Radiotherapy Workflow Research Articles

A data-driven approach to solve the RT scheduling problem

IntroductionThere is an increase in demand for Radiotherapy (RT) and it is a time critical treatment with a complex scheduling process. RT workflow is inter-dependent and involves various steps including pre-treatment and treatment-related tasks which adds to these challenges. Globally, scheduling delays are reported as one of the most common issues in RT. We aim to create and evaluate an automated strategy which generates a patient allocation list to assist the scheduling staff to create an efficient scheduling process. Methods and MaterialsWe used historical data from a large RT department in Sweden from January to December 2022 with 11–13 operational linear accelerators. The algorithm was developed in C# language. It utilizes patient and treatment-related characteristics including the patient timeline (referral date, preferred treatment start dates), booking category, diagnosis group and intent. Based on this, the algorithm assigns patient priority individually. ResultsThe algorithm’s output resulted in a scheduling list sorted by high to low patient priority per week. We evaluated the algorithm with historical manual allocations from the same year. The comparison between manual and algorithm allocations showed that the number of delayed patients reduced by 10 % in the algorithm suggestion with an average delay reduction of 2 weeks. Furthermore, the focus on patient-related characteristics resulted in diagnosis groups being better balanced. ConclusionThe algorithm’s ability to produce quick results may save significant time that the scheduling staff otherwise need to assess individual patient profiles. RT departments can incorporate such algorithms to accelerate their scheduling decisions and enhance their overall scheduling performance before going through major organizational changes.

Minimizing human interference in an online fully automated daily adaptive radiotherapy workflow for bladder cancer

PurposeThe aim was to study the potential for an online fully automated daily adaptive radiotherapy (RT) workflow for bladder cancer, employing a focal boost and fiducial markers. The study focused on comparing the geometric and dosimetric aspects between the simulated automated online adaptive RT (oART) workflow and the clinically performed workflow.MethodsSeventeen patients with muscle-invasive bladder cancer were treated with daily Cone Beam CT (CBCT)-guided oART. The bladder and pelvic lymph nodes (CTVelective) received a total dose of 40 Gy in 20 fractions and the tumor bed received an additional simultaneously integrated boost (SIB) of 15 Gy (CTVboost). During the online sessions a CBCT was acquired and used as input for the AI-network to automatically delineate the bladder and rectum, i.e. influencers. These influencers were employed to guide the algorithm utilized in the delineation process of the target. Manual adjustments to the generated contours are common during this clinical workflow prior to plan reoptimization and RT delivery. To study the potential for an online fully automated workflow, the oART workflow was repeated in a simulation environment without manual adjustments. A comparison was made between the clinical and automatic contours and between the treatment plans optimized on these clinical (Dclin) and automatic contours (Dauto).ResultsThe bladder and rectum delineated by the AI-network differed from the clinical contours with a median Dice Similarity Coefficient of 0.99 and 0.92, a Mean Distance to Agreement of 1.9 mm and 1.3 mm and a relative volume of 100% and 95%, respectively. For the CTVboost these differences were larger, namely 0.71, 7 mm and 78%. For the CTVboost the median target coverage was 0.42% lower for Dauto compared to Dclin. For CTVelective this difference was 0.03%. The target coverage of Dauto met the clinical requirement of the CTV-coverage in 65% of the sessions for CTVboost and 95% of the sessions for the CTVelective.ConclusionsWhile an online fully automated daily adaptive RT workflow shows promise for bladder treatment, its complexity becomes apparent when incorporating a focal boost, necessitating manual checks to prevent potential underdosage of the target.

