Adaptive Radiotherapy for Anatomical Changes

Enhancing adaptive proton therapy through CBCT images: Synthetic head and neck CT generation based on 3D vision transformers

BACKGROUND

Proton therapy is a form of radiotherapy commonly used to treat various cancers. Due to its high conformality, minor variations in patient anatomy can lead to significant alterations in dose distribution, making adaptation crucial. While cone-beam computed tomography (CBCT) is a well-established technique for adaptive radiation therapy (ART), it cannot be directly used for adaptive proton therapy (APT) treatments because the stopping power ratio (SPR) cannot be estimated from CBCT images.

PURPOSE

To address this limitation, Deep Learning methods have been suggested for converting pseudo-CT (pCT) images from CBCT images. In spite of convolutional neural networks (CNNs) have shown consistent improvement in pCT literature, there is still a need for further enhancements to make them suitable for clinical applications.

METHODS

The authors introduce the 3D vision transformer (ViT) block, studying its performance at various stages of the proposed architectures. Additionally, they conduct a retrospective analysis of a dataset that includes 259 image pairs from 59 patients who underwent treatment for head and neck cancer. The dataset is partitioned into 80% for training, 10% for validation, and 10% for testing purposes.

RESULTS

The SPR maps obtained from the pCT using the proposed method present an absolute relative error of less than 5% from those computed from the planning CT, thus improving the results of CBCT.

CONCLUSIONS

We introduce an enhanced ViT3D architecture for pCT image generation from CBCT images, reducing SPR error within clinical margins for APT workflows. The new method minimizes bias compared to CT-based SPR estimation and dose calculation, signaling a promising direction for future research in this field. However, further research is needed to assess the robustness and generalizability across different medical imaging applications.

A reference-point-method-based online proton treatment plan re-optimization strategy and a novel solution to planning constraint infeasibility problem

Objective. Propose a highly automated treatment plan re-optimization strategy suitable for online adaptive proton therapy. The strategy includes a rapid re-optimization method that generates quality replans and a novel solution that efficiently addresses the planning constraint infeasibility issue that can significantly prolong the re-optimization process.Approach. We propose a systematic reference point method (RPM) model that minimizes the l-infinity norm from the initial treatment plan in the daily objective space for online re-optimization. This model minimizes the largest objective value deviation among the objectives of the daily replan from their reference values, leading to a daily replan similar to the initial plan. Whether a set of planning constraints is feasible with respect to the daily anatomy cannot be known before solving the corresponding optimization problem. The conventional trial-and-error-based relaxation process can cost a significant amount of time. To that end, we propose an optimization problem that first estimates the magnitude of daily violation of each planning constraint. Guided by the violation magnitude and clinical importance of the constraints, the constraints are then iteratively converted into objectives based on their priority until the infeasibility issue is solved.Main results.The proposed RPM-based strategy generated replans similar to the offline manual replans within the online time requirement for six head and neck and four breast patients. The average targetD95and relevant organ at risk sparing parameter differences between the RPM replans and clinical offline replans were -0.23, -1.62 Gy for head and neck cases and 0.29, -0.39 Gy for breast cases. The proposed constraint relaxation solution made the RPM problem feasible after one round of relaxation for all four patients who encountered the infeasibility issue.Significance. We proposed a novel RPM-based re-optimization strategy and demonstrated its effectiveness on complex cases, regardless of whether constraint infeasibility is encountered.

Assessment of the deep learning-based gamma passing rate prediction system for 1.5 T magnetic resonance-guided linear accelerator

Measurement-based verification is impossible for the patient-specific quality assurance (QA) of online adaptive magnetic resonance imaging-guided radiotherapy (oMRgRT) because the patient remains on the couch throughout the session. We assessed a deep learning (DL) system for oMRgRT to predict the gamma passing rate (GPR). This study collected 125 verification plans [reference plan (RP), 100; adapted plan (AP), 25] from patients with prostate cancer treated using Elekta Unity. Based on our previous study, we employed a convolutional neural network that predicted the GPRs of nine pairs of gamma criteria from 1%/1 mm to 3%/3 mm. First, we trained and tested the DL model using RPs (n = 75 and n = 25 for training and testing, respectively) for its optimization. Second, we tested the GPR prediction accuracy using APs to determine whether the DL model could be applied to APs. The mean absolute error (MAE) and correlation coefficient (r) of the RPs were 1.22 ± 0.27% and 0.29 ± 0.10 in 3%/2 mm, 1.35 ± 0.16% and 0.37 ± 0.15 in 2%/2 mm, and 3.62 ± 0.55% and 0.32 ± 0.14 in 1%/1 mm, respectively. The MAE and r of the APs were 1.13 ± 0.33% and 0.35 ± 0.22 in 3%/2 mm, 1.68 ± 0.47% and 0.30 ± 0.11 in 2%/2 mm, and 5.08 ± 0.29% and 0.15 ± 0.10 in 1%/1 mm, respectively. The time cost was within 3 s for the prediction. The results suggest the DL-based model has the potential for rapid GPR prediction in Elekta Unity.

Artificial Intelligence and the future of radiotherapy planning: The Australian radiation therapists prepare to be ready

The use of artificial intelligence (AI) solutions is rapidly changing the way radiation therapy tasks, traditionally relying on human skills, are approached by enabling fast automation. This evolution represents a paradigm shift in all aspects of the profession, particularly for treatment planning applications, opening up opportunities but also causing concerns for the future of the multidisciplinary team. In Australia, radiation therapists (RTs), largely responsible for both treatment planning and delivery, are discussing the impact of the introduction of AI and the potential developments in the future of their role. As medical physicists, who are part of the multidisciplinary team, in this editorial we reflect on the considerations of RTs, and on the implications of this transition to AI.

A prospective observational study evaluating two patient immobilisation methods in lung stereotactic radiotherapy

PURPOSE

The main objective of this study was to assess inter- and intrafraction errors for two patient immobilisation devices in the context of lung stereotactic body radiation therapy: a vacuum cushion and a simple arm support.

MATERIALS AND METHODS

Twenty patients who were treated with lung stereotactic body radiation therapy in supine position with arms above their head were included in the study. Ten patients were setup in a vacuum cushion (Bluebag™, Elekta) and ten other patients with a simple arm support (Posirest™, Civco). A pretreatment four-dimensional cone-beam computed tomography and a post-treatment three-dimensional cone-beam computed tomography were acquired to compare positioning and immobilisation accuracy. Based on a rigid registration with the planning computed tomography on the spine at the target level, translational and rotational errors were reported.

RESULTS

The median number of fractions per treatment was 5 (range: 3-10). Mean interfraction errors based on 112 four-dimensional cone-beam computed tomographies were similar for both setups with deviations less than or equal to 1.3mm in lateral and vertical direction and 1.2° in roll and yaw. For longitudinal translational errors, mean interfraction errors were 0.7mm with vacuum cushion and -3.9mm with arm support. Based on 111 three-dimensional cone-beam computed tomographies, mean lateral, longitudinal and vertical intrafraction errors were -0.1mm, -0.2mm and 0.0mm respectively (SD: 1.0, 1.2 and 1.0mm respectively) for the patients setup with vacuum cushion, and mean vertical, longitudinal and lateral intrafraction errors were -0.3mm, -0.7mm and 0.1mm respectively (SD: 2.3, 1.8 and 1.4mm respectively) for the patients setup with arm support. Intrafraction errors means were not statistically different between both positions but standard deviations were statistically larger with arm support.

CONCLUSION

The results of our study showed similar inter and intrafraction mean deviations between both positioning but a large variability in intrafraction observed with arm support suggested a more accurate immobilization with vacuum cushion.

Unlocking the adaptive advantage: correlation and machine learning classification to identify optimal online adaptive stereotactic partial breast candidates

Objective.Online adaptive radiotherapy (OART) is a promising technique for delivering stereotactic accelerated partial breast irradiation (APBI), as lumpectomy cavities vary in location and size between simulation and treatment. However, OART is resource-intensive, increasing planning and treatment times and decreasing machine throughput compared to the standard of care (SOC). Thus, it is pertinent to identify high-yield OART candidates to best allocate resources.Approach.Reference plans (plans based on simulation anatomy), SOC plans (reference plans recalculated onto daily anatomy), and daily adaptive plans were analyzed for 31 sequential APBI targets, resulting in the analysis of 333 treatment plans. Spearman correlations between 22 reference plan metrics and 10 adaptive benefits, defined as the difference between mean SOC and delivered metrics, were analyzed to select a univariate predictor of OART benefit. A multivariate logistic regression model was then trained to stratify high- and low-benefit candidates.Main results.Adaptively delivered plans showed dosimetric benefit as compared to SOC plans for most plan metrics, although the degree of adaptive benefit varied per patient. The univariate model showed high likelihood for dosimetric adaptive benefit when the reference plan ipsilateral breast V15Gy exceeds 23.5%. Recursive feature elimination identified 5 metrics that predict high-dosimetric-benefit adaptive patients. Using leave-one-out cross validation, the univariate and multivariate models classified targets with 74.2% and 83.9% accuracy, resulting in improvement in per-fraction adaptive benefit between targets identified as high- and low-yield for 7/10 and 8/10 plan metrics, respectively.Significance.This retrospective, exploratory study demonstrated that dosimetric benefit can be predicted using only ipsilateral breast V15Gy on the reference treatment plan, allowing for a simple, interpretable model. Using multivariate logistic regression for adaptive benefit prediction led to increased accuracy at the cost of a more complicated model. This work presents a methodology for clinics wishing to triage OART resource allocation.

Adapt-On-Demand: A Novel Strategy for Personalized Adaptive Radiation Therapy for Locally Advanced Lung Cancer

PURPOSE

Real-time adaptation of thoracic radiation plans is compelling because offline adaptive experiences show that tumor volumes and lung anatomy can change during therapy. We present and analyze a novel adaptive-on-demand (AOD) workflow combining online adaptive radiation therapy (o-ART) on the ETHOS system with image guided radiation therapy delivery on a Halcyon unit for conventional fractionated radiation therapy of locally advanced lung cancer (LALC).

METHODS AND MATERIALS

We analyzed 26 patients with LALC treated with the AOD workflow, adapting weekly. We timed segments of the workflow to evaluate efficiency in a real-world clinic. Target coverage and organ at risk (OAR) doses were compared between adaptive plans (ADP) and nonadaptive scheduled plans (SCH). Planning robustness was evaluated by the frequency of preplanning goals achieved in ADP plans, stratified by tumor volume change.

