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

Waddington, David E. J.; Hindley, Nick; Koonjoo, Néha; Chiu, Christopher; Reynolds, Tess; Liu, Paul Z Y; Zhu, Bin; Bhutto, Danyal; Paganelli, Chiara; Keall, P.; Rosen, Matthew S.

doi:10.1002/mp.16224

Cited by 9 publications

(4 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, phantom, volunteer brain, and patient lung images were acquired with standard Cartesian TSE sequences. Non‐Cartesian sequences (e.g., spiral and radial sampling) have recently shown promise for dynamic tumor tracking for radiotherapy 52,63,64 . However, eddy currents are a significant additional challenge for non‐Cartesian acquisitions, often deviating k‐space trajectories and causing significant image artifact 30,65 .…”

Section: Discussionmentioning

confidence: 99%

“…Non‐Cartesian sequences (e.g., spiral and radial sampling) have recently shown promise for dynamic tumor tracking for radiotherapy. 52 , 63 , 64 However, eddy currents are a significant additional challenge for non‐Cartesian acquisitions, often deviating k‐space trajectories and causing significant image artifact. 30 , 65 In the future, we will investigate the application of DCReconNet to non‐Cartesian reconstruction and distortion‐correction problems.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Distortion‐corrected image reconstruction with deep learning on an MRI‐Linac

Shan

Gao

Liu

et al. 2023

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Distortion‐corrected image reconstruction with deep learning on an MRI‐Linac

Shan

Gao

Liu

et al. 2023

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, for most of these accelerated MRI acquisition techniques, the gain in acquisition time results in longer reconstruction times. Fortunately, machine learning approaches that transfer computational processing to offline training of a neural network 99–102 may overcome long reconstruction times of accelerated acquisitions. In the future, latency for treatment planning and image guidance could be further reduced through use of patient representations composited from models that extract various representative states and their probabilistic variations.…”

Section: Image Guidancementioning

confidence: 99%

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

Goodburn

Philippens

Lefebvre

et al. 2022

Magnetic Resonance in Med

View full text Add to dashboard Cite

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.

show abstract

“…Three-dimensional MRI with adequate spatial resolution in real-time is currently challenging (Bertholet et al 2019), which compromises target tracking efficiency and accuracy (Glitzner et al 2015, Bourque et al 2018. To overcome the challenges, several studies have reported advanced 3D MRI reconstruction, including radial trajectory k-space reconstruction (Zhu et al 2018, Goldman-Yassen et al 2022, Waddington et al 2023 and hybrid methodologies leveraging both k-space and image domains (Shen et al 2022). Although these efforts have reduced reconstruction times while preserving MRI quality, practical application is still limited due to the reconstruction time lasting several hundred milliseconds per patient.…”

Section: Introductionmentioning

confidence: 99%

Inter-scanner super-resolution of 3D cine MRI using a transfer-learning network for MRgRT

Yoon,

Chun,

Kiser

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective. Deep-learning networks for super-resolution (SR) reconstruction enhance the spatial-resolution of 3D magnetic resonance imaging (MRI) for MR-guided radiotherapy (MRgRT). However, variations between MRI scanners and patients impact the quality of SR for real-time 3D low-resolution (LR) cine MRI. In this study, we present a personalized super-resolution (psSR) network that incorporates transfer-learning to overcome the challenges in inter-scanner SR of 3D cine MRI.Approach: Development of the proposed psSR network comprises two-stages: 1) a cohort-specific SR (csSR) network using clinical patient datasets, and 2) a psSR network using transfer-learning to target datasets. The csSR network was developed by training on breath-hold and respiratory-gated high-resolution (HR) 3D MRIs and their k-space down-sampled LR MRIs from 53 thoracoabdominal patients scanned at 1.5 T. The psSR network was developed through transfer-learning to retrain the csSR network using a single breath-hold HR MRI and a corresponding 3D cine MRI from 5 healthy volunteers scanned at 0.55 T. Image quality was evaluated using the peak-signal-noise-ratio (PSNR) and the structure-similarity-index-measure (SSIM). The clinical feasibility was assessed by liver contouring on the psSR MRI using an auto-segmentation network and quantified using the Dice-similarity-coefficient (DSC).Results. Mean PSNR and SSIM values of psSR MRIs were increased by 57.2% (13.8 to 21.7) and 94.7% (0.38 to 0.74) compared to cine MRIs, with the reference 0.55 T breath-hold HR MRI. In the contour evaluation, DSC was increased by 15% (0.79 to 0.91). Average time consumed for transfer-learning was 90 s, psSR was 4.51 ms per volume, and auto-segmentation was 210 ms, respectively.Significance. The proposed psSR reconstruction substantially increased image and segmentation quality of cine MRI in an average of 215 ms across the scanners and patients with less than 2 minutes of prerequisite transfer-learning. This approach would be effective in overcoming cohort- and scanner-dependency of deep-learning for MRgRT.

show abstract

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

Cited by 9 publications

References 84 publications

Distortion‐corrected image reconstruction with deep learning on an MRI‐Linac

Distortion‐corrected image reconstruction with deep learning on an MRI‐Linac

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

Inter-scanner super-resolution of 3D cine MRI using a transfer-learning network for MRgRT

Contact Info

Product

Resources

About