineated structures. The developed deep learning model comprised a modified DenseNet architecture followed by a recurrent neural network. In the independent test set (n=51), the point-wise differences in the slice-by-slice DVHs between the clinical and predicted DVHs were small; the mean squared errors were 3.53, 1.58, 2.28, 3.37, and 1.44 [×10-4] for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively. With the derived cumulative DVHs, the mean absolute difference±standard deviation of mean doses between the clinical and the predicted DVH were 0.08± 0.04Gy, 0.24± 0.22Gy, 0.73± 0.46Gy, 0.07± 0.06Gy, and 0.14± 0.14Gy for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively. The deep learning-based approach enabled automatic and reliable prediction of the DVH based on delineated structures. The predicted DVHs could potentially serve as patient-specific clinical goals used to aid treatment planning and avoid suboptimal plans or to derive optimization objectives and constraints for automated treatment planning.

Validation of different automated segmentation models for target volume contouring in postoperative radiotherapy for breast cancer and regional nodal irradiation

IntroductionTarget volume delineation is routinely performed in postoperative radiotherapy (RT) for breast cancer patients, but it is a time-consuming process. The aim of the present study was to validate the quality, clinical usability and institutional-specific implementation of different auto-segmentation tools into clinical routine. MethodsThree different commercially available, artificial intelligence-, ESTRO-guideline-based segmentation models (M1-3) were applied to fifty consecutive reference patients who received postoperative local RT including regional nodal irradiation for breast cancer for the delineation of clinical target volumes: the residual breast, implant or chestwall, axilla levels 1 and 2, the infra- and supraclavicular regions, the interpectoral and internal mammary nodes. Objective evaluation metrics of the created structures were conducted with the Dice similarity index (DICE) and the Hausdorff distance, and a manual evaluation of usability. ResultsThe resulting geometries of the segmentation models were compared to the reference volumes for each patient and required no or only minor corrections in 72 % (M1), 64 % (M2) and 78 % (M3) of the cases. The median DICE and Hausdorff values for the resulting planning target volumes were 0.87–0.88 and 2.96–3.55, respectively. Clinical usability was significantly correlated with the DICE index, with calculated cut-off values used to define no or minor adjustments of 0.82–0.86. Right or left sided target and breathing method (deep inspiration breath hold vs. free breathing) did not impact the quality of the resulting structures. ConclusionArtificial intelligence-based auto-segmentation programs showed high-quality accuracy and provided standardization and efficient support for guideline-based target volume contouring as a precondition for fully automated workflows in radiotherapy treatment planning.

Optimum delineation of skin structure for dose calculation with the linear Boltzmann transport equation algorithm in radiotherapy treatment planning.

This study investigated the effectiveness of placing skin-ring structures to enhance the precision of skin dose calculations in patients who had undergone head and neck volumetric modulated arc therapy using the Acuros XB algorithm. The skin-ring structures in question were positioned 2mm below the skin surface (skin A) and 1mm above and below the skin surface (skin B) within the treatment-planning system. These structures were then tested on both acrylic cylindrical and anthropomorphic phantoms and compared with the Gafchromic EBT3 film (EBT3). The results revealed that the maximum dose differences between skins A and B for the cylindrical and anthropomorphic phantoms were approximately 12% and 2%, respectively. In patients 1 and 2, the dose differences between skins A and B were 9.2% and 8.2%, respectively. Ultimately, demonstrated that the skin-dose calculation accuracy of skin B was within 2% and did not impact the deep organs.

Automated plan generation for prostate radiotherapy patients using deep learning and scripted optimization

Background and PurposeTreatment planning is a time-intensive task that could be automated. We aimed to develop a “single-click” workflow, fully deployed within a commercial treatment planning system (TPS), for autoplanning prostate radiotherapy treatment plans using predictions from a deep learning model (DLM). Materials and MethodsAutomatically generated treatment plans were created with a single script, executed from within a commercial TPS scripting environment, that performed two stages sequentially. Initially, a 3D dose distribution was predicted with a ResUNet DLM. The DLM was trained and validated using previously treated datasets (n = 120) which used 3D contours as inputs. Following this, dose predictions were converted into treatment plans by extracting dose-volume metrics from the predictions to use as objectives for the inverse optimizer within the TPS. An independent test dataset (n = 20) was used to evaluate the similarity between automated and clinical plans. ResultsFor planning target volumes, the median percentage difference and interquartile range between the automatically generated plans and clinical plans were 0.4% [0.2-1.1%] for the V100%, −0.5% [(−1.0)-(−0.2)%] for D99% and −0.5% [(−1.0)-(−0.2)%] for D95%. Bladder and rectum volume-at-dose objectives agreed within −6.1% [(−12.5)-0.9%]. The conversion of the DLM prediction into a treatment plan took 15 min [13-16 min]. ConclusionsAn automatic plan generation workflow that uses a DL model with scripted optimization was fully deployed in a commercial TPS. Autoplans were compared to previously treated clinical plans and were found to be non-inferior.

