MR signature matching (MRSIGMA) implementation for true real-time free-breathing volumetric imaging with sub-200 ms latency on an MR-Linac.

PURPOSE: Develop a true real-time implementation of MR signature matching (MRSIGMA) for free-breathing 3D MRI with sub-200 ms latency on the Elekta Unity 1.5T MR-Linac. METHODS: MRSIGMA was implemented on an external computer with a network connection to the MR-Linac. Stack-of-stars with partial kz sampling was used to accelerate data acquisition and ReconSocket was employed for simultaneous data transmission. Movienet network computed the 4D MRI motion dictionary and correlation analysis was used for signature matching. A programmable 4D MRI phantom was utilized to evaluate MRSIGMA with respect to a ground-truth translational motion reference. In vivo validation was performed on patients with pancreatic cancer, where 15 patients were employed to train Movienet and 7 patients to test the real-time implementation of MRSIGMA. Dice coefficients between real-time MRSIGMA and a retrospectively computed 4D reference were used to evaluate motion tracking performance. RESULTS: Motion dictionary was computed in under 5 s. Signature acquisition and matching presented 173 ms latency on the phantom and 193 ms on patients. MRSIGMA presented a mean error of 1.3-1.6 mm for all phantom experiments, which was below the 2 mm acquisition resolution along the motion direction. The Dice coefficient over time between MRSIGMA and reference contours was 0.88 ± 0.02 (GTV), 0.87 ± 0.02(duodenum-stomach), and 0.78 ± 0.02(small bowel), demonstrating high motion tracking performance for both tumor and organs at risk. CONCLUSION: The real-time implementation of MRSIGMA enabled true real-time free-breathing 3D MRI with sub-200 ms imaging latency on a clinical MR-Linac system, which can be used for treatment monitoring, adaptive radiotherapy and dose accumulation mapping in tumors affected by respiratory motion.

Preclinical monitoring of radiation-induced brain injury via GluCEST MRI and resting-state fMRI at 7 T: an exploratory study on MRI-guided OAR avoidance.

PURPOSE: To assess the value of glutamate chemical exchange saturation transfer (GluCEST) after whole-brain radiotherapy (WBRT) as an imaging marker of radiation-induced brain injury (RBI) and to preliminarily show the feasibility of multiparametric MRI-guided organ at risk (OAR) avoidance. METHODS: Rats were divided into two groups: the control (CTRL) group (n = 9) and the RBI group (n = 9). The rats in the RBI group were irradiated with an X­ray radiator and then subjected to a water maze experiment 4 weeks later. In combination with high-performance liquid chromatography (HPLC), we evaluated the value of GluCEST applied to glutamate changes for RBI and investigated the effect of such changes on glutamatergic neuronal function. RESULTS: The average GluCEST values were markedly lower in the hippocampus and cerebral cortex. Positive correlations were observed between GluCEST values and regional homogeneity (ReHo) values in both the hippocampus and the cerebral cortex. HPLC showed a positive correlation with GluCEST values in the hippocampus. GluCEST values were positively correlated with spatial memory. CONCLUSION: GluCEST MRI provides a visual assessment of glutamate changes in RBI rats for monitoring OAR cognitive toxicity reactions and may be used as a biomarker of OAR avoidance as well as metabolism to facilitate monitoring and intervention in radiation damage that occurs after radiotherapy.

Distortion-corrected image reconstruction with deep learning on an MRI-Linac.

PURPOSE: MRI is increasingly utilized for image-guided radiotherapy due to its outstanding soft-tissue contrast and lack of ionizing radiation. However, geometric distortions caused by gradient nonlinearities (GNLs) limit anatomical accuracy, potentially compromising the quality of tumor treatments. In addition, slow MR acquisition and reconstruction limit the potential for effective image guidance. Here, we demonstrate a deep learning-based method that rapidly reconstructs distortion-corrected images from raw k-space data for MR-guided radiotherapy applications. METHODS: We leverage recent advances in interpretable unrolling networks to develop a Distortion-Corrected Reconstruction Network (DCReconNet) that applies convolutional neural networks (CNNs) to learn effective regularizations and nonuniform fast Fourier transforms for GNL-encoding. DCReconNet was trained on a public MR brain dataset from 11 healthy volunteers for fully sampled and accelerated techniques, including parallel imaging (PI) and compressed sensing (CS). The performance of DCReconNet was tested on phantom, brain, pelvis, and lung images acquired on a 1.0T MRI-Linac. The DCReconNet, CS-, PI-and UNet-based reconstructed image quality was measured by structural similarity (SSIM) and RMS error (RMSE) for numerical comparisons. The computation time and residual distortion for each method were also reported. RESULTS: Imaging results demonstrated that DCReconNet better preserves image structures compared to CS- and PI-based reconstruction methods. DCReconNet resulted in the highest SSIM (0.95 median value) and lowest RMSE (<0.04) on simulated brain images with four times acceleration. DCReconNet is over 10-times faster than iterative, regularized reconstruction methods. CONCLUSIONS: DCReconNet provides fast and geometrically accurate image reconstruction and has the potential for MRI-guided radiotherapy applications.

