基于离散剪切波的压缩感知MRI图像重建

针对二维小波变换捕捉方向信息有限, 不能稀疏地表示MRI图像中曲线状奇异特征的缺点, 提出了一种基于离散剪切波变换的压缩感知MRI图像重建新方法。先对MRI图像作剪切波变换, 得到各尺度、方向子带的剪切系数, 再采用正交匹配追踪算法恢复稀疏处理后的系数, 最后进行剪切波反变换得到重建图像。实验结果表明, 与小波变换相比, 基于离散剪切波的压缩感知MRI图像有更好的重建效果, 更有利于保留纹理和边缘信息。

Reconstruction of compressed sensing MRI image based ondiscrete shearlet transform

The two-dimensional wavelet transform for magnetic resonance imaging (MRI) images does not sparsely represent curve singularity characteristics, which can only capture the limited direction information. Pointing at this problem, this paper presented a new method based on discrete shearlet transform for compressed sensing MRI (CS-MRI). It got the frequency coefficients at all scales and in all directions after performing discrete shearlet transform to MRI image. Then it adopted orthogonal matching pursuit algorithm to recover the sparsing coefficients. Finally, it got the reconstructed image by inverse shearlet transform. Experimental results show that, compared with wavelet transform, discrete shearlet transform for CS-MRI improves quality of reconstructed image and preserves more information about texture and edge.