Multimodal MRI Reconstruction Assisted With Spatial Alignment Network

  title={Multimodal MRI Reconstruction Assisted With Spatial Alignment Network},
  author={Kai Xuan and L. Xiang and Xiaoqiang Huang and Lichi Zhang and Shu Liao and Dinggang Shen and Qian Wang},
  journal={IEEE Transactions on Medical Imaging},
In clinical practice, multi-modal magnetic resonance imaging (MRI) with different contrasts is usually acquired in a single study to assess different properties of the same region of interest in the human body. The whole acquisition process can be accelerated by having one or more modalities under-sampled in the <inline-formula> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula>-space. Recent research has shown that, considering the redundancy between different modalities, a target… 
1 Citations

Figures and Tables from this paper



Deep-Learning-Based Multi-Modal Fusion for Fast MR Reconstruction

The results have shown that Dense-Unet can reconstruct a three-dimensional T2WI volume in less than 10 s with an under-sampling rate of 8 for the k-space and negligible aliasing artifacts or signal-noise-ratio loss.

Reference-based MRI.

The proposed framework, referred to as FASTMER, for fast MRI by exploiting a reference image is a framework based on an iterative weighted reconstruction approach that supports cases in which similarity to the reference scan is not guaranteed.

Fast multi-contrast MRI reconstruction.

Enhanced Deep-Learning-Based Magnetic Resonance Image Reconstruction by Leveraging Prior Subject-Specific Brain Imaging: Proof-of-Concept Using a Cohort of Presumed Normal Subjects

A flexible three-step method that can use prior scan information to further accelerate MR examinations and have better volume agreement with the fully sampled reference images compared to the non-enhanced images is proposed.

Sparse MRI reconstruction using multi-contrast image guided graph representation.

Coupled Dictionary Learning for Multi-Contrast MRI Reconstruction

A Coupled Dictionary Learning based multi-contrast MRI reconstruction (CDLMRI) approach to leverage an available guidance contrast to restore the target contrast and improve MRI reconstruction, compared to state-of-the-art approaches.

Ultra-Fast T2-Weighted MR Reconstruction Using Complementary T1-Weighted Information

The results have shown that Dense-Unet can reconstruct a 3D T2WI volume in less than 10 s, i.e., with the acceleration rate as high as 8 or more but with negligible aliasing artefacts and signal-noise-ratio (SNR) loss.

Region-Adaptive Deformable Registration of CT/MRI Pelvic Images via Learning-Based Image Synthesis

Improved performances for both intra-subject and inter-subject deformable registration show improved performances compared with the state-of-the-art multimodal registration methods, which demonstrate the potentials of the method to be applied for the routine prostate cancer radiation therapy.

Multi-Contrast Super-Resolution MRI Through a Progressive Network

The proposed networks integrate multi-contrast information in a high-level feature space and optimize the imaging performance by minimizing a composite loss function, which includes mean-squared-error, adversarial loss, perceptual loss, and textural loss.