1
|
Jiao M, Xian X, Wang B, Zhang Y, Yang S, Chen S, Sun H, Liu F. XDL-ESI: Electrophysiological Sources Imaging via explainable deep learning framework with validation on simultaneous EEG and iEEG. Neuroimage 2024; 299:120802. [PMID: 39173694 DOI: 10.1016/j.neuroimage.2024.120802] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2024] [Revised: 08/17/2024] [Accepted: 08/19/2024] [Indexed: 08/24/2024] Open
Abstract
Electroencephalography (EEG) or Magnetoencephalography (MEG) source imaging aims to estimate the underlying activated brain sources to explain the observed EEG/MEG recordings. Solving the inverse problem of EEG/MEG Source Imaging (ESI) is challenging due to its ill-posed nature. To achieve a unique solution, it is essential to apply sophisticated regularization constraints to restrict the solution space. Traditionally, the design of regularization terms is based on assumptions about the spatiotemporal structure of the underlying source dynamics. In this paper, we propose a novel paradigm for ESI via an Explainable Deep Learning framework, termed as XDL-ESI, which connects the iterative optimization algorithm with deep learning architecture by unfolding the iterative updates with neural network modules. The proposed framework has the advantages of (1) establishing a data-driven approach to model the source solution structure instead of using hand-crafted regularization terms; (2) improving the robustness of source solutions by introducing a topological loss that leverages the geometric spatial information applying varying penalties on distinct localization errors; (3) improving the reconstruction efficiency and interpretability as it inherits the advantages from both the iterative optimization algorithms (interpretability) and deep learning approaches (function approximation). The proposed XDL-ESI framework provides an efficient, accurate, and interpretable paradigm to solve the ESI inverse problem with satisfactory performance in both simulated data and real clinical data. Specially, this approach is further validated using simultaneous EEG and intracranial EEG (iEEG).
Collapse
Affiliation(s)
- Meng Jiao
- Department of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ, 07030, United States
| | - Xiaochen Xian
- H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, 30332, United States
| | - Boyu Wang
- Department of Computer Science, University of Western Ontario, Ontario, N6A 3K7, Canada
| | - Yu Zhang
- Department of Bioengineering, Lehigh University, Bethlehem, PA, 18015, United States
| | - Shihao Yang
- Department of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ, 07030, United States
| | - Spencer Chen
- Department of Neurosurgery, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ, 08901, United States
| | - Hai Sun
- Department of Neurosurgery, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ, 08901, United States
| | - Feng Liu
- Department of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ, 07030, United States; Semcer Center for Healthcare Innovation, Stevens Institute of Technology, Hoboken, NJ, 07030, United States.
| |
Collapse
|
2
|
Jiao M, Yang S, Xian X, Fotedar N, Liu F. Multi-Modal Electrophysiological Source Imaging With Attention Neural Networks Based on Deep Fusion of EEG and MEG. IEEE Trans Neural Syst Rehabil Eng 2024; 32:2492-2502. [PMID: 38976470 PMCID: PMC11329068 DOI: 10.1109/tnsre.2024.3424669] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/10/2024]
Abstract
The process of reconstructing underlying cortical and subcortical electrical activities from Electroencephalography (EEG) or Magnetoencephalography (MEG) recordings is called Electrophysiological Source Imaging (ESI). Given the complementarity between EEG and MEG in measuring radial and tangential cortical sources, combined EEG/MEG is considered beneficial in improving the reconstruction performance of ESI algorithms. Traditional algorithms mainly emphasize incorporating predesigned neurophysiological priors to solve the ESI problem. Deep learning frameworks aim to directly learn the mapping from scalp EEG/MEG measurements to the underlying brain source activities in a data-driven manner, demonstrating superior performance compared to traditional methods. However, most of the existing deep learning approaches for the ESI problem are performed on a single modality of EEG or MEG, meaning the complementarity of these two modalities has not been fully utilized. How to fuse the EEG and MEG in a more principled manner under the deep learning paradigm remains a challenging question. This study develops a Multi-Modal Deep Fusion (MMDF) framework using Attention Neural Networks (ANN) to fully leverage the complementary information between EEG and MEG for solving the ESI inverse problem, which is termed as MMDF-ANN. Specifically, our proposed brain source imaging approach consists of four phases, including feature extraction, weight generation, deep feature fusion, and source mapping. Our experimental results on both synthetic dataset and real dataset demonstrated that using a fusion of EEG and MEG can significantly improve the source localization accuracy compared to using a single-modality of EEG or MEG. Compared to the benchmark algorithms, MMDF-ANN demonstrated good stability when reconstructing sources with extended activation areas and situations of EEG/MEG measurements with a low signal-to-noise ratio.
