Search

This review systematically investigates the role of radiomics in radiotherapy, with a particular emphasis on the use of quantitative imaging biomarkers for predicting clinical outcomes, assessing toxicity, and optimizing treatment planning. While the review encompasses various applications of radiomics in radiotherapy, it particularly highlights its potential for guiding reirradiation of recurrent cancers. A systematic review was conducted based on a Medline search with the search engine PubMed using the keywords "radiomics or radiomic" and "radiotherapy or reirradiation". Out of 189 abstracts reviewed, 147 original articles were included in the analysis. These studies were categorized by tumor localization, imaging modality, study objectives, and performance metrics, with a particular emphasis on the inclusion of external validation and adherence to a standardized radiomics pipeline. The review identified 14 tumor localizations, with the majority of studies focusing on lung (33 studies), head and neck (27 studies), and brain (15 studies) cancers. CT was the most frequently employed imaging modality (77 studies) for radiomics, followed by MRI (46 studies) and PET (13 studies). The overall AUC across all studies, primarily focused on predicting the risk of recurrence (94 studies) or toxicity (41 studies), was 0.80 (SD = 0.08). However, only 24 studies (16.3%) included external validation, with a slightly lower AUC compared to those without it. For studies using CT versus MRI or PET, both had a median AUC of 0.79, with IQRs of 0.73–0.86 for CT and 0.76–0.855 for MRI/PET, showing no significant differences in performance. Five studies involving reirradiation reported a median AUC of 0.81 (IQR: 0.73–0.825). Radiomics demonstrates considerable potential in personalizing radiotherapy by improving treatment precision through better outcome prediction and treatment planning. However, its clinical adoption is hindered by the lack of external validation and variability in study designs. Future research should focus on implementing rigorous validation methods and standardizing imaging protocols to enhance the reliability and generalizability of radiomics in clinical radiotherapy, with particular attention to its application in reirradiation. [ABSTRACT FROM AUTHOR]

Adaptive radiotherapy (ART) is a recent development in radiotherapy technology and treatment personalization that allows treatment to be tailored to the daily anatomical changes of patients. While it was until recently only performed "offline", i.e. between two radiotherapy sessions, it is now possible during ART to perform a daily online adaptive process for a given patient. Therefore, ART allows a daily customization to ensure optimal coverage of the treatment target volumes with minimized margins, taking into account only the uncertainties related to the adaptive process itself. This optimization appears particularly relevant in case of daily variations in the positioning of the target volume or of the organs at risk (OAR) associated with a proximity of these volumes and a tenuous therapeutic index. ART aims to minimize severe acute and late toxicity and allows tumor dose escalation. These new achievements have been possible thanks to technological development, the contribution of new multimodal and onboard imaging modalities and the integration of artificial intelligence tools for the contouring, planning and delivery of radiation therapy. Online ART is currently available on two types of radiotherapy machines: MR-linear accelerators and recently CBCT-linear accelerators. We will first describe the benefits, advantages, constraints and limitations of each of these two modalities, as well as the online adaptive process itself. We will then evaluate the clinical situations for which online adaptive radiotherapy is particularly indicated on MR- and CBCT-linear accelerators. Finally, we will detail some challenges and possible solutions in the development of online ART in the coming years. [ABSTRACT FROM AUTHOR]

In 2022, the radiation therapist committee of the Association française du personnel paramédical d'electroradiologie médicale (AFPPE, French association of paramedical electroradiology technicians), the Société française de radiothérapie oncologique (SFRO, French society of radiation oncology) and the Syndicat national des radiothérapeutes oncologue (SNRO, national syndicate of radiation oncologists) have been committed to working on the development of advanced practice roles. The objective of this article is to report the activities that should be in the scope of radiation therapists advanced practice and describe the competences required for these activities. This work was carried out by six radiation therapists, six radiation oncologists and one medical physicist representatives of the French national societies for each professional group. First, a basic list of activities was established and then competences were identified for groups of activities. In total, the list includes five core competences, nine competences and nine groups of activities that can be divided into the four pillars of advanced practice. The nine groups of activities can be presented in seven different dimensions including patient care and support, treatment planning, treatment imaging and delivery, management and consultancy, quality and risk management, research and innovation, education and training. The French advanced practice competences framework was developed with a multidisciplinary group to move forward the project of a master degree in advanced practice in radiation therapy in France. [ABSTRACT FROM AUTHOR]

The document provides an update on clinical practice guidelines for managing patients with sarcoma, rare and complex malignant tumors of bone and soft tissue. It highlights the importance of multidisciplinary expertise for optimal outcomes and discusses the need for equitable access to diagnosis and treatment for rare cancers. The guidelines focus on treatment at specialized sarcoma centers, management of retroperitoneal sarcoma, and pediatric patients with sarcoma. Recommendations emphasize timely referral to specialized centers to reduce local recurrence and surgical complications, improve limb conservation, and overall survival. The document encourages leveraging evidence-based recommendations to advocate for equitable access to specialized sarcoma care for all patients and families. [Extracted from the article]

Background Purpose Methods Results Conclusions 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% / 2 mm (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 50 Gy 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 26.9 Gy (lung) and up to 7.6 Gy (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. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions While electron beams of up to 20 MeV are commonly used in radiotherapy, the use of very‐high‐energy electrons (VHEEs) in the range of 100–200 MeV is now becoming a realistic option thanks to the recent advancements in accelerator technology. Indeed, VHEE offers several clinically attractive features and can be delivered using various conformation methods (including scanning, collimation, and focussing) at ultra‐high dose rates. To date, there is a lack of research tools for fast simulation of treatment plans using VHEE beams.This work aims to implement and validate a simple and fast dose calculation algorithm based on the Fermi–Eyges theory of multiple Coulomb scattering for VHEE radiation therapy, with energies up to 200 MeV. A treatment planning system (TPS) toolkit with VHEE modality would indeed allow for further preclinical investigations, including treatment plan optimization and evaluation, and thus contribute to the gradual introduction of VHEE radiotherapy in clinical practice.A VHEE pencil beam scanning double Gaussian model was introduced into the open‐source TPS matRad environment along with new functions and options dedicated to VHEE dose calculations. Various geometries and field configurations were then calculated in matRad (up to 200 MeV and 15 × 15 cm2, with complex bone or lung heterogeneities) and the results were compared to Monte Carlo simulations in the TOPAS/Geant4 toolkit. Two types of beam model (divergent or focused) were also tested. Examples of clinical treatment plans were computed, and the results were compared between the two codes.VHEE modality was fully implemented in matRad with GUI capabilities while preserving all original TPS features. New relevant options such as the importation of specific spot‐lists or adjustment of the lateral dose calculation cutoff to optimize the calculation speed were validated. Single spot and square field dose distributions were validated in water alone as well as in clinically relevant inhomogeneities. Dose maps from the VHEE model in matRad were in good agreement with TOPAS (2D gamma index [2%/1 mm] with passing rates superior to 90%, <6% mean dose differences), except for large interface heterogeneities.This work describes the implementation of a simple but efficient VHEE simulation model in matRad. A few configurations were studied in order to validate the model against accurate Monte Carlo simulations, demonstrating its usefulness for carrying out preliminary studies involving VHEE radiotherapy. [ABSTRACT FROM AUTHOR]

Background: High‐quality 3D‐anatomy of the day is needed for treatment plan adaptation in radiotherapy. For online x‐ray‐based CBCT workflows, one approach is to create a synthetic CT or to utilize a fan‐beam CT with corresponding registrations. The former potentially introduces uncertainties in the dose calculation if deformable image registration is used. The latter can introduce burden and complexity to the process, the facility, and the patient. Purpose: Using the CBCT of the day, acquired on the treatment device, for direct dose calculation and plan adaptation can overcome these limitations. This study aims to assess the accuracy of the calculated dose on the CBCT scans acquired on a Halcyon linear accelerator equipped with HyperSight. Methods: HyperSight's new CBCT reconstruction algorithm includes improvements in scatter correction, HU calibration of the imager, and beam shape adaptation. Furthermore, HyperSight introduced a new x‐ray detector. To show the effect of the implemented improvements, gamma comparisons of 2%/2 mm, 2%/1 mm, and 1%/1 mm were made between the dose distribution in phantoms calculated on the CBCT reconstructions and the simulation CT scans, considering this the standard of care. The resulting gamma passing rates were compared to those obtained with the Halcyon 3.0 reconstruction and hardware without HyperSight's technologies. Various anatomical phantoms for dosimetric evaluations on brain, head and neck, lung, breast, and prostate cases have been used in this study. Results: The overall results demonstrated that HyperSight outperformed the Halcyon 3.0 version. Based on the gamma analysis, the calculated dose using HyperSight was closer to the CT scan‐based doses than the calculated dose using iCBCT Halcyon 3.0 for most cases. Over all plans and gamma criteria, Halcyon 3.0 achieved an average passing rate of 92.9%, whereas HyperSight achieved 98.1%. Conclusion: Using HyperSight CBCT images for direct dose calculation, for example, in (online) plan adaptation, seems feasible for the investigated cases. [ABSTRACT FROM AUTHOR]