Simulation-free magnetic resonance-guided radiation therapy of prostate cancer

Background and purposeDespite recent advances of online image-guided high-precision patient positioning and adaptation using magnetic resonance imaging (MRI) or cone-beam computed tomography (CT), standard radiation therapy pathway still involves a dedicated simulation scan. The aim of this study was to evaluate the feasibility and planning quality of integrating a simulation-free treatment planning workflow for adaptive online MRI-guided radiation therapy on a 1.5 T MRI linear accelerator (MRI-Linac) in prostate cancer using diagnostic CT (dCT) scans. Materials and methodsFor ten patients with prostate cancer previously treated at the MRI-Linac with adaptive radiation therapy (42.7 Gy in 7 fractions), simulation-free reference plans based on dCT were retrospectively created, and adaptive plans were simulated for the first treatment fraction. Reference and adapted plans derived from both standard and simulation-free workflows were compared with regard to institutional dose volume criteria, followed by statistical assessment using the paired Wilcoxon signed-rank test with a Bonferroni-corrected significance level of α = 0.025. ResultsSimulation-free reference and adapted plans consistently met dose volume criteria. Statistical analysis revealed no significant differences between both workflows, except median values for near-maximum dose (D2%) in the planning target volume: 44.2 Gy (standard) vs. 44.5 Gy (simulation-free) in reference plans (p = 0.014), and 44.5 Gy vs. 44.6 Gy in adapted plans (p = 0.009). ConclusionThis study demonstrated the feasibility of simulation-free radiation therapy planning using dCT. Comparable treatment plan quality was observed for both reference and adapted radiation therapy plans in a curative setting for patients with prostate cancer.

DoseDiff: Distance-Aware Diffusion Model for Dose Prediction in Radiotherapy.

Treatment planning, which is a critical component of the radiotherapy workflow, is typically carried out by a medical physicist in a time-consuming trial-and-error manner. Previous studies have proposed knowledge-based or deep-learning-based methods for predicting dose distribution maps to assist medical physicists in improving the efficiency of treatment planning. However, these dose prediction methods usually fail to effectively utilize distance information between surrounding tissues and targets or organs-at-risk (OARs). Moreover, they are poor at maintaining the distribution characteristics of ray paths in the predicted dose distribution maps, resulting in a loss of valuable information. In this paper, we propose a distance-aware diffusion model (DoseDiff) for precise prediction of dose distribution. We define dose prediction as a sequence of denoising steps, wherein the predicted dose distribution map is generated with the conditions of the computed tomography (CT) image and signed distance maps (SDMs). The SDMs are obtained by distance transformation from the masks of targets or OARs, which provide the distance from each pixel in the image to the outline of the targets or OARs. We further propose a multi-encoder and multi-scale fusion network (MMFNet) that incorporates multi-scale and transformer-based fusion modules to enhance information fusion between the CT image and SDMs at the feature level. We evaluate our model on two in-house datasets and a public dataset, respectively. The results demonstrate that our DoseDiff method outperforms state-of-the-art dose prediction methods in terms of both quantitative performance and visual quality.

Technical Development and In Silico Implementation of SyntheticMR in Head and Neck Adaptive Radiation Therapy: A Prospective R-IDEAL Stage 0/1 Technology Development Report.

The purpose of this study was to investigate the technical feasibility of integrating the quantitative maps available from SyntheticMR into the head and neck adaptive radiation oncology workflow. While SyntheticMR has been investigated for diagnostic applications, no studies have investigated its feasibility and potential for MR-Simulation or MR-Linac workflow. Demonstrating the feasibility of using this technique will facilitate rapid quantitative biomarker extraction which can be leveraged to guide adaptive radiation therapy decision making. Two phantoms, two healthy volunteers, and one patient were scanned using SyntheticMR on the MR-Simulation and MR-Linac devices with scan times between four to six minutes. Images in phantoms and volunteers were conducted in a test/retest protocol. The correlation between measured and reference quantitative T1, T2, and PD values were determined across clinical ranges in the phantom. Distortion was also studied. Contours of head and neck organs-at-risk (OAR) were drawn and applied to extract T1, T2, and PD. These values were plotted against each other, clusters were computed, and their separability significance was determined to evaluate SyntheticMR for differentiating tumor and normal tissue. The Lin's Concordance Correlation Coefficient between the measured and phantom reference values was above 0.98 for both the MR-Sim and MR-Linac. No significant levels of distortion were measured. The mean bias between the measured and phantom reference values across repeated scans was below 4% for T1, 7% for T2, and 4% for PD for both the MR-Sim and MR-Linac. For T1 vs. T2 and T1 vs. PD, the GTV contour exhibited perfect purity against neighboring OARs while being 0.7 for T2 vs. PD. All cluster significance levels between the GTV and the nearest OAR, the tongue, using the SigClust method was p < 0.001. The technical feasibility of SyntheticMR was confirmed. Application of this technique to the head and neck adaptive radiation therapy workflow can enrich the current quantitative biomarker landscape.