Assessment of intrafractional prostate motion and its dosimetric impact in MRI-guided online adaptive radiotherapy with gating.

PURPOSE: This study aimed to evaluate the intrafractional prostate motion captured during gated magnetic resonance imaging (MRI)-guided online adaptive radiotherapy for prostate cancer and analyze its impact on the delivered dose as well as the effect of gating. METHODS: Sagittal 2D cine-MRI scans were acquired at 4 Hz during treatment at a ViewRay MRIdian (ViewRay Inc., Oakwood Village, OH, USA) MR linac. Prostate shifts in anterior-posterior (AP) and superior-inferior (SI) directions were extracted separately. Using the static dose cloud approximation, the planned fractional dose was shifted according to the 2D gated motion (residual motion in gating window) to estimate the delivered dose by superimposing and averaging the shifted dose volumes. The dose of a hypothetical non-gated delivery was reconstructed similarly using the non-gated motion. For the clinical target volume (CTV), rectum, and bladder, dose-volume histogram parameters of the planned and reconstructed doses were compared. RESULTS: In total, 174 fractions (15.7 h of cine-MRI) from 10 patients were evaluated. The average (±1 σ) non-gated prostate motion was 0.6 ± 1.0 mm in the AP and 0.0 ± 0.6 mm in the SI direction with respect to the centroid position of the gating boundary. 95% of the shifts were within [-3.5, 2.7] mm in the AP and [-2.9, 3.2] mm in the SI direction. For the gated treatment and averaged over all fractions, CTV D98% decreased by less than 2% for all patients. The rectum and the bladder D2% increased by less than 3% and 0.5%, respectively. Doses reconstructed for gated and non-gated delivery were similar for most fractions. CONCLUSION: A pipeline for extraction of prostate motion during gated MRI-guided radiotherapy based on 2D cine-MRI was implemented. The 2D motion data enabled an approximate estimation of the delivered dose. For the majority of fractions, the benefit of gating was negligible, and clinical dosimetric constraints were met, indicating safety of the currently adopted gated MRI-guided treatment workflow.

Randomized phase II trial of MRI-guided salvage radiotherapy for prostate cancer in 4 weeks versus 2 weeks (SHORTER).

BACKGROUND: Ultra-hypofractionated image-guided stereotactic body radiotherapy (SBRT) is increasingly used for definitive treatment of localized prostate cancer. Magnetic resonance imaging-guided radiotherapy (MRgRT) facilitates improved visualization, real-time tracking of targets and/or organs-at-risk (OAR), and capacity for adaptive planning which may translate to improved targeting and reduced toxicity to surrounding tissues. Given promising results from NRG-GU003 comparing conventional and moderate hypofractionation in the post-operative setting, there is growing interest in exploring ultra-hypofractionated post-operative regimens. It remains unclear whether this can be done safely and whether MRgRT may help mitigate potential toxicity. SHORTER (NCT04422132) is a phase II randomized trial prospectively evaluating whether salvage MRgRT delivered in 5 fractions versus 20 fractions is non-inferior with respect to gastrointestinal (GI) and genitourinary (GU) toxicities at 2-years post-treatment. METHODS: A total of 136 patients will be randomized in a 1:1 ratio to salvage MRgRT in 5 fractions or 20 fractions using permuted block randomization. Patients will be stratified according to baseline Expanded Prostate Cancer Index Composite (EPIC) bowel and urinary domain scores as well as nodal treatment and androgen deprivation therapy (ADT). Patients undergoing 5 fractions will receive a total of 32.5 Gy over 2 weeks and patients undergoing 20 fractions will receive a total of 55 Gy over 4 weeks, with or without nodal coverage (25.5 Gy over 2 weeks and 42 Gy over 4 weeks) and ADT as per the investigator's discretion. The co-primary endpoints are change scores in the bowel and the urinary domains of the EPIC. The change scores will reflect the 2-year score minus the pre-treatment (baseline) score. The secondary endpoints include safety endpoints, including change in GI and GU symptoms at 3, 6, 12 and 60 months from completion of treatment, and efficacy endpoints, including time to progression, prostate cancer specific survival and overall survival. DISCUSSION: The SHORTER trial is the first randomized phase II trial comparing toxicity of ultra-hypofractionated and hypofractionated MRgRT in the salvage setting. The primary hypothesis is that salvage MRgRT delivered in 5 fractions will not significantly increase GI and GU toxicities when compared to salvage MRgRT delivered in 20 fractions. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT04422132. Date of registration: June 9, 2020.