RESULTS

The AOD workflow was achievable within 30 minutes for most radiation fractions. Over the course of therapy, we observed an average 26.6% ± 23.3% reduction in internal target volume (ITV). Despite these changes, with o-ART, ITV and planning target volume (PTV) coverage (V100%) was 99.2% and 93.9% for all members of the cohort, respectively. This represented a 2.9% and 6.8% improvement over nonadaptive plans (P < .05), respectively. For tumors that grew >10%, V100% was 93.1% for o-ART and 76.4% for nonadaptive plans, representing a median 17.2% improvement in the PTV coverage (P < .05). In these plans, critical OAR constraints were met 94.1% of the time, whereas in nonadaptive plans, this figure was 81.9%. This represented reductions of 1.32 Gy, 1.34 Gy, or 1.75 Gy in the heart, esophagus, and lung, respectively. The effect was larger when tumors had shrunk more than 10%. Regardless of tumor volume alterations, the PTV/ITV coverage was achieved for all adaptive plans. Exceptional cases, where dose constraints were not met, were due to large initial tumor volumes or tumor growth.

CONCLUSIONS

The AOD workflow is efficient and robust in responding to anatomic changes in LALC patients, providing dosimetric advantages over standard therapy. Weekly adaptation was adequate to keep pace with changes. This approach is a feasible alternative to conventional offline replanning workflows for managing anatomy changes in LALC radiation therapy.

Clinical Workflow of Cone Beam Computer Tomography-Based Daily Online Adaptive Radiotherapy with Offline Magnetic Resonance Guidance: The Modular Adaptive Radiotherapy System (MARS)

PURPOSE

The Ethos (Varian Medical Systems) radiotherapy device combines semi-automated anatomy detection and plan generation for cone beam computer tomography (CBCT)-based daily online adaptive radiotherapy (oART). However, CBCT offers less soft tissue contrast than magnetic resonance imaging (MRI). This work aims to present the clinical workflow of CBCT-based oART with shuttle-based offline MR guidance.

METHODS

From February to November 2023, 31 patients underwent radiotherapy on the Ethos (Varian, Palo Alto, CA, USA) system with machine learning (ML)-supported daily oART. Moreover, patients received weekly MRI in treatment position, which was utilized for daily plan adaptation, via a shuttle-based system. Initial and adapted treatment plans were generated using the Ethos treatment planning system. Patient clinical data, fractional session times (MRI + shuttle transport + positioning, adaptation, QA, RT delivery) and plan selection were assessed for all fractions in all patients.

RESULTS

In total, 737 oART fractions were applied and 118 MRIs for offline MR guidance were acquired. Primary sites of tumors were prostate (n = 16), lung (n = 7), cervix (n = 5), bladder (n = 1) and endometrium (n = 2). The treatment was completed in all patients. The median MRI acquisition time including shuttle transport and positioning to initiation of the Ethos adaptive session was 53.6 min (IQR 46.5-63.4). The median total treatment time without MRI was 30.7 min (IQR 24.7-39.2). Separately, median adaptation, plan QA and RT times were 24.3 min (IQR 18.6-32.2), 0.4 min (IQR 0.3-1,0) and 5.3 min (IQR 4.5-6.7), respectively. The adapted plan was chosen over the scheduled plan in 97.7% of cases.

CONCLUSION

This study describes the first workflow to date of a CBCT-based oART combined with a shuttle-based offline approach for MR guidance. The oART duration times reported resemble the range shown by previous publications for first clinical experiences with the Ethos system.

Synthetic CT imaging for PET monitoring in proton therapy: a simulation study

Objective.This study addresses a fundamental limitation of in-beam positron emission tomography (IB-PET) in proton therapy: the lack of direct anatomical representation in the images it produces. We aim to overcome this shortcoming by pioneering the application of deep learning techniques to create synthetic control CT images (sCT) from combining IB-PET and planning CT scan data.Approach.We conducted simulations involving six patients who underwent irradiation with proton beams. Leveraging the architecture of a visual transformer (ViT) neural network, we developed a model to generate sCT images of these patients using the planning CT scans and the inter-fractional simulated PET activity maps during irradiation. To evaluate the model's performance, a comparison was conducted between the sCT images produced by the ViT model and the authentic control CT images-serving as the benchmark.Main results.The structural similarity index was computed at a mean value across all patients of 0.91, while the mean absolute error measured 22 Hounsfield Units (HU). Root mean squared error and peak signal-to-noise ratio values were 56 HU and 30 dB, respectively. The Dice similarity coefficient exhibited a value of 0.98. These values are comparable to or exceed those found in the literature. More than 70% of the synthetic morphological changes were found to be geometrically compatible with the ones reported in the real control CT scan.Significance.Our study presents an innovative approach to surface the hidden anatomical information of IB-PET in proton therapy. Our ViT-based model successfully generates sCT images from inter-fractional PET data and planning CT scans. Our model's performance stands on par with existing models relying on input from cone beam CT or magnetic resonance imaging, which contain more anatomical information than activity maps.

Improved Dosimetry and Plan Quality for Accelerated Partial Breast Irradiation Using Online Adaptive Radiation Therapy: A Single Institutional Study

Purpose

Accelerated partial breast irradiation (APBI) is an attractive treatment modality for eligible patients as it has been shown to result in similar local control and improved cosmetic outcomes compared with whole breast radiation therapy. The use of online adaptive radiation therapy (OART) for APBI is promising as it allows for a reduction of planning target volume margins because breast motion and lumpectomy cavity volume changes are accounted for in daily imaging. Here we present a retrospective, single-institution evaluation on the adequacy of kV-cone beam computed tomography (CBCT) OART for APBI treatments.

Methods and Materials

Nineteen patients (21 treatment sites) were treated to 30 Gy in 5 fractions between January of 2022 and May of 2023. Time between simulation and treatment, change in gross tumor (ie, lumpectomy cavity) volume, and differences in dose volume histogram metrics with adaption were analyzed. The Wilcoxon paired, nonparametric test was used to test for dose volume histogram metric differences between the scheduled plans (initial plans recalculated on daily CBCT anatomy) and delivered plans, either the scheduled or adapted plan, which was reoptimized using daily anatomy.

Results

Median (interquartile range) time from simulation to first treatment was 26 days (21-32 days). During this same time, median gross tumor volume reduction was 16.0% (7.3%-23.9%) relative to simulation volume. Adaptive treatments took 31.3 minutes (27.4-36.6 minutes) from start of CBCT to treatment session end. At treatment, the adaptive plan was selected for 86% (89/103) of evaluable fractions. In evaluating plan quality, 78% of delivered plans met all target, organs at risk, and conformity metrics evaluated, compared with 34% of scheduled plans.

Conclusions

Use of OART for stereotactic linac-based APBI allowed for safe, high-quality treatments in this cohort of 21 treatment courses. Although treatment delivery times were longer than traditional stereotactic body treatments, there were notable improvements in plan quality for APBI using OART.

Daily AI-Based Treatment Adaptation under Weekly Offline MR Guidance in Chemoradiotherapy for Cervical Cancer 1: The AIM-C1 Trial

(1) Background: External beam radiotherapy (EBRT) and concurrent chemotherapy, followed by brachytherapy (BT), offer a standard of care for patients with locally advanced cervical carcinoma. Conventionally, large safety margins are required to compensate for organ movement, potentially increasing toxicity. Lately, daily high-quality cone beam CT (CBCT)-guided adaptive radiotherapy, aided by artificial intelligence (AI), became clinically available. Thus, online treatment plans can be adapted to the current position of the tumor and the adjacent organs at risk (OAR), while the patient is lying on the treatment couch. We sought to evaluate the potential of this new technology, including a weekly shuttle-based 3T-MRI scan in various treatment positions for tumor evaluation and for decreasing treatment-related side effects. (2) Methods: This is a prospective one-armed phase-II trial consisting of 40 patients with cervical carcinoma (FIGO IB-IIIC1) with an age ≥ 18 years and a Karnofsky performance score ≥ 70%. EBRT (45-50.4 Gy in 25-28 fractions with 55.0-58.8 Gy simultaneous integrated boosts to lymph node metastases) will be accompanied by weekly shuttle-based MRIs. Concurrent platinum-based chemotherapy will be given, followed by 28 Gy of BT (four fractions). The primary endpoint will be the occurrence of overall early bowel and bladder toxicity CTCAE grade 2 or higher (CTCAE v5.0). Secondary outcomes include clinical feasibility, quality of life, and imaging-based response assessment.

Beam mask and sliding window-facilitated deep learning-based accurate and efficient dose prediction for pencil beam scanning proton therapy

BACKGROUND

Accurate and efficient dose calculation is essential for on-line adaptive planning in proton therapy. Deep learning (DL) has shown promising dose prediction results in photon therapy. However, there is a scarcity of DL-based dose prediction methods specifically designed for proton therapy. Successful dose prediction method for proton therapy should account for more challenging dose prediction problems in pencil beam scanning proton therapy (PBSPT) due to its sensitivity to heterogeneities.

PURPOSE

To develop a DL-based PBSPT dose prediction workflow with high accuracy and balanced complexity to support on-line adaptive proton therapy clinical decision and subsequent replanning.

METHODS

PBSPT plans of 103 prostate cancer patients (93 for training and the other 10 for independent testing) and 83 lung cancer patients (73 for training and the other 10 for independent testing) previously treated at our institution were included in the study, each with computed tomography scans (CTs), structure sets, and plan doses calculated by the in-house developed Monte-Carlo dose engine (considered as the ground truth in the model training and testing). For the ablation study, we designed three experiments corresponding to the following three methods: (1) Experiment 1, the conventional region of interest (ROI) (composed of targets and organs-at-risk [OARs]) method. (2) Experiment 2, the beam mask (generated by raytracing of proton beams) method to improve proton dose prediction. (3) Experiment 3, the sliding window method for the model to focus on local details to further improve proton dose prediction. A fully connected 3D-Unet was adopted as the backbone. Dose volume histogram (DVH) indices, 3D Gamma passing rates with a criterion of 3%/3 mm/10%, and dice coefficients for the structures enclosed by the iso-dose lines between the predicted and the ground truth doses were used as the evaluation metrics. The calculation time for each proton dose prediction was recorded to evaluate the method's efficiency.

