A hybrid 2D/4D-MRI methodology using simultaneous multislice imaging for radiotherapy guidance

Clinical Applications and Recent Updates of Simultaneous Multi-slice Technique in Accelerated MRI

Simultaneous multi-slice (SMS) is a magnetic resonance imaging (MRI) acceleration technique that utilizes multi-band radio-frequency pulses to simultaneously excite and encode multiple slices. Currently, SMS has been widely studied and applied in the MRI examination to reduce acquisition time, which can significantly improve the examination efficiency and patient throughput. Moreover, SMS technique can improve spatial resolution, which is of great value in disease diagnosis, treatment response monitoring, and prognosis prediction. This review will briefly introduce the technical principles of SMS, and summarize its current clinical applications. More importantly, we will discuss the recent technical progress and future research direction of SMS, hoping to highlight the clinical value and scientific potential of this technique.

Dynamic recurrent inference machines for accelerated MRI-guided radiotherapy of the liver

Recurrent inference machines (RIM), a deep learning model that learns an iterative scheme for reconstructing sparsely sampled MRI, has been shown able to perform well on accelerated 2D and 3D MRI scans, learn from small datasets and generalize well to unseen types of data. Here we propose the dynamic recurrent inference machine (DRIM) for reconstructing sparsely sampled 4D MRI by exploiting correlations between respiratory states. The DRIM was applied to a 4D protocol for MR-guided radiotherapy of liver lesions based on repetitive interleaved coronal 2D multi-slice T2-weighted acquisitions. We demonstrate with an ablation study that the DRIM outperforms the RIM, increasing the SSIM score from about 0.89 to 0.95. The DRIM allowed for an approximately 2.7 times faster scan time than the current clinical protocol with only a slight loss in image sharpness. Correlations between slice locations can also be used, but were found to be of less importance, as were a majority of tested variations in network architecture, as long as the respiratory states are processed by the network. Through cross-validation, the DRIM is also shown to be robust in terms of training data. We further demonstrate a good performance across a large range of subsampling factors, and conclude through an evaluation by a radiation oncologist that reconstructed images of the liver contour and inner structures are of a clinically acceptable standard at acceleration factors 10x and 8x, respectively. Finally, we show that binning the data with respect to respiratory states prior to reconstruction comes at a slight cost to reconstruction quality, but at greater speed of the overall protocol.

Sorting lung tumor volumes from 4D-MRI data using an automatic tumor-based signal reduces stitching artifacts

PURPOSE

To investigate whether a novel signal derived from tumor motion allows more precise sorting of 4D-magnetic resonance (4D-MR) image data than do signals based on normal anatomy, reducing levels of stitching artifacts within sorted lung tumor volumes.

METHODS

(4D-MRI) scans were collected for 10 lung cancer patients using a 2D T2-weighted single-shot turbo spin echo sequence, obtaining 25 repeat frames per image slice. For each slice, a tumor-motion signal was generated using the first principal component of movement in the tumor neighborhood (TumorPC1). Signals were also generated from displacements of the diaphragm (DIA) and upper and lower chest wall (UCW/LCW) and from slice body area changes (BA). Pearson r coefficients of correlations between observed tumor movement and respiratory signals were determined. TumorPC1, DIA, and UCW signals were used to compile image stacks showing each patient's tumor volume in a respiratory phase. Unsorted image stacks were also built for comparison. For each image stack, the presence of stitching artifacts was assessed by measuring the roughness of the compiled tumor surface according to a roughness metric (Rg). Statistical differences in weighted means of Rg between any two signals were determined using an exact permutation test.

RESULTS

The TumorPC1 signal was most strongly correlated with superior-inferior tumor motion, and had significantly higher Pearson r values (median 0.86) than those determined for correlations of UCW, LCW, and BA with superior-inferior tumor motion (p < 0.05). Weighted means of ratios of Rg values in TumorPC1 image stacks to those in unsorted, UCW, and DIA stacks were 0.67, 0.69, and 0.71, all significantly favoring TumorPC1 (p = 0.02-0.05). For other pairs of signals, weighted mean ratios did not differ significantly from one.