Ablative 5-Fraction Stereotactic MRI-Guided Adaptive Radiotherapy for Oligometastatic Pancreatic Adenocarcinoma.

INTRODUCTION: Metastatic pancreatic ductal adenocarcinoma (PDAC) carries a poor prognosis and significant morbidity from local tumor progression. We investigated outcomes among oligometastatic PDAC patients treated with stereotactic magnetic resonance image-guided ablative radiotherapy (SMART) to primary disease. METHODS: We performed a retrospective multi-institutional analysis of oligometastatic PDAC at diagnosis or with metachronous oligoprogression during induction chemotherapy treated with primary tumor SMART. Outcomes of interest included overall survival (OS), progression-free survival (PFS), freedom from locoregional failure (FFLRF), and freedom from distant failure (FFDF). Acute and late toxicity were reported and in exploratory analyses patients were stratified by the number of metastases, SMART indication, and addition of metastasis-directed therapy. RESULTS: From 2019 to 2021, 22 patients with oligometastatic PDAC (range: 1-6 metastases) received SMART to the primary tumor with a median follow-up of 11.2 months from SMART. Nineteen patients had de novo synchronous metastatic disease and three had metachronous oligoprogression. Metastasis location most commonly was liver only (40.9%), multiple organs (27.3%), lungs only (13.6%), or abdominal/pelvic nodes (13.6%). All patients received either FOLFIRINOX (64%) or gemcitabine/nab-paclitaxel (36%) followed by SMART (median 50 Gy, 5 fractions) for local control (77%), pain control (14%), or local progression (9%). Additionally, 41% of patients received other metastasis-directed treatments. The median OS from diagnosis and SMART was 23.9 months and 11.6 months, respectively. Calculated from SMART, the median PFS was 2.4 months with 91% of patients having distant progression, and 1-year local control was 68. Two patients (9%) experienced grade 3 toxicities, gastric outlet obstruction, and gastrointestinal bleed without grade 4 or 5 toxicity. CONCLUSION: There was minimal morbidity of local disease progression after SMART in this cohort of oligometastatic PDAC. As systemic therapy options improve, additional strategies to identify patients who may derive benefits from local consolidation or metastasis-directed therapy are needed.

A new frontier of image guidance: Organs at risk avoidance with MRI-guided respiratory-gated intensity modulated radiotherapy: Technical note and report of a case.

The case of a 50-year-old man affected by a rhabdomiosarcoma metastatic lesion in the left flank Is reported. The patient was addressed to 50.4 Gy radiotherapy with concomitant chemotherapy in order to locally control the lesion. A Tri-60-Co magnetic resonance hybrid radiotherapy unit was used for treatment delivery and a respiratory gating protocol was applied for the different breathing phases (Free Breathing, Deep Inspiration Breath Hold and Final Expiration Breath Hold). Three intensity modulated radiation therapy (IMRT) plans were calculated and Final Expiration Breath Hold plan was finally selected due to the absence of PTV coverage differences and better organs at risk sparing (i.e. kidneys). This case report suggests that organs at risk avoidance with MRI-guided respiratory-gated Radiotherapy is feasible and particularly advantageous whenever sparing the organs at risk is of utmost dosimetric or clinical importance.

Evaluating the accuracy of geometrical distortion correction of magnetic resonance images for use in intracranial brain tumor radiotherapy.

