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

HaN-Seg: The head and neck organ-at-risk CT and MR segmentation challenge

BACKGROUND AND PURPOSE

To promote the development of auto-segmentation methods for head and neck (HaN) radiation treatment (RT) planning that exploit the information of computed tomography (CT) and magnetic resonance (MR) imaging modalities, we organized HaN-Seg: The Head and Neck Organ-at-Risk CT and MR Segmentation Challenge.

MATERIALS AND METHODS

The challenge task was to automatically segment 30 organs-at-risk (OARs) of the HaN region in 14 withheld test cases given the availability of 42 publicly available training cases. Each case consisted of one contrast-enhanced CT and one T1-weighted MR image of the HaN region of the same patient, with up to 30 corresponding reference OAR delineation masks. The performance was evaluated in terms of the Dice similarity coefficient (DSC) and 95-percentile Hausdorff distance (HD95), and statistical ranking was applied for each metric by pairwise comparison of the submitted methods using the Wilcoxon signed-rank test.

RESULTS

While 23 teams registered for the challenge, only seven submitted their methods for the final phase. The top-performing team achieved a DSC of 76.9 % and a HD95 of 3.5 mm. All participating teams utilized architectures based on U-Net, with the winning team leveraging rigid MR to CT registration combined with network entry-level concatenation of both modalities.

CONCLUSION

This challenge simulated a real-world clinical scenario by providing non-registered MR and CT images with varying fields-of-view and voxel sizes. Remarkably, the top-performing teams achieved segmentation performance surpassing the inter-observer agreement on the same dataset. These results set a benchmark for future research on this publicly available dataset and on paired multi-modal image segmentation in general.

Three-row MRI receive array with remote circuitry to preserve radiation transparency

Objective.Up to this point, 1.5 T linac-compatible coil array layouts have been restricted to one or two rows of coils because of the desire to place radiation-opaque circuitry adjacent to the coils and outside the window through which the linac beam travels. Such layouts can limit parallel imaging performance. The purpose of this work was to design and build a three-row array in which remotely located circuits permitted a central row of coils while preserving the radiolucent window.Approach.The remote circuits consisted of a phase shifter to cancel the phase introduced by the coaxial link between the circuit and coil, followed by standard components for tuning, matching, detuning, and preamplifier decoupling. Tests were performed to compare prototype single-channel coils with remote or local circuits, which were followed by tests comparing two and three-row arrays .Main results.The single-channel coil with the remote circuit maintained 85% SNR at depths of 30 mm or more as compared to a coil with local circuit. The three-row array provided similar SNR as the two-row array, along with geometry factor advantages for parallel imaging acceleration in the head-foot direction.Significance.The remote circuit strategy could potentially support future MR-linac arrays by allowing greater flexibility in array layout compared to those confined by local circuits, which can be leveraged for parallel imaging acceleration.

Clinical feasibility of deep learning-based synthetic CT images from T2-weighted MR images for cervical cancer patients compared to MRCAT

This work aims to investigate the clinical feasibility of deep learning-based synthetic CT images for cervix cancer, comparing them to MR for calculating attenuation (MRCAT). Patient cohort with 50 pairs of T2-weighted MR and CT images from cervical cancer patients was split into 40 for training and 10 for testing phases. We conducted deformable image registration and Nyul intensity normalization for MR images to maximize the similarity between MR and CT images as a preprocessing step. The processed images were plugged into a deep learning model, generative adversarial network. To prove clinical feasibility, we assessed the accuracy of synthetic CT images in image similarity using structural similarity (SSIM) and mean-absolute-error (MAE) and dosimetry similarity using gamma passing rate (GPR). Dose calculation was performed on the true and synthetic CT images with a commercial Monte Carlo algorithm. Synthetic CT images generated by deep learning outperformed MRCAT images in image similarity by 1.5% in SSIM, and 18.5 HU in MAE. In dosimetry, the DL-based synthetic CT images achieved 98.71% and 96.39% in the GPR at 1% and 1 mm criterion with 10% and 60% cut-off values of the prescription dose, which were 0.9% and 5.1% greater GPRs over MRCAT images.

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.

MRI motion artifact reduction using a conditional diffusion probabilistic model (MAR-CDPM)

BACKGROUND

High-resolution magnetic resonance imaging (MRI) with excellent soft-tissue contrast is a valuable tool utilized for diagnosis and prognosis. However, MRI sequences with long acquisition time are susceptible to motion artifacts, which can adversely affect the accuracy of post-processing algorithms.

