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

Unification of sparse Bayesian learning algorithms for electromagnetic brain imaging with the majorization minimization framework

Hashemi, Ali; Cai, Chang; Kutyniok, Gitta; Mueller, Klaus-Robert; Nagarajan, Srikantan S.*; Haufe, Stefan*cent china normal univ
NeuroImage2021-10-1DOI: 10.1016/j.neuroimage.2021.118309
11被引6阅读
引用收藏
分享

摘要

Methods for electro-or magnetoencephalography (EEG/MEG) based brain source imaging (BSI) using sparse Bayesian learning (SBL) have been demonstrated to achieve excellent performance in situations with low numbers of distinct active sources, such as event-related designs. This paper extends the theory and practice of SBL in three important ways. First, we reformulate three existing SBL algorithms under the majorization-minimization (MM) framework. This unification perspective not only provides a useful theoretical framework for comparing different algorithms in terms of their convergence behavior, but also provides a principled recipe for constructing novel algorithms with specific properties by designing appropriate bounds of the Bayesian marginal likelihood function. Second, building on the MM principle, we propose a novel method called LowSNR-BSI that achieves favorable source reconstruction performance in low signal-to-noise-ratio (SNR) settings. Third, precise knowledge of the noise level is a crucial requirement for accurate source reconstruction. Here we present a novel principled technique to accurately learn the noise variance from the data either jointly within the source reconstruction procedure or using one of two proposed cross-validation strategies. Empirically, we could show that the monotonous convergence behavior predicted from MM theory is confirmed in numerical experiments. Using simulations, we further demonstrate the advantage of LowSNR-BSI over conventional SBL in low-SNR regimes, and the advantage of learned noise levels over estimates derived from baseline data. To demonstrate the usefulness of our novel approach, we show neurophysiologically plausible source reconstructions on averaged auditory evoked potential data.

学科与关键词

关键词
Electro-magnetoencephalographyBrain source imagingType III Bayesian learningNon-convexMajorization-MinimizationNoise learningHyperparameter learning
相关
加载中…
  • Electromagnetic Source Imaging With a Combination of Sparse Bayesian Learning and Deep Neural Network
    Liang, Jiawen; Yu, Zhu Liang*; Gu, Zhenghui; Li, YuanqingIEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2023, 31: 2338-2348.被引 1
  • Bayesian Adaptive Beamformer for Robust Electromagnetic Brain Imaging of Correlated Sources in High Spatial Resolution
    Cai, Chang*; Long, Yuanshun; Ghosh, Sanjay; Hashemi, Ali; Gao, Yijing; Diwakar, Mithun; Haufe, Stefan; Sekihara, Kensuke; Wu, Wei*; Nagarajan, Srikantan S.*IEEE Transactions on Medical Imaging, 2023, 42(9): 2502-2512.
  • BAYESIAN INFERENCE FOR BRAIN SOURCE IMAGING WITH JOINT ESTIMATION OF STRUCTURED LOW-RANK NOISE
    Ghosh, Sanjay; Cai, Chang; Gao, Yijing; Hashemi, Ali; Haufe, Stefan; Sekihara, Kensuke; Raj, Ashish; Nagarajan, Srikantan S.*20th IEEE International Symposium on Biomedical Imaging (ISBI), Cartagena, COLOMBIA, 2023-04-18 To 2023-04-21.
查看全部 →

发表信息

论文状态
公开发表
期刊
NeuroImage
发表日期
2021-10-01
卷期
第 239 卷
页码
118309
DOI
10.1016/j.neuroimage.2021.118309
语言
ENGLISH
期刊收录
NSL
期刊等级
1区
成果收录
SCIE
资助标注
European Research Council (ERC) under the European Union [758985]; Machine Learn-ing/Intelligent Data Analysis research group at Technische Universitat Berlin; Berlin International Graduate School in Model and Simulation based Research (BIMoS); Berlin Mathematical School (BMS); Berlin Mathematics Research Cen-ter MATH ; National Natural Science Foundation of China [62007013]; Bundesministerium fur Bildung und Forschung (BMBF) through the Berliner Zentrum for Machine Learn-ing (BZML) [RTG 2433, RTG 2260]; Berlin Mathematics Research Center MATH [EF1-1, EF14]; Institute of Information AMP; Communica-tions Technology Planning AMP; Evaluation (IITP) - Ko-rea Government [2017000451, 2019000079]; German Min-istry for Education and Research (BMBF) [01IS14013AE, 01GQ1115, 01GQ0850, 01IS18025A, 031L0207D, 01IS18037A]; German Research Foundation (DFG) under Grant Math , EXC 2046/1 [390685689]; National In-stitutes of Health [R01DC004855, R01EB022717, R01DC176960, R01DC010145, R01NS100440, R01AG062196, R01DC013979]; University of California MRPI [MRP17454755]; US Department of Defense [W81XWH1310494]; U.S. Department of Defense (DOD) [W81XWH1310494] Funding Source: U.S. Department of Defense (DOD); European Research Council (ERC) [758985] Funding Source: European Research Council (ERC)

作者

  • H

    Hashemi, Ali (第一作者)

  • C

    Cai, Chang

    cent china normal univ

查看全部 6 位作者收起作者
  • K

    Kutyniok, Gitta

  • M

    Mueller, Klaus-Robert

  • N

    Nagarajan, Srikantan S. (通讯)

  • H

    Haufe, Stefan (通讯)

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