CONCLUSION

Tumor volumes were smoother in 3D image stacks compiled using the first principal component of tumor motion than in stacks compiled with signals based on normal anatomy.

Stereotactic body radiotherapy of central lung tumours using a 1.5 T MR-linac: First clinical experiences

Background

MRI-guidance may aid better discrimination between Organs at Risk (OARs) and target volumes in proximity of the mediastinum. We report the first clinical experiences with Stereotactic Body Radiotherapy (SBRT) of (ultra)central lung tumours on a 1.5 T MR-linac.

Materials and Methods

Patients with an (ultra)central lung tumour were selected for MR-linac based SBRT treatment. A T2-weighted 3D sequence MRI acquired during free breathing was used for daily plan adaption. Prior to each fraction, contours of Internal Target Volume (ITV) and OARs were deformably propagated and amended by a radiation oncologist. Inter-fractional changes in volumes and coverage of target volumes as well as doses in OARs were evaluated in offline and online treatment plans.

Results

Ten patients were treated and completed 60 Gy in 8 or 12 fractions. In total 104 fractions were delivered. The median time in the treatment room was 41 min with a median beam-on time of 8.9 min. No grade ≥3 acute toxicity was observed. In two patients, the ITV significantly decreased during treatment (58 % and 37 %, respectively) due to tumour shrinkage. In the other patients, 81 % of online ITVs were within ±15 % of the volume of fraction 1. Comparison with the pre-treatment plan showed that ITV coverage of the online plan was similar in 52 % and improved in 34 % of cases. Adaptation to meet OAR constraints, led to decreased ITV coverage in 14 %.

Conclusions

We describe the workflow for MR-guided Radiotherapy and the feasibility of using 1.5 T MR-linac for SBRT of (ultra) central lung tumours.

Intrafraction Motion Management With MR-Guided Radiation Therapy

High quality radiation therapy requires highly accurate and precise dose delivery. MR-guided radiotherapy (MRgRT), integrating an MRI scanner with a linear accelerator, offers excellent quality images in the treatment room without subjecting patient to ionizing radiation. MRgRT therefore provides a powerful tool for intrafraction motion management. This paper summarizes different sources of intrafraction motion for different disease sites and describes the MR imaging techniques available to visualize and quantify intrafraction motion. It provides an overview of MR guided motion management strategies and of the current technical capabilities of the commercially available MRgRT systems. It describes how these motion management capabilities are currently being used in clinical studies, protocols and provides a future outlook.

Effectiveness of visual biofeedback-guided respiratory-correlated 4D-MRI for radiotherapy guidance on the MR-linac

PURPOSE

Respiratory-correlated 4D-MRI may provide motion characteristics for radiotherapy but is susceptible to irregular breathing. This study investigated the effectiveness of visual biofeedback (VBF) guidance for breathing regularization during 4D-MRI acquisitions on an MR-linac.

METHODS

A simultaneous multislice-accelerated 4D-MRI sequence was interleaved with a one-dimensional respiratory navigator (1D-RNAV) in 10 healthy volunteers on a 1.5T Unity MR-linac (Elekta AB, Stockholm, Sweden). Volunteer-specific breathing amplitudes and periods were derived from the 1D-RNAV signal obtained during unguided 4D-MRI acquisitions. These were used for the guidance waveform, while the 1D-RNAV positions were overlayed as VBF. VBF effectiveness was quantified by calculating the change in coefficient of variation (CV diff $$ {\mathrm{CV}}^{\mathrm{diff}} $$ ) for the breathing amplitude and period, the position SD of end-exhale, end-inhale and midposition locations, and the agreement between the 1D-RNAV signals and guidance waveforms. The 4D-MRI quality was assessed by quantifying amounts of missing data.