RESULTS

Compared to the conventional ROI method, the beam mask method improved the agreement of DVH indices for both targets and OARs and the sliding window method further improved the agreement of the DVH indices (for lung cancer, CTV D98 absolute deviation: 0.74 ± 0.18 vs. 0.57 ± 0.21 vs. 0.54 ± 0.15 Gy[RBE], ROI vs. beam mask vs. sliding window methods, respectively). For the 3D Gamma passing rates in the target, OARs, and BODY (outside target and OARs), the beam mask method improved the passing rates in these regions and the sliding window method further improved them (for prostate cancer, targets: 96.93% ± 0.53% vs. 98.88% ± 0.49% vs. 99.97% ± 0.07%, BODY: 86.88% ± 0.74% vs. 93.21% ± 0.56% vs. 95.17% ± 0.59%). A similar trend was also observed for the dice coefficients. This trend was especially remarkable for relatively low prescription isodose lines (for lung cancer, 10% isodose line dice: 0.871 ± 0.027 vs. 0.911 ± 0.023 vs. 0.927 ± 0.017). The dose predictions for all the testing cases were completed within 0.25 s.

CONCLUSIONS

An accurate and efficient deep learning-augmented proton dose prediction framework has been developed for PBSPT, which can predict accurate dose distributions not only inside but also outside ROI efficiently. The framework can potentially further reduce the initial planning and adaptive replanning workload in PBSPT.

A review of the clinical introduction of 4D particle therapy research concepts

Background and purpose

Many 4D particle therapy research concepts have been recently translated into clinics, however, remaining substantial differences depend on the indication and institute-related aspects. This work aims to summarise current state-of-the-art 4D particle therapy technology and outline a roadmap for future research and developments.

Material and methods

This review focused on the clinical implementation of 4D approaches for imaging, treatment planning, delivery and evaluation based on the 2021 and 2022 4D Treatment Workshops for Particle Therapy as well as a review of the most recent surveys, guidelines and scientific papers dedicated to this topic.

Results

Available technological capabilities for motion surveillance and compensation determined the course of each 4D particle treatment. 4D motion management, delivery techniques and strategies including imaging were diverse and depended on many factors. These included aspects of motion amplitude, tumour location, as well as accelerator technology driving the necessity of centre-specific dosimetric validation. Novel methodologies for X-ray based image processing and MRI for real-time tumour tracking and motion management were shown to have a large potential for online and offline adaptation schemes compensating for potential anatomical changes over the treatment course. The latest research developments were dominated by particle imaging, artificial intelligence methods and FLASH adding another level of complexity but also opportunities in the context of 4D treatments.

Conclusion

This review showed that the rapid technological advances in radiation oncology together with the available intrafractional motion management and adaptive strategies paved the way towards clinical implementation.

Safety and Efficacy of Neoadjuvant SABR in Pancreatic Cancer: Effect of Magnetic Resonance Imaging-Guided Respiratory-Gated Adaptive Radiation Therapy

Purpose

We aimed to evaluate the safety and efficacy of neoadjuvant SABR using magnetic resonance imaging-guided respiratory-gated adaptive radiation therapy (MRgRg-ART) in pancreatic cancer.

Methods and Materials

We performed a single-institution retrospective review in patients with pancreatic cancer who underwent neoadjuvant SABR followed by surgical resection. After neoadjuvant chemotherapy, those considered resectable by the multidisciplinary team received SABR over 5 consecutive days using MRgRg-ART. Factors associated with severe postoperative complications (Clavien-Dindo grade ≥III) and prognostic factors for overall survival were analyzed.

Results

Sixty-two patients were included in the analysis, with a median follow-up of 10.3 months. The median prescribed dose to the planning target volume was 50 Gy. Fifty-two (85.3%) patients underwent R0 resection, and 11 (18.0%) experienced severe postoperative complications. No factors were associated with the incidence of severe postoperative complications. There were 3 cases of locoregional recurrence, resulting in a 12-month local control rate of 93.1%. Elevated postoperative carbohydrate antigen 19-9 was significantly associated with poor overall survival in the multivariate analysis (P = .037).

Conclusions

Neoadjuvant SABR with 50 Gy using MRgRg-ART delivered to pancreatic cancer resulted in a notable survival outcome with acceptable toxicities. Further studies are warranted to investigate the long-term effects of this method.

Quantifying the Effect of 4-Dimensional Computed Tomography-Based Deformable Dose Accumulation on Representing Radiation Damage for Patients with Locally Advanced Non-Small Cell Lung Cancer Treated with Standard-Fractionated Intensity-Modulated Radiation Therapy

PURPOSE

The aim of this study was to investigate the dosimetric and clinical effects of 4-dimensional computed tomography (4DCT)-based longitudinal dose accumulation in patients with locally advanced non-small cell lung cancer treated with standard-fractionated intensity-modulated radiation therapy (IMRT).

METHODS AND MATERIALS

Sixty-seven patients were retrospectively selected from a randomized clinical trial. Their original IMRT plan, planning and verification 4DCTs, and ∼4-month posttreatment follow-up CTs were imported into a commercial treatment planning system. Two deformable image registration algorithms were implemented for dose accumulation, and their accuracies were assessed. The planned and accumulated doses computed using average-intensity images or phase images were compared. At the organ level, mean lung dose and normal-tissue complication probability (NTCP) for grade ≥2 radiation pneumonitis were compared. At the region level, mean dose in lung subsections and the volumetric overlap between isodose intervals were compared. At the voxel level, the accuracy in estimating the delivered dose was compared by evaluating the fit of a dose versus radiographic image density change (IDC) model. The dose-IDC model fit was also compared for subcohorts based on the magnitude of NTCP difference (|ΔNTCP|) between planned and accumulated doses.

RESULTS

Deformable image registration accuracy was quantified, and the uncertainty was considered for the voxel-level analysis. Compared with planned doses, accumulated doses on average resulted in <1-Gy lung dose increase and <2% NTCP increase (up to 8.2 Gy and 18.8% for a patient, respectively). Volumetric overlap of isodose intervals between the planned and accumulated dose distributions ranged from 0.01 to 0.93. Voxel-level dose-IDC models demonstrated a fit improvement from planned dose to accumulated dose (pseudo-R2 increased 0.0023) and a further improvement for patients with ≥2% |ΔNTCP| versus for patients with <2% |ΔNTCP|.

CONCLUSIONS

With a relatively large cohort, robust image registrations, multilevel metric comparisons, and radiographic image-based evidence, we demonstrated that dose accumulation more accurately represents the delivered dose and can be especially beneficial for patients with greater longitudinal response.

The Use of MR-Guided Radiation Therapy for Head and Neck Cancer and Recommended Reporting Guidance

Although magnetic resonance imaging (MRI) has become standard diagnostic workup for head and neck malignancies and is currently recommended by most radiological societies for pharyngeal and oral carcinomas, its utilization in radiotherapy has been heterogeneous during the last decades. However, few would argue that implementing MRI for annotation of target volumes and organs at risk provides several advantages, so that implementation of the modality for this purpose is widely accepted. Today, the term MR-guidance has received a much broader meaning, including MRI for adaptive treatments, MR-gating and tracking during radiotherapy application, MR-features as biomarkers and finally MR-only workflows. First studies on treatment of head and neck cancer on commercially available dedicated hybrid-platforms (MR-linacs), with distinct common features but also differences amongst them, have also been recently reported, as well as "biological adaptation" based on evaluation of early treatment response via functional MRI-sequences such as diffusion weighted ones. Yet, all of these approaches towards head and neck treatment remain at their infancy, especially when compared to other radiotherapy indications. Moreover, the lack of standardization for reporting MR-guided radiotherapy is a major obstacle both to further progress in the field and to conduct and compare clinical trials. Goals of this article is to present and explain all different aspects of MR-guidance for radiotherapy of head and neck cancer, summarize evidence, as well as possible advantages and challenges of the method and finally provide a comprehensive reporting guidance for use in clinical routine and trials.

Review and recommendations on deformable image registration uncertainties for radiotherapy applications

Deformable image registration (DIR) is a versatile tool used in many applications in radiotherapy (RT). DIR algorithms have been implemented in many commercial treatment planning systems providing accessible and easy-to-use solutions. However, the geometric uncertainty of DIR can be large and difficult to quantify, resulting in barriers to clinical practice. Currently, there is no agreement in the RT community on how to quantify these uncertainties and determine thresholds that distinguish a good DIR result from a poor one. This review summarises the current literature on sources of DIR uncertainties and their impact on RT applications. Recommendations are provided on how to handle these uncertainties for patient-specific use, commissioning, and research. Recommendations are also provided for developers and vendors to help users to understand DIR uncertainties and make the application of DIR in RT safer and more reliable.

Optimising the MR-Linac as a standard treatment modality

The magnetic resonance linear accelerator (MR-Linac) offers a new treatment paradigm, providing improved visualisation of targets and organs at risk while allowing for daily adaptation of treatment plans in real time. Online MR-guided adaptive treatment has reduced treatment uncertainties; however, the additional treatment time and resource requirements may be a concern. We present our experience of integrating an MR-Linac into a busy department and provide recommendations for improved clinical and resource efficiency. Furthermore, we discuss potential future technological innovations that can further optimise clinical productivity in a busy department.

End-to-end memory-efficient reconstruction for cone beam CT

BACKGROUND

Cone beam computed tomography (CBCT) plays an important role in many medical fields nowadays. Unfortunately, the potential of this imaging modality is hampered by lower image quality compared to the conventional CT, and producing accurate reconstructions remains challenging. A lot of recent research has been directed towards reconstruction methods relying on deep learning, which have shown great promise for various imaging modalities. However, practical application of deep learning to CBCT reconstruction is complicated by several issues, such as exceedingly high memory costs of deep learning methods when working with fully 3D data. Additionally, deep learning methods proposed in the literature are often trained and evaluated only on data from a specific region of interest, thus raising concerns about possible lack of generalization to other regions.

PURPOSE

In this work, we aim to address these limitations and propose LIRE: a learned invertible primal-dual iterative scheme for CBCT reconstruction.

METHODS

LIRE is a learned invertible primal-dual iterative scheme for CBCT reconstruction, wherein we employ a U-Net architecture in each primal block and a residual convolutional neural network (CNN) architecture in each dual block. Memory requirements of the network are substantially reduced while preserving its expressive power through a combination of invertible residual primal-dual blocks and patch-wise computations inside each of the blocks during both forward and backward pass. These techniques enable us to train on data with isotropic 2 mm voxel spacing, clinically-relevant projection count and detector panel resolution on current hardware with 24 GB video random access memory (VRAM).

