MRI-guided Radiotherapy Research Articles

Prostate motion in magnetic resonance imaging-guided radiotherapy and its impact on margins.

This study focused on reducing the margin for prostate cancer treatment using magnetic resonance imaging-guided radiotherapy by investigating the intrafractional motion of the prostate and different motion-mitigation strategies. We retrospectively analyzed intrafractional prostate motion in 77patients with low- to intermediate-risk prostate cancer treated with five fractions of 7.25 Gy on a1.5 T magnetic resonance linear accelerator. Systematic drift motion was observed and described by an intrafractional motion model. The planning target volume (PTV) margin was calculated in acohort of 77patients and prospectively evaluated for geometric coverage in aseparate cohort of 24patients. The intrafractional model showed that the prostate position starts out of equilibrium for the anterior-posterior (-1.8 ± 3.1mm) and superior-inferior (1.7 ± 2.6mm) directions, with relaxation times of12 and 15min, respectively. Position verification scans are acquired at 30min on average. At that time, the transient drift motion becomes indistinguishable from the residual random intrafractional motion. PTV margins can be reduced to 1.8 mm (left-right), 3.2 mm (anterior-posterior), and 2.9 mm (superior-inferior). Evaluation of the overlap with the clinical target volume (CTV) was performed for atotal of 120 fractions of 24patients. The overlap range between the CTV and the PTV was 93-100% and the applied 3‑mm PTV margin for the CTV had a99.5% averaged geometric overlap for all patients. APTV margin reduction to 3 mm is feasible. Apatient-specific approach could reduce the margins further.

Joint k-b space diffusion-weighted image reconstruction and apparent diffusion coefficient fitting for diffusion-weighted turbo-spin-echo imaging.

Diffusion-weighted (DW) turbo-spin-echo (TSE) imaging offers improved geometric fidelity compared to single-shot echo-planar-imaging (EPI). However, it suffers from low signal-to-noise ratio (SNR) and prolonged acquisition times, thereby restricting its applications in diagnosis and MRI-guided radiotherapy (MRgRT). To develop a joint k-b space reconstruction algorithm for concurrent reconstruction of DW-TSE images and the apparent diffusion coefficient (ADC) map with enhanced image quality and more accurate quantitative measurements. The joint k-b reconstruction model was formulated as an optimization problem subject to a self-consistency condition comprising the exponential decay relationship between DW images and the ADC map. The objective function included a data fidelity term confirming an agreement between the reconstructed images and measured k-space data, incorporating the mono-exponential decay relationship between DW images and ADC map as a constraint, along with spatial regularization terms on both amplitude and phase images. The optimization problem was solved using the alternating-direction method of multipliers (ADMM). We evaluated the performance of the joint reconstruction (JR) algorithm for DW-TSE in a phantom study and patient studies on five brain and head/neck cancer patients. Image distortion, accuracy, and repeatability of ADC measurements were assessed and compared with those from conventional Fourier-transformed (FFT)-based reconstruction and magnitude-based ADC fitting methods, as well as with the clinically used DW-EPI technique. The proposed joint k-b reconstruction method demonstrated improved SNR and enhanced accuracy of ADC measurements in DW-TSE compared to the conventional method. Additionally, JR-DW-TSE with fewer averages at high b-values provided better image quality than the conventional FFT-reconstructed DW-TSE with full averages. The proposed joint k-b reconstruction method for DW-TSE has the potential to deliver distortion-robust diffusion-weighted MRI (DWI) for clinical applications, which is particularly crucial for MRgRT.

MRgRT real-time target localization using foundation models for contour point tracking and promptable mask refinement.

This study aimed to evaluate two real-time target tracking approaches for magnetic resonance imaging (MRI) guided radiotherapy (MRgRT) based on foundation artificial intelligence (AI) models.

Approach: The first approach used a point-tracking model that propagates points from a reference contour. The second approach used a video-object-segmentation model, based on Segment Anything Model 2 (SAM2). Both approaches were evaluated and compared against each other, inter-observer variability, and a transformer-based image registration model, TransMorph, with and without patient-specific (PS) fine-tuning. The evaluation was carried out on 2D cine MRI datasets from two institutions, containing scans from 33 patients with 8060 labeled frames, with annotations from 2 to 5 observers per frame, totaling 29179 ground truth segmentations. The segmentations produced were assessed using the Dice similarity coefficient (DSC), 50% and 95% Hausdorff distances (HD50 / HD95), and the Euclidean center distance (ECD).