Collapse
|
3
|
Yang S, Jiao M, Xiang J, Fotedar N, Sun H, Liu F. Rejuvenating classical brain electrophysiology source localization methods with spatial graph Fourier filters for source extents estimation. Brain Inform 2024; 11:8. [PMID: 38472438 PMCID: PMC10933195 DOI: 10.1186/s40708-024-00221-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2023] [Accepted: 02/25/2024] [Indexed: 03/14/2024] Open
Abstract
EEG/MEG source imaging (ESI) aims to find the underlying brain sources to explain the observed EEG or MEG measurement. Multiple classical approaches have been proposed to solve the ESI problem based on different neurophysiological assumptions. To support clinical decision-making, it is important to estimate not only the exact location of the source signal but also the extended source activation regions. Existing methods may render over-diffuse or sparse solutions, which limit the source extent estimation accuracy. In this work, we leverage the graph structures defined in the 3D mesh of the brain and the spatial graph Fourier transform (GFT) to decompose the spatial graph structure into sub-spaces of low-, medium-, and high-frequency basis. We propose to use the low-frequency basis of spatial graph filters to approximate the extended areas of brain activation and embed the GFT into the classical ESI methods. We validated the classical source localization methods with the corresponding improved version using GFT in both synthetic data and real data. We found the proposed method can effectively reconstruct focal source patterns and significantly improve the performance compared to the classical algorithms.
Collapse
Affiliation(s)
- Shihao Yang
- School of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ, 07030, USA
| | - Meng Jiao
- School of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ, 07030, USA
| | - Jing Xiang
- MEG Center, Division of Neurology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, 45229, USA
| | - Neel Fotedar
- Epilepsy Center, Neurological Institute, University Hospitals Cleveland Medical Center, Cleveland, OH, 44106, USA
- Department of Neurology, Case Western Reserve University School of Medicine, Cleveland, OH, 44106, USA
| | - Hai Sun
- Department of Neurosurgery, Rutgers Robert Wood Johnson Medical School of Rutgers University, Brunswick, NJ, 08901, USA
| | - Feng Liu
- School of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ, 07030, USA.
- Semcer Center for Healthcare Innovation, Stevens Institute of Technology, Hoboken, NJ, 07030, USA.
| |
Collapse
|
4
|
Sun R, Zhang W, Bagić A, He B. Deep learning based source imaging provides strong sublobar localization of epileptogenic zone from MEG interictal spikes. Neuroimage 2023; 281:120366. [PMID: 37716593 PMCID: PMC10771628 DOI: 10.1016/j.neuroimage.2023.120366] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2023] [Revised: 08/07/2023] [Accepted: 09/06/2023] [Indexed: 09/18/2023] Open
Abstract
Electromagnetic source imaging (ESI) offers unique capability of imaging brain dynamics for studying brain functions and aiding the clinical management of brain disorders. Challenges exist in ESI due to the ill-posedness of the inverse problem and thus the need of modeling the underlying brain dynamics for regularizations. Advances in generative models provide opportunities for more accurate and realistic source modeling that could offer an alternative approach to ESI for modeling the underlying brain dynamics beyond equivalent physical source models. However, it is not straightforward to explicitly formulate the knowledge arising from these generative models within the conventional ESI framework. Here we investigate a novel source imaging framework based on mesoscale neuronal modeling and deep learning (DL) that can learn the sensor-source mapping relationship directly from MEG data for ESI. Two DL-based ESI models were trained based on data generated by neural mass models and either generic or personalized head models. The robustness of the two DL models was evaluated by systematic computer simulations and clinical validation in a cohort of 29 drug-resistant focal epilepsy patients who underwent intracranial EEG (iEEG) evaluation or surgical resection. Results estimated from pre-operative MEG interictal spikes were quantified using the overlap with resection regions and the distance to the seizure-onset zone (SOZ) defined by iEEG recordings. The DL-based ESI provided robust results when no personalized head geometry is considered, reaching a spatial dispersion of 21.90 ± 19.03 mm, sublobar concordance of 83 %, and sublobar sensitivity and specificity of 66 and 97 % respectively. When using personalized head geometry derived from individual patients' MRI in the training data, personalized DL-based ESI model can further improve the performance and reached a spatial dispersion of 8.19 ± 8.14 mm, sublobar concordance of 93 %, and sublobar sensitivity and specificity of 77 and 99 % respectively. When compared to the SOZ, the localization error of the personalized approach is 15.78 ± 5.54 mm, outperforming the conventional benchmarks. This work demonstrates that combining generative models and deep learning enables an accurate and robust imaging of epileptogenic zone from MEG recordings with strong sublobar precision, suggesting its added value to enhancing MEG source localization and imaging, and to epilepsy source localization and other clinical applications.