Simple Summary: Nasopharynx cancer treatment often involves radiation therapy, but choosing the best method can be challenging. This study compares two advanced radiation techniques: one using X-rays and another using protons. Both aim to target the tumor while sparing healthy tissues, but their effectiveness can vary based on the cancer's location and stage. Researchers want to determine which technique works best for different patients, particularly those with cancer close to sensitive brain structures. By analyzing treatment plans for 28 patients, we developed guidelines to help doctors choose the most suitable technique. This research could lead to more personalized and effective treatments, potentially improving outcomes and quality of life for patients with nasopharynx cancer. The findings may also help healthcare providers use resources more efficiently, benefiting both patients and the broader medical community. Background: Proton therapy requires caution when treating patients with targets near neural structures. Intuitive and quantitative guidelines are needed to support decision-making concerning the treatment modality. This study compared dosimetric profiles of intensity-modulated proton therapy (IMPT) and intensity-modulated radiation therapy (IMRT) using helical tomotherapy (HT) for adaptive re-planning in cT3-4 nasopharyngeal cancer (NPCa) patients, aiming to establish criteria for selecting appropriate treatment modalities. Methods: HT and IMPT plans were generated for 28 cT3-4 NPCa patients undergoing definitive radiotherapy. Dosimetric comparisons were performed for target coverage and high-priority organs at risk (OARs). The correlation between dosimetric parameters and RT modality selection was analyzed with the target OAR distances. Results: Target coverages were similar, while IMPT achieved better dose spillage. HT was more favorable for brainstem D1, optic chiasm Dmax, optic nerves Dmax, and p-cord D1. IMPT showed advantages for oral cavity Dmean. Actually, 14 IMPT and 14 HT plans were selected as adaptive plans, with IMPT allocated to most cT3 patients (92.9% vs. 42.9%, p = 0.013). The shortest distances from the target to neural structures were negatively correlated with OAR doses. Receiver operating characteristic curve analyses were carried out to discover the optimal cut-off values of the shortest distances between the target and the OARs (temporal lobes and brainstem), which were 0.75 cm (AUC = 0.908, specificity = 1.00) and 0.85 cm (AUC = 0.857, specificity = 0.929), respectively. Conclusions: NPCa patients with cT4 tumor or with the shortest distance between the target and critical neural structures < 0.8 cm were suboptimal candidates for IMPT adaptive re-planning. These criteria may improve resource utilization and clinical outcomes. [ABSTRACT FROM AUTHOR]

There is limited clinical data for recommendations on how to deliver thoracic radiation therapy (TRT) concurrently with chemotherapy in limited-stage small cell lung cancer. We reviewed radiation therapy treatment plans in a randomized phase 2 trial comparing high-dose with standard-dose twice-daily TRT to assess treatment planning techniques, dose-volume data for target volumes and organs at risk (OARs), evaluate compliance with the protocol, associations with radiation-induced toxicity, and whether an imbalance in treatment planning parameters might be a reason for the large survival benefit of the higher dose (median overall survival 43.6 vs 22.6 months). In the study, 170 patients were to receive 4 courses of platinum/etoposide and were randomized to receive twice-daily TRT of 60 Gy/40 fractions (fx) or 45 Gy/30 fx. TRT treatment plans for those who received 1 or more fx of TRT (n = 166) were analyzed. The most common treatment planning technique was 3-dimensional conformal radiation therapy (67%). The 75th percentile of the reported dose-volume parameters for the OARs were within the protocol-recommended limits for both groups. Mean doses to the esophagus of 25.5 Gy (IQR, 20.2-31.3; 60 Gy/40 fx) and 24.3 Gy (IQR, 20.3-27.5; 45 Gy/30 fx) were associated with 21% and 18% ≥ grade 3 acute esophagitis, respectively. In the 60 Gy/40 fx group, a mean dose to the lungs of 16.5 Gy (IQR, 15.8-16.9), V20 Gy of 29.5% (IQR, 28.8-30.4), and V5 Gy of 65.6% (IQR, 61.5-68.7) led to ≥ grade 3 pneumonitis in 4% of the patients. There was no ≥ grade 3 pneumonitis in the 45 Gy/30 fx group. The treatment planning techniques, the percentage change in volumes between original and redelineated OARs, planning target volumes, relative doses, and laterality were well balanced between the randomly assigned groups. Considering the incidences of severe radiation-induced toxicities were within the range of other recent trials, the reported doses to the OARs appear to be safe. Treatment planning parameters were well balanced between the randomly assigned groups, supporting that the survival benefit of the twice-daily 60 Gy/40 fx TRT schedule was due to the higher dose. [ABSTRACT FROM AUTHOR]

The article discusses the use of artificial intelligence in radiotherapy treatment planning and dose optimization, particularly focusing on Head and Neck Cancer (HNC). Artificial intelligence systems can enhance treatment accuracy, efficiency, and outcomes by automating treatment planning, determining appropriate doses, and reducing human errors. While there are challenges and concerns, such as negative perceptions, the integration of artificial intelligence in cancer radiotherapy shows promise for improving treatment outcomes and efficiency. Continued research and development in this field are crucial for unlocking the full potential of AI in cancer radiotherapy. [Extracted from the article]

Purpose: The impact of various hip prosthesis materials on the amount of dose perturbation generated by 9 MeV electron and 18 MV photon beams during pelvic radiation therapy is analyzed in this research. Materials and Methods: The Varian 2100 C/D LINAC head for the electron (9 MeV) and photon (18 MV) modes and a water phantom with a realistic hip prosthesis were modeled using the Monte Carlo (MC) code; MCNPX (Ver. 2.6.0) and were benchmarked for measurement. Four different materials, including Cobalt-Chromium-Molybdenumalloy (CCM), Stainless Steel (SS), Titanium, and Titanium-alloy (Ti-alloy) were evaluated. The changes in electron and photon fluences and dose perturbations due to the presence of the hip prostheses were investigated. Results: An increased dose of 13.29%, 13.77%, 6.16%, and 5.93% for 9 MeV and 30.43%, 33.05%, 10.89%, and 11.27% for 18 MV was calculated for Ti-alloy, Ti, CCM, and SS prosthesis, respectively. At 0.5 mm distance from the prosthesis, the Electron Backscatter Factor (EBF) of 1.31, 1.33, 1.15, and 1.14 for 9 MeV and 1.32, 1.34, 1.11, and 1.12 for 18 MV was calculated for Ti-alloy, Ti, CCM, and SS prosthesis, respectively. Dose perturbation is higher at a near distance from the prosthesis; by reducing the distance from the Ti-alloy prosthesis (1.5 to 0.5 mm), an increased dose of 7.70% and 5.54% resulted in 18 MV and 9 MeV, respectively. The dose decreases of up to 21% behind the hip prosthesis were calculated for 18 MV. Conclusion: It is essential to consider the dose perturbation due to the presence of a hip prosthesis to achieve the optimal treatment planning in radiotherapy. [ABSTRACT FROM AUTHOR]

Background: To explore the beneficial subgroups after radiotherapy in high-grade neuroendocrine cervical cancer (HGNECC) and construct two survival prognosis models to quantify the efficacy of radiotherapy assessment. Methods: In this retrospective study, we included 592 eligible samples from the Surveillance, Epidemiology, and End Results (SEER) database and 56 patients with lymph-node positive HGNECC from Chongqing Medical University. Cox regression analysis was used to identify independent survival prognosis risk factors for HGNECC patients. Propensity score matching (PSM) was employed as it balances the baseline differences among grouping methods. Kaplan--Meier (K-M) curves were used to analyze survival differences among different groups. Two survival prediction nomograms were constructed separately (using the "rms" package in R software) based on whether radiotherapy was administered. The stability and accuracy of these models were assessed using receiver operating characteristic (ROC) curves and calibration curves in both the training and validation datasets. P<0.05 was considered to indicate statistically significant differences. Results: Age, Federation of Gynecology and Obstetrics (FIGO)-stage, and treatment methods (surgery vs. chemotherapy) were independent risk factors that affected survival prognosis (P<0.05). Radiotherapy showed adverse effects on survival in patients with early tumor staging, lymph-node negative status, and absence of distant metastasis (all P<0.05). The lymph-node positive group had a beneficial response to radiotherapy (P<0.05), and patients with metastasis in the radiotherapy group showed a survival protection trend (P=0.069). Conclusion: In HGNECC, patients with lymph-node positive status can benefit from radiotherapy in terms of survival outcomes. We constructed two survival prediction models based on whether radiotherapy was administered, thereby offering a more scientifically guided approach to clinical treatment planning by quantifying the radiotherapy efficacy. [ABSTRACT FROM AUTHOR]