The InterVision Framework: An Enhanced Fine-Tuning Deep Learning Strategy for Auto-Segmentation in Head and Neck.

Adaptive radiotherapy (ART) workflows are increasingly adopted to achieve dose escalation and tissue sparing under dynamic anatomical conditions. However, recontouring and time constraints hinder the implementation of real-time ART workflows. Various auto-segmentation methods, including deformable image registration, atlas-based segmentation, and deep learning-based segmentation (DLS), have been developed to address these challenges. Despite the potential of DLS methods, clinical implementation remains difficult due to the need for large, high-quality datasets to ensure model generalizability. This study introduces an InterVision framework for segmentation. The InterVision framework can interpolate or create intermediate visuals between existing images to generate specific patient characteristics. The InterVision model is trained in two steps: (1) generating a general model using the dataset, and (2) tuning the general model using the dataset generated from the InterVision framework. The InterVision framework generates intermediate images between existing patient image slides using deformable vectors, effectively capturing unique patient characteristics. By creating a more comprehensive dataset that reflects these individual characteristics, the InterVision model demonstrates the ability to produce more accurate contours compared to general models. Models are evaluated using the volumetric dice similarity coefficient (VDSC) and the Hausdorff distance 95% (HD95%) for 18 structures in 20 test patients. As a result, the Dice score was 0.81 ± 0.05 for the general model, 0.82 ± 0.04 for the general fine-tuning model, and 0.85 ± 0.03 for the InterVision model. The Hausdorff distance was 3.06 ± 1.13 for the general model, 2.81 ± 0.77 for the general fine-tuning model, and 2.52 ± 0.50 for the InterVision model. The InterVision model showed the best performance compared to the general model. The InterVision framework presents a versatile approach adaptable to various tasks where prior information is accessible, such as in ART settings. This capability is particularly valuable for accurately predicting complex organs and targets that pose challenges for traditional deep learning algorithms.

Leveraging denoising diffusion probabilistic model to improve the multi-thickness CT segmentation

Organs-at-risk (OARs) segmentation in computed tomography (CT) is a fundamental step in the radiotherapy workflow, which has been prone as a time-consuming and labor-intensive task. Deep neural networks (DNNs) have gained significant popularity in the field of OAR segmentation tasks, achieving remarkable progress in clinical practice. Typically, OARs are distributed throughout different areas of the body and require varying thicknesses of CT scans for better diagnosis and segmentation in clinical. Most DNN-based segmentation focuses on single-thickness CT scans, limiting their applicability to varying thicknesses due to a lack of diverse thickness-related feature learning. While pre-training with the denoising diffusion probabilistic model (DDPM) offers an effective solution for dense feature learning, current works are constrained in addressing feature diversity, as exemplified by scenarios such as multi-thickness CT. To address the above challenges, this paper introduces a novel pre-training approach called DiffMT. This approach leverages the DDPM to extract valuable features from multi-thickness CT images. By transferring the pre-trained DDPM to the downstream segmentation for fine-tuning, the model gains proficiency in learning diverse multi-thickness CT features, leading to precise segmentation across varied thicknesses. We explore DiffMT’s feature learning capacity through experiments involving pre-trained models of varying sizes and different denoising thicknesses. Subsequently, thorough experiments comparing DDPM-based segmentation with other state-of-the-art (SOTA) CT segmentation methods, along with assessments on diverse OARs and modalities, empirically demonstrate that the proposed DiffMT method outperforms the control methods. The codes are available at https://github.com/ychengrong/DiffMT.