Main results: The results showed that the contour tracking (median DSC 0.92 ± 0.04 and ECD 1.9 ± 1.0 mm) and SAM2-based (median DSC 0.93 ± 0.03 and ECD 1.6 ± 1.1 mm) approaches produced target segmentations comparable or superior to TransMorph without PS fine-tuning (median DSC 0.91 ± 0.07 and ECD 2.6 ± 1.4 mm) and slightly inferior to TransMorph with PS fine-tuning (median DSC 0.94 ± 0.03 and ECD 1.4 ± 0.8 mm). Between the two novel approaches, the one based on SAM2 performed marginally better at a higher computational cost (inference times 92 ms for contour tracking and 109 ms for SAM2). Both approaches and TransMorph with PS fine-tuning exceeded inter-observer variability (median DSC 0.90 ± 0.06 and ECD 1.7 ± 0.7 mm).

Significance: This study demonstrates the potential of foundation models to achieve high-quality real-time target tracking in MRgRT, offering performance that matches state-of-the-art methods without requiring PS fine-tuning.

Real-time 3D MR guided radiation therapy through orthogonal MR imaging and manifold learning.

In magnetic resonance image (MRI)-guided radiotherapy (MRgRT), 2D rapid imaging is commonly used to track moving targets with high temporal frequency to minimize gating latency. However, anatomical motion is not constrained to 2D, and a portion of the target may be missed during treatment if 3D motion is not evaluated. While some MRgRT systems attempt to capture 3D motion by sequentially tracking motion in 2D orthogonal imaging planes, this approach assesses 3D motion via independent 2D measurements at alternating instances, lacking a simultaneous 3D motion assessment in both imaging planes. We hypothesized that a motion model could be derived from prior 2D orthogonal imaging to estimate 3D motion in both planes simultaneously. We present a manifold learning technique to estimate 3D motion from 2D orthogonal imaging. Five healthy volunteers were scanned under an IRB-approved protocol using a 3.0 T Siemens Skyra simulator. Images of the liver dome were acquired during free breathing (FB) with a 2.6mm × 2.6mm in-plane resolution for approximately 10min in alternating sagittal and coronal planes at ∼5 frames per second. The motion model was derived using a combined manifold learning and alignment approach based on locally linear embedding (LLE). The model utilized the spatially overlapping MRI signal shared by both imaging planes to group together images that had similar signals, enabling motion estimation in both planes simultaneously. The model's motion estimates were compared to the ground truth motion derived in each newly acquired image using deformable registration. A simulated target was defined on the dome of the liver and used to evaluate model performance. The Dice similarity coefficient and distance between the model-tracked and image-tracked contour centroids were evaluated. Motion modeling error was estimated in the orthogonal plane by back-propagating the motion to the currently imaged plane and by interpolating the motion between image acquisitions where ground truth motion was available. The motion observed in the healthy volunteer studies ranged from 12.6 to 38.7mm. On average, the model demonstrated sub-millimeter precision and>0.95 Dice coefficient compared to the ground truth motion observed in the currently imaged plane. The average Dice coefficient and centroid distance between the model-tracked and ground truth target contours were 0.96±0.03 and 0.26mm±0.27mm respectively across all volunteer studies. The out-of-plane centroid motion error was estimated to be 0.85mm±1.07mm and 1.26mm±1.38mm using the back-propagation (BP) and interpolation error estimation methods. The healthy volunteer studies indicate promising results using the proposed motion modeling technique. Out-of-plane modeling error was estimated to be higher but still demonstrated sub-voxel motion accuracy.

Clinical validation of a prognostic preclinical magnetic resonance imaging biomarker for radiotherapy outcome in head-and-neck cancer.

