Metraipolis › archive › dc_0632273a4fbb

NeuroDyn-EEG: An Interpretable Pre-trained Model for EEG Based on Neural Dynamics — arXiv:2609.36773

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36773
License (as archived)
CC0-1.0
Archived
2026-10-07T19:16:49.311Z
SHA-256 of the archived text
5071dbfca1ff053ee7ad42a46d5d1e671a2b4e7c4a5345bd07465cc70b899fa9
Stable URL of this page
https://metraipolis.com/documento/dc_0632273a4fbb

How to cite

NeuroDyn-EEG: An Interpretable Pre-trained Model for EEG Based on Neural Dynamics — arXiv:2609.36773 — arXiv (en), https://arxiv.org/abs/2609.36773 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0632273a4fbb (Metraipolis archive dc_0632273a4fbb, sha256 5071dbfca1ff053ee7ad42a46d5d1e671a2b4e7c4a5345bd07465cc70b899fa9)
BibTeX
@misc{dc0632273a4fbb,
  title = {NeuroDyn-EEG: An Interpretable Pre-trained Model for EEG Based on Neural Dynamics — arXiv:2609.36773},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36773},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0632273a4fbb; sha256 5071dbfca1ff053ee7ad42a46d5d1e671a2b4e7c4a5345bd07465cc70b899fa9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36773. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Clinical scalp electroencephalography (EEG) offers a noninvasive window into neural dynamics of neuropsychiatric disorders. However, discriminative deep models often lack anatomically indexed physiological interpretability. We propose NeuroDyn-EEG, a pretraining framework integrating generative priors from neural dynamics. It couples an extended Jansen-Rit neural mass model, leadfield-based source projection, and simulation-based parameter inversion. Trained on synthetic parameter-EEG pairs within physiological ranges, NeuroDyn-EEG estimates 11 regional parameter families across 90 AAL regions plus one global parameter from standard 19-channel EEG, using only ~2.43M trainable parameters. We evaluate the framework across three levels. First, controlled simulations demonstrate robust parameter recovery under diverse noise conditions, while real resting-state EEG evaluations confirm spectral and phase consistency in an inverse-forward closed loop. Second, on four clinical benchmarks (AD65, PD31, Figshare MDD, and TUAB), NeuroDyn-EEG achieves competitive classification performance, securing the highest BACC, AUROC, and AUCPR on PD31 and MDD, and highest BACC on AD65. Third, post hoc regional analyses reveal disease-specific alterations: local synaptic connectivity C_1 involves the most altered regions in AD65, whereas the firing threshold theta ranks first in MDD, offering testable mechanistic hypotheses. Overall, NeuroDyn-EEG maps scalp EEG to anatomically indexed dynamical parameters, bridging representation learning and mechanistic neurophysiology. Code: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.NE).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2609.36773 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T18:42:49.275Z dalla pagina https://arxiv.org/catchup/cs.NE/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).