Quantitative Assessment of Full-Time Equivalent Effort for Kilovoltage-Cone Beam Computed Tomography Guided Online Adaptive Radiation Therapy for Medical Physicists

Introduction: With recent clinical adoption of online adaptive radiotherapy and the increased workload associated with adaptive radiotherapy, proper staffing for medical physicists is paramount to safe clinical operation. However, there is currently no consensus on the full-time equivalent (FTE) requirements for safe administration of CBCT-guided online adaptive radiotherapy. This study aims to quantitatively assess medical physics workload and staffing needs of a CBCT-guided online adaptive radiotherapy program. Methods: We conducted a detailed analysis of the CBCT-guided adaptive planning and treatment workflows, encompassing tasks such as patient consultation, treatment planning, plan review, training, quality assurance, and treatment delivery. Utilizing data from machine logs, clinical database queries, and staff surveys, we present a framework for estimating FTE values for different staffing scenarios, considering medical physicists’ roles as planners, adaptors, or both. Results: FTE calculations, based on an example workload of 100 adaptive and 200 nonadaptive patients per year, for three staffing scenarios were provided: medical physicists as planners and adaptors (2.9 FTE), medical physicists as planners but not adaptors (2.6 FTE), and medical physicists as adaptors but not planners (1.4 FTE). These findings offer calculation guidance and benchmarks for staffing requirements in CBCT-guided online adaptive radiotherapy programs, emphasizing the need for specific staffing models to accommodate the complexities of adaptive radiotherapy. Conclusion: This study outlines a framework for calculating FTE requirements for medical physicists in a CBCT-guided online adaptive radiotherapy program. By analyzing the processes for three common adaptive radiotherapy workflows, this work can provide effective workforce planning and resource allocation estimates. This analysis can be used either prior to the implementation of an online adaptive radiotherapy program, for program development, or as a review of current practices to ensure operational efficiency and proper staffing levels are maintained.

2728: Introducing automated safety barriers into radiotherapy workflow

2728: Introducing automated safety barriers into radiotherapy workflow

2721: MR only radiotherapy workflow: time evaluation of the simulation process in pelvic cancer patients

2721: MR only radiotherapy workflow: time evaluation of the simulation process in pelvic cancer patients

Enhanced IDOL segmentation framework using personalized hyperspace learning IDOL.

Adaptive radiotherapy (ART) workflows have been increasingly adopted to achieve dose escalation and tissue sparing under shifting anatomic conditions, but the necessity of recontouring and the associated time burden hinders a real-time or online ART workflow. In response to this challenge, approaches to auto-segmentation involving deformable image registration, atlas-based segmentation, and deep learning-based segmentation (DLS) have been developed. Despite the particular promise shown by DLS methods, implementing these approaches in a clinical setting remains a challenge, namely due to the difficulty of curating a data set of sufficient size and quality so as to achieve generalizability in a trained model. To address this challenge, we have developed an intentional deep overfit learning (IDOL) framework tailored to the auto-segmentation task. However, certain limitations were identified, particularly the insufficiency of the personalized dataset to effectively overfit the model. In this study, we introduce a personalized hyperspace learning (PHL)-IDOL segmentation framework capable of generating datasets that induce the model to overfit specific patient characteristics for medical image segmentation. The PHL-IDOL model is trained in two stages. In the first, a conventional, general model is trained with a diverse set of patient data (n=100 patients) consisting of CT images and clinical contours. Following this, the general model is tuned with a data set consisting of two components: (a) selection of a subset of the patient data (m<n) using the similarity metrics (mean square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and the universal quality image index (UQI) values); (b) adjust the CT and the clinical contours using a deformed vector generated from the reference patient and the selected patients using (a). After training, the general model, the continual model, the conventional IDOL model, and the proposed PHL-IDOL model were evaluated using the volumetric dice similarity coefficient (VDSC) and the Hausdorff distance 95% (HD95%) computed for 18 structures in 20 test patients. Implementing the PHL-IDOL framework resulted in improved segmentation performance for each patient. The Dice scores increased from 0.81 0.05 with the general model, 0.83 for the continual model, 0.83 for the conventional IDOL model to an average of 0.87 with the PHL-IDOL model. Similarly, the Hausdorff distance decreased from 3.06 with the general model, 2.84 for the continual model, 2.79 for the conventional IDOL model and 2.36 for the PHL-IDOL model. All the standard deviations were decreased by nearly half of the values comparing the general model and the PHL-IDOL model. The PHL-IDOL framework applied to the auto-segmentation task achieves improved performance compared to the general DLS approach, demonstrating the promise of leveraging patient-specific prior information in a task central to online ART workflows.