Introduction Methods Results Conclusion Safety and quality improvement are essential to clinical practice in radiation therapy as planning and treatment increase in complexity and sophistication. An incident learning system (ILS) is a safety and quality improvement tool that can aid risk mitigation to improve patient safety and quality of care. The aim of this study was to quantify the impact of implementing a new e‐ILS, Learning In Radiation ONcology (LIRON), on reporting and safety culture within a local health district (LHD).The ILS (LIRON) was implemented in 2020 with the intent of tracking actual incidents, near misses and procedural non‐compliances for analysis of root causes and contributing factors. A survey was conducted after 12 months of LIRON use, and distributed to radiation oncologists, radiation therapists and radiation oncology medical physicists within the LHD. Results were compared with the responses to a pre‐ILS implementation survey, to review changes in staff perceptions of safety culture, barriers to reporting and ILS understanding.Survey response rates were similar at baseline and at the 12‐month follow‐up, 64% and 63%, respectively. Findings showed increased ILS participation (49–71%), increased perception of no barriers to reporting (34–43%) and increased encouragement to report (37–43%). Greater confidence in the department's ability to learn from the ILS was evident (24–46%).Initial findings of LIRON implementation show positive impact but warrant further long‐term review for greater understanding of its impact on staff perceptions, safety culture and improving departmental processes. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Background: Stereotactic body radiation therapy (SBRT) is known to modulate the immune system and contribute to the generation of anti‐tumor T cells and stimulate T cell infiltration into tumors. Radiation‐induced immune suppression (RIIS) is a side effect of radiation therapy that can decrease immunological function by killing naive T cells as well as SBRT‐induced newly created effector T cells, suppressing the immune response to tumors and increasing susceptibility to infections. Purpose: RIIS varies substantially among patients and it is currently unclear what drives this variability. Models that can accurately predict RIIS in near real time based on treatment plan characteristics would allow treatment planners to maintain current protocol specific dosimetric criteria while minimizing immune suppression. In this paper, we present an algorithm to predict RIIS based on a model of circulating blood using early stage lung cancer patients treated with SBRT. Methods: This Python‐based algorithm uses DICOM data for radiation therapy treatment plans, dose maps, patient CT data sets, and organ delineations to stochastically simulate blood flow and predict the doses absorbed by circulating lymphocytes. These absorbed doses are used to predict the fraction of lymphocytes killed by a given treatment plan. Finally, the time dependence of absolute lymphocyte count (ALC) following SBRT is modeled using longitudinal blood data up to a year after treatment. This model was developed and evaluated on a cohort of 64 patients with 10‐fold cross validation. Results: Our algorithm predicted post‐treatment ALC with an average error of 0.24±0.21×109$0.24 \pm 0.21 \times {10}^9$ cells/L with 89% of the patients having a prediction error below 0.5 × 109 cells/L. The accuracy was consistent across a wide range of clinical and treatment variables. Our model is able to predict post‐treatment ALC < 0.8 (grade 2 lymphopenia), with a sensitivity of 81% and a specificity of 98%. This model has a ∼38‐s end‐to‐end prediction time of post treatment ALC. Conclusion: Our model performed well in predicting RIIS in patients treated using lung SBRT. With near‐real time model prediction time, it has the capability to be interfaced with treatment planning systems to prospectively reduce immune cell toxicity while maintaining national SBRT conformity and plan quality criteria. [ABSTRACT FROM AUTHOR]

Simple Summary: The InterVision framework employs advanced deep learning techniques to interpolate or create intermediate images between existing ones using deformable vectors, thereby capturing specific patient characteristics, such as unique anatomical features and variations in organ shape, size, and position. These characteristics are vital for personalizing treatment plans in radiotherapy, as they allow for the use of pre-planning information, which is available before the treatment begins, ensuring a tailored and precise approach to each patient's care. The training process involves two steps: first, generating a general model using a comprehensive dataset, and second, fine-tuning this general model with additional data produced by the InterVision framework. By incorporating the dataset generated through the InterVision framework, we were able to create a more personalized model, surpassing the level of customization achieved by previous fine-tuning approaches. The performance of these models is evaluated using the volumetric dice similarity coefficient (VDSC) and the Hausdorff distance 95% (HD95%) across 18 anatomical structures in 20 test patients. A total of 18 anatomical structures were selected based on prior treatments that involved the most organs, and 20 test patients were chosen according to the availability that has a re-planning CT and manual contours within the total dataset. This framework is especially valuable for accurately predicting complex organs and targets that present significant challenges for traditional deep learning algorithms, particularly due to the intricate contours and the variability in organ shapes across different patients. 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. [ABSTRACT FROM AUTHOR]

Radiotherapy treatment planning (RTP) requires both magnetic resonance (MR) and computed tomography (CT) modalities. However, conducting separate MR and CT scans for patients leads to misalignment, increased radiation exposure, and higher costs. To address these challenges and mitigate the limitations of supervised synthesis methods, we propose a novel unsupervised perceptual attention image synthesis model based on cycleGAN (PA‐cycleGAN). The innovation of PA‐cycleGAN lies in its model structure, which incorporates dynamic feature encoding and deep feature extraction to improve the understanding of image structure and contextual information. To ensure the visual authenticity of the synthetic images, we design a hybrid loss function that incorporates perceptual constraints using high‐level features extracted by deep neural networks. Our PA‐cycleGAN achieves notable results, with an average peak signal‐to‐noise ratio (PSNR) of 28.06, structural similarity (SSIM) of 0.95, and mean absolute error (MAE) of 46.90 on a pelvic dataset. Additionally, we validate the generalization of our method by conducting experiments on an additional head dataset. These experiments demonstrate that PA‐cycleGAN consistently outperforms other state‐of‐the‐art methods in both quantitative metrics and image synthesis quality. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI)-guided radiation therapy has proven to provide many benefits such as real-time tracking, dose escalation, and the ability to perform online adaptive therapy. The objective of this study is to compare curative treatment plans for glioblastoma tumors on a low-field MR-guided linac vs a C-arm linac and evaluate if they are comparable in terms of coverage, organ at risk sparing, delivery time, and deliverability. This is a retrospective study that consisted of 15 previously treated patients who received radiation therapy for glioblastoma on a C-arm linac. The CT simulation data used for the original clinical plans was imported into the MR-linac treatment planning system (TPS) and utilized for MR-linac plan generation. The plans were evaluated utilizing the dose volumetric histogram (DVH) and isodose lines, then compared in terms of plan quality consisting of PTV coverage, dose distributions, and OAR constraints. Statistical analysis was performed to compare differences between the two planning techniques. QA was performed on a subset of the plans to verify deliverability. Plans generated on the MR-linac were more heterogenous compared to C-arm linac plans. A statistically significant difference was found in the homogeneity index (HI) and the PTV V105% volume (cc) values. The volume of the normal brain receiving 30 Gy also showed a statistically significant (p = 0.0479) difference, where on average an additional 41.5 cc's of the normal brain tissue received 30 Gy in the MR-linac plans. The maximum dose to the normal brain structure also increased in the MR-linac plans on average by 2.6 Gy (p = 0.0002). Similarly, the average maximum dose to the scalp 4 mm structure was 6.5 Gy higher in the MR-linac plans compared to C-arm linac plans (p = 0.0103). The total MU's were higher in the MR-linac plans compared to the C-arm linac plans (p = 0.0015). Both MR-linac and C-arm linac plans met constraints for PTV coverage and OAR sparing, were deliverable, and resulted to be clinically acceptable. However, our study showed that MR-linac plans were not as conformal or as homogenous as C-arm linac plans utilizing noncoplanar beams. [ABSTRACT FROM AUTHOR]

