Multi-dimensional low rank plus sparse decomposition for reconstruction of under-sampled dynamic MRI

详细信息    查看全文

• 作者：Shahrooz F. Roohi^a ; ^{shahroozfaghihroohi@gmail.com} ; ^{shahrooz.faghihroohi@nus.edu.sg}Author Vitae ; Dornoosh Zonoobi^b ; ^{zonoobi@ualberta.ca}Author Vitae ; Ashraf A. Kassim^a ; ^{ashraf@nus.edu.sg}Author Vitae ; Jacob L. Jaremko^b ; ^{jjaremko@ualberta.ca}Author Vitae
• 关键词：Low-rank and sparse tensor decomposition ; Dynamic 3D MRI ; Image reconstruction ; Compressive sensing
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：63
• 期：Complete
• 页码：667-679
• 全文大小：2387 K
• 卷排序：63

文摘

A novel multi-dimensional analysis model is learnt to recover higher quality MRI sequences. The dynamic MRI reconstruction is formulated as a higher-dimensional low rank plus sparse tensor reconstruction problem. An efficient numerical algorithm based on ADMM is proposed to solve the optimization problem.