To retrain a model based on a previously identified prognostic imaging biomarker using apparent diffusion coefficient (ADC) values from diffusion-weighted magnetic resonance imaging (DW-MRI) in a preclinical setting and validate the model using clinical DW-MRI data of patients with locally advanced head-and-neck cancer (HNC) acquired before radiochemotherapy. A total of 31 HNC patients underwent T2-weighted and DW-MRI using 3 T MRI before radiochemotherapy (35x2Gy). Gross tumor volumes (GTV) were delineated based on T2-weighted and b500 images. A preclinical model previously revealed that the size of high-risk subvolumes (HRS) defined by a band of ADC-values was correlated to radiation resistance. To validate this model, different bands of ADC-values were tested using two-sided thresholds on the low-ADC histogram flank to determine HRSs inside the GTV and correlated to treatment outcome after three years. The best model was used to fit a logistic regression model. Stratification potential regarding outcome was internally validated using bootstrap, receiver-operator-characteristic (ROC)-analysis, Kaplan-Meier- and Cox-method, and compared to GTV ADCmean and clinical factors. The best model was defined by 800<ADC<1100∙10-6mm2/s and correlated significantly to treatment outcome (p = 0.003). Optimal HRS cut-off value was found to be 5.8 cm3 according to ROC-analysis. This HRS demonstrated highly significant stratification potential (p < 0.001, bootstrap AUC ≥ 0.84) similar to GTV size (p < 0.001, AUC ≥ 0.79), in contrast to ADCmean (p = 0.361, AUC = 0.53). A preclinical prognostic model defined by an ADC-based HRS was successfully retrained and validated in HNC patients treated with radiochemotherapy. After thorough external validation, such functional HRS based on a band of ADC values may in the future allow interventional response-adaptive MRI-guided radiotherapy in online and offline approaches.

Analysis and Perspectives of MRI-Guided Proton Therapy Integrated Technology

This article explores the MRI-guided proton therapy (MRiPT) integrated technology, which is magnetic resonance imaging-guided radiation therapy. By precisely controlling dose distribution, MRiPT has the potential to enhance the efficacy of radiotherapy. This article reviews the development of MRiPT, analyzes its potential for clinical application, and discusses technical challenges and potential solutions. MRiPT technology offers significant advantages in improving treatment precision and reducing side effects, especially showing exceptional potential in the treatment of complex tumors. This article concludes by looking forward to the future development of MRiPT technology, emphasizes the importance of optimizing electromagnetic compatibility and reducing inter-system interference.

Surrogate gating strategies for the Elekta Unity MR-Linac gating system.

MRI-guided adaptive radiotherapy can directly monitor the anatomical positioning of the intended target during treatment with no additional imaging dose. Elekta has recently released its comprehensive motion management (CMM) solution that enables automatic radiation beam-gating on the Unity MR-Linac. Easily visualized targets that are distinct from the surrounding anatomy can be used to drive automatic gating decisions from the MRI cine imaging. However, poorly visualized targets can compromise the tracking and gating capabilities and may require surrogate tracking structures. This work presents strategies to generate robust tracking surrogates for a variety of treatment sites, enabling a wider application of CMM. Surrogate tracking strategies were developed from a cohort of patients treated using the CMM system on the Unity MR-Linac for treatment sites of the lung, pancreas, liver, and prostate. These sites posed challenging visualization or tracking of the primary target thereby compromising the tracking accuracy. Surrogate structures were developed using site-specific strategies to improve the imaging textured detail within the tracking volume while avoiding the dynamic overwhelming hypo- or hyper-intense anatomical structures. These surrogate volumes were applied within the anatomical positioning monitoring system as a proxy that drove the CMM gating decisions on the treatment unit. Robust site-specific surrogate structures were developed. Surrogate tracking structures for centrally located thoracic targets were created by expanding the target peripherally away from the heart and great vessels and into the lung. Pancreas surrogates required a vertically expanded column intersecting with the inferior liver edge. For the liver and prostate, surrogate structures consisted of a uniform expansion of the target, with liver surrogates intersecting the proximal liver edge or diaphragm while avoiding nearby ribs. These surrogate strategies have enabled the gating of complex moving targets among different treatment sites at our institution.

