Performance of a GPU- and Time-Efficient Pseudo 3D Network for Magnetic Resonance Image Super-Resolution and Motion Artifact Reduction

• URL: http://arxiv.org/abs/2111.14259v5
• Date: Thu, 17 Oct 2024 21:57:15 GMT
• Title: Performance of a GPU- and Time-Efficient Pseudo 3D Network for Magnetic Resonance Image Super-Resolution and Motion Artifact Reduction
• Authors: Hao Li, Jianan Liu, Marianne Schell, Tao Huang, Arne Lauer, Katharina Schregel, Jessica Jesser, Dominik F Vollherbst, Martin Bendszus, Sabine Heiland, Tim Hilgenfeld,
• Abstract summary: Shortening acquisition time and reducing motion artifacts are the most critical challenges in magnetic resonance imaging (MRI) Deep learning-based image restoration has emerged as a promising solution capable of generating high-resolution and motion-artifact-free MRI images. In this study, we adopted a unified 2D deep learning framework for pseudo-3D MRI image super-resolution reconstruction (SRR) and motion artifact reduction (MAR) The accuracy of the network was evaluated through a pixel-wise uncertainty map, and performance was benchmarked against state-of-the-art methods.
• Score: 7.532638301149741
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Shortening acquisition time and reducing motion artifacts are the most critical challenges in magnetic resonance imaging (MRI). Deep learning-based image restoration has emerged as a promising solution capable of generating high-resolution and motion-artifact-free MRI images from low-resolution images acquired with shortened acquisition times or from motion-artifact-corrupted images. To facilitate clinical integration, a time- and GPU-efficient network with reliable accuracy is essential. In this study, we adopted a unified 2D deep learning framework for pseudo-3D MRI image super-resolution reconstruction (SRR) and motion artifact reduction (MAR). The optimal down-sampling factors to optimize the acquisition time in SRR were identified. Training for MAR was performed using publicly available in vivo data, employing a novel standardized method to induce motion artifacts of varying severity in a controlled way. The accuracy of the network was evaluated through a pixel-wise uncertainty map, and performance was benchmarked against state-of-the-art methods. The results demonstrated that the down-sampling factor of 1x1x2 for x2 acceleration and 2x2x2 for x4 acceleration was optimal. For SRR, the proposed TS-RCAN outperformed the 3D networks of mDCSRN and ReCNN, with an improvement of more than 0.01 in SSIM and 1.5 dB in PSNR while reducing GPU load by up to and inference time by up to 90%. For MAR, TS-RCAN exceeded UNet's performance by up to 0.014 in SSIM and 1.48 dB in PSNR. Additionally, TS-RCAN provided uncertainty information, which can be used to estimate the quality of the reconstructed images. TS-RCAN has potential use for SRR and MAR in the clinical setting.