Mitigating Risks in Cone Beam Computed Tomography Guided Online Adaptive Radiation Therapy: A Preventative Reference Planning Review Approach

PurposeOnline adaptive radiotherapy (oART) treatment planning requires evaluating the temporal robustness of reference plans, anticipating the potential changes during treatment courses that may even lead to risks unique to the adaptive workflow. This study conducted a risk analysis of the CBCT-guided adaptive workflow and is the first to assess an adaptive specific reference planning review that mitigates risk in the planning process to prevent events and treatment deficiencies during adaptation. Methods and MaterialsA quality management team of medical physicists, residents, physicians, and radiation therapists performed a fault tree analysis, and failure mode and effects analysis (FMEA). Fault trees were created for under/overdosing targets, treatment deficiencies, as well as assisted in identifying failure modes for the FMEA. Treatment deficiency was defined to include a non-ideal oART plan resulting in treatment with a lower quality plan (either oART or scheduled plan), treatment delay, or cancelling treatment for the day. A reference planning checklist was created to catch failure modes before reaching the patient. Risk priority numbers (RPN=Severity*Detectability*Occurrence) were scored with and without the reference planning checklist to quantify risk mitigation. A root cause analysis was conducted for an event where an adaptive plan failed to generate. ResultsThe reference planning checklist (with items covering patient background, contouring/planning robustness for anatomy variability, and machine limitations) reduced the RPN for all failure modes. Only 1 failure mode with a risk priority number >150 occurred with the reference planning checklist compared to 29 failure modes without, including 14 adaptive specific failure modes. Contouring, planning, setup, scheduling, and documentation errors were identified during the fault tree analysis. 29/70 errors were adaptive specific. The reference planning checklist could address 23/33 for over/under dosing and 28/37 errors for treatment deficiency. The root cause analysis highlighted the need for checking setup prior to adaptive plan delivery, and time-out checklist. ConclusionsThe reference planning checklist improved detection of the failure modes and improves the quality and robustness of the plans produced for oART. It is ideally performed before physician plan review to prevent last minute re-plan (before or after first adaptive treatment) and delay of patient start. The checklist presented can be modified based on failures specific to individual clinics and utilized at various planning steps based on available resources.

Moving beyond mean heart dose: The importance of cardiac substructures in radiation therapy toxicity.

Normal tissue tolerance dose limits to the heart have been established to reduce the risk of radiation-induced cardiac disease (RICD). Dose constraints have been developed based on either the mean dose delivered to the whole heart (MHD) or the dose delivered to a specific volume, for example, volume of heart receiving equal to or greater than 30 Gy (V30). There is increasing evidence that the impact of thoracic radiation on cardiac morbidity and mortality has been underestimated. Consequently, there is a need to reduce the dose delivered to the heart in radical radiotherapy treatment planning. The pathophysiology of RICD may relate to dose to specific cardiac substructures (CS) rather than the traditionally observed MHD for common toxicities. The MHD or V30 Gy threshold dose rarely represents the true dose delivered to individual CS. Studies have shown the dose to specific areas may be more strongly correlated with overall survival (OS). With advances in modern radiotherapy techniques, it is vital that we develop robust, evidence-based dose limits for CS, to fully understand and reduce the risk of RICD, particularly in high-risk populations with cardiac risk factors. The following review will summarise the existing evidence of dose limits to CS, explain how dose limits may vary according to different disease sites or radiation techniques and propose how radiotherapy plans can be optimised to reduce the dose to these CS in clinical practice.

The Effect of Contrast Material in Three Dimensional Conformal and Helical Treatment Plans in Rectal Radiotherapy

The Effect of Contrast Material in Three Dimensional Conformal and Helical Treatment Plans in Rectal Radiotherapy

Fully automated radiotherapy treatment planning: A scan to plan challenge

Background and PurposeOver the past decade, tools for automation of various sub-tasks in radiotherapy planning have been introduced, such as auto-contouring and auto-planning. The purpose of this study was to benchmark what degree of automation is possible. Materials and MethodsA challenge to perform automated treatment planning for prostate and prostate bed radiotherapy was set up. Participants were provided with simulation CTs and a treatment prescription and were asked to use automated tools to produce a deliverable radiotherapy treatment plan with as little human intervention as possible. Plans were scored for their adherence to the protocol when assessed using consensus expert contours. ResultsThirteen entries were received. The top submission adhered to 81.8% of the minimum objectives across all cases using the consensus contour, meeting all objectives in one of the ten cases. The same system met 89.5% of objectives when assessed with their own auto-contours, meeting all objectives in four of the ten cases. The majority of systems used in the challenge had regulatory clearance (Auto-contouring: 82.5%, Auto-planning: 77%). Despite the ‘hard’ rule that participants should not check or edit contours or plans, 69% reported looking at their results before submission. ConclusionsAutomation of the full planning workflow from simulation CT to deliverable treatment plan is possible for prostate and prostate bed radiotherapy. While many generated plans were found to require none or minor adjustment to be regarded as clinically acceptable, the result indicated there is still a lack of trust in such systems preventing full automation.