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.

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.
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.
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.
DCReconNet provides fast and geometrically accurate image reconstruction and has the potential for MRI-guided radiotherapy applications.

Magnetic resonance imaging (MRI) has become an important imaging modality in the field of radiotherapy (RT) in the past decade, especially with the development of various novel MRI and image-guidance techniques. In this review article, we will describe recent developments and discuss the applications of multi-parametric MRI (mpMRI) in RT simulation. In this review, mpMRI refers to a general and loose definition which includes various multi-contrast MRI techniques. Specifically, we will focus on the implementation, challenges, and future directions of mpMRI techniques for RT simulation.

Multiparametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for the diagnosis and treatment planning of various diseases. Machine learning-based artificial intelligence (AI) methods, especially those adopting the deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, and super-resolution. The current availabilities of increasing computational power and fast-improving AI algorithms have empowered numerous computer-based systems for applying mpMRI to disease diagnosis, imaging-guided radiotherapy, patient risk and overall survival time prediction, and the development of advanced quantitative imaging technology for magnetic resonance fingerprinting. However, the wide application of these developed systems in the clinic is still limited by a number of factors, including robustness, reliability, and interpretability. This survey aims to provide an overview for new researchers in the field as well as radiologists with the hope that they can understand the general concepts, main application scenarios, and remaining challenges of AI in mpMRI.

OBJECTIVE: MR-Linac integrates an MRI scanner and a linear accelerator to provide adaptive radiation treatment. Superior tissue contrast and real-time imaging can give the clinicians confidence to reduce the margins of the planning target volume (PTV). The purpose of this study was to verify the dosimetric accuracy of an MR-Linac system in treating a moving target and assess the error with different motion patterns and adaptation methods.
METHODS: We performed an end-to-end test for Elekta Unity (Elekta) using the 4D Dynamic Thorax Phantom (CIRS MRgRT 008Z), comparing the measured and planned dose. The moving phantom had four measurement locations in the tumor, liver, kidney, and spinal cord regions with a PTW30013 ion chamber. For seven different motion patterns, we first acquired simulation CT using a slow-scanning protocol, based on which we generated reference plans. The treatment technique was the standard intensity-modulated radiation therapy (IMRT). We tested both adaptation workflows: the Adapt-to-Position (ATP) and the Adapt-to-Shape (ATS). The three-dimensional (3D) distribution was measured using a diode array phantom (Sun Nuclear Inc.) to check the dose distribution accuracy as part of the routine QA process. We also performed end-to-end tests on a conventional Linac. Finally, we used SPSS Statistics 22.0 (Inc., Chicago, IL, USA) for data analysis.
RESULTS: All pretreatment reference plans and delivered plans had excellent QA results with a better than 95% passing rate of relative gamma analysis (2%/2 mm criteria). The adaptive planning for MR-Linac produced quality plans. The measured dose in the target agreed with the calculated dose.
CONCLUSIONS: The adaptive treatment on the MR-Linac system investigated met the expected performance with tumor motions. The outline of the target could be visualized and accurately contoured on the 3D MR for online planning. Under different motion patterns, the difference between the measured and calculated dose was acceptable clinically.

In this study, we assess the dosimetric qualities and usability of planning for 1.5 T MR-Linac based intensity modulated radiotherapy (MRL-IMRT) for various clinical sites in comparison with IMRT plans using a conventional linac. In total of 30 patients with disease sites in the brain, esophagus, lung, rectum and vertebra were re-planned retrospectively for simulated MRL-IMRT using the Elekta Unity dedicated treatment planning system (TPS) Monaco (v5.40.01). Currently, the step-and-shoot (ss) is the only delivery technique for IMRT available on Unity. All patients were treated on an Elekta Versa HDTM with IMRT using the dynamic multileaf collimator (dMLC) technique, and the plans were designed using Monaco v5.11. For comparison, the same dMLC-IMRT plan was recalculated with the same machine and TPS but only changing the technique to step-and-shoot. The dosimetric qualities of the MRL-IMRT plans, to be evaluated by the Dose Volume Histograms (DVH) metrics, Homogeneity Index and Conformality Index, were compared with the clinical plans. The planning usability was measured by the optimization time and the number of Monitor Units (MUs). Comparing MRL-IMRT with conventional linac based plans, all created plans were clinically equivalent to current clinical practice. However, MRL-IMRT plans had higher dose to skin and larger low dose region of normal tissues. Furthermore, MRL-IMRT plans had significantly reduced optimization time by comparing conventional linac based plans. The number of MUs of MRL-IMRT was increased by 23% compared with ss-IMRT, and no difference from dMLC-IMRT. In conclusion, clinically acceptable plans can be achieved with 1.5 T MR-Linac system for multiple tumor sites. Given the differences in machine characteristics, some minor differences in plan quality were found between MR-Linac plans and current clinical practice and this should be considered in clinical practice.