Magnetic resonance imaging-guided single-fraction preoperative radiotherapy for early-stage breast cancer (the RICE trial): feasibility study

BackgroundOver the past decade, the adoption of screening programs, digital mammography, and magnetic resonance imaging (MRI) has increased early-stage breast cancer diagnosis rates. Mortality rates have decreased due to early detection and improved treatments, including personalized therapies. Accelerated partial-breast irradiation (APBI) is emerging as a convenient and effective treatment for some patients, with studies exploring its preoperative use. Preoperative APBI, especially with MRI guidance, offers improved tumor targeting and potentially reduced side effects. Magnetic Resonance Imaging-Guided Single-Fraction Pre-Operative Radiotherapy for Early-Stage Breast Cancer (RICE trial) aims to assess the feasibility and efficacy of MRI-guided single-dose radiotherapy (RT) for early-stage breast cancer.MethodsThe RICE study is a prospective, single-arm study evaluating single-fraction preoperative, APBI treatment for patients with early-stage breast cancer using a magnetic resonance imaging linear accelerator (MRI linac). Eligible patients enrolled in this study will have a core biopsy to confirm estrogen receptor-positive and HER2-negative sub-type. RT planning will use a planning computed tomography (CT) co-registered with a MRI with the patient in either the supine or prone position. For the diagnostic workup, [18F] fluorodeoxyglucose positron emission tomography/CT ([18F] FDG PET/CT) and [18F] fluoroestradiol positron emission tomography/CT ([18F] FES PET/CT) will be performed prior to treatment. Thirty patients will receive a single ablative RT dose of 21 Gray to the tumor. Pre-treatment and post-treatment MRI scans will be acquired at baseline and 5 weeks post-RT respectively. Breast-conserving surgery will be scheduled for 6 weeks after APBI treatment using the MRI linac.The primary study endpoint is the successful administration of a single fraction of preoperative breast RT under the guidance of an MRI linac. Secondary endpoints include evaluating the utility of MRI, [18F] FDG PET/CT, and [18F] FES PET/CT as a non-invasive method for assessing treatment response in patients undergoing single-fraction preoperative APBI.ConclusionThe RICE trial represents a significant step in breast cancer treatment, offering insights that could lead to treatment protocols with minimized RT appointments and enhanced patient outcomes.Trial registrationThis trial is registered with the Australian New Zealand Clinical Trials Registry (ANZCTR). Registered 31st of May 2021. Registration number: ACTRN12621000659808.

A Review of Contemporary Image Guidance Techniques in Head and Neck Cancer.

Traditional head and neck cancer treatment involves open surgery, cytotoxic chemotherapy, and conventional radiotherapy planning. Emerging techniques aim to improve precision and reduce associated toxicity and functional impairment in current practice. This review article describes four such adaptations in image guidance, tailored to next generation therapies. This is a review of current literature, including feasibility studies from our cancer center, relating to: saline-aided intra-oral ultrasound-guided retropharyngeal biopsy; intra-oral ultrasound guided trans-oral robotic surgery (TORS); ultrasound-guided injection of "directly injectedtherapies"; and magnetic resonance imaging-guided radiotherapy. Presented within the context of the wider literature, initial local experience and data indicate good technical outcomes and patient tolerance, and low technical complications in all four image guidance techniques. Initial findings suggest a potentially important future role for these four image guidance techniques, on which next generation therapies are reliant. The broader implications on cross-disciplinary collaboration are also explored herein.

Simulation of Focal Boosting in Online Adaptive MRI-Guided SBRT for Patients With Locally Advanced Prostate Cancer With Seminal Vesicle Involvement