The paper examines the violations of monotonicity and semiconvergence of the inverse optimization problem to equilibrium iterative solutions under conditions of physical density discontinuities in therapy planning techniques. Additionally, it addresses aspects of quasi-Newton iterations of the obtained solution in both voxel representation and continuous approximation. Examples include radiation treatment plans for patients treated with proton beam at the Prometheus therapeutic facility at the A. Tsyb Medical Radiological Research Center, Obninsk, Kaluga oblast, Russia. The presented aspects of the theory and its applications form the basis of the dose-anatomical planning program. [ABSTRACT FROM AUTHOR]

Purpose: The study aimed to investigate the optimal isodose line (IDL) in linear accelerator‐based stereotactic radiotherapy for single brain metastasis, using HyperArc. We compared the dosimetric parameters for target and normal brain tissue among six plans with different IDLs. Methods: This study included 30 patients with single brain metastasis. We retrospectively generated six plans for each tumor with different IDLs (80%, 70%, 60%, 50%, 40%, and 33%) using HyperArc. All treatment plans were normalized to the prescription dose of 35 Gy in five fractions which was covered by 95% of the planning target volume (PTV), defined by adding a 1.0 mm margin to the gross tumor volume (GTV). The dosimetric parameters were compared among the six plans. Results: For GTV > 0.1 cm3, the ratio of brain–GTV volumes receiving 25 Gy to PTV (V25Gy/PTV) was significantly lower at IDL 40%–70% than at IDL 80% and 33% (p < 0.01, retrospectively). For GTV < 0.1 cm3, V25Gy/PTV decreased continuously as IDL decreased. The values of D99% and D80% for GTV increased with decreasing IDL. An IDL of 50% or less was required to achieve D99% of greater than 43 Gy and D80% of greater than 50 Gy. The mean values of D99% and D80% for IDL 50% were 44.3 and 51.9 Gy. Conclusion: The optimal IDL is 40%–50% for GTV > 0.1 cm3. These lower IDLs could increase D99% and D80% of GTV while lowering V25Gy of normal brain tissue, which may help reduce the risk of radiation necrosis and improve local control. [ABSTRACT FROM AUTHOR]

The present study aimed to summarize and report data on errors related to treatment planning, which were collected by medical physicists. The following analyses were performed based on the 10-year error report data: (1) listing of high-risk errors that occurred and (2) the relationship between the number of treatments and error rates, (3) usefulness of the Automated Plan Checking System (APCS) with the Eclipse Scripting Application Programming Interface and (4) the relationship between human factors and error rates. Differences in error rates were observed before and after the use of APCS. APCS reduced the error rate by ~1% for high-risk errors and 3% for low-risk errors. The number of treatments was negatively correlated with error rates. Therefore, we examined the relationship between the workload of medical physicists and error occurrence and revealed that a very large workload may contribute to overlooking errors. Meanwhile, an increase in the number of medical physicists may lead to the detection of more errors. The number of errors was correlated with the number of physicians with less clinical experience; the error rates were higher when there were more physicians with less experience. This is likely due to the lack of training among clinically inexperienced physicians. An environment to provide adequate training is important, as inexperience in clinical practice can easily and directly lead to the occurrence of errors. In any environment, the need for additional plan checkers is an essential factor for eliminating errors. [ABSTRACT FROM AUTHOR]

Purpose: Radiotherapy treatment planning (RTP) using MR has been used increasingly for the abdominal site. Multiple contrast weightings and motion‐resolved imaging are desired for accurate delineation of the target and various organs‐at‐risk and patient‐tailored planning. Current MR protocols achieve these through multiple scans with distinct contrast and variable respiratory motion management strategies and acquisition parameters, leading to a complex and inaccurate planning process. This study presents a standalone MR Multitasking (MT)–based technique to produce volumetric, motion‐resolved, multicontrast images for abdominal radiotherapy treatment planning. Methods: The MT technique resolves motion and provides a wide range of contrast weightings by repeating a magnetization‐prepared (saturation recovery and T2 preparations) spoiled gradient‐echo readout series and adopting the MT image reconstruction framework. The performance of the technique was assessed through digital phantom simulations and in vivo studies of both healthy volunteers and patients with liver tumors. Results: In the digital phantom study, the MT technique presented structural details and motion in excellent agreement with the digital ground truth. The in vivo studies showed that the motion range was highly correlated (R2 = 0.82) between MT and 2D cine imaging. MT allowed for a flexible contrast‐weighting selection for better visualization. Initial clinical testing with interobserver analysis demonstrated acceptable target delineation quality (Dice coefficient = 0.85 ± 0.05, Hausdorff distance = 3.3 ± 0.72 mm). Conclusion: The developed MT‐based, abdomen‐dedicated technique is capable of providing motion‐resolved, multicontrast volumetric images in a single scan, which may facilitate abdominal radiotherapy treatment planning. [ABSTRACT FROM AUTHOR]

The participation of radiation oncology team members in the irradiation of Imaging and Radiation Oncology Core (IROC) phantom for cooperative group clinical trials is essential to comply with the latest quality management philosophy. Medical dosimetrists are expected to develop treatment plans for the irradiation of IROC phantoms. For advanced treatment techniques, such as three-dimensional conformal radiation therapy (3DCRT), intensity-modulated radiation therapy (IMRT), and volumetric-modulated arc therapy (VMAT), the irradiation of the IROC phantoms serves as quality audit. If successful, the irradiation processes demonstrate that the institution has the knowledge of the protocol, and has the appropriate equipment to comply with the protocol requirements. This article describes three IROC phantoms used for credentialing external beam photon beam therapy, delivered using conventional medical linear accelerators, to the medical dosimetry community. Guidance and strategies for the development of treatment plans are discussed. Our institutional irradiation of the three IROC phantoms, delivered using the Truebeam medical linear accelerator, resulted in consistent dose accuracy to within ±1%. The participation of the team members may reduce the overall published failing rate stated to be about one-third of all participating institutions. [ABSTRACT FROM AUTHOR]

This paper examines the dosimetric uncertainty arising from the use of thermoplastic masks in the treatment of head and neck cancer through radiotherapy. This study was conducted through Monte Carlo simulations using the Monte Carlo N-Particle eXtended (MCNPX code), and the theoretical results are compared with radiochromic films. Using material characterization techniques, the compounds of the thermoplastic mask were identified, confirming that most of the material corresponds to the polymer C10H16O4. The theoretical results show increases ranging from 42% to 57.4% in the surface absorbed dose for 6 and 15 MV photon beams, respectively, compared to the absorbed dose without the mask. The experimental data corroborate these findings, showing dose increases ranging from 18.4% to 52.1% compared to the expected surface absorbed dose without the mask. These results highlight the need to consider the bolus effect induced by thermoplastic masks during the precise and safe planning and application of radiotherapy treatment in order to ensure its therapeutic efficacy and minimize the associated risks to patients. [ABSTRACT FROM AUTHOR]

Over the last decades, the use of artificial intelligence, machine learning and deep learning in medical fields has skyrocketed. Well known for their results in segmentation, motion management and posttreatment outcome tasks, investigations of machine learning and deep learning models as fast dose calculation or quality assurance tools have been present since 2000. The main motivation for this increasing research and interest in artificial intelligence, machine learning and deep learning is the enhancement of treatment workflows, specifically dosimetry and quality assurance accuracy and time points, which remain important time-consuming aspects of clinical patient management. Since 2014, the evolution of models and architectures for dose calculation has been related to innovations and interest in the theory of information research with pronounced improvements in architecture design. The use of knowledge-based approaches to patient-specific methods has also considerably improved the accuracy of dose predictions. This paper covers the state of all known deep learning architectures and models applied to external radiotherapy with a description of each architecture, followed by a discussion on the performance and future of deep learning predictive models in external radiotherapy. [ABSTRACT FROM AUTHOR]