First implementation of artificial intelligence empowered all-in-one radiotherapy workflow for nasopharyngeal carcinoma.

134 Background: To establish an artificial intelligence (AI)-empowered All-In-One (AIO) workflow for providing one-stop radiotherapy to patients with nasopharyngeal carcinoma (NPC), and evaluate its feasibility and performance. Methods: The NPC-specific AIO workflow operates on a CT-integrated linac and integrates AI contouring and AI planning modules. A 3D U-net was employed for contours generation and 3D dose distribution. Knowledge-based planning approach and a protocol-based approach were used for plan optimization. MRI datasets with contours of primary gross tumors, CT datasets with contours of targets and organs at risk, and radiotherapy treatment planning datasets were collected from 877, 139, and 243 patients, respectively, for the training, validation, and testing of AI contouring and planning models. The NPC-specific AIO workflow underwent real-world clinical testing with an end-to-end evaluation involving 120 patients with NPC. The technical characteristics, implementation procedures and performance of AIO workflow were described and evaluated. Results: From March 2022 to October 2023, 120 patients with newly-diagnosed, non-metastatic NPC underwent AIO workflow, and 117 patients completed it in a median time of 23.2 min (range: 16.3 to 45.8 min). Median translation motions were 0.2 mm (CT scan to planning approval) and 0.1 mm (during beam delivery). AI-generated contours required little revision for clinical target volume (CTV1) and organs at risk (OARs), minor revision for cervical lymph nodes (GTVn) and clinical target volume (CTV2), with median Dice similarity coefficients (DSCs) of 0.98 and 0.94, respectively; more revision for GTVp, with a median DSC of 0.84. Of the 117 AI-generated plannings, 108 (92.3%) passed after initial auto-optimization. Volumes receiving ≥ 100% of the prescribed dose for all planning target volumes was ≥ 97.8%. Mean dosimetric parameters met dose constraints for all OARs except the thyroid and submandibulars. One patient died from acute renal failure after 10 fractions of radiotherapy. At week 12 after radiotherapy completion, 115 patients achieved complete response;1 had stable disease. Grade 3-4 acute effects were reported by 54 of 115 patients (36%). Conclusions: We successfully established an AI-empowered AIO workflow for initial radiotherapy of NPC, confirming its feasibility and safety for clinical application.

Efficient application of deep learning-based elective lymph node regions delineation for pelvic malignancies.

While there are established international consensuses on the delineation of pelvic lymph node regions (LNRs), significant inter- and intra-observer variabilities persist. Contouring these clinical target volumes for irradiation in pelvic malignancies is both time-consuming and labor-intensive. The purpose of this study was to develop a deep learning model of pelvic LNRs delineation for patients with pelvic cancers. Planning computed tomography (CT) studies of 160 patients with pelvic primary malignancies (including rectal, prostate, and cervical cancer) were retrospectively collected and divided into training set (n=120) and testing set (n=40). Six pelvic LNRs, including abdominal presacral, pelvic presacral, internal iliac nodes, external iliac nodes, obturator nodes, and inguinal nodes were delineated by two radiation oncologists as ground truth (Gt) contours. The cascaded multi-heads U-net (CMU-net) was constructed based on the Gt contours from training cohort, which was subsequently verified in the testing cohort. The automatic delineation of six LNRs (Auto) was evaluated using dice similarity coefficient (DSC), average surface distance (ASD), 95th percentile Hausdorff distance (HD95), and a 7-point scale score. In the testing set, the DSC of six pelvic LNRs by CMU-net model varied from 0.851 to 0.942, ASD from 0.381 to 1.037mm, and HD95 from 2.025 to 3.697mm. No significant differences were founded in these three parameters between postoperative and preoperative cases. 95.9% and 96.2% of auto delineations by CMU-net model got a score of 1-3 by two expert radiation oncologists, respectively, meaning only minor edits needed. The CMU-net was successfully developed for automated delineation of pelvic LNRs for pelvic malignancies radiotherapy with improved contouring efficiency and highly consistent, which might justify its implementation in radiotherapy work flow.

