基于多分类字典学习的灵敏度编码重建算法

Sensitivity encoding reconstruction algorithm based on multi-category dictionary learning

灵敏度编码(SENSE)方法利用多个线圈的灵敏度信息来减少扫描时间,利用SENSE模型重构的图像易存在伪影,不利于医学诊断。为减少重叠伪影,提高磁共振成像质量,将分类图像块的快速正交字典引入SENSE模型中,得到一种基于多分类字典学习的灵敏度编码重建算法。该算法通过对图像块分类,在每个类中训练字典,得到不同类别的多个字典,运用交替方向乘子法进行图像重构。在人体脑部和膝盖数据上进行实验,结果表明:相比于TV-SENSE、TVLORAKS-SENSE和LpTV-SENSE算法,所提算法的平均信噪比分别提高了1.53 dB、1.22 dB和1.05 dB,重构图像与参考图像的一致性较高,图像细节部分和边缘轮廓信息保留完整。

The sensitivity encoding(SENSE) method explicitly utilizes sensitivity information from multiple receiving coils to reduce scan time.The images reconstructed using the SENSE model have a portion of blurring artifacts that are not conducive to medical diagnosis.We propose a sensitivity coding reconstruction approach based on multi-classification dictionary learning to minimize overlap artifacts and enhance the quality of parallel magnetic resonance imaging by integrating fast dictionary learning on classed patches into the SENSE model.In order to obtain picture reconstructions using alternating direction method of multipliers,the algorithm first classifies the image blocks and then trains multiple dictionaries of various classes in each category.The results on the human brain and knee data show that the algorithm improves the average signal-to-noise ratio by 1.53 dB,1.22 dB and 1.05 dB over the TVSENSE,TV-LORAKS-SENSE and LpTV-SENSE algorithms,respectively.The reconstructed image is in high agreement with the reference image,and the image detail part and edge contour information are kept intact.