Super-resolution neural networks improve the spatiotemporal resolution of adaptive MRI-guided radiation therapy

BACKGROUND

Magnetic resonance imaging (MRI) offers superb non-invasive, soft tissue imaging of the human body. However, extensive data sampling requirements severely restrict the spatiotemporal resolution achievable with MRI. This limits the modality's utility in real-time guidance applications, particularly for the rapidly growing MRI-guided radiation therapy approach to cancer treatment. Recent advances in artificial intelligence (AI) could reduce the trade-off between the spatial and the temporal resolution of MRI, thus increasing the clinical utility of the imaging modality.

METHODS

We trained deep learning-based super-resolution neural networks to increase the spatial resolution of real-time MRI. We developed a framework to integrate neural networks directly onto a 1.0 T MRI-linac enabling real-time super-resolution imaging. We integrated this framework with the targeting system of the MRI-linac to demonstrate real-time beam adaptation with super-resolution-based imaging. We tested the integrated system using large publicly available datasets, healthy volunteer imaging, phantom imaging, and beam tracking experiments using bicubic interpolation as a baseline comparison.

RESULTS

Deep learning-based super-resolution increases the spatial resolution of real-time MRI across a variety of experiments, offering measured performance benefits compared to bicubic interpolation. The temporal resolution is not compromised as measured by a real-time adaptation latency experiment. These two effects, an increase in the spatial resolution with a negligible decrease in the temporal resolution, leads to a net increase in the spatiotemporal resolution.

CONCLUSIONS

Deployed super-resolution neural networks can increase the spatiotemporal resolution of real-time MRI. This has applications to domains such as MRI-guided radiation therapy and interventional procedures.

The MANGO study: a prospective investigation of oxygen enhanced and blood-oxygen level dependent MRI as imaging biomarkers of hypoxia in glioblastoma

Background

Glioblastoma (GBM) is the most aggressive type of brain cancer, with a 5-year survival rate of ~5% and most tumours recurring locally within months of first-line treatment. Hypoxia is associated with worse clinical outcomes in GBM, as it leads to localized resistance to radiotherapy and subsequent tumour recurrence. Current standard of care treatment does not account for tumour hypoxia, due to the challenges of mapping tumour hypoxia in routine clinical practice. In this clinical study, we aim to investigate the role of oxygen enhanced (OE) and blood-oxygen level dependent (BOLD) MRI as non-invasive imaging biomarkers of hypoxia in GBM, and to evaluate their potential role in dose-painting radiotherapy planning and treatment response assessment.

Methods

The primary endpoint is to evaluate the quantitative and spatial correlation between OE and BOLD MRI measurements and [18F]MISO values of uptake in the tumour. The secondary endpoints are to evaluate the repeatability of MRI biomarkers of hypoxia in a test-retest study, to estimate the potential clinical benefits of using MRI biomarkers of hypoxia to guide dose-painting radiotherapy, and to evaluate the ability of MRI biomarkers of hypoxia to assess treatment response. Twenty newly diagnosed GBM patients will be enrolled in this study. Patients will undergo standard of care treatment while receiving additional OE/BOLD MRI and [18F]MISO PET scans at several timepoints during treatment. The ability of OE/BOLD MRI to map hypoxic tumour regions will be evaluated by assessing spatial and quantitative correlations with areas of hypoxic tumour identified via [18F]MISO PET imaging.

Discussion

MANGO (Magnetic resonance imaging of hypoxia for radiation treatment guidance in glioblastoma multiforme) is a diagnostic/prognostic study investigating the role of imaging biomarkers of hypoxia in GBM management. The study will generate a large amount of longitudinal multimodal MRI and PET imaging data that could be used to unveil dynamic changes in tumour physiology that currently limit treatment efficacy, thereby providing a means to develop more effective and personalised treatments.

