Coarse-Super-Resolution-Fine Network (CoSF-Net): A Unified End-to-End Neural Network for 4D-MRI with Simultaneous Motion Estimation and Super-Resolution

• URL: http://arxiv.org/abs/2211.11144v1
• Date: Mon, 21 Nov 2022 01:42:51 GMT
• Title: Coarse-Super-Resolution-Fine Network (CoSF-Net): A Unified End-to-End Neural Network for 4D-MRI with Simultaneous Motion Estimation and Super-Resolution
• Authors: Shaohua Zhi, Yinghui Wang, Haonan Xiao, Ti Bai, Hong Ge, Bing Li, Chenyang Liu, Wen Li, Tian Li, Jing Cai
• Abstract summary: We develop a novel deep learning framework called the coarse-super-resolution-fine network (CoSF-Net) to achieve simultaneous motion estimation and excavating super-resolution in a unified model. Compared with existing networks and three state-of-the-art conventional algorithms, CoSF-Net not only accurately estimated the deformable vector fields between the respiratory phases of 4D-MRI but also simultaneously improved the spatial resolution of 4D-MRI with enhanced anatomic features.
• Score: 21.75329634476446
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Four-dimensional magnetic resonance imaging (4D-MRI) is an emerging technique for tumor motion management in image-guided radiation therapy (IGRT). However, current 4D-MRI suffers from low spatial resolution and strong motion artifacts owing to the long acquisition time and patients' respiratory variations; these limitations, if not managed properly, can adversely affect treatment planning and delivery in IGRT. Herein, we developed a novel deep learning framework called the coarse-super-resolution-fine network (CoSF-Net) to achieve simultaneous motion estimation and super-resolution in a unified model. We designed CoSF-Net by fully excavating the inherent properties of 4D-MRI, with consideration of limited and imperfectly matched training datasets. We conducted extensive experiments on multiple real patient datasets to verify the feasibility and robustness of the developed network. Compared with existing networks and three state-of-the-art conventional algorithms, CoSF-Net not only accurately estimated the deformable vector fields between the respiratory phases of 4D-MRI but also simultaneously improved the spatial resolution of 4D-MRI with enhanced anatomic features, yielding 4D-MR images with high spatiotemporal resolution.

Related papers

• 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)
• Generalized super-resolution 4D Flow MRI $\unicode{x2013}$ using ensemble learning to extend across the cardiovascular system [28.516235368817586]
  The aim of our study was to explore the generalizability of SR 4D Flow MRI using a combination of heterogeneous training sets and dedicated ensemble learning. Results show that both bagging and stacking ensembling enhance SR performance across domains, accurately predicting high-resolution velocities from low-resolution input data in-silico. In conclusion, our work presents a viable approach for generalized SR 4D Flow MRI, with ensemble learning extending utility across various clinical areas of interest.
  arXiv  Detail & Related papers  (2023-11-20T14:55:40Z)
• Robust Depth Linear Error Decomposition with Double Total Variation and Nuclear Norm for Dynamic MRI Reconstruction [15.444386058967579]
  There are still problems with dynamic MRI k-space reconstruction based on Compressed Sensing (CS) In this paper, we propose a novel robust lowrank dynamic MRI reconstruction optimization model via highly under-sampled Fourier Transform (DFT) Experiments on dynamic MRI data demonstrate the superior performance proposed method in terms of both reconstruction accuracy and time complexity.
  arXiv  Detail & Related papers  (2023-10-23T13:34:59Z)
• Implicit neural representations for unsupervised super-resolution and denoising of 4D flow MRI [1.207455285737927]
  Our study investigates SIRENs for time-varying 3-directional velocity fields measured in the aorta by 4D flow MRI. We trained our method on voxel coordinates and benchmarked our approach using synthetic measurements and a real 4D flow MRI scan. Our optimized SIREN architecture outperformed state-of-the-art techniques, producing denoised and super-resolved velocity fields from clinical data.
  arXiv  Detail & Related papers  (2023-02-24T08:42:04Z)
• Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution Reconstruction [68.80715727288514]
  We show how to unfold an iterative MGDUN algorithm into a novel model-guided deep unfolding network by taking the MRI observation matrix. In this paper, we propose a novel Model-Guided interpretable Deep Unfolding Network (MGDUN) for medical image SR reconstruction.
  arXiv  Detail & Related papers  (2022-09-15T03:58:30Z)
• Predicting 4D Liver MRI for MR-guided Interventions [2.9699476315275772]
  Organ motion poses an unresolved challenge in image-guided interventions. We propose a novel approach for real-time, high-resolution 4D MRI with large fields of view. We show that small training sizes with short acquisition times down to 2min can already achieve promising results.
  arXiv  Detail & Related papers  (2022-02-25T11:34:25Z)
• Non-invasive hemodynamic analysis for aortic regurgitation using computational fluid dynamics and deep learning [2.150638298922378]
  Changes in cardiovascular hemodynamics are closely related to the development of aortic regurgitation (AR) These metrics can be non-invasively obtained using four-dimensional (4D) flow magnetic resonance imaging (MRI) However, insufficient resolution often results from limitations in 4D flow MRI and complex AR hemodynamics. To address this, computational fluid dynamics simulations were transformed into synthetic 4D flow MRI data and used to train a variety of neural networks.
  arXiv  Detail & Related papers  (2021-11-23T05:19:42Z)
• 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)
• 4D Spatio-Temporal Convolutional Networks for Object Position Estimation in OCT Volumes [69.62333053044712]
  3D convolutional neural networks (CNNs) have shown promising performance for pose estimation of a marker object using single OCT images. We extend 3D CNNs to 4D-temporal CNNs to evaluate the impact of additional temporal information for marker object tracking.
  arXiv  Detail & Related papers  (2020-07-02T12:02:20Z)
• 4D Deep Learning for Multiple Sclerosis Lesion Activity Segmentation [49.32653090178743]
  We investigate whether extending this problem to full 4D deep learning using a history of MRI volumes can improve performance. We find that our proposed architecture outperforms previous approaches with a lesion-wise true positive rate of 0.84 at a lesion-wise false positive rate of 0.19.
  arXiv  Detail & Related papers  (2020-04-20T11:41:01Z)
• Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE) [50.65891535040752]
  We propose a diffusion encoding scheme, called Slice-Interleaved Diffusion. SIDE, that interleaves each diffusion-weighted (DW) image volume with slices encoded with different diffusion gradients. We also present a method based on deep learning for effective reconstruction of DW images from the highly slice-undersampled data.
  arXiv  Detail & Related papers  (2020-02-25T14:48:17Z)

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.