RESULTS

Two LIRE models for small and for large field-of-view (FoV) setting were trained and validated on a set of 260 + 22 thorax CT scans and tested using a set of 142 thorax CT scans plus an out-of-distribution dataset of 79 head and neck CT scans. For both settings, our method surpasses the classical methods and the deep learning baselines on both test sets. On the thorax CT set, our method achieves peak signal-to-noise ratio (PSNR) of 33.84 ± 2.28 for the small FoV setting and 35.14 ± 2.69 for the large FoV setting; U-Net baseline achieves PSNR of 33.08 ± 1.75 and 34.29 ± 2.71 respectively. On the head and neck CT set, our method achieves PSNR of 39.35 ± 1.75 for the small FoV setting and 41.21 ± 1.41 for the large FoV setting; U-Net baseline achieves PSNR of 33.08 ± 1.75 and 34.29 ± 2.71 respectively. Additionally, we demonstrate that LIRE can be finetuned to reconstruct high-resolution CBCT data with the same geometry but 1 mm voxel spacing and higher detector panel resolution, where it outperforms the U-Net baseline as well.

CONCLUSIONS

Learned invertible primal-dual schemes with additional memory optimizations can be trained to reconstruct CBCT volumes directly from the projection data with clinically-relevant geometry and resolution. Such methods can offer better reconstruction quality and generalization compared to classical deep learning baselines.

Feasibility study of adaptive radiotherapy with Ethos for breast cancer

Purpose

The aim of this study was to assess the feasibility of online adaptive radiotherapy with Ethos for breast cancer.

Materials and methods

This retrospective study included 20 breast cancer patients previously treated with TrueBeam. All had undergone breast surgery for different indications (right/left, lumpectomy/mastectomy) and were evenly divided between these four cases, with five extended cone beam computed tomography (CBCT) scans per patient. The dataset was used in an Ethos emulator to test the full adaptive workflow. The contours generated by artificial intelligence (AI) for the influencers (left and right breasts and lungs, heart) and elastic or rigid propagation for the target volumes (internal mammary chain (IMC) and clavicular lymph nodes (CLNs)) were compared to the initial contours delineated by the physician using two metrics: Dice similarity coefficient (DICE) and Hausdorff 95% distance (HD95). The repeatability of influencer generation was investigated. The times taken by the emulator to generate contours, optimize plans, and calculate doses were recorded. The quality of the scheduled and adapted plans generated by Ethos was assessed using planning target volume (PTV) coverage, homogeneity indices (HIs), and doses to organs at risk (OARs) via dose-volume histogram (DVH) metrics. Quality assurance (QA) of the treatment plans was performed using an independent portal dosimetry tool (EpiQA) and gamma index.

Results

On average, the DICE for the influencers was greater than 0.9. Contours resulting from rigid propagation had a higher DICE and a lower HD95 than those resulting from elastic deformation but remained below the values obtained for the influencers: DICE values were 0.79 ± 0.11 and 0.46 ± 0.17 for the CLN and IMC, respectively. Regarding the repeatability of the influencer segmentation, the DICE was close to 1, and the mean HD95 was strictly less than 0.15 mm. The mean time was 73 ± 4 s for contour generation per AI and 80 ± 9 s for propagations. The average time was 53 ± 3 s for dose calculation and 125 ± 9 s for plan optimization. A dosimetric comparison of scheduled and adapted plans showed a significant difference in PTV coverage: dose received by 95% of the volume (D95%) values were higher and closer to the prescribed doses for adapted plans. Doses to organs at risk were similar. The average gamma index for quality assurance of adapted plans was 99.93 ± 0.38 for a 3%/3mm criterion.

Conclusion

This study comprehensively evaluated the Ethos® adaptive workflow for breast cancer and its potential technical limitations. Although the results demonstrated the high accuracy of AI segmentation and the superiority of adapted plans in terms of target volume coverage, a medical assessment is still required.

A stochastic model of blood flow to calculate blood dose during radiotherapy

Purpose. Lymphopenia is a common side effect in patients treated with radiotherapy, potentially caused by direct cell killing of circulating lymphocytes in the blood. To investigate this hypothesis, a method to assess dose to circulating lymphocytes is needed.Methods. A stochastic model to simulate systemic blood flow in the human body was developed based on a previously designed compartment model. Blood dose was obtained by superimposing the spatiotemporal distribution of blood particles with a time-varying dose rate field, and used as a surrogate for dose to circulating lymphocytes. We discuss relevant theory on compartmental modeling and how to combine it with models of explicit organ vasculature.Results. A general workflow was established which can be used for any anatomical site. Stochastic compartments can be replaced by explicit models of organ vasculatures for improved spatial resolution, and tumor compartments can be dynamically assigned. Generating a patient-specific blood flow distribution takes about one minute, fast enough to investigate the effect of varying treatment parameters such as the dose rate. Furthermore, the anatomical structures contributing most to the overall blood dose can be identified, which could potentially be used for lymphocyte-sparing treatment planning.Conclusion. The ability to report the blood dose distribution during radiotherapy is imperative to test and act upon the current paradigm that radiation-induced lymphopenia is caused by direct cell killing of lymphocytes in the blood. We have built a general model that can do so for various treatment sites. The presented framework is publicly available athttp://github.com/mghro/hedos.

Online Adaptive MRI-Guided Stereotactic Body Radiotherapy for Pancreatic and Other Intra-Abdominal Cancers

A 1.5T MRI combined with a linear accelerator (Unity®, Elekta; Stockholm, Sweden) is a device that shows promise in MRI-guided stereotactic body radiation treatment (SBRT). Previous studies utilized the manufacturer's pre-set MRI sequences (i.e., T2 Weighted (T2W)), which limited the visualization of pancreatic and intra-abdominal tumors and organs at risk (OAR). Here, a T1 Weighted (T1W) sequence was utilized to improve the visualization of tumors and OAR for online adapted-to-position (ATP) and adapted-to-shape (ATS) during MRI-guided SBRT. Twenty-six patients, 19 with pancreatic and 7 with intra-abdominal cancers, underwent CT and MRI simulations for SBRT planning before being treated with multi-fractionated MRI-guided SBRT. The boundary of tumors and OAR was more clearly seen on T1W image sets, resulting in fast and accurate contouring during online ATP/ATS planning. Plan quality in 26 patients was dependent on OAR proximity to the target tumor and achieved 96 ± 5% and 92 ± 9% in gross tumor volume D90% and planning target volume D90%. We utilized T1W imaging (about 120 s) to shorten imaging time by 67% compared to T2W imaging (about 360 s) and improve tumor visualization, minimizing target/OAR delineation uncertainty and the treatment margin for sparing OAR. The average time-consumption of MRI-guided SBRT for the first 21 patients was 55 ± 15 min for ATP and 79 ± 20 min for ATS.

Contour subregion error detection methodology using deep learning auto-segmentation

BACKGROUND

Inaccurate manual organ delineation is one of the high-risk failure modes in radiation treatment. Numerous automated contour quality assurance (QA) systems have been developed to assess contour acceptability; however, manual inspection of flagged cases is a time-consuming and challenging process, and can lead to users overlooking the exact error location.

PURPOSE

Our aim is to develop and validate a contour QA system that can effectively detect and visualize subregional contour errors, both qualitatively and quantitatively.

METHODS/MATERIALS

A novel contour subregion error detection (CSED) system was developed using subregional surface distance discrepancies between manual and deep learning auto-segmentation (DLAS) contours. A validation study was conducted using a head and neck public dataset containing 339 cases and evaluated according to knowledge-based pass criteria derived from a clinical training dataset of 60 cases. A blind qualitative evaluation was conducted, comparing the results from the CSED system with manual labels. Subsequently, the CSED-flagged cases were re-examined by a radiation oncologist.

RESULTS

The CSED system could visualize the diverse types of subregional contour errors qualitatively and quantitatively. In the validation dataset, the CSED system resulted in true positive rates (TPR) of 0.814, 0.800, and 0.771; false positive rates (FPR) of 0.310, 0.267, and 0.298; and accuracies of 0.735, 0.759, and 0.730, for brainstem and left and right parotid contours, respectively. The CSED-assisted manual review caught 13 brainstem, 19 left parotid, and 21 right parotid contour errors missed by conventional human review. The TPR/FPR/accuracy of the CSED-assisted manual review improved to 0.836/0.253/0.784, 0.831/0.171/0.830, and 0.808/0.193/0.807 for each structure, respectively. Further, the time savings achieved through CSED-assisted review improved by 75%, with the time for review taking 24.81 ± 12.84, 26.75 ± 10.41, and 28.71 ± 13.72 s for each structure, respectively.

CONCLUSIONS

The CSED system enables qualitative and quantitative detection, localization, and visualization of manual segmentation subregional errors utilizing DLAS contours as references. The use of this system has been shown to help reduce the risk of high-risk failure modes resulting from inaccurate organ segmentation.

Online adaptive radiotherapy: Assessment of planning technique and its impact on longitudinal plan quality robustness in pancreatic cancer

BACKGROUND AND PURPOSE

Planning on a static dataset that reflects the simulation day anatomy is routine for SBRT. We hypothesize the quality of on-table adaptive plans is similar to the baseline plan when delivering stereotactic MR-guided adaptive radiotherapy (SMART) for pancreatic cancer (PCa).

MATERIALS AND METHODS

Sixty-seven inoperable PCa patients were prescribed 50 Gy/5-fraction SMART. Baseline planning included: 3-5 mm gastrointestinal (GI) PRV, 50 Gy optimization target (PTVopt) based on GI PRV, conformality rings, and contracted GTV to guide the hotspot. For each adaptation, GI anatomy was re-contoured, followed by re-optimization. Plan quality was evaluated for target coverage (TC = PTVopt V100%/volume), PTV D90% and D80%, homogeneity index (HI = PTVopt D2%/D98%), prescription isodose/target volume (PITV), low-dose conformity (D2cm = maximum dose at 2 cm from PTVopt/Rx dose), and gradient index (R50%=50% Rx isodose volume/PTVopt volume).A novel global planning metric, termed the Pancreas Adaptive Radiotherapy Score (PARTS), was developed and implemented based on GI OAR sparing, PTV/GTV coverage, and conformality. Adaptive robustness (baseline to fraction 1) and stability (difference between two fractions with highest GI PRV variation) were quantified.