The added value of a new high-performance ring-gantry CBCT imaging system for prostate cancer patients

Background and purposeA novel Cone-Beam Computed Tomography (CBCT) named HyperSight provides superior CBCT image quality compared to conventional ring gantry CBCT imaging, and it is suitable for dose calculations for prostate cancer, but it comes with considerable additional costs. The aim of this study was to determine the added value of HyperSight CBCT imaging compared to conventional CBCT imaging in terms of organ visibility in the male pelvic region. Materials and methodsTwenty prostate cancer patients were included in this prospective clinical study. For each patient three CBCT pairs, consisting of HyperSight and conventional CBCT scans acquired on consecutive days, were included. CBCT scans were evaluated by four observers in terms of visibility of the prostate, bladder, rectum and seminal vesicles. Visibility was scored on a 1-to-5 scale and by annotating axial slices where the organs were hard to delineate. Lastly, observers indicated whether the CBCT scans were of sufficient quality for an online adaptive radiation therapy workflow. ResultsAll four organs were better visible on HyperSight CBCT scans compared to conventional CBCT scans. The mean visibility scores increased from 3.1 to 4.5 on a 1––5 scale of and the mean number of annotated slices reduced from 4.5 to 1.1. 99% Of the HyperSight CBCT scans were considered suitable for an online adaptive workflow vs 25–83% for the conventional CBCT scans. ConclusionHyperSight CBCT scans yielded a visibility of prostate, bladder, rectum and seminal vesicles comparable to planning CT scans and, can replace a repeat planning CT scan in case of anatomical changes requiring a new treatment plan.

Evaluation of knowledge-based planning models for male pelvic CBCT-based online adaptive radiotherapy on conventional linear accelerators.

To assess the practicality of employing a commercial knowledge-based planning tool (RapidPlan) to generate adapted intact prostate and prostate bed volumetric modulated arc therapy (VMAT) plans on iterative cone-beam computed tomography (iCBCT) datasets. Intact prostate and prostate bed RapidPlan models were trained utilizing planning data from 50 and 44 clinical cases, respectively. To ensure that refined models were capable of producing adequate clinical plans with a single optimization, models were tested with 50 clinical planning CT datasets by comparing dose-volume histogram (DVH) and plan quality metric (PQM) values between clinical and RapidPlan-generated plans. The RapidPlan tool was then used to retrospectively generate adapted VMAT plans on daily iCBCT images for 20 intact prostate and 15 prostate bed cases. As before, DVH and PQM metrics were utilized to dosimetrically compare scheduled (iCBCT Verify) and adapted (iCBCT RapidPlan) plans. Timing data was collected to further evaluate the feasibility of integrating this approach within an online adaptive radiotherapy workflow. Model testing results confirmed the models were capable of producing VMAT plans within a single optimization that were overall improved upon or dosimetrically comparable to original clinical plans. Direct application of RapidPlan on iCBCT datasets produced satisfactory intact prostate and prostate bed plans with generally improved target volume coverage/conformality and rectal sparing relative to iCBCT Verify plans as indicated by DVH values, though bladder metrics were marginally increased on average. Average PQM values for iCBCT RapidPlans were significantly improved compared to iCBCT Verify plans. The average time required [in mm:ss] to generate adapted plans was 06:09±02:06 (intact) and 07:12±01:04 (bed). This study demonstrated the feasibility of leveraging RapidPlan to expeditiously generate adapted VMAT intact prostate and prostate bed plans on iCBCT datasets. In general, adapted plans were dosimetrically improved relative to scheduled plans, emphasizing the practicality of the proposed approach.

