Saved in:
Bibliographic Details
Main Authors: Morik, Marco, Hashemi, Ali, Müller, Klaus-Robert, Haufe, Stefan, Nakajima, Shinichi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.00143
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914385283252224
author Morik, Marco
Hashemi, Ali
Müller, Klaus-Robert
Haufe, Stefan
Nakajima, Shinichi
author_facet Morik, Marco
Hashemi, Ali
Müller, Klaus-Robert
Haufe, Stefan
Nakajima, Shinichi
contents Reconstructing brain sources is a fundamental challenge in neuroscience, crucial for understanding brain function and dysfunction. Electroencephalography (EEG) signals have a high temporal resolution. However, identifying the correct spatial location of brain sources from these signals remains difficult due to the ill-posed structure of the problem. Traditional methods predominantly rely on manually crafted priors, missing the flexibility of data-driven learning, while recent deep learning approaches focus on end-to-end learning, typically using the physical information of the forward model only for generating training data. We propose the novel hybrid method 3D-PIUNet for EEG source localization that effectively integrates the strengths of traditional and deep learning techniques. 3D-PIUNet starts from an initial physics-informed estimate by using the pseudo inverse to map from measurements to source space. Secondly, by viewing the brain as a 3D volume, we use a 3D convolutional U-Net to capture spatial dependencies and refine the solution according to the learned data prior. Training the model relies on simulated pseudo-realistic brain source data, covering different source distributions. Trained on this data, our model significantly improves spatial accuracy, demonstrating superior performance over both traditional and end-to-end data-driven methods. Additionally, we validate our findings with real EEG data from a visual task, where 3D-PIUNet successfully identifies the visual cortex and reconstructs the expected temporal behavior, thereby showcasing its practical applicability.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00143
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Brain Source Reconstruction by Initializing 3D Neural Networks with Physical Inverse Solutions
Morik, Marco
Hashemi, Ali
Müller, Klaus-Robert
Haufe, Stefan
Nakajima, Shinichi
Image and Video Processing
Machine Learning
Reconstructing brain sources is a fundamental challenge in neuroscience, crucial for understanding brain function and dysfunction. Electroencephalography (EEG) signals have a high temporal resolution. However, identifying the correct spatial location of brain sources from these signals remains difficult due to the ill-posed structure of the problem. Traditional methods predominantly rely on manually crafted priors, missing the flexibility of data-driven learning, while recent deep learning approaches focus on end-to-end learning, typically using the physical information of the forward model only for generating training data. We propose the novel hybrid method 3D-PIUNet for EEG source localization that effectively integrates the strengths of traditional and deep learning techniques. 3D-PIUNet starts from an initial physics-informed estimate by using the pseudo inverse to map from measurements to source space. Secondly, by viewing the brain as a 3D volume, we use a 3D convolutional U-Net to capture spatial dependencies and refine the solution according to the learned data prior. Training the model relies on simulated pseudo-realistic brain source data, covering different source distributions. Trained on this data, our model significantly improves spatial accuracy, demonstrating superior performance over both traditional and end-to-end data-driven methods. Additionally, we validate our findings with real EEG data from a visual task, where 3D-PIUNet successfully identifies the visual cortex and reconstructs the expected temporal behavior, thereby showcasing its practical applicability.
title Enhancing Brain Source Reconstruction by Initializing 3D Neural Networks with Physical Inverse Solutions
topic Image and Video Processing
Machine Learning
url https://arxiv.org/abs/2411.00143