RESULTS

VBF had an average latency of 520 ± 2 ms. VBF reduced median breathing variations by 18% to 35% (amplitude) and 29% to 57% (period). Median position SD reductions ranged from -3% to 35% (end-exhale), 29% to 38% (end-inhale), and 25% to 37% (midposition). Average differences between guidance waveforms and 1D-RNAV signals were 0.0 s (period) and +1.7 mm (amplitude). VBF also decreased the median amount of missing data by 11% and 29%.

CONCLUSION

A VBF system was successfully implemented, and all volunteers were able to adapt to the guidance waveform. VBF during 4D-MRI acquisitions drastically reduced breathing variability but had limited effect on missing data in respiratory-correlated 4D-MRI.

Real-time motion management in MRI-guided radiotherapy: Current status and AI-enabled prospects

MRI-guided radiotherapy (MRIgRT) is a highly complex treatment modality, allowing adaptation to anatomical changes occurring from one treatment day to the other (inter-fractional), but also to motion occurring during a treatment fraction (intra-fractional). In this vision paper, we describe the different steps of intra-fractional motion management during MRIgRT, from imaging to beam adaptation, and the solutions currently available both clinically and at a research level. Furthermore, considering the latest developments in the literature, a workflow is foreseen in which motion-induced over- and/or under-dosage is compensated in 3D, with minimal impact to the radiotherapy treatment time. Considering the time constraints of real-time adaptation, a particular focus is put on artificial intelligence (AI) solutions as a fast and accurate alternative to conventional algorithms.

Experimental comparison of linear regression and LSTM motion prediction models for MLC-tracking on an MRI-linac

BACKGROUND

Magnetic resonance imaging (MRI)-guided radiotherapy with multileaf collimator (MLC)-tracking is a promising technique for intra-fractional motion management, achieving high dose conformality without prolonging treatment times. To improve beam-target alignment, the geometric error due to system latency should be reduced by using temporal prediction.

PURPOSE

To experimentally compare linear regression (LR) and long-short-term memory (LSTM) motion prediction models for MLC-tracking on an MRI-linac using multiple patient-derived traces with different complexities.

METHODS

Experiments were performed on a prototype 1.0 T MRI-linac capable of MLC-tracking. A motion phantom was programmed to move a target in superior-inferior (SI) direction according to eight lung cancer patient respiratory motion traces. Target centroid positions were localized from sagittal 2D cine MRIs acquired at 4 Hz using a template matching algorithm. The centroid positions were input to one of four motion prediction models. We used (1) a LSTM network which had been optimized in a previous study on patient data from another cohort (offline LSTM). We also used (2) the same LSTM model as a starting point for continuous re-optimization of its weights during the experiment based on recent motion (offline+online LSTM). Furthermore, we implemented (3) a continuously updated LR model, which was solely based on recent motion (online LR). Finally, we used (4) the last available target centroid without any changes as a baseline (no-predictor). The predictions of the models were used to shift the MLC aperture in real-time. An electronic portal imaging device (EPID) was used to visualize the target and MLC aperture during the experiments. Based on the EPID frames, the root-mean-square error (RMSE) between the target and the MLC aperture positions was used to assess the performance of the different motion predictors. Each combination of motion trace and prediction model was repeated twice to test stability, for a total of 64 experiments.

RESULTS

The end-to-end latency of the system was measured to be (389 ± 15) ms and was successfully mitigated by both LR and LSTM models. The offline+online LSTM was found to outperform the other models for all investigated motion traces. It obtained a median RMSE over all traces of (2.8 ± 1.3) mm, compared to the (3.2 ± 1.9) mm of the offline LSTM, the (3.3 ± 1.4) mm of the online LR and the (4.4 ± 2.4) mm when using the no-predictor. According to statistical tests, differences were significant (p-value <0.05) among all models in a pair-wise comparison, but for the offline LSTM and online LR pair. The offline+online LSTM was found to be more reproducible than the offline LSTM and the online LR with a maximum deviation in RMSE between two measurements of 10%.