To develop and externally validate an automatic artificial intelligence (AI) tool for delineating gross tumor volume (GTV) in patients with esophageal squamous cell carcinoma (ESCC), which can assist in neo-adjuvant or radical radiation therapy treatment planning. In this multi-institutional study, contrast-enhanced CT images from 580 eligible ESCC patients were retrospectively collected. The GTV contours delineated by 2 experts via consensus were used as ground truth. A 3-dimensional deep learning model was developed for GTV contouring in the training cohort and internally and externally validated in 3 validation cohorts. The AI tool was compared against 12 board-certified experts in 25 patients randomly selected from the external validation cohort to evaluate its assistance in improving contouring performance and reducing variation. Contouring performance was measured using dice similarity coefficient (DSC) and average surface distance. Additionally, our previously established radiomics model for predicting pathologic complete response was used to compare AI-generated and ground truth contours, to assess the potential of the AI contouring tool in radiomics analysis. The AI tool demonstrated good GTV contouring performance in multicenter validation cohorts, with median DSC values of 0.865, 0.876, and 0.866 and median average surface distance values of 0.939, 0.789, and 0.875 mm, respectively. Furthermore, the AI tool significantly improved contouring performance for half of 12 board-certified experts (DSC values, 0.794-0.835 vs 0.856-0.881, P =.003-0.048), reduced the intra- and interobserver variations by 37.4% and 55.2%, respectively, and saved contouring time by 77.6%. In the radiomics analysis, 88.7% of radiomic features from ground truth and AI-generated contours demonstrated stable reproducibility, and similar pathologic complete response prediction performance for these contours (P =.430) was observed. Our AI contouring tool can improve GTV contouring performance and facilitate radiomics analysis in ESCC patients, which indicates its potential for GTV contouring during radiation therapy treatment planning and radiomics studies. [ABSTRACT FROM AUTHOR]

Background: Quality assurance (QA) of patient‐specific treatment plans for intensity‐modulated radiation therapy (IMRT) and volumetric modulated arc therapy (VMAT) necessitates prior validation. However, the standard methodology exhibits deficiencies and lacks sensitivity in the analysis of positional dose distribution data, leading to difficulties in accurately identifying reasons for plan verification failure. This issue complicates and impedes the efficiency of QA tasks. Purpose: The primary aim of this research is to utilize deep learning algorithms for the extraction of 3D dose distribution maps and the creation of a predictive model for error classification across multiple machine models, treatment methodologies, and tumor locations. Method: We devised five categories of validation plans (normal, gantry error, collimator error, couch error, and dose error), conforming to tolerance limits of different accuracy levels and employing 3D dose distribution data from a sample of 94 tumor patients. A CNN model was then constructed to predict the diverse error types, with predictions compared against the gamma pass rate (GPR) standard employing distinct thresholds (3%, 3 mm; 3%, 2 mm; 2%, 2 mm) to evaluate the model's performance. Furthermore, we appraised the model's robustness by assessing its functionality across diverse accelerators. Results: The accuracy, precision, recall, and F1 scores of CNN model performance were 0.907, 0.925, 0.907, and 0.908, respectively. Meanwhile, the performance on another device is 0.900, 0.918, 0.900, and 0.898. In addition, compared to the GPR method, the CNN model achieved better results in predicting different types of errors. Conclusion: When juxtaposed with the GPR methodology, the CNN model exhibits superior predictive capability for classification in the validation of the radiation therapy plan on different devices. By using this model, the plan validation failures can be detected more rapidly and efficiently, minimizing the time required for QA tasks and serving as a valuable adjunct to overcome the constraints of the GPR method. [ABSTRACT FROM AUTHOR]

Purpose objective(s): Manual contouring of the prostate region in planning computed tomography (CT) images is a challenging task due to factors such as low contrast in soft tissues, inter- and intra-observer variability, and variations in organ size and shape. Consequently, the use of automated contouring methods can offer significant advantages. In this study, we aimed to investigate automated male pelvic multi-organ contouring in multi-center planning CT images using a hybrid convolutional neural network-vision transformer (CNN-ViT) that combines convolutional and ViT techniques. Materials/methods: We used retrospective data from 104 localized prostate cancer patients, with delineations of the clinical target volume (CTV) and critical organs at risk (OAR) for external beam radiotherapy. We introduced a novel attention-based fusion module that merges detailed features extracted through convolution with the global features obtained through the ViT. Results: The average dice similarity coefficients (DSCs) achieved by VGG16-UNet-ViT for the prostate, bladder, rectum, right femoral head (RFH), and left femoral head (LFH) were 91.75%, 95.32%, 87.00%, 96.30%, and 96.34%, respectively. Experiments conducted on multi-center planning CT images indicate that combining the ViT structure with the CNN network resulted in superior performance for all organs compared to pure CNN and transformer architectures. Furthermore, the proposed method achieves more precise contours compared to state-of-the-art techniques. Conclusion: Results demonstrate that integrating ViT into CNN architectures significantly improves segmentation performance. These results show promise as a reliable and efficient tool to facilitate prostate radiotherapy treatment planning. [ABSTRACT FROM AUTHOR]

Background: Conventional single-energy CT can only provide a raw estimation of electron density (ED) for dose calculation by developing a calibration curve that simply maps the HU values to ED values through their correlations. Spectral CT, also known as dual-energy CT (DECT) or multi-energy CT, can generate a series of quantitative maps, such as ED maps. Using spectral CT for radiotherapy simulations can directly acquire ED information without developing specific calibration curves. The purpose of this study is to assess the feasibility of utilizing electron density (ED) maps generated by a novel dual-layer detector spectral CT simulator for dose calculation in radiotherapy treatment plans. Methods: 30 patients from head&neck, chest, and pelvic treatment sites were selected retrospectively, and all of them underwent spectral CT simulation. Treatment plans based on conventional CT images were transplanted to ED maps with the same structure set, including planning target volume (PTV) and organs at risk (OARs), and the dose distributions were then recalculated. The differences in dose and volume histogram (DVH) parameters of the PTV and OARs between the two types of plans were analyzed and compared. Besides, gamma analysis between these plans was performed by using MEPHYSTO Navigator software. Results: In terms of PTV, the homogeneity index (HI), gradient index (GI), D2%, D98%, and Dmean showed no significant difference between conventional plans and ED plans. For OARs, statistically significant differences were observed in parotids D50%, brainstem in head&neck plans, spinal cord in chest plans and rectum D50% in pelvic plans, whereas the variance remained minor. For the rest, the DVH parameters exhibited no significant difference between conventional plans and ED plans. All of the mean gamma passing rates (GPRs) of gamma analysis were higher than 90%. Conclusion: Compared to conventional treatment plans relying on CT images, plans utilizing ED maps demonstrated similar dosimetric quality. However, the latter approach enables direct utilization in dose calculation without the requirements of establishing and selecting a specific Hounsfield unit (HU) to ED calibration curve, providing an advantage in clinical applications. [ABSTRACT FROM AUTHOR]

Background: 3D printing holds great potential of improving examination, diagnosis and treatment planning as well as interprofessional communication in the field of gynecological oncology. In the current manuscript we evaluated five individualized, patient-specific models of cervical cancer FIGO Stage I-III, created with 3D printing, concerning their value for translational oncology. Methods: Magnetic resonance imaging (MRI) of the pelvis was performed on a 3.0 Tesla MRI, including a T2-weighted isotropic 3D sequence. The MRI images were segmented and transferred to virtual 3D models via a custom-built 3D-model generation pipeline and printed by material extrusion. The 3D models were evaluated by all medical specialties involved in patient care of cervical cancer, namely surgeons, radiologists, pathologists and radiation oncologists. Information was obtained from evaluated profession-specific questionnaires which were filled out after inspecting all five models. The questionnaires included multiple-select questions, questions based on Likert scales (1 = „strongly disagree " or „not at all useful " up to 5 = „strongly agree " or „extremely useful ") and dichotomous questions ("Yes" or "No"). Results: Surgeons rated the models as useful during surgery (4.0 out of 5) and for patient communication (4.7 out of 5). Furthermore, they believed that the models had the potential to revise the patients' treatment plan (3.7 out of 5). Pathologists evaluated with mean ratings of 3.0 out of 5 for the usefulness of the models in diagnostic reporting and macroscopic evaluation. Radiologist acknowledged the possibility of providing additional information compared to imaging alone (3.7 out of 5). Radiation oncologists strongly supported the concept by rating the models highly for understanding patient-specific pathological characteristics (4.3 out of 5), assisting interprofessional communication (mean 4.3 out of 5) and communication with patients (4.7 out of 5). They also found the models useful for improving radiotherapy treatment planning (4.3 out of 5). Conclusion: The study revealed that the 3D printed models were generally well-received by all medical disciplines, with radiation oncologists showing particularly strong support. Addressing the concerns and tailoring the use of 3D models to the specific needs of each medical speciality will be essential for realizing their full potential in clinical practice. [ABSTRACT FROM AUTHOR]

