Deep Learning-Based Localization of EEG Electrodes Within MRI Acquisitions

被引:2
|
作者
Pinte, Caroline [1 ]
Fleury, Mathis [1 ]
Maurel, Pierre [1 ]
机构
[1] Univ Rennes, INRIA, CNRS, INSERM,Empenn ERL,U1228, Rennes, France
来源
FRONTIERS IN NEUROLOGY | 2021年 / 12卷
关键词
EEG; fMRI; electrode detection; electrode labeling; deep learning; U-Net; ICP; POSITIONS; REGISTRATION; NETWORKS; EPILEPSY;
D O I
10.3389/fneur.2021.644278
中图分类号
R74 [神经病学与精神病学];
学科分类号
摘要
The simultaneous acquisition of electroencephalographic (EEG) signals and functional magnetic resonance images (fMRI) aims to measure brain activity with good spatial and temporal resolution. This bimodal neuroimaging can bring complementary and very relevant information in many cases and in particular for epilepsy. Indeed, it has been shown that it can facilitate the localization of epileptic networks. Regarding the EEG, source localization requires the resolution of a complex inverse problem that depends on several parameters, one of the most important of which is the position of the EEG electrodes on the scalp. These positions are often roughly estimated using fiducial points. In simultaneous EEG-fMRI acquisitions, specific MRI sequences can provide valuable spatial information. In this work, we propose a new fully automatic method based on neural networks to segment an ultra-short echo-time MR volume in order to retrieve the coordinates and labels of the EEG electrodes. It consists of two steps: a segmentation of the images by a neural network, followed by the registration of an EEG template on the obtained detections. We trained the neural network using 37 MR volumes and then we tested our method on 23 new volumes. The results show an average detection accuracy of 99.7% with an average position error of 2.24 mm, as well as 100% accuracy in the labeling.
引用
收藏
页数:8
相关论文
共 50 条
  • [31] Damage localization using a deep learning-based response modeling method
    Chen, Chengbin
    Tang, Liqun
    Xiao, Qingkai
    Zhou, Licheng
    Liu, Zejia
    Liu, Yiping
    Jiang, Zhenyu
    Yang, Bao
    COMPUTERS & STRUCTURES, 2025, 310
  • [32] A deep learning-based method for classification, detection, and localization of weeds in turfgrass
    Jin, Xiaojun
    Bagavathiannan, Muthukumar
    McCullough, Patrick E.
    Chen, Yong
    Yu, Jialin
    PEST MANAGEMENT SCIENCE, 2022, 78 (11) : 4809 - 4821
  • [33] Backdoor Attacks Against Deep Learning-based Massive MIMO Localization
    Zhao, Tianya
    Wang, Xuyu
    Mao, Shiwen
    IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM, 2023, : 2796 - 2801
  • [34] Feature assortment for deep learning-based bug localization with a program graph
    Kim, Youngkyoung
    Kim, Misoo
    Lee, Eunseok
    Proceedings of the ACM Symposium on Applied Computing, 2022, : 1536 - 1544
  • [35] DEEP LEARNING-BASED APPROACH FOR ACOUSTIC SOURCE LOCALIZATION IN TURBULENT FLOWS
    Joshi, Arnav
    Hickey, Jean-Pierre
    Canadian Acoustics - Acoustique Canadienne, 2023, 51 (03): : 74 - 75
  • [36] Deep Learning-Based Model for Defect Detection and Localization on Photovoltaic Panels
    Prabhakaran, S.
    Uthra, R. Annie
    Preetharoselyn, J.
    COMPUTER SYSTEMS SCIENCE AND ENGINEERING, 2023, 44 (03): : 2683 - 2700
  • [37] Deep learning-based localization of electrical connector sockets for automated mating
    Beck, Leopold
    Gebauer, Daniel
    Rauh, Thomas
    Dirr, Jonas
    Daub, Ruediger
    PRODUCTION ENGINEERING-RESEARCH AND DEVELOPMENT, 2025, 19 (02): : 187 - 194
  • [38] Deep Learning-Based Facial Landmarks Localization Using Compound Scaling
    Colaco, Savina Jassica
    Han, Dong Seog
    IEEE ACCESS, 2022, 10 : 7653 - 7663
  • [39] Feature Assortment for Deep Learning-based Bug Localization with a Program Graph
    Kim, Youngkyoung
    Kim, Misoo
    Lee, Eunseok
    37TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, 2022, : 1536 - 1544
  • [40] Deep Learning-Based Landmark Detection for Mobile Robot Outdoor Localization
    Nilwong, Sivapong
    Hossain, Delowar
    Kaneko, Shin-ichiro
    Capi, Genci
    MACHINES, 2019, 7 (02)