Multimodal data analysis of epileptic EEG and rs-fMRI via deep learning and edge computing

作者：

Highlights：

• An edge computing framework for real-time and ubiquitous processing of medical big data such as EEG, iEEG and fMRI.

• Multimodal data analysis method for localization and prediction of epileptogenicity using independently acquired EEG and rs-fMRI data.

• An unsupervised feature extraction model for identification of preictal and non-preictal time intervals in electrographic data via CNN deep learning.

• Multimodal analysis of rs-fMRI and EEG via LSTM deep learning.

摘要

•An edge computing framework for real-time and ubiquitous processing of medical big data such as EEG, iEEG and fMRI.•Multimodal data analysis method for localization and prediction of epileptogenicity using independently acquired EEG and rs-fMRI data.•An unsupervised feature extraction model for identification of preictal and non-preictal time intervals in electrographic data via CNN deep learning.•Multimodal analysis of rs-fMRI and EEG via LSTM deep learning.

论文关键词：Autonomic computing,Deep learning,Edge computing,Multimodal analysis EEG,FMRI,Brain–computer interface,Convolutional neural network

论文评审过程：Received 12 November 2018, Revised 26 December 2019, Accepted 31 January 2020, Available online 19 February 2020, Version of Record 24 February 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101813