Department of Physics, Zhejiang Sci-Tech University, Hangzhou 310018, PR China.
School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, PR China.
Comput Methods Programs Biomed. 2024 Oct;255:108359. doi: 10.1016/j.cmpb.2024.108359. Epub 2024 Jul 29.
As a widely used technique for Magnetic Resonance Image (MRI) acceleration, compressed sensing MRI involves two main issues: designing an effective sampling strategy and reconstructing the image from significantly under-sampled K-space data. In this paper, an innovative approach is proposed to address these two challenges simultaneously.
A novel MRI reconstruction method, termed as LUCMT, is implemented by integrating a learnable under-sampling strategy with a reconstruction network based on the Cross Multi-head Attention Transformer. In contrast to conventional static sampling methods, the proposed adaptive sampling scheme is processed optimally by learning the optimal sampling technique, which involves binarizing the sampling pattern by a sigmoid function and computing gradients by backpropagation. And the reconstruction network is designed by using CS-MRI depth unfolding network that incorporates a Cross Multi-head Attention (CMA) module with inertial and gradient descent terms.
T1 brain MR images from the FastMRI dataset are used to validate the performance of the proposed method. A series of experiments are conducted to validate the superior performance of our proposed network in terms of quantitative metrics and visual quality. Compared with other state-of-the-art reconstruction methods, LUCMT achieves better reconstruction performances with more accurate details. Specifically, LUCMT achieves PSNR and SSIM results of 41.87/0.9749, 46.64/0.9868, 50.41/0.9924, and 53.51/0.9955 at sampling rates of 10 %, 20 %, 30 %, and 40 %, respectively.
The proposed LUCMT method can provide a promising way for generating optimal under-sampling mask and accelerating MRI reconstruction accurately.
压缩感知磁共振成像（CS-MRI）作为磁共振图像（MRI）加速的一种广泛应用技术，涉及到两个主要问题：设计有效的采样策略和从显著欠采样的 K 空间数据中重建图像。本文提出了一种创新的方法来同时解决这两个挑战。
通过将基于交叉多头注意力 Transformer 的重建网络与可学习的欠采样策略集成，提出了一种新的 MRI 重建方法，称为 LUCMT。与传统的静态采样方法不同，所提出的自适应采样方案通过学习最优采样技术进行最优处理，该技术涉及通过 sigmoid 函数对采样模式进行二值化，并通过反向传播计算梯度。重建网络是通过使用 CS-MRI 深度展开网络设计的，该网络包含带有惯性和梯度下降项的交叉多头注意力（CMA）模块。
使用来自 FastMRI 数据集的 T1 脑 MRI 图像验证了所提出方法的性能。进行了一系列实验来验证所提出的网络在定量指标和视觉质量方面的优越性能。与其他最先进的重建方法相比，LUCMT 具有更准确的细节，实现了更好的重建性能。具体来说，LUCMT 在采样率为 10%、20%、30%和 40%时，分别达到了 41.87/0.9749、46.64/0.9868、50.41/0.9924 和 53.51/0.9955 的 PSNR 和 SSIM 结果。
所提出的 LUCMT 方法可以为生成最优欠采样掩模和准确加速 MRI 重建提供一种有前途的方法。