AIM: Determine the 1) effectiveness of correction for gradient-non-linearity and susceptibility effects on both QUASAR GRID3D and CIRS phantoms; and 2) the magnitude and location of regions of residual distortion before and after correction. BACKGROUND: Using magnetic resonance imaging (MRI) as a primary dataset for radiotherapy planning requires correction for geometrical distortion and non-uniform intensity. MATERIALS AND METHODS: Phantom Study: MRI, computed tomography (CT) and cone beam CT images of QUASAR GRID3D and CIRS head phantoms were acquired. Patient Study: Ten patients were MRI-scanned for stereotactic radiosurgery treatment. Correction algorithm: Two magnitude and one phase difference image were acquired to create a field map. A MATLAB program was used to calculate geometrical distortion in the frequency encoding direction, and 3D interpolation was applied to resize it to match 3D T1-weighted magnetization-prepared rapid gradient-echo (MPRAGE) images. MPRAGE images were warped according to the interpolated field map in the frequency encoding direction. The corrected and uncorrected MRI images were fused, deformable registered, and a difference distortion map generated. RESULTS: Maximum deviation improvements: GRID3D , 0.27 mm y-direction, 0.07 mm z-direction, 0.23 mm x-direction. CIRS, 0.34 mm, 0.1 mm and 0.09 mm at 20-, 40- and 60-mm diameters from the isocenter. Patient data show corrections from 0.2 to 1.2 mm, based on location. The most-distorted areas are around air cavities, e.g. sinuses. CONCLUSIONS: The phantom data show the validity of our fast distortion correction algorithm. Patient-specific data are acquired in <2 min and analyzed and available for planning in less than a minute.

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 4 Hz, 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.

Inter-fractional portability of deep learning models for lung target tracking on cine imaging acquired in MRI-guided radiotherapy.

MRI-guided radiotherapy systems enable beam gating by tracking the target on planar, two-dimensional cine images acquired during treatment. This study aims to evaluate how deep-learning (DL) models for target tracking that are trained on data from one fraction can be translated to subsequent fractions. Cine images were acquired for six patients treated on an MRI-guided radiotherapy platform (MRIdian, Viewray Inc.) with an onboard 0.35 T MRI scanner. Three DL models (U-net, attention U-net and nested U-net) for target tracking were trained using two training strategies: (1) uniform training using data obtained only from the first fraction with testing performed on data from subsequent fractions and (2) adaptive training in which training was updated each fraction by adding 20 samples from the current fraction with testing performed on the remaining images from that fraction. Tracking performance was compared between algorithms, models and training strategies by evaluating the Dice similarity coefficient (DSC) and 95% Hausdorff Distance (HD95) between automatically generated and manually specified contours. The mean DSC for all six patients in comparing manual contours and contours generated by the onboard algorithm (OBT) were 0.68 ± 0.16. Compared to OBT, the DSC values improved 17.0 - 19.3% for the three DL models with uniform training, and 24.7 - 25.7% for the models based on adaptive training. The HD95 values improved 50.6 - 54.5% for the models based on adaptive training. DL-based techniques achieved better tracking performance than the onboard, registration-based tracking approach. DL-based tracking performance improved when implementing an adaptive strategy that augments training data fraction-by-fraction.

Does the presence of Magtrace preclude adaptive breast radiotherapy on an MR-Linac?

INTRODUCTION: This work reports on an unusual finding observed during image quality assessment in the preparation for the clinical implementation of breast magnetic resonance image-guided radiotherapy (MRIgRT) on a 1.5 Tesla (T) magnetic resonance linear accelerator (MR-Linac) (Elekta AB, Stockholm, Sweden). CASE AND OUTCOMES: A patient with T2 N0 M0 right breast invasive ductal carcinoma, receiving adjuvant radiotherapy, underwent two imaging sessions on the MR-Linac. The imaging protocol included T1- and T2-weighted (W) turbo spin echo (TSE) sequences, a T1W mDixon, and a T2W TSE navigated sequence acquired on end-expiration. All images were reconstructed in the axial plane. Images were assessed for image quality and appropriateness for use within the treatment pathway using visual grading analysis (VGA). An artefact in the right breast was noted independently by all observers. The patient's skin and medical notes were reviewed for possible explanation. The findings were discussed with the patient's responsible clinician, and subsequent referral to the local multi-disciplinary team (MDT) for radiologist review was made. On further investigation, the patient's images demonstrated a signal void in the subareolar region of the right breast coinciding with the surgical site. This was distal from the tumour bed and deemed unlikely to be related to a Magseed marker or intraoperative clips. The patient reported no history of nipple tattoo or piercing. There was nothing on clothing that this could be attributed to. DISCUSSION: Following MDT review, where all potential sources of signal void were considered, it was concluded that the cause was Magtrace, a superparamagnetic iron oxide tracer, recommended for sentinel lymph node localisation in patients with breast cancer in the United Kingdom. The artefact was characteristic of a magnetic susceptibility artefact. These can arise from local magnetic field inhomogeneities caused by the presence of the metal compounds in MagTrace. For breast MRIgRT on the MR-Linac, treatment verification and the possibility of real-time replanning is a critical aspect. The magnetic susceptibility artefact significantly inhibited plan adaption and confidence in the online image registration process making the patient ineligible for treatment on the MR-Linac. CONCLUSION: As part of ongoing work-up for breast MRIgRT, the screening of patients for Magtrace is now included. Optimisation of MR imaging sequences for radiotherapy planning and image review to minimise distortion are being developed.