PURPOSE

This study proposes a novel retrospective motion correction method named "motion artifact reduction using conditional diffusion probabilistic model" (MAR-CDPM). The MAR-CDPM aimed to remove motion artifacts from multicenter three-dimensional contrast-enhanced T1 magnetization-prepared rapid acquisition gradient echo (3D ceT1 MPRAGE) brain dataset with different brain tumor types.

MATERIALS AND METHODS

This study employed two publicly accessible MRI datasets: one containing 3D ceT1 MPRAGE and 2D T2-fluid attenuated inversion recovery (FLAIR) images from 230 patients with diverse brain tumors, and the other comprising 3D T1-weighted (T1W) MRI images of 148 healthy volunteers, which included real motion artifacts. The former was used to train and evaluate the model using the in silico data, and the latter was used to evaluate the model performance to remove real motion artifacts. A motion simulation was performed in k-space domain to generate an in silico dataset with minor, moderate, and heavy distortion levels. The diffusion process of the MAR-CDPM was then implemented in k-space to convert structure data into Gaussian noise by gradually increasing motion artifact levels. A conditional network with a Unet backbone was trained to reverse the diffusion process to convert the distorted images to structured data. The MAR-CDPM was trained in two scenarios: one conditioning on the time step t $t$ of the diffusion process, and the other conditioning on both t $t$ and T2-FLAIR images. The MAR-CDPM was quantitatively and qualitatively compared with supervised Unet, Unet conditioned on T2-FLAIR, CycleGAN, Pix2pix, and Pix2pix conditioned on T2-FLAIR models. To quantify the spatial distortions and the level of remaining motion artifacts after applying the models, quantitative metrics were reported including normalized mean squared error (NMSE), structural similarity index (SSIM), multiscale structural similarity index (MS-SSIM), peak signal-to-noise ratio (PSNR), visual information fidelity (VIF), and multiscale gradient magnitude similarity deviation (MS-GMSD). Tukey's Honestly Significant Difference multiple comparison test was employed to quantify the difference between the models where p-value < 0.05 $ < 0.05$ was considered statistically significant.

RESULTS

Qualitatively, MAR-CDPM outperformed these methods in preserving soft-tissue contrast and different brain regions. It also successfully preserved tumor boundaries for heavy motion artifacts, like the supervised method. Our MAR-CDPM recovered motion-free in silico images with the highest PSNR and VIF for all distortion levels where the differences were statistically significant (p-values< 0.05 $< 0.05$ ). In addition, our method conditioned on t and T2-FLAIR outperformed (p-values< 0.05 $< 0.05$ ) other methods to remove motion artifacts from the in silico dataset in terms of NMSE, MS-SSIM, SSIM, and MS-GMSD. Moreover, our method conditioned on only t outperformed generative models (p-values< 0.05 $< 0.05$ ) and had comparable performances compared with the supervised model (p-values> 0.05 $> 0.05$ ) to remove real motion artifacts.

CONCLUSIONS

The MAR-CDPM could successfully remove motion artifacts from 3D ceT1 MPRAGE. It is particularly beneficial for elderly who may experience involuntary movements during high-resolution MRI imaging with long acquisition times.

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.

How Imaging Advances Are Defining the Future of Precision Radiation Therapy

Radiation therapy is fundamental in the treatment of cancer. Imaging has always played a central role in radiation oncology. Integrating imaging technology into irradiation devices has increased the precision and accuracy of dose delivery and decreased the toxic effects of the treatment. Although CT has become the standard imaging modality in radiation therapy, the development of recently introduced next-generation imaging techniques has improved diagnostic and therapeutic decision making in radiation oncology. Functional and molecular imaging techniques, as well as other advanced imaging modalities such as SPECT, yield information about the anatomic and biologic characteristics of tumors for the radiation therapy workflow. In clinical practice, they can be useful for characterizing tumor phenotypes, delineating volumes, planning treatment, determining patients' prognoses, predicting toxic effects, assessing responses to therapy, and detecting tumor relapse. Next-generation imaging can enable personalization of radiation therapy based on a greater understanding of tumor biologic factors. It can be used to map tumor characteristics, such as metabolic pathways, vascularity, cellular proliferation, and hypoxia, that are known to define tumor phenotype. It can also be used to consider tumor heterogeneity by highlighting areas at risk for radiation resistance for focused biologic dose escalation, which can impact the radiation planning process and patient outcomes. The authors review the possible contributions of next-generation imaging to the treatment of patients undergoing radiation therapy. In addition, the possible roles of radio(geno)mics in radiation therapy, the limitations of these techniques, and hurdles in introducing them into clinical practice are discussed. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