Related papers

• MRI motion correction via efficient residual-guided denoising diffusion probabilistic models [4.304746362090954]
  Methods: Res-MoCoDiff incorporates a novel residual error shifting mechanism in the forward diffusion process.<n>Training employs a combined l1+l2 loss, which promotes image sharpness and reduces pixel-level errors.<n>Results: The proposed method demonstrated superior performance in removing motion artifacts across all motion severity levels.
  arXiv  Detail & Related papers  (2025-05-06T13:02:40Z)
• Rapid Whole Brain Motion-robust Mesoscale In-vivo MR Imaging using Multi-scale Implicit Neural Representation [6.894117592271847]
  This study proposes Rotating-view super-resolution (ROVER)-MRI, an unsupervised framework based on multi-scale implicit neural representations (INR)<n>ROVER-MRI employs coordinate-based neural networks to implicitly and continuously encode image structures at multiple spatial scales.<n> validation on ex-vivo monkey brain data and multiple in-vivo human datasets demonstrates substantially improved reconstruction performance.
  arXiv  Detail & Related papers  (2025-02-12T18:48:12Z)
• A Unified Model for Compressed Sensing MRI Across Undersampling Patterns [69.19631302047569]
  Deep neural networks have shown great potential for reconstructing high-fidelity images from undersampled measurements. Our model is based on neural operators, a discretization-agnostic architecture. Our inference speed is also 1,400x faster than diffusion methods.
  arXiv  Detail & Related papers  (2024-10-05T20:03:57Z)
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction [83.73429628413773]
  Supervised deep learning methods have shown the ability to remove noise in images but require accurate ground truth. We propose a novel self-supervised framework for LDCT, in which ground truth is not required for training the convolutional neural network (CNN) Numerical and experimental results show that the reconstruction accuracy of N2I with sparse views is degrading while the proposed rotational augmented Noise2Inverse (RAN2I) method keeps better image quality over a different range of sampling angles.
  arXiv  Detail & Related papers  (2023-12-19T22:40:51Z)
• Denoising Simulated Low-Field MRI (70mT) using Denoising Autoencoders (DAE) and Cycle-Consistent Generative Adversarial Networks (Cycle-GAN) [68.8204255655161]
  Cycle Consistent Generative Adversarial Network (GAN) is implemented to yield high-field, high resolution, high signal-to-noise ratio (SNR) Magnetic Resonance Imaging (MRI) images. Images were utilized to train a Denoising Autoencoder (DAE) and a Cycle-GAN, with paired and unpaired cases. This work demonstrates the use of a generative deep learning model that can outperform classical DAEs to improve low-field MRI images and does not require image pairs.
  arXiv  Detail & Related papers  (2023-07-12T00:01:00Z)
• DDoS-UNet: Incorporating temporal information using Dynamic Dual-channel UNet for enhancing super-resolution of dynamic MRI [0.27998963147546135]
  Magnetic resonance imaging (MRI) provides high spatial resolution and excellent soft-tissue contrast without using harmful ionising radiation. MRI with high temporal resolution suffers from limited spatial resolution. Deep learning based super-resolution approaches have been proposed to mitigate this trade-off. This research addresses the problem by creating a deep learning model which attempts to learn both spatial and temporal relationships.
  arXiv  Detail & Related papers  (2022-02-10T22:20:58Z)
• High-Resolution Pelvic MRI Reconstruction Using a Generative Adversarial Network with Attention and Cyclic Loss [3.4358954898228604]
  Super-resolution methods have shown excellent performance in accelerating MRI. In some circumstances, it is difficult to obtain high-resolution images even with prolonged scan time. We proposed a novel super-resolution method that uses a generative adversarial network (GAN) with cyclic loss and attention mechanism.
  arXiv  Detail & Related papers  (2021-07-21T10:07:22Z)
• Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives [5.3148259096171175]
  One drawback of MRI is its comparatively slow scanning and reconstruction compared to other image modalities. Deep Neural Networks (DNNs) have been used in sparse MRI reconstruction models to recreate relatively high-quality images. Generative Adversarial Networks (GAN) based methods are proposed to solve fast MRI with enhanced image perceptual quality.
  arXiv  Detail & Related papers  (2021-05-04T23:59:00Z)
• Adaptive Gradient Balancing for UndersampledMRI Reconstruction and Image-to-Image Translation [60.663499381212425]
  We enhance the image quality by using a Wasserstein Generative Adversarial Network combined with a novel Adaptive Gradient Balancing technique. In MRI, our method minimizes artifacts, while maintaining a high-quality reconstruction that produces sharper images than other techniques.
  arXiv  Detail & Related papers  (2021-04-05T13:05:22Z)
• Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution [65.25508348574974]
  We go below the MRI acceleration factors reported by all published papers that reference the original fastMRI challenge. We consider powerful deep learning based image enhancement methods to compensate for the underresolved images. The quality of the reconstructed images surpasses that of the other methods, yielding an MSE of 0.00114, a PSNR of 29.6 dB, and an SSIM of 0.956 at x16 acceleration factor.
  arXiv  Detail & Related papers  (2021-03-04T10:45:01Z)
• ShuffleUNet: Super resolution of diffusion-weighted MRIs using deep learning [47.68307909984442]
  Single Image Super-Resolution (SISR) is a technique aimed to obtain high-resolution (HR) details from one single low-resolution input image. Deep learning extracts prior knowledge from big datasets and produces superior MRI images from the low-resolution counterparts.
  arXiv  Detail & Related papers  (2021-02-25T14:52:23Z)
• Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledge [0.3914676152740142]
  This research presents a super-resolution (SR) MRI reconstruction with prior knowledge based fine-tuning to maximise spatial information. An U-Net based network with loss is trained on a benchmark and fine-tuned using one subject-specific static high resolution MRI as prior knowledge to obtain high resolution dynamic images.
  arXiv  Detail & Related papers  (2021-02-04T16:11:53Z)
• Cine Cardiac MRI Motion Artifact Reduction Using a Recurrent Neural Network [18.433956246011466]
  We propose a recurrent neural network to simultaneously extract both spatial and temporal features from motion-blurred cine cardiac images. The experimental results demonstrate substantially improved image quality on two clinical test datasets.
  arXiv  Detail & Related papers  (2020-06-23T01:55:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.