RESULTS

OAR constraints were met on all baseline (n = 67) and adaptive (n = 318) plans. Coverage for baseline/adaptive plans was mean ± SD at 44.9 ± 5.8 Gy/44.3 ± 5.5 Gy (PTV D80%), 50.1 ± 4.2 Gy/49.1 ± 4.7 Gy (PTVopt D80%), and 80%±18%/74%±18% (TC), respectively. Mean homogeneity and conformality for baseline/adaptive plans were 0.87 ± 0.25/0.81 ± 0.30 (PITV), 3.81 ± 1.87/3.87 ± 2.0 (R50%), 1.53 ± 0.23/1.55 ± 0.23 (HI), and 58%±7%/59%±7% (D2cm), respectively. PARTS was found to be a sensitive metric due to its additive influence of geometry changes on PARTS' sub-metrics. There were no statistical differences (p > 0.05) for stability, except for PARTS (p = 0.04, median difference -0.6%). Statistical differences for robustness when significant were small for most metrics (<2.0% median). Median adaptive re-optimizations were 2.

CONCLUSION

We describe a 5-fraction ablative SMART planning approach for PCa that is robust and stable during on-table adaption, due to gradients controlled by a GI PRV technique and the use of rings. These findings are noteworthy given that daily interfraction anatomic GI OAR differences are routine, thus necessitating on-table adaptation. This work supports feasibility towards utilizing a patient-independent, template on-table adaptive approach.

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

BACKGROUND

Cone-beam computed tomography (CBCT) scanning is used for patient setup in image-guided radiotherapy. However, its inaccurate CT numbers limit its applicability in dose calculation and treatment planning.

PURPOSE

This study compares four deep learning methods for generating synthetic CT (sCT) to determine which method is more appropriate and offers potential for further clinical exploration in adaptive proton therapy for nasopharynx cancer.

METHODS

CBCTs and deformed planning CT (dCT) from 75 patients (60/5/10 for training, validation and testing) were used to compare cycle-consistent Generative Adversarial Network (cycleGAN), Unet, Unet+cycleGAN and conditionalGenerative Adversarial Network (cGAN) for sCT generation. The sCT images generated by each method were evaluated against dCT images using mean absolute error (MAE), structural similarity (SSIM), peak signal-to-noise ratio (PSNR), spatial non-uniformity (SNU) and radial averaging in the frequency domain. In addition, dosimetric accuracy was assessed through gamma analysis, differences in water equivalent thickness (WET), and dose-volume histogram metrics.

RESULTS

The cGAN model has demonstrated optimal performance in the four models across various indicators. In terms of image quality under global condition, the average MAE has been reduced to 16.39HU, SSIM has increased to 95.24%, and PSNR has increased to 28.98. Regarding dosimetric accuracy, the gamma passing rate (2%/2 mm) has reached 99.02%, and the WET difference is only 1.28 mm. The D95 value of CTVs coverage and Dmax value of spinal cord, brainstem show no significant differences between dCT and sCT generated by cGAN model.

CONCLUSIONS

The cGAN model has been shown to be a more suitable approach for generating sCT using CBCT, considering its characteristics and concepts. The resulting sCT has the potential for application in adaptive proton therapy.

Patient-specific quality assurance for deformable IMRT/IMPT dose accumulation: Proposition and validation of energy conservation based validation criterion

BACKGROUND

Deformable image registration (DIR)-based dose accumulation (DDA) is regularly used in adaptive radiotherapy research. However, the applicability and reliability of DDA for direct clinical usage are still being debated. One primary concern is the validity of DDA, particularly for scenarios with substantial anatomical changes, for which energy-conservation problems were observed in conceptual studies.

PURPOSE

We present and validate an energy-conservation (EC)-based DDA validation workflow and further investigate its usefulness for actual patient data, specifically for lung cancer cases.

METHODS

For five non-small cell lung cancer (NSCLC) patients, DDA based on five selective DIR methods were calculated for five different treatment plans, which include one intensity-modulated photon therapy (IMRT), two intensity-modulated proton therapy (IMPT), and two combined proton-photon therapy (CPPT) plans. All plans were optimized on the planning CT (planCT) acquired in deep inspiration breath-hold (DIBH) and were re-optimized on the repeated DIBH CTs of three later fractions. The resulting fractional doses were warped back to the planCT using each DIR. An EC-based validation of the accumulation process was implemented and applied to all DDA results. Correlations between relative organ mass/volume variations and the extent of EC violation were then studied using Bayesian linear regression (BLR).

RESULTS

For most OARs, EC violation within 10% is observed. However, for the PTVs and GTVs with substantial regression, severe overestimation of the fractional energy was found regardless of treatment type and applied DIR method. BLR results show that EC violation is linearly correlated to the relative mass variation (R^2 > 0.95) and volume variation (R^2 > 0.60).

CONCLUSION

DDA results should be used with caution in regions with high mass/volume variation for intensity-based DIRs. EC-based validation is a useful approach to provide patient-specific quality assurance of the validity of DDA in radiotherapy.

Advancing knowledge-based intensity modulated proton planning for adaptive treatment of high-risk prostate cancer

To assess the performance of a knowledge-based planning (KBP) model for generating intensity-modulated proton therapy (IMPT) treatment plans as part of an adaptive radiotherapy (ART) strategy for patients with high-risk prostate cancer. A knowledge-based planning (KBP) model for proton adaptive treatment plan generation was developed based on thirty patient treatment plans utilizing RapidPlanTM PT (Varian Medical Systems, Palo Alto, CA). The model was subsequently validated using an additional eleven patient cases. All patients in the study were administered a prescribed dose of 70.2 Gy to the prostate and seminal vesicle (CTV70.2), along with 46.8 Gy to the pelvic lymph nodes (CTV46.8) through simultaneous integrated boost (SIB) technique. To assess the quality of the validation knowledge-based proton plans (KBPPs), target coverage and organ-at-risk (OAR) dose-volume constraints were compared against those of clinically used expert plans using paired t-tests. The KBP model training statistics (R2) (mean ± SD, 0.763 ± 0.167, range, 0.406 to 0.907) and χ² values (1.162 ± 0.0867, 1.039-1.253) indicate acceptable model training quality. Moreover, the average total treatment planning optimization and calculation time for adaptive plan generation is approximately 10 minutes. The CTV70.2 D98% for the KBPPs (mean ± SD, 69.1 ± 0.08 Gy) and expert plans (69.9 ± 0.04 Gy) shows a significant difference (p < 0.05) but are both within 1.1 Gy of the prescribed dose which is clinically acceptable. While the maximum dose for some organs-at-risk (OARs) such as the bladder and rectum is generally higher in the KBPPs, the doses still fall within clinical constraints. Among all the OARs, most of them received comparable results to the expert plan, except the cauda equina Dmax, which shows statistical significance and was lower in the KBPPs than in expert plans (48.5 ± 0.06 Gy vs 49.3 ± 0.05 Gy). The generated KBPPs were clinically comparable to manually crafted plans by expert treatment planners. The adaptive plan generation process was completed within an acceptable timeframe, offering a quick same-day adaptive treatment option. Our study supports the integration of KBP as a crucial component of an ART strategy, including maintaining plan consistency, improving quality, and enhancing efficiency. This advancement in speed and adaptability promises more precise treatment in proton ART.

Predictive digital twin for optimizing patient-specific radiotherapy regimens under uncertainty in high-grade gliomas

We develop a methodology to create data-driven predictive digital twins for optimal risk-aware clinical decision-making. We illustrate the methodology as an enabler for an anticipatory personalized treatment that accounts for uncertainties in the underlying tumor biology in high-grade gliomas, where heterogeneity in the response to standard-of-care (SOC) radiotherapy contributes to sub-optimal patient outcomes. The digital twin is initialized through prior distributions derived from population-level clinical data in the literature for a mechanistic model's parameters. Then the digital twin is personalized using Bayesian model calibration for assimilating patient-specific magnetic resonance imaging data. The calibrated digital twin is used to propose optimal radiotherapy treatment regimens by solving a multi-objective risk-based optimization under uncertainty problem. The solution leads to a suite of patient-specific optimal radiotherapy treatment regimens exhibiting varying levels of trade-off between the two competing clinical objectives: (i) maximizing tumor control (characterized by minimizing the risk of tumor volume growth) and (ii) minimizing the toxicity from radiotherapy. The proposed digital twin framework is illustrated by generating an in silico cohort of 100 patients with high-grade glioma growth and response properties typically observed in the literature. For the same total radiation dose as the SOC, the personalized treatment regimens lead to median increase in tumor time to progression of around six days. Alternatively, for the same level of tumor control as the SOC, the digital twin provides optimal treatment options that lead to a median reduction in radiation dose by 16.7% (10 Gy) compared to SOC total dose of 60 Gy. The range of optimal solutions also provide options with increased doses for patients with aggressive cancer, where SOC does not lead to sufficient tumor control.

Patient-Specific Auto-segmentation on Daily kVCT Images for Adaptive Radiation Therapy

PURPOSE

This study explored deep-learning-based patient-specific auto-segmentation using transfer learning on daily RefleXion kilovoltage computed tomography (kVCT) images to facilitate adaptive radiation therapy, based on data from the first group of patients treated with the innovative RefleXion system.

METHODS AND MATERIALS

For head and neck (HaN) and pelvic cancers, a deep convolutional segmentation network was initially trained on a population data set that contained 67 and 56 patient cases, respectively. Then the pretrained population network was adapted to the specific RefleXion patient by fine-tuning the network weights with a transfer learning method. For each of the 6 collected RefleXion HaN cases and 4 pelvic cases, initial planning computed tomography (CT) scans and 5 to 26 sets of daily kVCT images were used for the patient-specific learning and evaluation separately. The performance of the patient-specific network was compared with the population network and the clinical rigid registration method and evaluated by the Dice similarity coefficient (DSC) with manual contours being the reference. The corresponding dosimetric effects resulting from different auto-segmentation and registration methods were also investigated.

RESULTS

The proposed patient-specific network achieved mean DSC results of 0.88 for 3 HaN organs at risk (OARs) of interest and 0.90 for 8 pelvic target and OARs, outperforming the population network (0.70 and 0.63) and the registration method (0.72 and 0.72). The DSC of the patient-specific network gradually increased with the increment of longitudinal training cases and approached saturation with more than 6 training cases. Compared with using the registration contour, the target and OAR mean doses and dose-volume histograms obtained using the patient-specific auto-segmentation were closer to the results using the manual contour.

CONCLUSIONS

Auto-segmentation of RefleXion kVCT images based on the patient-specific transfer learning could achieve higher accuracy, outperforming a common population network and clinical registration-based method. This approach shows promise in improving dose evaluation accuracy in RefleXion adaptive radiation therapy.

Clinical experiences with online adaptive radiotherapy of vulvar carcinoma

BACKGROUND AND PURPOSE

Radiotherapy for vulvar carcinoma is challenging due to relatively high risk of locoregional disease recurrence, a technically challenging target, and postoperative lymphocele, and a high risk radiation sequelae. We aim to explore, if it is possible to reduce dose to normal tissue, while maintaining CTV coverage for this patient group with online adaptive radiotherapy.