CONCLUSIONS

This study represents the first experimental comparison of different prediction models for MRI-guided MLC-tracking using several patient-derived respiratory motion traces. We have shown that among the investigated models, continuously re-optimized LSTM networks are the most promising to account for the end-to-end system latency in MRI-guided radiotherapy with MLC-tracking.

Accelerated respiratory-resolved 4D-MRI with separable spatio-temporal neural networks

BACKGROUND

Respiratory-resolved four-dimensional magnetic resonance imaging (4D-MRI) provides essential motion information for accurate radiation treatments of mobile tumors. However, obtaining high-quality 4D-MRI suffers from long acquisition and reconstruction times.

PURPOSE

To develop a deep learning architecture to quickly acquire and reconstruct high-quality 4D-MRI, enabling accurate motion quantification for MRI-guided radiotherapy (MRIgRT).

METHODS

A small convolutional neural network called MODEST is proposed to reconstruct 4D-MRI by performing a spatial and temporal decomposition, omitting the need for 4D convolutions to use all the spatio-temporal information present in 4D-MRI. This network is trained on undersampled 4D-MRI after respiratory binning to reconstruct high-quality 4D-MRI obtained by compressed sensing reconstruction. The network is trained, validated, and tested on 4D-MRI of 28 lung cancer patients acquired with a T1-weighted golden-angle radial stack-of-stars (GA-SOS) sequence. The 4D-MRI of 18, 5, and 5 patients were used for training, validation, and testing. Network performances are evaluated on image quality measured by the structural similarity index (SSIM) and motion consistency by comparing the position of the lung-liver interface on undersampled 4D-MRI before and after respiratory binning. The network is compared to conventional architectures such as a U-Net, which has 30 times more trainable parameters.

RESULTS

MODEST can reconstruct high-quality 4D-MRI with higher image quality than a U-Net, despite a thirty-fold reduction in trainable parameters. High-quality 4D-MRI can be obtained using MODEST in approximately 2.5 min, including acquisition, processing, and reconstruction.

CONCLUSION

High-quality accelerated 4D-MRI can be obtained using MODEST, which is particularly interesting for MRIgRT.

Multi-parametric MRI for radiotherapy simulation

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.

Rapid distortion correction enables accurate magnetic resonance imaging-guided real-time adaptive radiotherapy

Background and purpose

Magnetic resonance imaging (MRI)-Linac systems combine simultaneous MRI with radiation delivery, allowing treatments to be guided by anatomically detailed, real-time images. However, MRI can be degraded by geometric distortions that cause uncertainty between imaged and actual anatomy. In this work, we develop and integrate a real-time distortion correction method that enables accurate real-time adaptive radiotherapy.

Materials and methods

The method was based on the pre-treatment calculation of distortion and the rapid correction of intrafraction images. A motion phantom was set up in an MRI-Linac at isocentre (P₀ ), the edge (P ₁) and just outside (P ₂) the imaging volume. The target was irradiated and tracked during real-time adaptive radiotherapy with and without the distortion correction. The geometric tracking error and latency were derived from the measurements of the beam and target positions in the EPID images.

Results

Without distortion correction, the mean geometric tracking error was 1.3 mm at P ₁ and 3.1 mm at P ₂. When distortion correction was applied, the error was reduced to 1.0 mm at P ₁ and 1.1 mm at P ₂. The corrected error was similar to an error of 0.9 mm at P₀ where the target was unaffected by distortion indicating that this method has accurately accounted for distortion during tracking. The latency was 319 ± 12 ms without distortion correction and 335 ± 34 ms with distortion correction.

Conclusions

We have demonstrated a real-time distortion correction method that maintains accurate radiation delivery to the target, even at treatment locations with large distortion.