Deep Inspiration Breath Hold in Left-Sided Breast Radiotherapy: A Balance Between Side Effects and Costs

BackgroundDeep inspiration breath hold (DIBH) is an effective technique for reducing heart exposure during radiotherapy for left-sided breast cancer. Despite its benefits, cost considerations and its impact on workflow remain significant barriers to widespread adoption. ObjectivesThis study aimed to assess the cost-effectiveness of DIBH and compare its operational, financial, and clinical outcomes with free breathing (FB) in breast cancer treatment. MethodsTreatment plans for 100 patients with left-sided breast cancer were generated using both DIBH and FB techniques. Dosimetric data, including the average mean heart dose, were calculated for each technique and used to estimate the cardiotoxicity of radiotherapy. A state-transition microsimulation model based on SCORE2 (Systematic Coronary Risk Evaluation) algorithms projected the effects of DIBH on cardiovascular outcomes and quality-adjusted life-years (QALYs). Costs were calculated from a provider perspective using time-driven activity-based costing, applying a willingness-to-pay threshold of €40,000 for cost-effectiveness assessment. A discrete event simulation model assessed the impacts of DIBH vs FB on throughput and waiting times in the radiotherapy workflow. ResultsIn the base case scenario, DIBH was associated with an absolute risk reduction of 1.72% (95% CI: 1.67%-1.76%) in total cardiovascular events and 0.69% (95% CI: 0.67%-0.72%) in fatal cardiovascular events over 20 years. Additionally, DIBH was estimated to provide an incremental 0.04 QALYs (95% CI: 0.05-0.05) per left-sided breast cancer patient over the same time period. However, DIBH increased treatment times, reducing maximum achievable throughput by 12.48% (95% CI: 12.36%-12.75%) and increasing costs by €617 per left-sided breast cancer patient (95% CI: €615-€619). The incremental cost-effectiveness ratio was €14,023 per QALY. ConclusionsDespite time investments, DIBH is cost-effective in the Belgian population. The growing adoption of DIBH may benefit long-term cardiovascular health in breast cancer survivors.

RadDeploy: A framework for integrating in-house developed software and artificial intelligence models seamlessly into radiotherapy workflows

The use of and research in automation and artificial intelligence (AI) in radiotherapy is moving with incredible pace. Many innovations do, however, not make it into the clinic. One technical reason for this may be the lack of a platform to deploy such software into clinical practice. We suggest RadDeploy as a framework for integrating containerized software in clinical workflows outside of treatment planning systems. RadDeploy supports multiple DICOM as input for model containers and can run model containers asynchronously across GPUs and computers. This technical note summarizes the inner workings of RadDeploy and demonstrates three use-cases with varying complexity.

3D Unsupervised deep learning method for magnetic resonance imaging-to-computed tomography synthesis in prostate radiotherapy

Background and purposeMagnetic resonance imaging (MRI)-to-computed tomography (CT) synthesis is essential in MRI-only radiotherapy workflows, particularly through deep learning techniques known for their accuracy. However, current supervised methods are limited to specific center’s learnings and depend on registration precision. The aim of this study was to evaluate the accuracy of unsupervised and supervised approaches in the context of prostate MRI-to-CT generation for radiotherapy dose calculation. MethodsCT/MRI image pairs from 99 prostate cancer patients across three different centers were used. A comparison between supervised and unsupervised conditional Generative Adversarial Networks (cGAN) was conducted. Unsupervised training incorporates a style transfer method with. Content and Style Representation for Enhanced Perceptual synthesis (CREPs) loss. For dose evaluation, the photon prescription dose was 60 Gy delivered in volumetric modulated arc therapy (VMAT). Imaging endpoint for sCT evaluation was Mean Absolute Error (MAE). Dosimetric endpoints included absolute dose differences and gamma analysis between CT and sCT dose calculations. ResultsThe unsupervised paired network exhibited the highest accuracy for the body with a MAE at 33.6 HU, the highest MAE was 45.5 HU obtained with unsupervised unpaired learning. All architectures provided clinically acceptable results for dose calculation with gamma pass rates above 94 % (1 % 1 mm 10 %). ConclusionsThis study shows that multicenter data can produce accurate sCTs via unsupervised learning, eliminating CT-MRI registration. The sCTs not only matched HU values but also enabled precise dose calculations, suggesting their potential for wider use in MRI-only radiotherapy workflows.