Delta radiomics to track radiation response in lung tumors receiving stereotactic magnetic resonance-guided radiotherapy.

Background and purpose: Lung cancer is a leading cause of cancer-related mortality, and stereotactic body radiotherapy (SBRT) has become a standard treatment for early-stage lung cancer. However, the heterogeneous response to radiation at the tumor level poses challenges. Currently, standardized dosage regimens lack adaptation based on individual patient or tumor characteristics. Thus, we explore the potential of delta radiomics from on-treatment magnetic resonance (MR) imaging to track radiation dose response, inform personalized radiotherapy dosing, and predict outcomes. Materials and methods: A retrospective study of 47 MR-guided lung SBRT treatments for 39 patients was conducted. Radiomic features were extracted using Pyradiomics, and stability was evaluated temporally and spatially. Delta radiomics were correlated with radiation dose delivery and assessed for associations with tumor control and survival with Cox regressions. Results: Among 107 features, 49 demonstrated temporal stability, and 57 showed spatial stability. Fifteen stable and non-collinear features were analyzed. Median Skewness and surface to volume ratio decreased with radiation dose fraction delivery, while coarseness and 90th percentile values increased. Skewness had the largest relative median absolute changes (22 %-45 %) per fraction from baseline and was associated with locoregional failure (p = 0.012) by analysis of covariance. Skewness, Elongation, and Flatness were significantly associated with local recurrence-free survival, while tumor diameter and volume were not. Conclusions: Our study establishes the feasibility and stability of delta radiomics analysis for MR-guided lung SBRT. Findings suggest that MR delta radiomics can capture short-term radiographic manifestations of the intra-tumoral radiation effect.

Evaluation of the impact of cardiac implantable electronic devices on cine MRI for real-time adaptive cardiac radioablation on a 1.5 T MR-linac.

