Wu Zhengliang, Liao Weibin, Yan Chao, Zhao Mangsuo, Liu Guowen, Ma Ning, Li Xuesong
School of Computer Science & Technology, Beijing Institute of Technology, No. 5, South Street, Zhongguancun, Beijing, 100081, China.
School of Computer Science & Technology, Beijing Institute of Technology, No. 5, South Street, Zhongguancun, Beijing, 100081, China.
Comput Methods Programs Biomed. 2023 May;233:107452. doi: 10.1016/j.cmpb.2023.107452. Epub 2023 Mar 1.
Magnetic resonance imaging (MRI) has become one of the most powerful imaging techniques in medical diagnosis, yet the prolonged scanning time becomes a bottleneck for application. Reconstruction methods based on compress sensing (CS) have made progress in reducing this cost by acquiring fewer points in the k-space. Traditional CS methods impose restrictions from different sparse domains to regularize the optimization that always requires balancing time with accuracy. Neural network techniques enable learning a better prior from sample pairs and generating the results in an analytic way. In this paper, we propose a deep learning based reconstruction method to restore high-quality MRI images from undersampled k-space data in an end-to-end style. Unlike prior literature adopting convolutional neural networks (CNN), advanced Swin Transformer is used as the backbone of our work, which proved to be powerful in extracting deep features of the image. In addition, we combined the k-space consistency in the output and further improved the quality. We compared our models with several reconstruction methods and variants, and the experiment results proved that our model achieves the best results in samples at low sampling rates. The source code of KTMR could be acquired at https://github.com/BITwzl/KTMR.
磁共振成像（MRI）已成为医学诊断中最强大的成像技术之一，但长时间的扫描时间成为其应用的瓶颈。基于压缩感知（CS）的重建方法通过在k空间中采集更少的点，在降低这一成本方面取得了进展。传统的CS方法从不同的稀疏域施加限制来规范优化，这总是需要在时间和准确性之间进行平衡。神经网络技术能够从样本对中学习更好的先验，并以解析的方式生成结果。在本文中，我们提出了一种基于深度学习的重建方法，以端到端的方式从欠采样的k空间数据中恢复高质量的MRI图像。与采用卷积神经网络（CNN）的先前文献不同，我们使用先进的Swin Transformer作为工作的主干，事实证明它在提取图像的深度特征方面非常强大。此外，我们结合了输出中的k空间一致性，进一步提高了质量。我们将我们的模型与几种重建方法和变体进行了比较，实验结果证明我们的模型在低采样率样本中取得了最佳结果。KTMR的源代码可在https://github.com/BITwzl/KTMR获取。