Comparison between [68Ga]Ga-PSMA-617 and [18F]FET PET as Imaging Biomarkers in Adult Recurrent Glioblastoma

The aim of this prospective clinical study was to evaluate the potential of the prostate specific membrane antigen (PSMA) targeting ligand, [68Ga]-PSMA-Glu-NH-CO-NH-Lys-2-naphthyl-L-Ala-cyclohexane-DOTA ([68Ga]Ga-PSMA-617) as a positron emission tomography (PET) imaging biomarker in recurrent glioblastoma patients. Patients underwent [68Ga]Ga-PSMA-617 and O-(2-[18F]-fluoroethyl)-L-tyrosine ([18F]FET) PET scans on two separate days. [68Ga]Ga-PSMA-617 tumour selectivity was assessed by comparing tumour volume delineation and by assessing the intra-patient correlation between tumour uptake on [68Ga]Ga-PSMA-617 and [18F]FET PET images. [68Ga]Ga-PSMA-617 tumour specificity was evaluated by comparing its tumour-to-brain ratio (TBR) with [18F]FET TBR and its tumour volume with the magnetic resonance imaging (MRI) contrast-enhancing (CE) tumour volume. Ten patients were recruited in this study. [68Ga]Ga-PSMA-617-avid tumour volume was larger than the [18F]FET tumour volume (p = 0.063). There was a positive intra-patient correlation (median Pearson r = 0.51; p < 0.0001) between [68Ga]Ga-PSMA-617 and [18F]FET in the tumour volume. [68Ga]Ga-PSMA-617 had significantly higher TBR (p = 0.002) than [18F]FET. The [68Ga]Ga-PSMA-617-avid tumour volume was larger than the CE tumour volume (p = 0.0039). Overall, accumulation of [68Ga]-Ga-PSMA-617 beyond [18F]FET-avid tumour regions suggests the presence of neoangiogenesis in tumour regions that are not overly metabolically active yet. Higher tumour specificity suggests that [68Ga]-Ga-PSMA-617 could be a better imaging biomarker for recurrent tumour delineation and secondary treatment planning than [18F]FET and CE MRI.

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.

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.

Real-time radial reconstruction with domain transform manifold learning for MRI-guided radiotherapy

BACKGROUND

MRI-guidance techniques that dynamically adapt radiation beams to follow tumor motion in real time will lead to more accurate cancer treatments and reduced collateral healthy tissue damage. The gold-standard for reconstruction of undersampled MR data is compressed sensing (CS) which is computationally slow and limits the rate that images can be available for real-time adaptation.

PURPOSE

Once trained, neural networks can be used to accurately reconstruct raw MRI data with minimal latency. Here, we test the suitability of deep-learning-based image reconstruction for real-time tracking applications on MRI-Linacs.

METHODS

We use automated transform by manifold approximation (AUTOMAP), a generalized framework that maps raw MR signal to the target image domain, to rapidly reconstruct images from undersampled radial k-space data. The AUTOMAP neural network was trained to reconstruct images from a golden-angle radial acquisition, a benchmark for motion-sensitive imaging, on lung cancer patient data and generic images from ImageNet. Model training was subsequently augmented with motion-encoded k-space data derived from videos in the YouTube-8M dataset to encourage motion robust reconstruction.

RESULTS

AUTOMAP models fine-tuned on retrospectively acquired lung cancer patient data reconstructed radial k-space with equivalent accuracy to CS but with much shorter processing times. Validation of motion-trained models with a virtual dynamic lung tumor phantom showed that the generalized motion properties learned from YouTube lead to improved target tracking accuracy.

CONCLUSION

AUTOMAP can achieve real-time, accurate reconstruction of radial data. These findings imply that neural-network-based reconstruction is potentially superior to alternative approaches for real-time image guidance applications.

The future of MRI in radiation therapy: Challenges and opportunities for the MR community

Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim of this treatment is to achieve tumor control through the delivery of ionizing radiation while preserving healthy tissues for minimal radiation toxicity. Because radiation therapy relies on accurate localization of the target and surrounding tissues, imaging plays a crucial role throughout the treatment chain. In the treatment planning phase, radiological images are essential for defining target volumes and organs-at-risk, as well as providing elemental composition (e.g., electron density) information for radiation dose calculations. At treatment, onboard imaging informs patient setup and could be used to guide radiation dose placement for sites affected by motion. Imaging is also an important tool for treatment response assessment and treatment plan adaptation. MRI, with its excellent soft tissue contrast and capacity to probe functional tissue properties, holds great untapped potential for transforming treatment paradigms in radiation therapy. The MR in Radiation Therapy ISMRM Study Group was established to provide a forum within the MR community to discuss the unmet needs and fuel opportunities for further advancement of MRI for radiation therapy applications. During the summer of 2021, the study group organized its first virtual workshop, attended by a diverse international group of clinicians, scientists, and clinical physicists, to explore our predictions for the future of MRI in radiation therapy for the next 25 years. This article reviews the main findings from the event and considers the opportunities and challenges of reaching our vision for the future in this expanding field.

