基于多尺度低秩的心脏磁共振图像的高质量重构算法

借助信号内在的稀疏性或可压缩性,压缩感知利用随机投影实现以远低于奈奎斯特频率的采样频率下对压缩后数据的采集。结合压缩感知和低秩思想,可以加快心脏磁共振(CMR)图像的扫描速度,减轻患者不适,提高检查质量。本文提出CMR图像的多尺度低秩分解模型,并采用交替方向拉格朗日乘子法(ADMM)进行求解。以峰值信噪比(PSNR)和相对误差(RLNE)作为定量评价指标,结合人眼视觉感受以及局部区域放大,对比分析本文算法与L+S分解、kt FOCUSS、k-t SPARSE SENSE等主流算法的性能优劣。实验结果表明:本文提出的多尺度低秩分解模型,经过ADMM算法重构的效果在性能指标上明显优于其他对比算法,同时图像细节和边缘轮廓成像质量更佳。该方法将推动CMR快速成像技术的发展及其在临床疾病诊疗中的应用。

High quality reconstruction algorithm for cardiac magnetic resonance images based on multiscale low rank modeling

Taking advantages of the sparsity or compressibility inherent in real world signals, compressed sensing (CS) can collect compressed data at the sampling rate much lower than that needed in Shannon’s theorem. The combination of CS and low rank modeling is used to medical imaging techniques to increase the scanning speed of cardiac magnetic resonance (CMR), alleviate the patients* suffering and improve the images quality. The alternating direction method of multipliers (ADMM) algorithm is proposed for multiscale low rank matrix decomposition of CMR images. The algorithm performance is evaluated quantitatively by the peak signal to noise ratio (PSNR) and relative l2 norm error (RLNE), with the human visual system and the local region magnification as the qualitative comparison. Compared to L + S, kt FOCUSS, k-t SPARSE SENSE algorithms, experimental results demonstrate that the proposed algorithm can achieve the best performance indices, and maintain the most detail features and edge contours. The proposed algorithm can encourage the development of fast imaging techniques, and improve the diagnoses values of CMR in clinical applications.