{"doi":"10.3389/fnhum.2025.1680395","title":"Using vision transformers for electrographic seizure classification to aid physician review of intracranial electroencephalography recordings","abstract":"We introduce a vision transformer (ViT)-based approach for automated electrographic seizure classification using time-frequency spectrogram representations of intracranial EEG (iEEG) recordings collected from patients implanted with the NeuroPace ® RNS ® System. The ViT model was trained and evaluated using 5-fold cross-validation on a large-scale dataset of 136,878 iEEG recordings from 113 patients with drug-resistant focal epilepsy, achieving an average test accuracy of 96.8%. Clinical validation was performed on an independent expert-labeled dataset of 3,010 iEEG recordings from 241 patients, where the model achieved 95.8% accuracy and 94.8% F1 score on recordings with unanimous expert agreement, outperforming both ResNet-50 and standard 2D CNN baselines. To evaluate generalizability, the model was tested on a separate out-of-distribution dataset of 136 recordings from 44 patients with idiopathic generalized epilepsy (IGE), achieving over 75% accuracy and F1 scores across all expert comparisons. Explainability analysis revealed focused attention on characteristic electrographic seizure patterns within iEEG time-frequency spectrograms during high-confidence seizure predictions, while more diffuse attention was observed in non-seizure classifications, providing insight into the underlying decision process. By enabling reliable electrographic seizure classification, this approach may assist physicians in the manual review of large volumes of iEEG recordings.","journal":"Frontiers in Human Neuroscience","year":2025,"id":536837,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9577,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1401974,"name":"Sharanya Arcot Desai","orcid":"0000-0003-4542-6905","position":1,"is_corresponding":false},{"id":1402536,"name":"Wade Barry","orcid":null,"position":2,"is_corresponding":false},{"id":1401976,"name":"Thomas K. Tcheng","orcid":"0000-0002-5491-5295","position":3,"is_corresponding":false},{"id":1422676,"name":"Jonathan T. W. Kuo","orcid":null,"position":4,"is_corresponding":false},{"id":1402537,"name":"Shawna Benard","orcid":null,"position":5,"is_corresponding":false},{"id":1402538,"name":"Christopher B. Traner","orcid":null,"position":6,"is_corresponding":false},{"id":1055414,"name":"David Greene","orcid":"0000-0001-9574-3656","position":7,"is_corresponding":false},{"id":229614,"name":"Cairn G. Seale","orcid":null,"position":8,"is_corresponding":false},{"id":227196,"name":"Martha J. Morrell","orcid":"0000-0001-8157-5313","position":9,"is_corresponding":false},{"id":811581,"name":"Muhammad Furqan Afzal","orcid":"0000-0002-8476-4539","position":0,"is_corresponding":true}],"reference_count":34,"raw_metadata":null,"created_at":"2026-07-19T02:52:09.056872Z","pmid":"41132588","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}