To evaluate the feasibility and accuracy of focal boosting in online adaptive MRI-guided stereotactic body radiation therapy (SBRT) for patients with prostate cancer (PCa) with seminal vesicle invasion (T3b) by analyzing the impact of intrafraction motion on the dose planned for the gross tumor volume (GTV) and clinical target volume (CTV). Data from 23 patients with T1-T3a PCa who received focal boosting SBRT on a 1.5T MR-Linac was used. A radiation oncologist replaced clinical GTVs with artificial GTVs representative for T3b tumor(s). For each MRI used for daily adaptation (MRIadapt), an automated treatment plan was generated (Df1-5) using the adapted contours. Patients were planned to receive 35 Gy to the CTV, with an isotoxic focal boost to the GTV up to 50 Gy. During each fraction, an additional MRI was acquired to assess intrafraction motion (MRIduring). Dose accumulation of all fractions was performed by deformable registration of MRIadapt, f2-5 to MRIadapt, f1 (DACC, planned). The Df1-5 were projected to their corresponding MRIduring, which were used to reconstruct DACC, delivered, likewise. Our results were compared to patients with tumor(s) without seminal vesicle invasion (T1-T3a). The median (10th-90th percentile) D98%ACC, planned to the GTV, which correlates most strongly with outcome, was 41.1 Gy (40.1-43.0 Gy) in the plans for patients with artificial T3b tumors, compared to 43.0 Gy (40.4-47.2 Gy) in the plans for patients with T1-T3a tumors. The D98%ACC, delivered to the GTV, taking into account intrafraction motion, was 41.0 Gy (39.3-42.6 Gy) and 42.5 Gy (40.0-46.6 Gy) in the plans for the artificial and clinical GTVs, respectively. MRI-guidance can ensure high accuracy of focal boosting in patients with T3b disease. Because of the unfavorable location of the GTV, a lower boost dose was feasible compared to patients with T1-T3a PCa.

P188 Stereotactic MRI-guided adaptive radiotherapy for renal tumors in a solitary kidney

P188 Stereotactic MRI-guided adaptive radiotherapy for renal tumors in a solitary kidney

PO0248: MRI-Guided Intensity-Modulated Radiotherapy Boost in Gynecologic Cancers for Patients Unsuitable for Brachytherapy (BT): A Case Series

PO0248: MRI-Guided Intensity-Modulated Radiotherapy Boost in Gynecologic Cancers for Patients Unsuitable for Brachytherapy (BT): A Case Series

Modeling of artificial intelligence-based respiratory motion prediction in MRI-guided radiotherapy: a review.

The advancement of precision radiotherapy techniques, such as volumetric modulated arc therapy (VMAT), stereotactic body radiotherapy (SBRT), and particle therapy, highlights the importance of radiotherapy in the treatment of cancer, while also posing challenges for respiratory motion management in thoracic and abdominal tumors. MRI-guided radiotherapy (MRIgRT) stands out as state-of-art real-time respiratory motion management approach owing to the non-ionizing radiation nature and superior soft-tissue contrast characteristic of MR imaging. In clinical practice, MR imaging often operates at a frequency of 4Hz, resulting in approximately a 300 ms system latency of MRIgRT. This system latency decreases the accuracy of respiratory motion management in MRIgRT. Artificial intelligence (AI)-based respiratory motion prediction has recently emerged as a promising solution to address the system latency issues in MRIgRT, particularly for advanced contour prediction and volumetric prediction. However, implementing AI-based respiratory motion prediction faces several challenges including the collection of training datasets, the selection of prediction methods, and the formulation of complex contour and volumetric prediction problems. This review presents modeling approaches of AI-based respiratory motion prediction in MRIgRT, and provides recommendations for achieving consistent and generalizable results in this field.

Patient-Specific Deep Learning Tracking Framework for Real-Time 2D Target Localization in Magnetic Resonance Imaging-Guided Radiation Therapy

Purpose: We propose a tumor tracking framework for 2D cine MRI based on a pair of deep learning (DL) models relying on patient-specific (PS) training.Methods and materials: The chosen DL models are: 1) an image registration transformer and 2) an auto-segmentation convolutional neural network (CNN). We collected over 1,400,000 cine MRI frames from 219 patients treated on a 0.35 T MRI-linac plus 7,500 frames from additional 35 patients which were manually labelled and subdivided into fine-tuning, validation, and testing sets. The transformer was first trained on the unlabeled data (without segmentations). We then continued training (with segmentations) either on the fine-tuning set or for PS models based on eight randomly selected frames from the first 5 s of each patient's cine MRI. The PS auto-segmentation CNN was trained from scratch with the same eight frames for each patient, without pre-training. Furthermore, we implemented B-spline image registration as a conventional model, as well as different baselines. Output segmentations of all models were compared on the testing set using the Dice similarity coefficient (DSC), the 50% and 95% Hausdorff distance (HD50%/HD95%), and the root-mean-square-error of the target centroid in superior-inferior direction (RMSESI).Results: The PS transformer and CNN significantly outperformed all other models, achieving a median (inter-quartile range) DSC of 0.92 (0.03)/0.90 (0.04), HD50% of 1.0 (0.1)/1.0 (0.4) mm, HD95% of 3.1 (1.9)/3.8 (2.0) mm and RMSESI of 0.7 (0.4)/0.9 (1.0) mm on the testing set. Their inference time was about 36/8 ms per frame and PS fine-tuning required 3 min for labelling and 8/4 min for training. The transformer was better than the CNN in 9/12 patients, the CNN better in 1/12 patients and the two PS models achieved the same performance on the remaining 2/12 testing patients.Conclusion: For targets in the thorax, abdomen and pelvis, we found two PS DL models to provide accurate real-time target localization during MRI-guided radiotherapy.