MATERIALS AND METHODS

20 patients with vulvar carcinoma (527 fractions) were treated with online adaptation on a Varian Ethos accelerator. Setup CBCTs were acquired daily for adaptive planning. Verification CBCTs were acquired immediately prior to dose delivery. CTV dose coverage and dose to bladder and rectum were extracted from the scheduled and adapted plans as well as from adapted plans recalculated based on verification CBCTs. In addition, analysis of the decision of the adaptive procedure was performed for 17 patients (465 fractions).

RESULTS

Mean CTV D95% and standard deviation was 98% ± 5% for the scheduled plan compared to 100.0 ± 0.3% and 100.0 ± 0.8% for the adapted plan on the setup and verification CBCT respectively. Dose to OARs varied substantially and did not show any benefit from adaption itself, however a margin reduction was implemented after the first patients treated. The adapted plan was chosen for 63.5% of the fractions and dominant reasons for not adapting were 'no significant dosimetric gain' (75 fractions, 14%) and 'Medical doctor (MD) not available for treatment' (50 fractions, 9.5%). The median adaption time was 15 min and the 25th and 75th percentile was 12 and 17 min, respectively.

CONCLUSION

CTVs and PTVs dose coverage were significantly improved with adaptation compared to image-guided RT. This gain was robust during the treatment time.

Generating synthetic images from cone beam computed tomography using self-attention residual UNet for head and neck radiotherapy

Background and purpose

Accurate CT numbers in Cone Beam CT (CBCT) are crucial for precise dose calculations in adaptive radiotherapy (ART). This study aimed to generate synthetic CT (sCT) from CBCT using deep learning (DL) models in head and neck (HN) radiotherapy.

Materials and methods

A novel DL model, the 'self-attention-residual-UNet' (ResUNet), was developed for accurate sCT generation. ResUNet incorporates a self-attention mechanism in its long skip connections to enhance information transfer between the encoder and decoder. Data from 93 HN patients, each with planning CT (pCT) and first-day CBCT images were used. Model performance was evaluated using two DL approaches (non-adversarial and adversarial training) and two model types (2D axial only vs. 2.5D axial, sagittal, and coronal). ResUNet was compared with the traditional UNet through image quality assessment (Mean Absolute Error (MAE), Peak-Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM)) and dose calculation accuracy evaluation (DVH deviation and gamma evaluation (1 %/1mm)).

Results

Image similarity evaluation results for the 2.5D-ResUNet and 2.5D-UNet models were: MAE: 46±7 HU vs. 51±9 HU, PSNR: 66.6±2.0 dB vs. 65.8±1.8 dB, and SSIM: 0.81±0.04 vs. 0.79±0.05. There were no significant differences in dose calculation accuracy between DL models. Both models demonstrated DVH deviation below 0.5 % and a gamma-pass-rate (1 %/1mm) exceeding 97 %.

Conclusions

ResUNet enhanced CT number accuracy and image quality of sCT and outperformed UNet in sCT generation from CBCT. This method holds promise for generating precise sCT for HN ART.

Triggering daily online adaptive radiotherapy in the pelvis: Dosimetric effects and procedural implications of trigger parameter-value selection

BACKGROUND

Online adaptive radiotherapy (ART) can address dosimetric consequences of variations in anatomy by creating a new plan during treatment. However, ART is time- and labor-intensive and should be implemented in a resource-conscious way. Adaptive triggers composed of parameter-value pairs may direct the judicious use of online ART.

PURPOSE

This work analyzed our clinical experience using CBCT-based daily online ART to demonstrate how a conceptual framework based on adaptive triggers affects the dosimetric and procedural impact of ART.

METHODS

Sixteen patients across several pelvic sites were treated with CBCT-based daily online ART. Differences in standardized dose metrics were compared between the original plan, the original plan recalculated on the daily anatomy, and an adaptive plan. For each metric, trigger values were analyzed in terms of the proportion of treatments adapted and the distribution of metric values.

RESULTS

Target coverage metrics were compromised due to anatomic variation with the average change per treatment ranging from -0.90 to -0.05 Gy, -0.47 to -0.02 Gy, -0.31 to -0.01 Gy, and -12.45% to -2.65% for PTV D99%, PTV D95%, CTV D99%, and CTV V100%, respectively. These were improved using the adaptive plan (-0.03 to 0.01 Gy, -0.02 to 0.00 Gy, -0.03 to 0.00 Gy, and -4.70% to 0.00%, respectively). Increasingly strict triggers resulted in a non-linear increase in the proportion of treatments adapted and improved the distribution of metric values with diminishing returns. Some organ-at-risk (OAR) metrics were compromised by anatomic variation and improved using the adaptive plan, but changes in most OAR metrics were randomly distributed.

CONCLUSIONS

Daily online ART improved target coverage across multiple pelvic treatment sites and techniques. These effects were larger than those for OAR metrics, suggesting that maintaining target coverage was our primary benefit of CBCT-based daily online ART. Analyses like these can determine online ART triggers from a cost-benefit perspective.

Using RegGAN to generate synthetic CT images from CBCT images acquired with different linear accelerators

BACKGROUND

The goal was to investigate the feasibility of the registration generative adversarial network (RegGAN) model in image conversion for performing adaptive radiation therapy on the head and neck and its stability under different cone beam computed tomography (CBCT) models.

METHODS

A total of 100 CBCT and CT images of patients diagnosed with head and neck tumors were utilized for the training phase, whereas the testing phase involved 40 distinct patients obtained from four different linear accelerators. The RegGAN model was trained and tested to evaluate its performance. The generated synthetic CT (sCT) image quality was compared to that of planning CT (pCT) images by employing metrics such as the mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). Moreover, the radiation therapy plan was uniformly applied to both the sCT and pCT images to analyze the planning target volume (PTV) dose statistics and calculate the dose difference rate, reinforcing the model's accuracy.

RESULTS

The generated sCT images had good image quality, and no significant differences were observed among the different CBCT modes. The conversion effect achieved for Synergy was the best, and the MAE decreased from 231.3 ± 55.48 to 45.63 ± 10.78; the PSNR increased from 19.40 ± 1.46 to 26.75 ± 1.32; the SSIM increased from 0.82 ± 0.02 to 0.85 ± 0.04. The quality improvement effect achieved for sCT image synthesis based on RegGAN was obvious, and no significant sCT synthesis differences were observed among different accelerators.

CONCLUSION

The sCT images generated by the RegGAN model had high image quality, and the RegGAN model exhibited a strong generalization ability across different accelerators, enabling its outputs to be used as reference images for performing adaptive radiation therapy on the head and neck.

A multi-center survey on adaptive radiation therapy for head and neck cancer in Malaysia

The survey is to assess the current state of adaptive radiation therapy (ART) for head and neck (H&N) cases among radiotherapy centers in Malaysia and to identify any implementation limitations. An online questionnaire was sent to all radiotherapy centers in Malaysia. The 24-question questionnaire consists of general information about the center, ART practices, and limitations faced in implementing ART. 28 out of 36 radiotherapy centers responded, resulting in an overall response rate of 78%. About 52% of the responding centers rescanned and replanned less than 5% of their H&N patients. The majority (88.9%) of the respondents reported the use Cone Beam Computed Tomography alone or in combination with other modalities to trigger the ART process. The main reasons cited for adopting ART were weight loss, changes in the immobilization fitting, and anatomical variation. The adaptation process typically occurred during week 3 or week 4 of treatment. More than half of the respondents require three days or more from re-simulation to starting a new treatment plan. Both target and organ at risk delineation on new planning CT relied heavily on manual delineation by physicians and physicists, respectively. All centers perform patient-specific quality assurance for their new adaptive plans. Two main limitations in implementing ART are "limited financial resources or equipment" and "limitation on technical knowledge". There is a need for a common consensus to standardize the practice of ART and address these limitations to improve the implementation of ART in Malaysia.

An efficient strategy to select head and neck cancer patients for adaptive radiotherapy

BACKGROUND AND PURPOSE

Adaptive radiotherapy (ART) is workload intensive but only benefits a subgroup of patients. We aimed to develop an efficient strategy to select candidates for ART in the first two weeks of head and neck cancer (HNC) radiotherapy.

MATERIALS AND METHODS

This study retrospectively enrolled 110 HNC patients who underwent modern photon radiotherapy with at least 5 weekly in-treatment re-scan CTs. A semi auto-segmentation method was applied to obtain the weekly mean dose (Dmean) to OARs. A comprehensive NTCP-profile was applied to obtain NTCP's. The difference between planning and actual values of Dmean (ΔDmean) and dichotomized difference of clinical relevance (BIOΔNTCP) were used for modelling to determine the cut-off maximum ΔDmean of OARs in week 1 and 2 (maxΔDmean_1 and maxΔDmean_2). Four strategies to select candidates for ART, using cut-off maxΔDmean were compared.

RESULTS

The Spearman's rank correlation test showed significant positive correlation between maxΔDmean and BIOΔNTCP (p-value <0.001). For major BIOΔNTCP (>5%) of acute and late toxicity, 10.9% and 4.5% of the patients were true candidates for ART. Strategy C using both cut-off maxΔDmean_1 (3.01 and 5.14 Gy) and cut-off maxΔDmean_2 (3.41 and 5.30 Gy) showed the best sensitivity, specificity, positive and negative predictive values (0.92, 0.82, 0.38, 0.99 for acute toxicity and 1.00, 0.92, 0.38, 1.00 for late toxicity, respectively).

CONCLUSIONS

We propose an efficient selection strategy for ART that is able to classify the subgroup of patients with >5% BIOΔNTCP for late toxicity using imaging in the first two treatment weeks.

Evaluation of morphological changes based on cone beam CT for adaptive radiotherapy

BACKGROUND

During radiotherapy treatment, morphological changes can occur in patients (as weight loss). This can lead to significant dosimetric consequences on target volumes and/or organs at risk. The process of adaptive radiotherapy can compensate for these variations. Its deployment in the clinic is slowed by the considerable additional workload for the medical teams. The need for a tool facilitating the detection of patients whose treatment plans need adaptation has been clearly expressed in clinical practice, hence the usefulness of studying the impact of these morphological changes before the decision of adaptive radiotherapy.