Objective: The aim of the study is to compare the accuracy of dose calculation for different dose calculation algorithms with different prescription points (air, tissue, air--tissue interface in carcinoma lung patients and bone, tissue, and bone--tissue interface in carcinoma buccal Mucosa tumors). Materials and Methods: Forty-one patients with carcinoma lung and buccal mucosa were retrospectively selected for this study. A three-dimensional conformal radiotherapy reference plan was created using the prescription point in the tissue with Monte Carlo (MC) algorithms for both the groups of patients. The reference plan was modified by changing the prescription point and algorithms in the tissue, air, air--tissue interface for lung patients and tissue, bone, and bone--tissue interface for buccal mucosa patients. The dose received by the target volume and other organs at risk (OAR) structures was compared. To find out the statistical difference between different prescription points and algorithms, the statistical tests were performed with repeated measures ANOVA. Results: The target volume receiving 95% dose coverage in lung patients decreased to -3.08%, -5.75%, and -1.87% in the dose prescription point at the air--tissue interface with the dose calculation algorithms like MC, collapsed cone (CC), and pencil beam (PB), respectively, compared to that of the MC tissue. Spinal cord dose was increased in the CC and PB algorithms in all prescription points in patients with lung and buccal mucosa. OAR dose calculated by PB in all prescription points showed a significant deviation compared to MC tissue prescription point. Conclusion: This study will help demonstrate the accuracy of dose calculation for the different dose prescription points with the different treatment algorithms in radiotherapy treatment planning. [ABSTRACT FROM AUTHOR]

BACKGROUND: Accurate volumetric segmentation of primary central nervous system lymphoma (PCNSL) is essential for assessing and monitoring the tumor before radiotherapy and the treatment planning. The tedious manual segmentation leads to interindividual and intraindividual differences, while existing automatic segmentation methods cause under-segmentation of PCNSL due to the complex and multifaceted nature of the tumor. OBJECTIVE: To address the challenges of small size, diffused distribution, poor inter-layer continuity on the same axis, and tendency for over-segmentation in brain MRI PCNSL segmentation, we propose an improved attention module based on nnUNet for automated segmentation. METHODS: We collected 114 T1 MRI images of patients in the Huashan Hospital, Shanghai. Then randomly split the total of 114 cases into 5 distinct training and test sets for a 5-fold cross-validation. To efficiently and accurately delineate the PCNSL, we proposed an improved attention module based on nnU-Net with 3D convolutions, batch normalization, and residual attention (res-attention) to learn the tumor region information. Additionally, multi-scale dilated convolution kernels with different dilation rates were integrated to broaden the receptive field. We further used attentional feature fusion with 3D convolutions (AFF3D) to fuse the feature maps generated by multi-scale dilated convolution kernels to reduce under-segmentation. RESULTS: Compared to existing methods, our attention module improves the ability to distinguish diffuse and edge enhanced types of tumors; and the broadened receptive field captures tumor features of various scales and shapes more effectively, achieving a 0.9349 Dice Similarity Coefficient (DSC). CONCLUSIONS: Quantitative results demonstrate the effectiveness of the proposed method in segmenting the PCNSL. To our knowledge, this is the first study to introduce attention modules into deep learning for segmenting PCNSL based on brain magnetic resonance imaging (MRI), promoting the localization of PCNSL before radiotherapy. [ABSTRACT FROM AUTHOR]

BACKGROUND: Accurate volumetric segmentation of primary central nervous system lymphoma (PCNSL) is essential for assessing and monitoring the tumor before radiotherapy and the treatment planning. The tedious manual segmentation leads to interindividual and intraindividual differences, while existing automatic segmentation methods cause under-segmentation of PCNSL due to the complex and multifaceted nature of the tumor. OBJECTIVE: To address the challenges of small size, diffused distribution, poor inter-layer continuity on the same axis, and tendency for over-segmentation in brain MRI PCNSL segmentation, we propose an improved attention module based on nnUNet for automated segmentation. METHODS: We collected 114 T1 MRI images of patients in the Huashan Hospital, Shanghai. Then randomly split the total of 114 cases into 5 distinct training and test sets for a 5-fold cross-validation. To efficiently and accurately delineate the PCNSL, we proposed an improved attention module based on nnU-Net with 3D convolutions, batch normalization, and residual attention (res-attention) to learn the tumor region information. Additionally, multi-scale dilated convolution kernels with different dilation rates were integrated to broaden the receptive field. We further used attentional feature fusion with 3D convolutions (AFF3D) to fuse the feature maps generated by multi-scale dilated convolution kernels to reduce under-segmentation. RESULTS: Compared to existing methods, our attention module improves the ability to distinguish diffuse and edge enhanced types of tumors; and the broadened receptive field captures tumor features of various scales and shapes more effectively, achieving a 0.9349 Dice Similarity Coefficient (DSC). CONCLUSIONS: Quantitative results demonstrate the effectiveness of the proposed method in segmenting the PCNSL. To our knowledge, this is the first study to introduce attention modules into deep learning for segmenting PCNSL based on brain magnetic resonance imaging (MRI), promoting the localization of PCNSL before radiotherapy. [ABSTRACT FROM AUTHOR]

An editorial is presented that focuses on the role of technological innovation in Medical Radiation Sciences (MRS), emphasizing its integration into clinical practice to enhance patient care through advancements like artificial intelligence, and patient-centric approaches. It underscores the need for rigorous governance, inclusive co-design with stakeholders, and specialized education to effectively implement these innovations while ensuring patient safety and improving healthcare outcomes.

Background: Glioblastoma (GBM) is the most common and aggressive primary brain cancer. The treatment of GBM consists of a combination of surgery and subsequent oncological therapy, i.e., radiotherapy, chemotherapy, or their combination. If postoperative oncological therapy involves irradiation, magnetic resonance imaging (MRI) is used for radiotherapy treatment planning. Unfortunately, in some cases, a very early worsening (progression) or return (recurrence) of the disease is observed several weeks after the surgery and is called rapid early progression (REP). Radiotherapy planning is currently based on MRI for target volumes definitions in many radiotherapy facilities. However, patients with REP may benefit from targeting radiotherapy with other imaging modalities. The purpose of the presented clinical trial is to evaluate the utility of 11C-methionine in optimizing radiotherapy for glioblastoma patients with REP. Methods: This study is a nonrandomized, open-label, parallel-setting, prospective, monocentric clinical trial. The main aim of this study was to refine the diagnosis in patients with GBM with REP and to optimize subsequent radiotherapy planning. Glioblastoma patients who develop REP within approximately 6 weeks after surgery will undergo 11C-methionine positron emission tomography (PET/CT) examinations. Target volumes for radiotherapy are defined using both standard planning T1-weighted contrast-enhanced MRI and PET/CT. The primary outcome is progression-free survival defined using RANO criteria and compared to a historical cohort with REP treated without PET/CT optimization of radiotherapy. Discussion: PET is one of the most modern methods of molecular imaging. 11C-Methionine is an example of a radiolabelled (carbon 11) amino acid commonly used in the diagnosis of brain tumors and in the evaluation of response to treatment. Optimized radiotherapy may also have the potential to cover those regions with a high risk of subsequent progression, which would not be identified using standard-of-care MRI for radiotherapy planning. This is one of the first study focused on radiotherapy optimization for subgroup of patinets with REP. Trial Registration: NCT05608395, registered on 8.11.2022 in clinicaltrials.gov; EudraCT Number: 2020–000640-64, registered on 26.5.2020 in clinicaltrialsregister.eu. Protocol ID: MOU-2020–01, version 3.2, date 18.09.2020. [ABSTRACT FROM AUTHOR]

Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role in computer-aided diagnosis, surgical simulation, image-guided interventions, and especially in radiotherapy treatment planning. Thus, it is of great significance to explore automatic segmentation approaches, among which deep learning-based approaches have evolved rapidly and witnessed remarkable progress in multi-organ segmentation. However, obtaining an appropriately sized and fine-grained annotated dataset of multiple organs is extremely hard and expensive. Such scarce annotation limits the development of high-performance multi-organ segmentation models but promotes many annotation-efficient learning paradigms. Among these, studies on transfer learning leveraging external datasets, semi-supervised learning including unannotated datasets and partially-supervised learning integrating partially-labeled datasets have led the dominant way to break such dilemmas in multi-organ segmentation. We first review the fully supervised method, then present a comprehensive and systematic elaboration of the 3 abovementioned learning paradigms in the context of multi-organ segmentation from both technical and methodological perspectives, and finally summarize their challenges and future trends. [ABSTRACT FROM AUTHOR]

