基于残差图卷积神经网络的高倍欠采样核磁共振图像重建算法

Reconstruction algorithm for highly undersampled magnetic resonance images based on residual graph convolutional neural network

磁共振成像(MRI)因其无创伤和较高的软组织对比度而被广泛地用于复杂疾病诊断。目前多通过在k空间高倍欠采样磁共振(MR)信号解决MRI速度较慢的问题,然而代表性算法重建高倍欠采样的MR图像时往往存在细节模糊的问题。因此,提出一种基于残差图卷积神经网络(RGCNET)的高倍欠采样MR图像重建算法。首先,使用自编码技术与图卷积神经网络(GCN)构建生成器;其次,将欠采样图像输入特征提取(编码)网络中从底层提取特征;接着,通过GCN块提取MR图像的高层特征;然后,通过解码网络生成初始的重建图像;最后,经过生成器和鉴别器的动态博弈得到最终的高分辨率重建图像。在FastMRI数据集上的测试结果表明,与基于空间正交注意力机制的MRI重建算法SOGAN(Spatial Orthogonal attention Generative Adversarial Network)相比,在10%、20%、30%、40%和50%的采样率下,所提算法在标准均方根误差(NRMSE)指标上分别下降了3.5%、26.6%、23.9%、13.3%和14.3%,在峰值信噪比(PSNR)指标上分别提升了1.2%、8.7%、6.9%、2.9%和3.2%,而结构相似性(SSIM)指标上分别提升了0.8%、2.9%、1.5%、0.5%和0.5%。同时,主观观察也验证了所提算法能保留更多细节和取得更逼真的视觉效果。

Magnetic Resonance Imaging(MRI)is widely used in the diagnosis of complex diseases because of its noninvasiveness and good soft tissue contrast.Due to the low speed of MRI,most of the acceleration is currently performed by highly undersampled Magnetic Resonance(MR)signals in k-space.However,the representative algorithms often have the problem of blurred details when reconstructing highly undersampled MR images.Therefore,a highly undersampled MR image reconstruction algorithm based on Residual Graph Convolutional Neural nETwork(RGCNET)was proposed.Firstly,auto-encoding technology and Graph Convolutional neural Network(GCN)were used to build a generator.Secondly,the undersampled image was input into the feature extraction(encoder)network to extract features at the bottom layer.Thirdly,the high-level features of MR images were extracted by the GCN block.Fourthly,the initial reconstructed image was generated through the decoder network.Finally,the final high-resolution reconstructed image was obtained through a dynamic game between the generator and the discriminator.Test results on FastMRI dataset show that at 10%,20%,30%,40%and 50%sampling rates,compared with spatial orthogonal attention mechanism based MRI reconstruction algorithm SOGAN(Spatial Orthogonal attention Generative Adversarial Network),the proposed algorithm decreases 3.5%,26.6%,23.9%,13.3%and 14.3%on Normalized Root Mean Square Error(NRMSE),increases 1.2%,8.7%,6.9%,2.9%and 3.2%on Peak Signal-to-Noise Ratio(PSNR)and increases 0.8%,2.9%,1.5%,0.5%and 0.5%on Structural SIMilarity(SSIM)respectively.At the same time,subjective observation also proves that the proposed algorithm can preserve more details and have more realistic visual effects.