Evaluating the Hounsfield unit assignment and dose differences between CT-based standard and deep learning-based synthetic CT images for MRI-only radiation therapy of the head and neck

BACKGROUND

Magnetic resonance image only (MRI-only) simulation for head and neck (H&N) radiotherapy (RT) could allow for single-image modality planning with excellent soft tissue contrast. In the MRI-only simulation workflow, synthetic computed tomography (sCT) is generated from MRI to provide electron density information for dose calculation. Bone/air regions produce little MRI signal which could lead to electron density misclassification in sCT. Establishing the dosimetric impact of this error could inform quality assurance (QA) procedures using MRI-only RT planning or compensatory methods for accurate dosimetric calculation.

PURPOSE

The aim of this study was to investigate if Hounsfield unit (HU) voxel misassignments from sCT images result in dosimetric errors in clinical treatment plans.

METHODS

Fourteen H&N cancer patients undergoing same-day CT and 3T MRI simulation were retrospectively identified. MRI was deformed to the CT using multimodal deformable image registration. sCTs were generated from T1w DIXON MRIs using a commercially available deep learning-based generator (MRIplanner, Spectronic Medical AB, Helsingborg, Sweden). Tissue voxel assignment was quantified by creating a CT-derived HU threshold contour. CT/sCT HU differences for anatomical/target contours and tissue classification regions including air (<250 HU), adipose tissue (-250 HU to -51 HU), soft tissue (-50 HU to 199 HU), spongy (200 HU to 499 HU) and cortical bone (>500 HU) were quantified. t-test was used to determine if sCT/CT HU differences were significant. The frequency of structures that had a HU difference > 80 HU (the CT window-width setting for intra-cranial structures) was computed to establish structure classification accuracy. Clinical intensity modulated radiation therapy (IMRT) treatment plans created on CT were retrospectively recalculated on sCT images and compared using the gamma metric.

RESULTS

The mean ratio of sCT HUs relative to CT for air, adipose tissue, soft tissue, spongy and cortical bone were 1.7 ± 0.3, 1.1 ± 0.1, 1.0 ± 0.1, 0.9 ± 0.1 and 0.8 ± 0.1 (value of 1 indicates perfect agreement). T-tests (significance set at t = 0.05) identified differences in HU values for air, spongy and cortical bone in sCT images compared to CT. The structures with sCT/CT HU differences > 80 HU of note were the left and right (L/R) cochlea and mandible (>79% of the tested cohort), the oral cavity (for 57% of the tested cohort), the epiglottis (for 43% of the tested cohort) and the L/R TM joints (occurring > 29% of the cohort). In the case of the cochlea and TM joints, these structures contain dense bone/air interfaces. In the case of the oral cavity and mandible, these structures suffer the additional challenge of being positionally altered in CT versus MRI simulation (due to a non-MR safe immobilizing bite block requiring absence of bite block in MR). Finally, the epiglottis HU assignment suffers from its small size and unstable positionality. Plans recalculated on sCT yielded global/local gamma pass rates of 95.5% ± 2% (3 mm, 3%) and 92.7% ± 2.1% (2 mm, 2%). The largest mean differences in D95, Dmean , D50 dose volume histogram (DVH) metrics for organ-at-risk (OAR) and planning tumor volumes (PTVs) were 2.3% ± 3.0% and 0.7% ± 1.9% respectively.

CONCLUSIONS

In this cohort, HU differences of CT and sCT were observed but did not translate into a reduction in gamma pass rates or differences in average PTV/OAR dose metrics greater than 3%. For sites such as the H&N where there are many tissue interfaces we did not observe large scale dose deviations but further studies using larger retrospective cohorts are merited to establish the variation in sCT dosimetric accuracy which could help to inform QA limits on clinical sCT usage.