Objectives To determine if Limbus, an artificial intelligence (AI) auto-contouring software, can offer meaningful time savings for prostate radiotherapy treatment planning. Methods Three clinical oncologists recorded the time taken to contour prostate and seminal vesicles, lymph nodes, bladder, rectum, bowel, and femoral heads on CT scans for 30 prostate patients (15 prostate, 15 prostate and nodes). Limbus 1.6.0 was used to generate these contours on the 30 CT scans. The time taken by the oncologists to modify individual Limbus contours was noted and compared with manual contouring times. The geometric similarity of Limbus and expert contours was assessed using the Dice Similarity Coefficient (DSC), and the dosimetric impact of using un-edited Limbus organs at risk contours was studied. Results Limbus reduced the time to produce clinically acceptable contours by 26 minutes for prostate and nodes patients and by 13 minutes for the prostate only patients. DSC values of greater than 0.7 were calculated for all contours, demonstrating good initial agreement. A dosimetric study showed that 5 of the 20 plans optimized using unmodified AI structures required unnecessary compromise of PTV coverage, highlighting the importance of expert review. Conclusions Limbus offers significant time saving and has become an essential part of our clinical practice. Advances in knowledge This article is the first to include bowel and lymph nodes when assessing potential time savings using Limbus software. It demonstrates that Limbus can be used as an aid for prostate and node radiotherapy treatment planning. [ABSTRACT FROM AUTHOR]

Background: Preliminary data have shown a close association of the generalized ionization cluster size dose (in short, cluster dose) with cell survival, independent of particle type, and energy, when cluster dose is derived from an ionization detail parameter preferred for its association with cell survival. Such results suggest cluster dose has the potential to replace RBE‐weighted dose in proton and ion beam radiotherapy treatment plan optimization, should a uniform cluster dose lead to comparable biological effects. However, further preclinical investigations are warranted to confirm this premise. Purpose: To present an analytical approach to create uniform cluster dose spread‐out Bragg peaks (SOBP) for evaluation of the potential of cluster dose to result in uniform biological effect. Methods: We modified the coefficients of the Bortfeld and Schlegel weight formula, an analytical method typically used for the creation of radiation dose SOBP in particle therapy, to produce uniform cluster dose SOBP of different widths (1–5 cm) at relevant clinical proton and carbon beam energies. Optimum parameters were found by minimization of the ratio between the maximum and minimum cluster dose in the SOBP region using the Nelder–Mead method. Results: The coefficients of the Bortfeld and Schlegel weight formula leading to uniform cluster dose SOBPs were determined for each combination of beam energy and SOBP width studied. The uniformity of the resulting cluster dose SOBPs, calculated as the relative difference between the maximum and minimum cluster dose within the SOBP, was within 0.3%–3.5% for the evaluated proton beams and 1.3%–3.4% for the evaluated carbon beams. Conclusions: The modifications to the analytical approach to create radiation dose SOBPs resulted in uniform cluster dose proton and carbon SOBPs over a wide range of beam energies and SOBP widths. Such SOBPs should prove valuable in preclinical investigations for the selection of nanodosimetric quantities to be used in proton and ion therapy treatment planning. [ABSTRACT FROM AUTHOR]

Background: MR‐only radiotherapy treatment planning is an attractive alternative to conventional workflow, reducing scan time and ionizing radiation. It is crucial to derive the electron density map or synthetic CT (sCT) from MR data to perform dose calculations to enable MR‐only treatment planning. Automatic segmentation of relevant organs in MR images can accelerate the process by preventing the time‐consuming manual contouring step. However, the segmentation label is available only for CT data in many cases. Purpose: We propose CycleSeg, a unified framework that generates sCT and corresponding segmentation from MR images without access to MR segmentation labels Methods: CycleSeg utilizes the CycleGAN formulation to perform unpaired synthesis of sCT and image alignment. To enable MR (sCT) segmentation, CycleSeg incorporates unsupervised domain adaptation by using a pseudo‐labeling approach with feature alignment in semantic segmentation space. In contrast to previous approaches that perform segmentation on MR data, CycleSeg could perform segmentation on both MR and sCT. Experiments were performed with data from prostate cancer patients, with 78/7/10 subjects in the training/validation/test sets, respectively. Results: CycleSeg showed the best sCT generation results, with the lowest mean absolute error of 102.2 and the lowest Fréchet inception distance of 13.0. CycleSeg also performed best on MR segmentation, with the highest average dice score of 81.0 and 81.1 for MR and sCT segmentation, respectively. Ablation experiments confirmed the contribution of the proposed components of CycleSeg. Conclusion: CycleSeg effectively synthesized CT and performed segmentation on MR images of prostate cancer patients. Thus, CycleSeg has the potential to expedite MR‐only radiotherapy treatment planning, reducing the prescribed scans and manual segmentation effort, and increasing throughput. [ABSTRACT FROM AUTHOR]

Automation and artificial intelligence (AI) is already possible for many radiation therapy planning and treatment processes with the aim of improving workflows and increasing efficiency in radiation oncology departments. Currently, AI technology is advancing at an exponential rate, as are its applications in radiation oncology. This commentary highlights the way AI has begun to impact radiation therapy treatment planning and looks ahead to potential future developments in this space. Historically, radiation therapist's (RT's) role has evolved alongside the adoption of new technology. In Australia, RTs have key clinical roles in both planning and treatment delivery and have been integral in the implementation of automated solutions for both areas. They will need to continue to be informed, to adapt and to transform with AI technologies implemented into clinical practice in radiation oncology departments. RTs will play an important role in how AI‐based automation is implemented into practice in Australia, ensuring its application can truly enable personalised and higher‐quality treatment for patients. To inform and optimise utilisation of AI, research should not only focus on clinical outcomes but also AI's impact on professional roles, responsibilities and service delivery. Increased efficiencies in the radiation therapy workflow and workforce need to maintain safe improvements in practice and should not come at the cost of creativity, innovation, oversight and safety. [ABSTRACT FROM AUTHOR]

Backgroud and objectives: The implementation of patient-specific quality assurance (PSQA) has become a crucial aspect of the radiation therapy process. Machine learning models have demonstrated their potential as virtual QA tools, accurately predicting the gamma passing rate (GPR) of volumetric modulated arc therapy (VMAT)plans, thereby ensuring safe and efficient treatment for patients. However, there is limited multi-center research dedicated to predicting the GPR. In this study, a dosiomics-based machine learning approach was employed to construct a prediction model for classifying GPR in multiple radiotherapy institutions. Additionally, the model's performance was compared by evaluating the impact of two distinct feature selection methods. Methods: A retrospective data collection was conducted on 572 VMAT patients across three radiotherapy institutions. Utilizing a three-dimensional dose verification technique grounded in real-time measurements, y analysis was conducted according to the criteria of 3%/2 mm and 2%/2 mm, employing a dose threshold of 10% along with absolute dose and global normalization mode. Dosiomics features were extracted from the dose files, and distinct subsets of features were selected as inputs for the model using the random forest (RF) and RF combined with SHapley Additive exPlanations (SHAP) methods. The data underwent training using the extreme gradient boosting (XGBoost) algorithm, and the model's classification performance was assessed through F1-score and area under the curve (AUC) values. Results: The model exhibited optimal performance under the 3%/2 mm criteria, utilizing a subset of 20 features and attaining an AUC value of 0.88 and an F1score of 0.89. Similarly, under the 2%/2 mm criteria, the model demonstrated superior performance with a subset of 10 features, resulting in an AUC value of 0.91 and an F1-score of 0.89. The feature selection methods of RF and RF + SHAP have achieved good model performance by selecting as few features as possible. Conclusion: Based on the multi-center PSQA results, it is possible to utilize dosiomics features extracted from dose files to construct a machine learning predictive model. This model demonstrates excellent discriminative abilities, thus promoting the progress of gamma passing rate prognostic models in clinical application and implementation. Furthermore, it holds potential in providing patients with secure and efficient personalized QA management, while also reducing the workload of medical physicists. [ABSTRACT FROM AUTHOR]