METHODS

We considered the cases of 26 patients treated for pelvic cancer where CBCT (Cone Beam Computed Tomography) repositioning images were used. These images have undergone pre-processing to improve their quality and obtain a more precise registration using seven algorithms. We compared the results obtained in order to choose the most adequate algorithm allowing the calculation of external morphological differences using similarity metrics, such as DSC, NCC, MI and TC.

RESULTS

In this study, we showed that the "rigid body" algorithm, based on the rigid registration, gives the best results. The conservation of external contours allowed quantification of the variation in the external volumes of the patients. The obtained variations were on average (6.12±1.69)% and (4.36±1.22)% for rectum and prostate cancers, respectively.

CONCLUSION

Morphological changes evaluated in this study may influence the quality of patient treatment; hence the need for adaptive radiotherapy to take these variations into consideration. However, a rigorous evaluation of the dosimetric impact of these morphological variations is necessary to determine decision criteria for treatment plan adaptation.

Intentional deep overfit learning for patient-specific dose predictions in adaptive radiotherapy

BACKGROUND

The framework of adaptive radiation therapy (ART) was crafted to address the underlying sources of intra-patient variation that were observed throughout numerous patients' radiation sessions. ART seeks to minimize the consequential dosimetric uncertainty resulting from this daily variation, commonly through treatment planning re-optimization. Re-optimization typically consists of manual evaluation and modification of previously utilized optimization criteria. Ideally, frequent treatment plan adaptation through re-optimization on each day's computed tomography (CT) scan may improve dosimetric accuracy and minimize dose delivered to organs at risk (OARs) as the planning target volume (PTV) changes throughout the course of treatment.

PURPOSE

Re-optimization in its current form is time-consuming and inefficient. In response to this ART bottleneck, we propose a deep learning based adaptive dose prediction model that utilizes a head and neck (H&N) patient's initial planning data to fine-tune a previously trained population model towards a patient-specific model. Our fine-tuned, patient-specific (FT-PS) model, which is trained using the intentional deep overfit learning (IDOL) method, may enable clinicians and treatment planners to rapidly evaluate relevant dosimetric changes daily and re-optimize accordingly.

METHODS

An adaptive population (AP) model was trained using adaptive data from 33 patients. Separately, 10 patients were selected for training FT-PS models. The previously trained AP model was utilized as the base model weights prior to re-initializing model training for each FT-PS model. Ten FT-PS models were separately trained by fine-tuning the previous model weights based on each respective patient's initial treatment plan. From these 10 patients, 26 ART treatment plans were withheld from training as the test dataset for retrospective evaluation of dose prediction performance between the AP and FT-PS models. Each AP and FT-PS dose prediction was compared against the ground truth dose distribution as originally generated during the patient's course of treatment. Mean absolute percent error (MAPE) evaluated the dose differences between a model's prediction and the ground truth.

RESULTS

MAPE was calculated within the 10% isodose volume region of interest for each of the AP and FT-PS models dose predictions and averaged across all test adaptive sessions, yielding 5.759% and 3.747% respectively. MAPE differences were compared between AP and FT-PS models across each test session in a test of statistical significance. The differences were statistically significant in a paired t-test with two-tailed p-value equal to3.851 × 10 - 9 $3.851 \times {10}^{ - 9}$ and 95% confidence interval (CI) equal to [-2.483, -1.542]. Furthermore, MAPE was calculated using each individually segmented structure as an ROI. Nineteen of 24 structures demonstrated statistically significant differences between the AP and FT-PS models.

CONCLUSION

We utilized the IDOL method to fine-tune a population-based dose prediction model into an adaptive, patient-specific model. The averaged MAPE across the test dataset was 5.759% for the population-based model versus 3.747% for the fine-tuned, patient-specific model, and the difference in MAPE between models was found to be statistically significant. Our work demonstrates the feasibility of patient-specific models in adaptive radiotherapy, and offers unique clinical benefit by utilizing initial planning data that contains the physician's treatment intent.

Dosimetric comparison of autocontouring techniques for online adaptive proton therapy

Objective.Anatomical and daily set-up uncertainties impede high precision delivery of proton therapy. With online adaptation, the daily plan is reoptimized on an image taken shortly before the treatment, reducing these uncertainties and, hence, allowing a more accurate delivery. This reoptimization requires target and organs-at-risk (OAR) contours on the daily image, which need to be delineated automatically since manual contouring is too slow. Whereas multiple methods for autocontouring exist, none of them are fully accurate, which affects the daily dose. This work aims to quantify the magnitude of this dosimetric effect for four contouring techniques.Approach.Plans reoptimized on automatic contours are compared with plans reoptimized on manual contours. The methods include rigid and deformable registration (DIR), deep-learning based segmentation and patient-specific segmentation.Main results.It was found that independently of the contouring method, the dosimetric influence of usingautomaticOARcontoursis small (<5% prescribed dose in most cases), with DIR yielding the best results. Contrarily, the dosimetric effect of using theautomatic target contourwas larger (>5% prescribed dose in most cases), indicating that manual verification of that contour remains necessary. However, when compared to non-adaptive therapy, the dose differences caused by automatically contouring the target were small and target coverage was improved, especially for DIR.Significance.The results show that manual adjustment of OARs is rarely necessary and that several autocontouring techniques are directly usable. Contrarily, manual adjustment of the target is important. This allows prioritizing tasks during time-critical online adaptive proton therapy and therefore supports its further clinical implementation.

Adaptive Radiation Therapy: A Review of CT-based Techniques

Adaptive radiation therapy is a feedback process by which imaging information acquired over the course of treatment, such as changes in patient anatomy, can be used to reoptimize the treatment plan, with the end goal of improving target coverage and reducing treatment toxicity. This review describes different types of adaptive radiation therapy and their clinical implementation with a focus on CT-guided online adaptive radiation therapy. Depending on local anatomic changes and clinical context, different anatomic sites and/or disease stages and presentations benefit from different adaptation strategies. Online adaptive radiation therapy, where images acquired in-room before each fraction are used to adjust the treatment plan while the patient remains on the treatment table, has emerged to address unpredictable anatomic changes between treatment fractions. Online treatment adaptation places unique pressures on the radiation therapy workflow, requiring high-quality daily imaging and rapid recontouring, replanning, plan review, and quality assurance. Generating a new plan with every fraction is resource intensive and time sensitive, emphasizing the need for workflow efficiency and clinical resource allocation. Cone-beam CT is widely used for image-guided radiation therapy, so implementing cone-beam CT-guided online adaptive radiation therapy can be easily integrated into the radiation therapy workflow and potentially allow for rapid imaging and replanning. The major challenge of this approach is the reduced image quality due to poor resolution, scatter, and artifacts. Keywords: Adaptive Radiation Therapy, Cone-Beam CT, Organs at Risk, Oncology © RSNA, 2023.

Forecasting patient-specific dosimetric benefit from daily online adaptive radiotherapy for cervical cancer

Objective. Adaptive Radiotherapy (ART) is an emerging technique for treating cancer patients which facilitates higher delivery accuracy and has the potential to reduce toxicity. However, ART is also resource-intensive, Requiring extra human and machine time compared to standard treatment methods. In this analysis, we sought to predict the subset of node-negative cervical cancer patients with the greatest benefit from ART, so resources might be properly allocated to the highest-yield patients.Approach. CT images, initial plan data, and on-treatment Cone-Beam CT (CBCT) images for 20 retrospective cervical cancer patients were used to simulate doses from daily non-adaptive and adaptive techniques. We evaluated the coefficient of determination (R2) between dose and volume metrics from initial treatment plans and the dosimetric benefits to theBowelV40Gy,BowelV45Gy,BladderDmean,andRectumDmeanfrom adaptive radiotherapy using reduced 3 mm or 5 mm CTV-to-PTV margins. The LASSO technique was used to identify the most predictive metrics forBowelV40Gy.The three highest performing metrics were used to build multivariate models with leave-one-out validation forBowelV40Gy.Main results. Patients with higher initial bowel doses were correlated with the largest decreases in BowelV40Gyfrom daily adaptation (linear best fit R2= 0.77 for a 3 mm PTV margin and R2= 0.8 for a 5 mm PTV margin). Other metrics had intermediate or no correlation. Selected covariates for the multivariate model were differences in the initialBowelV40GyandBladderDmeanusing standard versus reduced margins and the initial bladder volume. Leave-one-out validation had an R2of 0.66 between predicted and true adaptiveBowelV40Gybenefits for both margins.Significance. The resulting models could be used to prospectively triage cervical cancer patients on or off daily adaptation to optimally manage clinical resources. Additionally, this work presents a critical foundation for predicting benefits from daily adaptation that can be extended to other patient cohorts.

Research progress on deep learning in magnetic resonance imaging-based diagnosis and treatment of prostate cancer: a review on the current status and perspectives

Multiparametric magnetic resonance imaging (mpMRI) has emerged as a first-line screening and diagnostic tool for prostate cancer, aiding in treatment selection and noninvasive radiotherapy guidance. However, the manual interpretation of MRI data is challenging and time-consuming, which may impact sensitivity and specificity. With recent technological advances, artificial intelligence (AI) in the form of computer-aided diagnosis (CAD) based on MRI data has been applied to prostate cancer diagnosis and treatment. Among AI techniques, deep learning involving convolutional neural networks contributes to detection, segmentation, scoring, grading, and prognostic evaluation of prostate cancer. CAD systems have automatic operation, rapid processing, and accuracy, incorporating multiple sequences of multiparametric MRI data of the prostate gland into the deep learning model. Thus, they have become a research direction of great interest, especially in smart healthcare. This review highlights the current progress of deep learning technology in MRI-based diagnosis and treatment of prostate cancer. The key elements of deep learning-based MRI image processing in CAD systems and radiotherapy of prostate cancer are briefly described, making it understandable not only for radiologists but also for general physicians without specialized imaging interpretation training. Deep learning technology enables lesion identification, detection, and segmentation, grading and scoring of prostate cancer, and prediction of postoperative recurrence and prognostic outcomes. The diagnostic accuracy of deep learning can be improved by optimizing models and algorithms, expanding medical database resources, and combining multi-omics data and comprehensive analysis of various morphological data. Deep learning has the potential to become the key diagnostic method in prostate cancer diagnosis and treatment in the future.

Image guidance and interfractional anatomical variation in paediatric abdominal radiotherapy

OBJECTIVES

To identify variables predicting interfractional anatomical variations measured with cone-beam CT (CBCT) throughout abdominal paediatric radiotherapy, and to assess the potential of surface-guided radiotherapy (SGRT) to monitor these changes.

