波谱学杂志2016，Vol.33Issue(4)：559-569,11.DOI:10.11938/cjmr20160405
用于压缩感知磁共振成像的分割字典学习算法
Dictionary Learning with Segmentation for Compressed-Sensing Magnetic Resonance Imaging
摘要
Abstract
Dictionary learning (DL) builds a set of basis functions from the input data, such that the data can be represented more sparsely. Based on the fact that certain magnetic resonance (MR) images can be easily segmented, we propose an algorithm named dictionary learning with segmentation (DLS). The algorithm achieves better image reconstruction quality by optimizing construction of the dictionary and to making representation of the MR images sparser though incorporating image segmentation into dictionary learning. The experimental results on simulated datasets andin vivo images demonstrated that the proposed algorithm can yield better reconstruction relative to the traditional dictionary learning algorithm.关键词
磁共振成像(MRI)/压缩感知/字典学习/图像分割Key words
magnetic resonance imaging (MRI)/compressed sensing/dictionary learning/segmentation分类
数理科学引用本文复制引用
宋阳,谢海滨,杨光..用于压缩感知磁共振成像的分割字典学习算法[J].波谱学杂志,2016,33(4):559-569,11.基金项目
国家高技术研究发展计划资助项目(2014AA123400) （2014AA123400）