The Future of MR-Guided Radiation Therapy

Magnetic resonance image guided radiation therapy (MRIgRT) is a relatively new technology that has already shown outcomes benefits but that has not yet reached its clinical potential. The improved soft-tissue contrast provided with MR, coupled with the immediacy of image acquisition with respect to the treatment, enables expansion of on-table adaptive protocols, currently at a cost of increased treatment complexity, use of human resources, and longer treatment slot times, which translate to decreased throughput. Many approaches are being investigated to meet these challenges, including the development of artificial intelligence (AI) algorithms to accelerate and automate much of the workflow and improved technology that parallelizes workflow tasks, as well as improvements in image acquisition speed and quality. This article summarizes limitations of current available integrated MRIgRT systems and gives an outlook about scientific developments to further expand the use of MRIgRT.

Advances in and applications of imaging and radiomics in head and neck cancer survivorship

PURPOSE OF REVIEW

Radiological imaging is an essential component of head/neck cancer (HNC) care. Advances in imaging modalities (including CT, PET, MRI and ultrasound) and analysis have enhanced our understanding of tumour characteristics and prognosis. However, the application of these methods to evaluate treatment-related toxicities and functional burden is still emerging. This review showcases recent literature applying advanced imaging and radiomics to the assessment and management of sequelae following chemoradiotherapy for HNC.

RECENT FINDINGS

Whilst primarily early-stage/exploratory studies, recent investigations have showcased the feasibility of using radiological imaging, particularly advanced/functional MRI (including diffusion-weighted and dynamic contrast-enhanced MRI), to quantify treatment-induced tissue change in the head/neck musculature, and the clinical manifestation of lymphoedema/fibrosis and dysphagia. Advanced feature analysis and radiomic studies have also begun to give specific focus to the prediction of functional endpoints, including dysphagia, trismus and fibrosis.

SUMMARY

There is demonstrated potential in the use of novel imaging techniques, to help better understand pathophysiology, and improve assessment and treatment of functional deficits following HNC treatment. As larger studies emerge, technologies continue to progress, and pathways to clinical translation are honed, the application of these methods offers an exciting opportunity to transform clinical practices and improve outcomes for HNC survivors.

Implementation of a retrofit MRI simulator for radiation therapy planning

Magnetic resonance imaging (MRI) is being integrated into routine radiation therapy (RT) planning workflows. To reap the benefits of this imaging modality, patient positioning, image acquisition parameters and a quality assurance programme must be considered for accurate use. This paper will report on the implementation of a retrofit MRI Simulator for RT planning, demonstrating an economical, resource efficient solution to improve the accuracy of MRI in this setting.

Accelerating 4D image reconstruction for magnetic resonance-guided radiotherapy

Background and purpose

Physiological motion impacts the dose delivered to tumours and vital organs in external beam radiotherapy and particularly in particle therapy. The excellent soft-tissue demarcation of 4D magnetic resonance imaging (4D-MRI) could inform on intra-fractional motion, but long image reconstruction times hinder its use in online treatment adaptation. Here we employ techniques from high-performance computing to reduce 4D-MRI reconstruction times below two minutes to facilitate their use in MR-guided radiotherapy.

Material and methods

Four patients with pancreatic adenocarcinoma were scanned with a radial stack-of-stars gradient echo sequence on a 1.5T MR-Linac. Fast parallelised open-source implementations of the extra-dimensional golden-angle radial sparse parallel algorithm were developed for central processing unit (CPU) and graphics processing unit (GPU) architectures. We assessed the impact of architecture, oversampling and respiratory binning strategy on 4D-MRI reconstruction time and compared images using the structural similarity (SSIM) index against a MATLAB reference implementation. Scaling and bottlenecks for the different architectures were studied using multi-GPU systems.

Results

All reconstructed 4D-MRI were identical to the reference implementation (SSIM > 0.99). Images reconstructed with overlapping respiratory bins were sharper at the cost of longer reconstruction times. The CPU  + GPU implementation was over 17 times faster than the reference implementation, reconstructing images in 60 ± 1 s and hyper-scaled using multiple GPUs.

Conclusion

Respiratory-resolved 4D-MRI reconstruction times can be reduced using high-performance computing methods for online workflows in MR-guided radiotherapy with potential applications in particle therapy.

AI in MRI: Computational Frameworks for a Faster, Optimized, and Automated Imaging Workflow

Over the last decade, artificial intelligence (AI) has made an enormous impact on a wide range of fields, including science, engineering, informatics, finance, and transportation [...].