Seizure Sources Can Be Imaged from Scalp EEG by Means of Biophysically Constrained Deep Neural Networks
Source check: Source checked. Not independent scientific confirmation.
Finding: In 33 patients, source maps were evaluated against iEEG-defined seizure-onset zones and successful resection; reported source localization was close to the clinically referenced focus. Clinical-reference comparison in 33 patients; retrospective validation, no prospective utility study. Exact DOI/title and result-level epilepsy comparisons in active/archive snapshots found no match.
Technology: A biophysically constrained deep neural network maps scalp EEG to intracranial seizure-source locations.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A biophysically constrained deep neural network maps scalp EEG to intracranial seizure-source locations.
- Test and result
- In 33 patients, source maps were evaluated against iEEG-defined seizure-onset zones and successful resection; reported source localization was close to the clinically referenced focus.
- Limitation / still unknown
- Clinical-reference comparison in 33 patients; retrospective validation, no prospective utility study. Exact DOI/title and result-level epilepsy comparisons in active/archive snapshots found no match.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://europepmc.org/articles/PMC11653641
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary source full text Methods and Results; version/date checked against bibliographic record..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.