BACKGROUND: Stereotactic arrhythmia radioablation (STAR) is a novel treatment approach for refractory ventricular tachycardia (VT). The risk of treatment-induced toxicity and geographic miss can be reduced with online MRI-guidance on an MR-linac. However, most VT patients carry cardiac implantable electronic devices (CIED), which compromise MR images. PURPOSE: Robust MR-linac imaging sequences are required for cardiac visualization and accurate motion monitoring in presence of a CIED during MRI-guided STAR. We optimized two clinically available cine sequences for cardiorespiratory motion estimation in presence of a CIED on a 1.5 T MR-linac. The image quality, motion estimation accuracy, and geometric fidelity using these cine sequences were evaluated. METHODS: Clinically available 2D balanced steady-state free precession (bSSFP, voxel size = 3.0 × $\times$ 3.0 × $\times$ 10 mm3, Tscan = 96 ms, bandwidth (BW) = 1884 Hz/px) and T 1 ${\rm T}_{1}$ -spoiled gradient echo ( T 1 ${\rm T}_{1}$ -GRE, voxel size = 4.0 × $ \times$ 4.0 × $ \times$ 10 mm3, Tscan = 97 ms, BW = 500 Hz/px) sequences were adjusted for real-time cardiac visualization and cardiorespiratory motion estimation on a 1.5 T Unity MR-linac (Elekta AB, Stockholm, Sweden), while complying with safety guidelines for MRI in presence of CIEDs (specific absorption rate < $ <$ 2 W/kg and d B d t < $\frac{dB}{dt}<$ 80 mT/s). Cine acquisitions were performed in five healthy volunteers, with and without an implantable cardioverter- defibrillator (ICD) placed on the clavicle, and a VT patient. Generalized divergence-curl (GDC) deformable image registration (DIR) was used for automated landmark motion estimation in the left ventricle (LV). Gaussian processes (GP), a machine-learning technique, was trained using GDC landmarks and deployed for real-time cardiorespiratory motion prediction. B 0 $B_{0}$ -mapping was performed to assess geometric image fidelity in the presence of CIEDs. RESULTS: CIEDs introduced banding artifacts partially obscuring cardiac structures in bSSFP acquisitions. In contrast, the T 1 ${\rm T}_{1}$ -GRE was more robust to CIED-induced artifacts at the expense of a lower signal-to-noise ratio. In presence of an ICD, image-based cardiorespiratory motion estimation was possible for 85% (100%) of the volunteers using the bSSFP ( T 1 ${\rm T}_{1}$ -GRE) sequence. The in-plane 2D root-mean-squared deviation (RMSD) range between GDC-derived landmarks and manual annotations using the bSSFP (T1-GRE) sequence was 3.1-3.3 (3.3-4.1) mm without ICD and 4.6-4.6 (3.2-3.3) mm with ICD. Without ICD, the RMSD between the GP-predictions and GDC-derived landmarks ranged between 0.9 and 2.2 mm (1.3-3.0 mm) for the bSSFP (T1-GRE) sequence. With ICD, the RMSD between the GP-predictions and GDC-derived landmarks ranged between 1.3 and 2.2 mm (1.2-3.2 mm) using the bSSFP (T1-GRE) sequence resulting in an RMSD-increase of 42%-143% (bSSFP) and -61%-142% (T1-GRE). Lead-induced spatial distortions ranged between -0.2 and 0.2 mm (-0.7-1.2 mm) using the bSSFP ( T 1 ${\rm T}_{1}$ -GRE) sequence. The 98th percentile range of the spatial distortions in the gross target volume of the patient was between 0.0 and 0.4 mm (0.0-1.8 mm) when using bSSFP ( T 1 ${\rm T}_{1}$ -GRE). CONCLUSIONS: Tailored bSSFP and T 1 ${\rm T}_{1}$ -GRE sequences can facilitate real-time cardiorespiratory estimation using GP trained with GDC-derived landmarks in the majority of landmark locations in the LV despite the presence of CIEDs. The need for high temporal resolution noticeably reduced achievable spatial resolution of the cine MRIs. However, the effect of the CIED-induced artifacts is device, patient and sequence dependent and requires specific assessment per case.

Auto-segmentation of pelvic organs at risk on 0.35T MRI using 2D and 3D Generative Adversarial Network models.

PURPOSE: Manual recontouring of targets and Organs At Risk (OARs) is a time-consuming and operator-dependent task. We explored the potential of Generative Adversarial Networks (GAN) to auto-segment the rectum, bladder and femoral heads on 0.35T MRIs to accelerate the online MRI-guided-Radiotherapy (MRIgRT) workflow. METHODS: 3D planning MRIs from 60 prostate cancer patients treated with 0.35T MR-Linac were collected. A 3D GAN architecture and its equivalent 2D version were trained, validated and tested on 40, 10 and 10 patients respectively. The volumetric Dice Similarity Coefficient (DSC) and 95th percentile Hausdorff Distance (HD95th) were computed against expert drawn ground-truth delineations. The networks were also validated on an independent external dataset of 16 patients. RESULTS: In the internal test set, the 3D and 2D GANs showed DSC/HD95th of 0.83/9.72 mm and 0.81/10.65 mm for the rectum, 0.92/5.91 mm and 0.85/15.72 mm for the bladder, and 0.94/3.62 mm and 0.90/9.49 mm for the femoral heads. In the external test set, the performance was 0.74/31.13 mm and 0.72/25.07 mm for the rectum, 0.92/9.46 mm and 0.88/11.28 mm for the bladder, and 0.89/7.00 mm and 0.88/10.06 mm for the femoral heads. The 3D and 2D GANs required on average 1.44 s and 6.59 s respectively to generate the OARs' volumetric segmentation for a single patient. CONCLUSIONS: The proposed 3D GAN auto-segments pelvic OARs with high accuracy on 0.35T, in both the internal and the external test sets, outperforming its 2D equivalent in both segmentation robustness and volume generation time.