A treatment-site-specific evaluation of commercial synthetic computed tomography solutions for proton therapy

Background and purposeDespite the superior dose conformity of proton therapy, the dose distribution is sensitive to daily anatomical changes, which can affect treatment accuracy. This study evaluated the dose recalculation accuracy of two synthetic computed tomography (sCT) generation algorithms in a commercial treatment planning system. Materials and methodsThe evaluation was conducted for head-and-neck, thorax-and-abdomen, and pelvis sites treated with proton therapy. Thirty patients with two cone-beam computed tomography (CBCT) scans each were selected. The sCT images were generated from CBCT scans using two algorithms, Corrected CBCT (corrCBCT) and Virtual CT (vCT). Dose recalculations were performed based on these images for comparison with “ground truth” deformed CTs. ResultsThe choice of algorithm influenced dose recalculation accuracy, particularly in high dose regions. For head-and-neck cases, the corrCBCT method showed closer agreement with the “ground truth”, while for thorax-and-abdomen and pelvis cases, the vCT algorithm yielded better results (mean percentage dose discrepancy of 0.6 %, 1.3 % and 0.5 % for the three sites, respectively, in the high dose region). Head-and-neck and pelvis cases exhibited excellent agreement in high dose regions (2 %/2 mm gamma passing rate >98 %), while thorax-and-abdomen cases exhibited the largest differences, suggesting caution in sCT algorithm usage for this site. Significant systematic differences were observed in the clinical target volume and organ-at-risk doses in head-and-neck and pelvis cases, highlighting the importance of using the correct algorithm. ConclusionsThis study provided treatment site-specific recommendations for sCT algorithm selection in proton therapy. The findings offered insights for proton beam centers implementing adaptive radiotherapy workflows.

Machine learning and lean six sigma for targeted patient-specific quality assurance of volumetric modulated arc therapy plans

Background and purposeRadiotherapy plans with excessive complexity exhibit higher uncertainties and worse patient-specific quality assurance (PSQA) results, while the workload of measurement-based PSQA can impact the efficiency of the radiotherapy workflow. Machine Learning (ML) and Lean Six Sigma, a process optimization method, were implemented to adopt a targeted PSQA approach, aiming to reduce workload, risk of failures, and monitor complexity. Materials and methodsLean Six Sigma was applied using DMAIC (define, measure, analyze, improve, and control) steps. Ten complexity metrics were computed for 69,811 volumetric modulated arc therapy (VMAT) arcs from 28,612 plans delivered in our Institute (2013–2021). Outlier complexities were defined as >95th-percentile of the historical distributions, stratified by treatment. An ML model was trained to predict the gamma passing rate (GPR-3 %/1mm) of an arc given its complexity. A decision support system was developed to monitor the complexity and expected GPR. Plans at risk of PSQA failure, either extremely complex or with average GPR <90 %, were identified. The tool’s impact was assessed after nine months of clinical use. ResultsAmong 1722 VMAT plans monitored prospectively, 29 (1.7 %) were found at risk of failure. Planners reacted by performing PSQA measurement and re-optimizing the plan. Occurrences of outlier complexities remained stable within 5 %. The expected GPR increased from a median of 97.4 % to 98.2 % (Mann-Whitney p < 0.05) due to plan re-optimization. ConclusionsML and Lean Six Sigma have been implemented in clinical practice enabling a targeted measurement-based PSQA approach for plans at risk of failure to improve overall quality and patient safety.