Purpose: Artificial intelligence (AI) based commercial software can be used to automatically delineate organs at risk (OAR), with potential for efficiency savings in the radiotherapy treatment planning pathway, and reduction of inter‐ and intra‐observer variability. There has been little research investigating gross failure rates and failure modes of such systems. Method: 50 head and neck (H&N) patient data sets with "gold standard" contours were compared to AI‐generated contours to produce expected mean and standard deviation values for the Dice Similarity Coefficient (DSC), for four common H&N OARs (brainstem, mandible, left and right parotid). An AI‐based commercial system was applied to 500 H&N patients. AI‐generated contours were compared to manual contours, outlined by an expert human, and a gross failure was set at three standard deviations below the expected mean DSC. Failures were inspected to assess reason for failure of the AI‐based system with failures relating to suboptimal manual contouring censored. True failures were classified into 4 sub‐types (setup position, anatomy, image artefacts and unknown). Results: There were 24 true failures of the AI‐based commercial software, a gross failure rate of 1.2%. Fifteen failures were due to patient anatomy, four were due to dental image artefacts, three were due to patient position and two were unknown. True failure rates by OAR were 0.4% (brainstem), 2.2% (mandible), 1.4% (left parotid) and 0.8% (right parotid). Conclusion: True failures of the AI‐based system were predominantly associated with a non‐standard element within the CT scan. It is likely that these non‐standard elements were the reason for the gross failure, and suggests that patient datasets used to train the AI model did not contain sufficient heterogeneity of data. Regardless of the reasons for failure, the true failure rate for the AI‐based system in the H&N region for the OARs investigated was low (∼1%). [ABSTRACT FROM AUTHOR]

Objective. Four-dimensional computed tomography (4DCT) imaging consists in reconstructing a CT acquisition into multiple phases to track internal organ and tumor motion. It is commonly used in radiotherapy treatment planning to establish planning target volumes. However, 4DCT increases protocol complexity, may not align with patient breathing during treatment, and lead to higher radiation delivery. Approach. In this study, we propose a deep synthesis method to generate pseudo respiratory CT phases from static images for motion-aware treatment planning. The model produces patient-specific deformation vector fields (DVFs) by conditioning synthesis on external patient surface-based estimation, mimicking respiratory monitoring devices. A key methodological contribution is to encourage DVF realism through supervised DVF training while using an adversarial term jointly not only on the warped image but also on the magnitude of the DVF itself. This way, we avoid excessive smoothness typically obtained through deep unsupervised learning, and encourage correlations with the respiratory amplitude. Main results. Performance is evaluated using real 4DCT acquisitions with smaller tumor volumes than previously reported. Results demonstrate for the first time that the generated pseudo-respiratory CT phases can capture organ and tumor motion with similar accuracy to repeated 4DCT scans of the same patient. Mean inter-scans tumor center-of-mass distances and Dice similarity coefficients were 1.97 mm and 0.63, respectively, for real 4DCT phases and 2.35 mm and 0.71 for synthetic phases, and compares favorably to a state-of-the-art technique (RMSim). Significance. This study presents a deep image synthesis method that addresses the limitations of conventional 4DCT by generating pseudo-respiratory CT phases from static images. Although further studies are needed to assess the dosimetric impact of the proposed method, this approach has the potential to reduce radiation exposure in radiotherapy treatment planning while maintaining accurate motion representation. Our training and testing code can be found at https://github.com/cyiheng/Dynagan. [ABSTRACT FROM AUTHOR]

Background: Accurate and automated segmentation of thoracic organs‐at‐risk (OARs) is critical for radiotherapy treatment planning of thoracic cancers. However, this has remained a challenging task for four major reasons: (1) thoracic OARs have diverse morphologies; (2) thoracic OARs have low contrast with the background; (3) boundaries of thoracic OARs are blurry; (4) class imbalance issue caused by small organs. Purpose: To overcome the above challenges and achieve accurate and automated segmentation of thoracic OARs on thoracic CT. Methods: A novel cascaded framework based on mixed attention and multiscale information for thoracic OARs segmentation, called Cascaded‐TOARNet. This cascaded framework comprises two stages: localization and segmentation. During the localization stage, TOARNet locates each organ to crop the regions of interest (ROIs). During the segmentation stage, TOARNet accurately segments the ROIs, and the segmentation results are merged into a complete result. Results: We evaluated our proposed method and other common segmentation methods on two public datasets: the AAPM Thoracic Auto‐Segmentation Challenge dataset and the Segmentation of Thoracic Organs at Risk (SegTHOR) dataset. Our method demonstrated superior performance, achieving a mean Dice score of 92.6% on the SegTHOR dataset and 90.8% on the AAPM dataset. Conclusions: This segmentation method holds great promise as an essential tool for enhancing the efficiency of thoracic radiotherapy planning. [ABSTRACT FROM AUTHOR]

Radiotherapy treatment plans have become highly conformal, posing additional constraints on the accuracy of treatment delivery. Here, we explore the use of radiation-sensitive ultrasound contrast agents (superheated phase-change nanodroplets) as dosimetric radiation sensors. In a series of experiments, we irradiated perfluorobutane nanodroplets dispersed in gel phantoms at various temperatures and assessed the radiation-induced nanodroplet vaporization events using offline or online ultrasound imaging. At 25 °C and 37 °C, the nanodroplet response was only present at higher photon energies (≥10 MV) and limited to <2 vaporization events per cm2 per Gy. A strong response (~2000 vaporizations per cm2 per Gy) was observed at 65 °C, suggesting radiation-induced nucleation of the droplet core at a sufficiently high degree of superheat. These results emphasize the need for alternative nanodroplet formulations, with a more volatile perfluorocarbon core, to enable in vivo photon dosimetry. The current nanodroplet formulation carries potential as an innovative gel dosimeter if an appropriate gel matrix can be found to ensure reproducibility. Eventually, the proposed technology might unlock unprecedented temporal and spatial resolution in image-based dosimetry, thanks to the combination of high-frame-rate ultrasound imaging and the detection of individual vaporization events, thereby addressing some of the burning challenges of new radiotherapy innovations. [ABSTRACT FROM AUTHOR]

Background: In planning radiotherapy treatments, computed tomography (CT) has become a crucial tool. CT scans involve exposure to ionizing radiation, which can increase the risk of cancer and other adverse health effects in patients. Ionizing radiation doses for medical exposure must be kept "As Low As Reasonably Achievable". Very few articles on guidelines for radiotherapy-computed tomography scans are available. This paper reviews the current literature on radiation dose optimization based on the effective dose and diagnostic reference level (DRL) for head, neck, and pelvic CT procedures used in radiation therapy planning. This paper explores the strategies used to optimize radiation doses, and high-quality images for diagnosis and treatment planning. Methods: A cross-sectional study was conducted on 300 patients with head, neck, and pelvic region cancer in our institution. The DRL, effective dose, volumetric CT dose index (CTDIvol), and dose-length product (DLP) for the present and optimized protocol were calculated. DRLs were proposed for the DLP using the 75th percentile of the distribution. The DLP is a measure of the radiation dose received by a patient during a CT scan and is calculated by multiplying the CT dose index (CTDI) by the scan length. To calculate a DRL from a DLP, a large dataset of DLP values obtained from a specific imaging procedure must be collected and can be used to determine the median or 75th-percentile DLP value for each imaging procedure. Results: Significant variations were found in the DLP, CTDIvol, and effective dose when we compared both the standard protocol and the optimized protocol. Also, the optimized protocol was compared with other diagnostic and radiotherapy CT scan studies conducted by other centers. As a result, we found that our institution's DRL was significantly low. The optimized dose protocol showed a reduction in the CTDIvol (70% and 63%), DLP (60% and 61%), and effective dose (67% and 62%) for both head, neck, and pelvic scans. Conclusions: Optimized protocol DRLs were proposed for comparison purposes. [ABSTRACT FROM AUTHOR]

This study aimed to propose an automated prediction approach of the consolidation tumor ratios (CTRs) of part-solid tumors of patients treated with radiotherapy on treatment planning computed tomography images using deep learning segmentation (DLS) models. For training the DLS model for cancer regions, a total of 115 patients with non-small cell lung cancer (NSCLC) who underwent stereotactic body radiation therapy were selected as the training dataset, including solid, part-solid, and ground-glass opacity tumors. For testing the automated prediction approach of CTRs based on segmented tumor regions, 38 patients with part-solid tumors were selected as an internal test dataset A (IN) from a same institute as the training dataset, and 49 patients as an external test dataset (EX) from a public database. The CTRs for part-solid tumors were predicted as ratios of the maximum diameters of solid components to those of whole tumors. Pearson correlations between reference and predicted CTRs for the two test datasets were 0.953 (IN) and 0.926 (EX) for one of the DLS models (p < 0.01). Intraclass correlation coefficients between reference and predicted CTRs for the two test datasets were 0.943 (IN) and 0.904 (EX) for the same DLS models. The findings suggest that the automated prediction approach could be robust in calculating the CTRs of part-solid tumors. [ABSTRACT FROM AUTHOR]