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

Background and purpose: In 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 methods: 243 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. Results: All 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). Conclusion: Patient-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.

Deep-learning-based joint rigid and deformable contour propagation for magnetic resonance imaging-guided prostate radiotherapy.

BACKGROUND: Deep learning-based unsupervised image registration has recently been proposed, promising fast registration. However, it has yet to be adopted in the online adaptive magnetic resonance imaging-guided radiotherapy (MRgRT) workflow. PURPOSE: In this paper, we design an unsupervised, joint rigid, and deformable registration framework for contour propagation in MRgRT of prostate cancer. METHODS: Three-dimensional pelvic T2-weighted MRIs of 143 prostate cancer patients undergoing radiotherapy were collected and divided into 110, 13, and 20 patients for training, validation, and testing. We designed a framework using convolutional neural networks (CNNs) for rigid and deformable registration. We selected the deformable registration network architecture among U-Net, MS-D Net, and LapIRN and optimized the training strategy (end-to-end vs. sequential). The framework was compared against an iterative baseline registration. We evaluated registration accuracy (the Dice and Hausdorff distance of the prostate and bladder contours), structural similarity index, and folding percentage to compare the methods. We also evaluated the framework's robustness to rigid and elastic deformations and bias field perturbations. RESULTS: The end-to-end trained framework comprising LapIRN for the deformable component achieved the best median (interquartile range) prostate and bladder Dice of 0.89 (0.85-0.91) and 0.86 (0.80-0.91), respectively. This accuracy was comparable to the iterative baseline registration: prostate and bladder Dice of 0.91 (0.88-0.93) and 0.86 (0.80-0.92). The best models complete rigid and deformable registration in 0.002 (0.0005) and 0.74 (0.43) s (Nvidia Tesla V100-PCIe 32 GB GPU), respectively. We found that the models are robust to translations up to 52 mm, rotations up to 15 ∘ $^\circ$ , elastic deformations up to 40 mm, and bias fields. CONCLUSIONS: Our proposed unsupervised, deep learning-based registration framework can perform rigid and deformable registration in less than a second with contour propagation accuracy comparable with iterative registration.

Intravoxel incoherent motion magnetic resonance imaging to assess early tumor response to radiation therapy: Review and future directions.

Early prediction of radiation response by imaging is a dynamic field of research and it can be obtained using a variety of noninvasive magnetic resonance imaging methods. Recently, intravoxel incoherent motion (IVIM) has gained interest in cancer imaging. IVIM carries both diffusion and perfusion information, making it a promising tool to assess tumor response. Here, we briefly introduced the basics of IVIM, reviewed existing studies of IVIM in various type of tumors during radiotherapy in order to show whether IVIM is a useful technique for an early assessment of radiation response. 31/40 studies reported an increase of IVIM parameters during radiotherapy compared to baseline. In 27 studies, this increase was higher in patients with good response to radiotherapy. Future directions including implementation of IVIM on MR-Linac and its limitation are discussed. Obtaining new radiologic biomarkers of radiotherapy response could open the way for a more personalized, biology-guided radiation therapy.

Full daily re-optimization improves plan quality during online adaptive radiotherapy.

Background and purpose: Daily online treatment plan adaptation requires a fast workflow and planning process. Current online planning consists of adaptation of a predefined reference plan, which might be suboptimal in cases of large anatomic changes. The aim of this study was to investigate plan quality differences between the current online re-planning approach and a complete re-optimization. Material and methods: Magnetic resonance linear accelerator reference plans for ten prostate cancer patients were automatically generated using particle swarm optimization (PSO). Adapted plans were created for each fraction using (1) the current re-planning approach and (2) full PSO re-optimization and evaluated overall compliance with institutional dose-volume criteria compared to (3) clinically delivered fractions. Relative volume differences between reference and daily anatomy were assessed for planning target volumes (PTV60, PTV57.6), rectum and bladder and correlated with dose-volume results. Results: The PSO approach showed significantly higher adherence to dose-volume criteria than the reference approach and clinical fractions (p < 0.001). In 74 % of PSO plans at most one criterion failed compared to 56 % in the reference approach and 41 % in clinical plans. A fair correlation between PTV60 D98% and relative bladder volume change was observed for the reference approach. Bladder volume reductions larger than 50 % compared to the reference plan recurrently decreased PTV60 D98% below 56 Gy. Conclusion: Complete re-optimization maintained target coverage and organs at risk sparing even after large anatomic variations. Re-planning based on daily magnetic resonance imaging was sufficient for small variations, while large variations led to decreasing target coverage and organ-at-risk sparing.