Comparison of online adaptive and non-adaptive magnetic resonance image-guided radiation therapy in prostate cancer using dose accumulation

Background and purposeConventional image-guided radiotherapy (conv-IGRT) is standard in prostate cancer (PC) but does not account for inter-fraction anatomical changes. Online-adaptive magnetic resonance-guided RT (OA-MRgRT) may improve organ-at-risk (OARs) sparing and clinical target volume (CTV) coverage. The aim of this study was to analyze accumulated OAR and target doses in PC after OA-MRgRT and conv-IGRT in comparison to pre-treatment reference planning (refPlan). Material and methodsTen patients with PC, previously treated with OA-MRgRT at the 1.5 T MR-Linac (20x3Gy), were included. Accumulated OA-MRgRT doses were determined by deformably registering all fraction’s MR-images. Conv-IGRT was simulated through rigid registration of the planning computed tomography with each fraction’s MR-image for dose mapping/accumulation. Dose-volume parameters (DVPs), including CTV D50% and D98%, rectum, bladder, urethra, Dmax and V56Gy for OA-MRgRT, conv-IGRT and refPlan were compared using the Wilcoxon signed-rank test. Clinical relevance of accumulated dose differences was analyzed using a normal-tissue complication-probability model. ResultsCTV-DVPs were comparable, whereas OA-MRgRT yielded decreased median OAR-DVPs compared to conv-IGRT, except for bladder V56Gy. OA-MRgRT demonstrated significantly lower median rectum Dmax over conv-IGRT (59.1/59.9 Gy, p = 0.006) and refPlan (60.1 Gy, p = 0.012). Similarly, OA-MRgRT yielded reduced median bladder Dmax compared to conv-IGRT (60.0/60.4 Gy, p = 0.006), and refPlan (61.2 Gy, p = 0.002). Overall, accumulated dose differences were small and did not translate into clinically relevant effects. ConclusionDeformably accumulated OA-MRgRT using 20x3Gy in PC showed significant but small dosimetric differences comparted to conv-IGRT. Feasibility of a dose accumulation methodology was demonstrated, which may be relevant for evaluating future hypo-fractionated OA-MRgRT approaches.

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

Background and purposeDespite recent advances of online image-guided high-precision patient positioning and adaptation using magnetic resonance imaging (MRI) or cone-beam computed tomography (CT), standard radiation therapy pathway still involves a dedicated simulation scan. The aim of this study was to evaluate the feasibility and planning quality of integrating a simulation-free treatment planning workflow for adaptive online MRI-guided radiation therapy on a 1.5 T MRI linear accelerator (MRI-Linac) in prostate cancer using diagnostic CT (dCT) scans. Materials and methodsFor ten patients with prostate cancer previously treated at the MRI-Linac with adaptive radiation therapy (42.7 Gy in 7 fractions), simulation-free reference plans based on dCT were retrospectively created, and adaptive plans were simulated for the first treatment fraction. Reference and adapted plans derived from both standard and simulation-free workflows were compared with regard to institutional dose/volume criteria, followed by statistical assessment using the paired Wilcoxon signed-rank test with a Bonferroni-corrected significance level of α = 0.025. ResultsSimulation-free reference and adapted plans consistently met dose/volume criteria. Statistical analysis revealed no significant differences between both workflows, except median values for near-maximum dose (D2%) in the planning target volume: 44.2 Gy (standard) vs. 44.5 Gy (simulation-free) in reference plans (p = 0.01), and 44.5 Gy vs. 44.6 Gy in adapted plans (p = 0.01). ConclusionThis study demonstrated the feasibility of simulation-free radiation therapy planning using dCT. Comparable treatment plan quality was observed for both reference and adapted radiation therapy plans in a curative setting for patients with prostate cancer.

