跳到主要导航 跳到搜索 跳到主要内容

Discriminative feature representation to improve projection data inconsistency for low dose CT Imaging

  • Jin Liu
  • , Jianhua Ma
  • , Yi Zhang
  • , Yang Chen
  • , Jian Yang
  • , Huazhong Shu
  • , Limin Luo
  • , Gouenou Coatrieux
  • , Wei Yang
  • , Qianjin Feng
  • , Wufan Chen
  • Southeast University, Nanjing
  • Centre de Recherche en Information Biomedicale Sino-Francais (LIA CRIBs)
  • Joint International Research Laboratory of Information Display and Visualization
  • Southern Medical University
  • Beijing Institute of Technology
  • Sichuan University
  • Telecom Bretagne

科研成果: 期刊稿件 › 文章 › 同行评审

103 引用 (Scopus)

摘要

In low dose computed tomography (LDCT) imaging, the data inconsistency of measured noisy projections can significantly deteriorate reconstruction images. To deal with this problem, we propose here a new sinogram restoration approach, the sinogram-discriminative feature representation (S-DFR)method. Different fromother sinogram restorationmethods, the proposedmethod works through a 3-D representation-based feature decomposition of the projected attenuation component and the noise component using awell-designedcomposite dictionary containing atoms with discriminative features. This method can be easily implemented with good robustness in parameter setting. Its comparisonto othercompetingmethods through experiments on simulated and real data demonstrated that the S-DFR method offers a sound alternative in LDCT.

源语言英语
期刊论文编号8010446
页(从-至)2499-2509
页数11
期刊IEEE Transactions on Medical Imaging
卷36
期12
DOI
出版状态已出版 - 12月 2017
已对外发布是

学术指纹

探究 'Discriminative feature representation to improve projection data inconsistency for low dose CT Imaging' 的科研主题。它们共同构成独一无二的学术指纹。

引用此