Integrated MRI-guided radiotherapy - opportunities and challenges

MRI can help to categorize tissues as malignant or non-malignant both anatomically and functionally, with a high level of spatial and temporal resolution. This non-invasive imaging modality has been integrated with radiotherapy in devices that can differentially target the most aggressive and resistant regions of tumours. The past decade has seen the clinical deployment of treatment devices that combine imaging with targeted irradiation, making the aspiration of integrated MRI-guided radiotherapy (MRIgRT) a reality. The two main clinical drivers for the adoption of MRIgRT are the ability to image anatomical changes that occur before and during treatment in order to adapt the treatment approach, and to image and target the biological features of each tumour. Using motion management and biological targeting, the radiation dose delivered to the tumour can be adjusted during treatment to improve the probability of tumour control, while simultaneously reducing the radiation delivered to non-malignant tissues, thereby reducing the risk of treatment-related toxicities. The benefits of this approach are expected to increase survival and quality of life. In this Review, we describe the current state of MRIgRT, and the opportunities and challenges of this new radiotherapy approach.

An investigation of the conformity, feasibility, and expected clinical benefits of multiparametric MRI-guided dose painting radiotherapy in glioblastoma

Background

New technologies developed to improve survival outcomes for glioblastoma (GBM) continue to have limited success. Recently, image-guided dose painting (DP) radiotherapy has emerged as a promising strategy to increase local control rates. In this study, we evaluate the practical application of a multiparametric MRI model of glioma infiltration for DP radiotherapy in GBM by measuring its conformity, feasibility, and expected clinical benefits against standard of care treatment.

Methods

Maps of tumor probability were generated from perfusion/diffusion MRI data from 17 GBM patients via a previously developed model of GBM infiltration. Prescriptions for DP were linearly derived from tumor probability maps and used to develop dose optimized treatment plans. Conformity of DP plans to dose prescriptions was measured via a quality factor. Feasibility of DP plans was evaluated by dose metrics to target volumes and critical brain structures. Expected clinical benefit of DP plans was assessed by tumor control probability. The DP plans were compared to standard radiotherapy plans.

Results

The conformity of the DP plans was >90%. Compared to the standard plans, DP (1) did not affect dose delivered to organs at risk; (2) increased mean and maximum dose and improved minimum dose coverage for the target volumes; (3) reduced minimum dose within the radiotherapy treatment margins; (4) improved local tumor control probability within the target volumes for all patients.

Conclusions

A multiparametric MRI model of GBM infiltration can enable conformal, feasible, and potentially beneficial dose painting radiotherapy plans.

High-sensitivity in vivo contrast for ultra-low field magnetic resonance imaging using superparamagnetic iron oxide nanoparticles

Magnetic resonance imaging (MRI) scanners operating at ultra-low magnetic fields (ULF; <10 mT) are uniquely positioned to reduce the cost and expand the clinical accessibility of MRI. A fundamental challenge for ULF MRI is obtaining high-contrast images without compromising acquisition sensitivity to the point that scan times become clinically unacceptable. Here, we demonstrate that the high magnetization of superparamagnetic iron oxide nanoparticles (SPIONs) at ULF makes possible relaxivity- and susceptibility-based effects unachievable with conventional contrast agents (CAs). We leverage these effects to acquire high-contrast images of SPIONs in a rat model with ULF MRI using short scan times. This work overcomes a key limitation of ULF MRI by enabling in vivo imaging of biocompatible CAs. These results open a new clinical translation pathway for ULF MRI and have broader implications for disease detection with low-field portable MRI scanners.

An Overhauser-enhanced-MRI platform for dynamic free radical imaging in vivo

Overhauser-enhanced MRI (OMRI) is an electron-proton double-resonance imaging technique of interest for its ability to non-invasively measure the concentration and distribution of free radicals. In vivo OMRI experiments are typically undertaken at ultra-low magnetic field (ULF), as both RF power absorption and penetration issues-a consequence of the high resonance frequencies of electron spins-are mitigated. However, working at ULF causes a drastic reduction in MRI sensitivity. Here, we report on the design, construction and performance of an OMRI platform optimized for high NMR sensitivity and low RF power absorbance, exploring challenges unique to probe design in the ULF regime. We use this platform to demonstrate dynamic imaging of TEMPOL in a rat model. The work presented here demonstrates improved speed and sensitivity of in vivo OMRI, extending the scope of OMRI to the study of dynamic processes such as metabolism.

