ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Stochastic EM methods with variance reduction for penalised PET reconstructions

Kereta, Zeljko*; Twyman, Robert; Arridge, Simon; Thielemans, Kris; Jin, Bangti
Inverse Problems2021-11DOI: 10.1088/1361-6420/ac2d74
5被引5阅读
引用收藏
分享

摘要

Expectation-maximisation (EM) is a popular and well-established method for image reconstruction in positron emission tomography (PET) but it often suffers from slow convergence. Ordered subset EM (OSEM) is an effective reconstruction algorithm that provides significant acceleration during initial iterations, but it has been observed to enter a limit cycle. In this work, we investigate two classes of algorithms for accelerating OSEM based on variance reduction for penalised PET reconstructions. The first is a stochastic variance reduced EM algorithm, termed as SVREM, an extension of the classical EM to the stochastic context that combines classical OSEM with variance reduction techniques for gradient descent. The second views OSEM as a preconditioned stochastic gradient ascent, and applies variance reduction techniques, i.e., SAGA and SVRG, to estimate the update direction. We present several numerical experiments to illustrate the efficiency and accuracy of the approaches. The numerical results show that these approaches significantly outperform existing OSEM type methods for penalised PET reconstructions, and hold great potential.

学科与关键词

关键词
positron emission tomographystochastic gradientvariance reductionexpectation maximizationordered subset expectation maximisation
相关
加载中…
  • Tomographic reconstruction from Poisson distributed data: a fast and convergent EM-TV dual approach
    Maxim, Voichita*; Feng, Yuemeng; Banjak, Hussein; Bretin, ElieNUMERICAL ALGORITHMS, 2023, 94(2): 701-731.被引 2
  • String-averaging expectation-maximization for maximum likelihood estimation in emission tomography
    Helou, Elias Salomao*; Censor, Yair; Chen, Tai-Been; Chern, I-Liang; De Pierro, Alvaro Rodolfo; Jiang, Ming; Lu, Henry Horng-ShingInverse Problems, 2014, 30(5): 055003.被引 8
  • PET Image Reconstruction With Kernel and Kernel Space Composite Regularizer
    Guo, Shiyao; Sheng, Yuxia*; Chai, Li; Zhang, Jingxin*IEEE Transactions on Medical Imaging, 2023, 42(6): 1786-1798.
查看全部 →

发表信息

论文状态
公开发表
期刊
Inverse Problems
发表日期
2021-11
卷期
第 37 卷, 第 11 期
页码
115006
DOI
10.1088/1361-6420/ac2d74
语言
MULTI-LANGUAGE
期刊收录
NSL
期刊等级
2区
成果收录
SCIE
资助标注
UK EPSRC [EP/T000864/1]; GE Healthcare [EP/T026693/1]; EPSRC [EP/H046410/1, EP/T000864/1, EP/T026693/1, EP/N032055/1, EP/P022200/1, EP/K005278/1] Funding Source: UKRI

作者

  • K

    Kereta, Zeljko (通讯) (第一作者)

  • T

    Twyman, Robert

查看全部 5 位作者收起作者
  • A

    Arridge, Simon

  • T

    Thielemans, Kris

  • J

    Jin, Bangti

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417