METHODS

Metrics of variation in gastrointestinal (GI) gas volume and separation of the body contour and abdominal wall were calculated from 21 planning CTs and 77 weekly CBCTs for 21 abdominal neuroblastoma patients (median 4 years, range: 2 - 19 years). Age, sex, feeding tubes, and general anaesthesia (GA) were explored as predictive variables for anatomical variation. Furthermore, GI gas variation was correlated with changes in body and abdominal wall separation, as well as simulated SGRT metrics of translational and rotational corrections between CT/CBCT.

RESULTS

GI gas volumes varied 74 ± 54 ml across all scans, while body and abdominal wall separation varied 2.0 ± 0.7 mm and 4.1 ± 1.5 mm from planning, respectively. Patients < 3.5 years (p = 0.04) and treated under GA (p < 0.01) experienced greater GI gas variation; GA was the strongest predictor in multivariate analysis (p < 0.01). Absence of feeding tubes was linked to greater body contour variation (p = 0.03). GI gas variation correlated with body (R = 0.53) and abdominal wall (R = 0.63) changes. The strongest correlations with SGRT metrics were found for anterior-posterior translation (R = 0.65) and rotation of the left-right axis (R = -0.36).

CONCLUSIONS

Young age, GA, and absence of feeding tubes were linked to stronger interfractional anatomical variation and are likely indicative of patients benefiting from adaptive/robust planning pathways. Our data suggest a role for SGRT to inform the need for CBCT at each treatment fraction in this patient group.

ADVANCES IN KNOWLEDGE

This is the first study to suggest the potential role of SGRT for the management of internal interfractional anatomical variation in paediatric abdominal radiotherapy.

Online adaptive planning methods for intensity-modulated radiotherapy

Online adaptive radiation therapy aims at adapting a patient's treatment plan to their current anatomy to account for inter-fraction variations before daily treatment delivery. As this process needs to be accomplished while the patient is immobilized on the treatment couch, it requires time-efficient adaptive planning methods to generate a quality daily treatment plan rapidly. The conventional planning methods do not meet the time requirement of online adaptive radiation therapy because they often involve excessive human intervention, significantly prolonging the planning phase. This article reviews the planning strategies employed by current commercial online adaptive radiation therapy systems, research on online adaptive planning, and artificial intelligence's potential application to online adaptive planning.

Artificial intelligence-assisted selection and efficacy prediction of antineoplastic strategies for precision cancer therapy

The rapid development of artificial intelligence (AI) technologies in the context of the vast amount of collectable data obtained from high-throughput sequencing has led to an unprecedented understanding of cancer and accelerated the advent of a new era of clinical oncology with a tone of precision treatment and personalized medicine. However, the gains achieved by a variety of AI models in clinical oncology practice are far from what one would expect, and in particular, there are still many uncertainties in the selection of clinical treatment options that pose significant challenges to the application of AI in clinical oncology. In this review, we summarize emerging approaches, relevant datasets and open-source software of AI and show how to integrate them to address problems from clinical oncology and cancer research. We focus on the principles and procedures for identifying different antitumor strategies with the assistance of AI, including targeted cancer therapy, conventional cancer therapy, and cancer immunotherapy. In addition, we also highlight the current challenges and directions of AI in clinical oncology translation. Overall, we hope this article will provide researchers and clinicians with a deeper understanding of the role and implications of AI in precision cancer therapy, and help AI move more quickly into accepted cancer guidelines.

Applicability and usage of dose mapping/accumulation in radiotherapy

Dose mapping/accumulation (DMA) is a topic in radiotherapy (RT) for years, but has not yet found its widespread way into clinical RT routine. During the ESTRO Physics workshop 2021 on "commissioning and quality assurance of deformable image registration (DIR) for current and future RT applications", we built a working group on DMA from which we present the results of our discussions in this article. Our aim in this manuscript is to shed light on the current situation of DMA in RT and to highlight the issues that hinder consciously integrating it into clinical RT routine. As a first outcome of our discussions, we present a scheme where representative RT use cases are positioned, considering expected anatomical variations and the impact of dose mapping uncertainties on patient safety, which we have named the DMA landscape (DMAL). This tool is useful for future reference when DMA applications get closer to clinical day-to-day use. Secondly, we discussed current challenges, lightly touching on first-order effects (related to the impact of DIR uncertainties in dose mapping), and focusing in detail on second-order effects often dismissed in the current literature (as resampling and interpolation, quality assurance considerations, and radiobiological issues). Finally, we developed recommendations, and guidelines for vendors and users. Our main point include: Strive for context-driven DIR (by considering their impact on clinical decisions/judgements) rather than perfect DIR; be conscious of the limitations of the implemented DIR algorithm; and consider when dose mapping (with properly quantified uncertainties) is a better alternative than no mapping.

Improving synthetic CT accuracy by combining the benefits of multiple normalized preprocesses

PURPOSE

To investigate the effect of different normalization preprocesses in deep learning on the accuracy of different tissues in synthetic computed tomography (sCT) and to combine their advantages to improve the accuracy of all tissues.

METHODS

The cycle-consistent adversarial network (CycleGAN) model was used to generate sCT images from megavolt cone-beam CT (MVCBCT) images. In this study, 2639 head MVCBCT and CT image pairs from 203 patients were collected as a training set, and 249 image pairs from 29 patients were collected as a test set. We normalized the voxel values in images to 0 to 1 or -1 to 1, using two linear and five nonlinear normalization preprocessing methods to obtain seven data sets and compared the accuracy of different tissues in different sCT obtained from training these data. Finally, to combine the advantages of different normalization preprocessing methods, we obtained sCT_Blur by cropping, stitching, and smoothing (OpenCV's cv2.medianBlur, kernel size 5) each group of sCTs and evaluated its image quality and accuracy of OARs.

RESULTS

Different normalization preprocesses made sCT more accurate in different tissues. The proposed sCT_Blur took advantage of multiple normalization preprocessing methods, and all tissues are more accurate than the sCT obtained using a single conventional normalization method. Compared with other sCT images, the structural similarity of sCT_Blur versus CT was improved to 0.906 ± 0.019. The mean absolute errors of the CT numbers were reduced to 15.7 ± 4.1 HU, 23.2 ± 7.1 HU, 11.5 ± 4.1 HU, 212.8 ± 104.6 HU, 219.4 ± 35.1 HU, and 268.8 ± 88.8 HU for the oral cavity, parotid, spinal cord, cavity, mandible, and teeth, respectively.

CONCLUSION

The proposed approach combined the advantages of several normalization preprocessing methods to improve the accuracy of all tissues in sCT images, which is promising for improving the accuracy of dose calculations based on CBCT images in adaptive radiotherapy.

A survey of practice patterns for adaptive particle therapy for interfractional changes

Background and purpose

Anatomical changes may compromise the planned target coverage and organs-at-risk dose in particle therapy. This study reports on the practice patterns for adaptive particle therapy (APT) to evaluate current clinical practice and wishes and barriers to further implementation.

Materials and methods

An institutional questionnaire was distributed to PT centres worldwide (7/2020-6/2021) asking which type of APT was used, details of the workflow, and what the wishes and barriers to implementation were. Seventy centres from 17 countries participated. A three-round Delphi consensus analysis (10/2022) among the authors followed to define recommendations on required actions and future vision.

Results

Out of the 68 clinically operational centres, 84% were users of APT for at least one treatment site with head and neck being most common. APT was mostly performed offline with only two online APT users (plan-library). No centre used online daily re-planning. Daily 3D imaging was used for APT by 19% of users. Sixty-eight percent of users had plans to increase their use or change their technique for APT. The main barrier was "lack of integrated and efficient workflows". Automation and speed, reliable dose deformation for dose accumulation and higher quality of in-room volumetric imaging were identified as the most urgent task for clinical implementation of online daily APT.

Conclusion

Offline APT was implemented by the majority of PT centres. Joint efforts between industry research and clinics are needed to translate innovations into efficient and clinically feasible workflows for broad-scale implementation of online APT.

CBCT-to-CT Translation Using Registration-Based Generative Adversarial Networks in Patients with Head and Neck Cancer

Recently, deep learning with generative adversarial networks (GANs) has been applied in multi-domain image-to-image translation. This study aims to improve the image quality of cone-beam computed tomography (CBCT) by generating synthetic CT (sCT) that maintains the patient’s anatomy as in CBCT, while having the image quality of CT. As CBCT and CT are acquired at different time points, it is challenging to obtain paired images with aligned anatomy for supervised training. To address this limitation, the study incorporated a registration network (RegNet) into GAN during training. RegNet can dynamically estimate the correct labels, allowing supervised learning with noisy labels. The study developed and evaluated the approach using imaging data from 146 patients with head and neck cancer. The results showed that GAN trained with RegNet performed better than those trained without RegNet. Specifically, in the UNIT model trained with RegNet, the mean absolute error (MAE) was reduced from 40.46 to 37.21, the root mean-square error (RMSE) was reduced from 119.45 to 108.86, the peak signal-to-noise ratio (PSNR) was increased from 28.67 to 29.55, and the structural similarity index (SSIM) was increased from 0.8630 to 0.8791. The sCT generated from the model had fewer artifacts and retained the anatomical information as in CBCT.

One Stone, Two Birds: A Peptide-Au(I) Infinite Coordination Supermolecule for the Confederate Physical and Biological Radiosensitization in Cancer Radiation Therapy

Over half of cancer patients are subjected to radiotherapy, but owing to the deficient amount of reactive oxygen radicals (ROS) and DNA double-strand breaks (DSBs), a fair number of them suffer from radiotherapy resistance and the subsequent short-term survival opportunity. To overcome it, many successes have been achieved in radiosensitizer discovery using physical strategy and/or biological strategy, but significant challenges remain regarding developing clinically translational radiosensitizers. Herein, a peptide-Au(I) infinite coordination supermolecule termed PAICS is developed that combined both physical and biological radiosensitization and possessed pharmaceutical characteristics including adequate circulatory stability, controllable drug release, tumor-prioritized accumulation, and the favorable body eliminability. As expected, monovalent gold ion endowed this supermolecule with high X-ray absorption and the subsequent radiosensitization. Furthermore, a peptide targeting CRM1, is assembled into the supermolecule, which successfully activates p53 and apoptosis pathway, thereby further sensitizing radiotherapy. As a result, PAICS showed superior ability for radiotherapy sensitization in vivo and maintained a favorable safety profile. Thus, the PAICS reported here will offer a feasible solution to simultaneously overcome both the pharmaceutical obstacles of physical and biological radiosensitizers and will enable the development of a class of nanomedicines for tumor radiotherapy sensitization.