Non-Invasive Reconstruction of Intracranial EEG Across the Deep Temporal Lobe from Scalp EEG based on Conditional Normalizing Flow

2026-02-27

AI Summary

This study addresses the challenge of non-invasively reconstructing high-fidelity intracranial electroencephalography (iEEG) signals from scalp EEG (sEEG) to uncover deep temporal lobe dynamics. To this end, the authors propose NeuroFlowNet, a novel framework that achieves, for the first time, end-to-end generation of iEEG across the entire deep temporal lobe. The method leverages conditional normalizing flows (CNFs) to explicitly model the complex conditional probability distribution from sEEG to iEEG, effectively capturing signal stochasticity and mitigating mode collapse. Integrated with a multi-scale architecture and self-attention mechanisms, NeuroFlowNet enhances cross-modal generative capacity. Evaluated on a publicly available synchronized sEEG–iEEG dataset, the model demonstrates superior performance in reconstructing time-domain waveforms, spectral characteristics, and functional connectivity, establishing a new paradigm for non-invasive deep brain analysis.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Although obtaining deep brain activity from non-invasive scalp electroencephalography (sEEG) is crucial for neuroscience and clinical diagnosis, directly generating high-fidelity intracranial electroencephalography (iEEG) signals remains a largely unexplored field, limiting our understanding of deep brain dynamics. Current research primarily focuses on traditional signal processing or source localization methods, which struggle to capture the complex waveforms and random characteristics of iEEG. To address this critical challenge, this paper introduces NeuroFlowNet, a novel cross-modal generative framework whose core contribution lies in the first-ever reconstruction of iEEG signals from the entire deep temporal lobe region using sEEG signals. NeuroFlowNet is built on Conditional Normalizing Flow (CNF), which directly models complex conditional probability distributions through reversible transformations, thereby explicitly capturing the randomness of brain signals and fundamentally avoiding the pattern collapse issues common in existing generative models. Additionally, the model integrates a multi-scale architecture and self-attention mechanisms to robustly capture fine-grained temporal details and long-range dependencies. Validation results on a publicly available synchronized sEEG-iEEG dataset demonstrate NeuroFlowNet's effectiveness in terms of temporal waveform fidelity, spectral feature reproduction, and functional connectivity restoration. This study establishes a more reliable and scalable new paradigm for non-invasive analysis of deep brain dynamics. The code of this study is available in https://github.com/hdy6438/NeuroFlowNet

Problem

• intracranial EEG
• scalp EEG
• deep temporal lobe
• non-invasive reconstruction
• brain signal generation

Innovation

• Conditional Normalizing Flow
• Non-invasive iEEG reconstruction
• NeuroFlowNet
• Cross-modal generation
• Deep temporal lobe