Nanodiamond-enhanced MRI via in situ hyperpolarization

Nanodiamonds are of interest as nontoxic substrates for targeted drug delivery and as highly biostable fluorescent markers for cellular tracking. Beyond optical techniques, however, options for noninvasive imaging of nanodiamonds in vivo are severely limited. Here, we demonstrate that the Overhauser effect, a proton–electron polarization transfer technique, can enable high-contrast magnetic resonance imaging (MRI) of nanodiamonds in water at room temperature and ultra-low magnetic field. The technique transfers spin polarization from paramagnetic impurities at nanodiamond surfaces to ¹H spins in the surrounding water solution, creating MRI contrast on-demand. We examine the conditions required for maximum enhancement as well as the ultimate sensitivity of the technique. The ability to perform continuous in situ hyperpolarization via the Overhauser mechanism, in combination with the excellent in vivo stability of nanodiamond, raises the possibility of performing noninvasive in vivo tracking of nanodiamond over indefinitely long periods of time.

Hyperpolarized magnetic resonance imaging can enhance imaging contrast by orders of magnitude, but applications are limited by the thermal relaxation of hyperpolarized states. Here, Waddington et al. demonstrate the on-demand hyperpolarization of hydrogen spins through the Overhauser effect with nanodiamonds.

Hyperpolarized Nanodiamond Surfaces

The widespread use of nanodiamond as a biomedical platform for drug-delivery, imaging, and subcellular tracking applications stems from its nontoxicity and unique quantum mechanical properties. Here, we extend this functionality to the domain of magnetic resonance, by demonstrating that the intrinsic electron spins on the nanodiamond surface can be used to hyperpolarize adsorbed liquid compounds at low fields and room temperature. By combining relaxation measurements with hyperpolarization, spins on the surface of the nanodiamond can be distinguished from those in the bulk liquid. These results are likely of use in signaling the controlled release of pharmaceutical payloads.

Low-Cost High-Performance MRI

Magnetic Resonance Imaging (MRI) is unparalleled in its ability to visualize anatomical structure and function non-invasively with high spatial and temporal resolution. Yet to overcome the low sensitivity inherent in inductive detection of weakly polarized nuclear spins, the vast majority of clinical MRI scanners employ superconducting magnets producing very high magnetic fields. Commonly found at 1.5-3 tesla (T), these powerful magnets are massive and have very strict infrastructure demands that preclude operation in many environments. MRI scanners are costly to purchase, site, and maintain, with the purchase price approaching $1 M per tesla (T) of magnetic field. We present here a remarkably simple, non-cryogenic approach to high-performance human MRI at ultra-low magnetic field, whereby modern under-sampling strategies are combined with fully-refocused dynamic spin control using steady-state free precession techniques. At 6.5 mT (more than 450 times lower than clinical MRI scanners) we demonstrate (2.5 × 3.5 × 8.5) mm(3) imaging resolution in the living human brain using a simple, open-geometry electromagnet, with 3D image acquisition over the entire brain in 6 minutes. We contend that these practical ultra-low magnetic field implementations of MRI (<10 mT) will complement traditional MRI, providing clinically relevant images and setting new standards for affordable (<$50,000) and robust portable devices.

The effect of (NH4)2Sx passivation on the (311)A GaAs surface and its use in AlGaAs/GaAs heterostructure devices

We have studied the efficacy of (NH4)2Sx surface passivation on the (311)A GaAs surface. We report XPS studies of simultaneously-grown (311)A and (100) heterostructures showing that the (NH4)2Sx solution removes surface oxide and sulfidizes both surfaces. Passivation is often characterized using photoluminescence measurements; we show that while (NH4)2Sx treatment gives a 40-60 ×  increase in photoluminescence intensity for the (100) surface, an increase of only 2-3 ×  is obtained for the (311)A surface. A corresponding lack of reproducible improvement in the gate hysteresis of (311)A heterostructure transistor devices made with the passivation treatment performed immediately prior to gate deposition is also found. We discuss possible reasons why sulfur passivation is ineffective for (311)A GaAs, and propose alternative strategies for passivation of this surface.