Intra-fractional geometric and dose/volume metric variations of magnetic resonance imaging-guided stereotactic radiotherapy of prostate bed after radical prostatectomy.

Background and purpose: Magnetic Resonance Imaging (MRI)-guided Stereotactic body radiotherapy (SBRT) treatment to prostate bed after radical prostatectomy has garnered growing interests. The aim of this study is to evaluate intra-fractional anatomic and dose/volume metric variations for patients receiving this treatment. Materials and methods: Nineteen patients who received 30-34 Gy in 5 fractions on a 0.35T MR-Linac were included. Pre- and post-treatment MRIs were acquired for each fraction (total of 75 fractions). The Clinical Target Volume (CTV), bladder, rectum, and rectal wall were contoured on all images. Volumetric changes, Hausdorff distance, Mean Distance to Agreement (MDA), and Dice similarity coefficient (DSC) for each structure were calculated. Median value and Interquartile range (IQR) were recorded. Changes in target coverage and Organ at Risk (OAR) constraints were compared and evaluated using Wilcoxon rank sum tests at a significant level of 0.05. Results: Bladder had the largest volumetric changes, with a median volume increase of 48.9 % (IQR 28.9-76.8 %) and a median MDA of 5.1 mm (IQR 3.4-7.1 mm). Intra-fractional CTV volume remained stable with a median volume change of 1.2 % (0.0-4.8 %). DSC was 0.97 (IQR 0.94-0.99). For the dose/volume metrics, there were no statistically significant changes observed except for an increase in bladder hotspot and a decrease of bladder V32.5 Gy and mean dose. The CTV V95% changed from 99.9 % (IQR 98.8-100 %) to 99.6 % (IQR 93.9-100 %). Conclusion: Despite intra-fractional variations of OARs, CTV coverage remained stable during MRI-guided SBRT treatments for the prostate bed.

MRI-based inter- and intrafraction motion analysis of the pancreatic tail and spleen as preparation for adaptive MRI-guided radiotherapy in neuroblastoma.

BACKGROUND: In pediatric radiotherapy treatment planning of abdominal tumors, dose constraints to the pancreatic tail/spleen are applied to reduce late toxicity. In this study, an analysis of inter- and intrafraction motion of the pancreatic tail/spleen is performed to estimate the potential benefits of online MRI-guided radiotherapy (MRgRT). MATERIALS AND METHODS: Ten randomly selected neuroblastoma patients (median age: 3.4 years), irradiated with intensity-modulated arc therapy at our department (prescription dose: 21.6/1.8 Gy), were retrospectively evaluated for inter- and intrafraction motion of the pancreatic tail/spleen. Three follow-up MRIs (T2- and T1-weighted ± gadolinium) were rigidly registered to a planning CT (pCT), on the vertebrae around the target volume. The pancreatic tail/spleen were delineated on all MRIs and pCT. Interfraction motion was defined as a center of gravity change between pCT and T2-weighted images in left-right (LR), anterior-posterior (AP) and cranial-caudal (CC) direction. For intrafraction motion analysis, organ position on T1-weighted ± gadolinium was compared to T2-weighted. The clinical radiation plan was used to estimate the dose received by the pancreatic tail/spleen for each position. RESULTS: The median (IQR) interfraction motion was minimal in LR/AP, and largest in CC direction; pancreatic tail 2.5 mm (8.9), and spleen 0.9 mm (3.9). Intrafraction motion was smaller, but showed a similar motion pattern (pancreatic tail, CC: 0.4 mm (1.6); spleen, CC: 0.9 mm (2.8)). The differences of Dmean associated with inter- and intrafraction motions ranged from - 3.5 to 5.8 Gy for the pancreatic tail and - 1.2 to 3.0 Gy for the spleen. In 6 out of 10 patients, movements of the pancreatic tail and spleen were highlighted as potentially clinically significant because of ≥ 1 Gy dose constraint violation. CONCLUSION: Inter- and intrafraction organ motion results into unexpected constrain violations in 60% of a randomly selected neuroblastoma cohort, supporting further prospective exploration of MRgRT.