Incorporating patient-specific information for the development of rectal tumor auto-segmentation models for online adaptive magnetic resonance Image-guided radiotherapy

Background and purposeIn online adaptive magnetic resonance image (MRI)-guided radiotherapy (MRIgRT), manual contouring of rectal tumors on daily images is labor-intensive and time-consuming. Automation of this task is complex due to substantial variation in tumor shape and location between patients. The aim of this work was to investigate different approaches of propagating patient-specific prior information to the online adaptive treatment fractions to improve deep-learning based auto-segmentation of rectal tumors. Materials and methods243 T2-weighted MRI scans of 49 rectal cancer patients treated on the 1.5T MR-Linear accelerator (MR-Linac) were utilized to train models to segment rectal tumors. As benchmark, an MRI_only auto-segmentation model was trained. Three approaches of including a patient-specific prior were studied: 1. include the segmentations of fraction 1 as extra input channel for the auto-segmentation of subsequent fractions, 2. fine-tuning of the MRI_only model to fraction 1 (PSF_1) and 3. fine-tuning of the MRI_only model on all earlier fractions (PSF_cumulative). Auto-segmentations were compared to the manual segmentation using geometric similarity metrics. Clinical impact was assessed by evaluating post-treatment target coverage. ResultsAll patient-specific methods outperformed the MRI_only segmentation approach. Median 95th percentile Hausdorff (95HD) were 22.0 (range: 6.1–76.6) mm for MRI_only segmentation, 9.9 (range: 2.5–38.2) mm for MRI+prior segmentation, 6.4 (range: 2.4–17.8) mm for PSF_1 and 4.8 (range: 1.7–26.9) mm for PSF_cumulative. PSF_cumulative was found to be superior to PSF_1 from fraction 4 onward (p = 0.014). ConclusionPatient-specific fine-tuning of automatically segmented rectal tumors, using images and segmentations from all previous fractions, yields superior quality compared to other auto-segmentation approaches.

A patient-specific auto-planning method for MRI-guided adaptive radiotherapy in prostate cancer

Background and purposeFast and automated generation of treatment plans is desirable for magnetic resonance imaging (MRI)-guided adaptive radiotherapy (MRIgART). This study proposed a novel patient-specific auto-planning method and validated its feasibility in improving the existing online planning workflow. Materials and methodsData from 40 patients with prostate cancer were collected retrospectively. A patient-specific auto-planning method was proposed to generate adaptive treatment plans. First, a population dose-prediction model (M0) was trained using data from previous patients. Second, a patient-specific model (Mps) was created for each new patient by fine-tuning M0 with the patient’s data. Finally, an auto plan was optimized using the parameters derived from the predicted dose distribution by Mps. The auto plans were compared with manual plans in terms of plan quality, efficiency, dosimetric verification, and clinical evaluation. ResultsThe auto plans improved target coverage, reduced irradiation to the rectum, and provided comparable protection to other organs-at-risk. Target coverage for the planning target volume (+0.61 %, P = 0.023) and clinical target volume 4000 (+1.60 %, P < 0.001) increased. V2900cGy (−1.06 %, P = 0.004) and V1810cGy (−2.49 %, P < 0.001) to the rectal wall and V1810cGy (−2.82 %, P = 0.012) to the rectum were significantly reduced. The auto plans required less planning time (−3.92 min, P = 0.001), monitor units (−46.48, P = 0.003), and delivery time (−0.26 min, P = 0.004), and their gamma pass rates (3 %/2 mm) were higher (+0.47 %, P = 0.014). ConclusionThe proposed patient-specific auto-planning method demonstrated a robust level of automation and was able to generate high-quality treatment plans in less time for MRIgART in prostate cancer.

109 T2/FLAIR Variation During MRI-Guided Radiotherapy for Glioblastoma

109 T2/FLAIR Variation During MRI-Guided Radiotherapy for Glioblastoma

2285: One year follow-up of total neoadjuvant treatment of rectal cancer by MRI-guided radiotherapy

2285: One year follow-up of total neoadjuvant treatment of rectal cancer by MRI-guided radiotherapy