Collapse
Affiliation(s)
- Rui Sun
- Department of Biomedical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA
| | - Wenbo Zhang
- Minnesota Epilepsy Group, John Nasseff Neuroscience Center at United Hospital, Saint Paul, USA
| | - Anto Bagić
- Department of Neurology, University of Pittsburgh Comprehensive Epilepsy Center (UPCEC), University of Pittsburgh Medical School, Pittsburgh, USA
| | - Bin He
- Department of Biomedical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA.
| |
Collapse
|
5
|
Dou G, Zhang Y, Yang H, Han M, Guo M, Gai W. RC Bridge Oscillation Memristor Chaotic Circuit for Electrical and Electronic Technology Extended Simulation Experiment. MICROMACHINES 2023; 14:410. [PMID: 36838110 PMCID: PMC9967385 DOI: 10.3390/mi14020410] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/02/2023] [Revised: 01/29/2023] [Accepted: 02/05/2023] [Indexed: 06/18/2023]
Abstract
The fourth basic circuit component, the memristor, has been proposed for a long time, but it is not mentioned in the experiment teaching system of Electrical and Electronic Technology. In this paper, an RC bridge oscillation chaotic circuit based on memristor is designed to solve this problem. The dynamical behavior of the circuit system is analyzed using Lyapunov exponents spectrum, bifurcation diagram, phase portrait and Poincaré map. A series of complex dynamical behaviors such as symmetric single-scroll coexistence, asymmetrical single-scroll coexistence, symmetric double-scroll coexistence and asymmetrical limit-cycle coexistence exist in the circuit system. This research plays a critical role in enriching students' knowledge and improving the experiment teaching system of Electrical and Electronic Technology.
Collapse
Affiliation(s)
- Gang Dou
- The College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China
| | - Yongcheng Zhang
- The College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China
| | - Hai Yang
- The College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China
| | - Mingqiao Han
- Faculty of Science and Engineering, University of Nottingham Ningbo China, Ningbo 315100, China
| | - Mei Guo
- The College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China
| | - Wendong Gai
- The College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China
| |
Collapse
|
6
|
Guo Y, Jiao M, Wan G, Xiang J, Wang S, Liu F. EEG Source Imaging using GANs with Deep Image Prior. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2022; 2022:572-575. [PMID: 36083924 DOI: 10.1109/embc48229.2022.9871172] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Brain source localization from electroencephalogram (EEG) signals is an challenging problem for noninvasively localizing the brain activity. Conventional methods use handcrafted regularization terms based on neural-physiological assumptions by exploiting the spatial-temporal structure on the source signals. In recent years, deep learning frameworks have demonstrated superior performance for solving the inverse problems in the natural and medical imaging field. This study proposes a novel unsupervised learning training-free framework based on Generative Adversarial Networks and deep image prior (GANs-DIP) as a generative model simulating spatially structured source signal. The proposed framework can faithfully recover extended source patches activation patterns of the brain in an unsupervised manner. Numerical experiments on a realistic brain model are performed under different levels of signal-to-noise ratio (SNR). The proposed model shows satisfactory performance in recovering the underlying source activation.
Collapse
|
7
|
Jiao M, Liu F, Asan O, Nilchiani R, Ju X, Xiang J. Brain Source Reconstruction Solution Quality Assessment with Spatial Graph Frequency Features. Brain Inform 2022. [DOI: 10.1007/978-3-031-15037-1_15] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022] Open
|