{"doi":"10.1093/braincomms/fcab267","title":"Refining epileptogenic high-frequency oscillations using deep learning: a reverse engineering approach","abstract":"Abstract Intracranially recorded interictal high-frequency oscillations have been proposed as a promising spatial biomarker of the epileptogenic zone. However, its visual verification is time-consuming and exhibits poor inter-rater reliability. Furthermore, no method is currently available to distinguish high-frequency oscillations generated from the epileptogenic zone (epileptogenic high-frequency oscillations) from those generated from other areas (non-epileptogenic high-frequency oscillations). To address these issues, we constructed a deep learning-based algorithm using chronic intracranial EEG data via subdural grids from 19 children with medication-resistant neocortical epilepsy to: (i) replicate human expert annotation of artefacts and high-frequency oscillations with or without spikes, and (ii) discover epileptogenic high-frequency oscillations by designing a novel weakly supervised model. The ‘purification power’ of deep learning is then used to automatically relabel the high-frequency oscillations to distill epileptogenic high-frequency oscillations. Using 12 958 annotated high-frequency oscillation events from 19 patients, the model achieved 96.3% accuracy on artefact detection (F1 score = 96.8%) and 86.5% accuracy on classifying high-frequency oscillations with or without spikes (F1 score = 80.8%) using patient-wise cross-validation. Based on the algorithm trained from 84 602 high-frequency oscillation events from nine patients who achieved seizure-freedom after resection, the majority of such discovered epileptogenic high-frequency oscillations were found to be ones with spikes (78.6%, P < 0.001). While the resection ratio of detected high-frequency oscillations (number of resected events/number of detected events) did not correlate significantly with post-operative seizure freedom (the area under the curve = 0.76, P = 0.06), the resection ratio of epileptogenic high-frequency oscillations positively correlated with post-operative seizure freedom (the area under the curve = 0.87, P = 0.01). We discovered that epileptogenic high-frequency oscillations had a higher signal intensity associated with ripple (80–250 Hz) and fast ripple (250–500 Hz) bands at the high-frequency oscillation onset and with a lower frequency band throughout the event time window (the inverted T-shaped), compared to non-epileptogenic high-frequency oscillations. We then designed perturbations on the input of the trained model for non-epileptogenic high-frequency oscillations to determine the model’s decision-making logic. The model confidence significantly increased towards epileptogenic high-frequency oscillations by the artificial introduction of the inverted T-shaped signal template (mean probability increase: 0.285, P < 0.001), and by the artificial insertion of spike-like signals into the time domain (mean probability increase: 0.452, P < 0.001). With this deep learning-based framework, we reliably replicated high-frequency oscillation classification tasks by human experts. Using a reverse engineering technique, we distinguished epileptogenic high-frequency oscillations from others and identified its salient features that aligned with current knowledge.","journal":"Brain Communications","year":2021,"id":158457,"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":46,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9559,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":667614,"name":"Qiujing Lu","orcid":"0000-0002-3038-256X","position":1,"is_corresponding":false},{"id":668503,"name":"Tonmoy Monsoor","orcid":null,"position":2,"is_corresponding":false},{"id":367088,"name":"Shaun A. Hussain","orcid":"0000-0001-6947-8852","position":3,"is_corresponding":false},{"id":667615,"name":"Joe X Qiao","orcid":"0000-0003-0089-7930","position":4,"is_corresponding":false},{"id":397177,"name":"Noriko Salamon","orcid":"0000-0002-3520-9467","position":5,"is_corresponding":false},{"id":457492,"name":"Aria Fallah","orcid":"0000-0002-9703-0964","position":6,"is_corresponding":false},{"id":284479,"name":"Myung‐Shin Sim","orcid":"0000-0001-9706-1499","position":7,"is_corresponding":false},{"id":311335,"name":"Eishi Asano","orcid":"0000-0001-8391-4067","position":8,"is_corresponding":false},{"id":419219,"name":"Raman Sankar","orcid":null,"position":9,"is_corresponding":false},{"id":581696,"name":"Richard J. Staba","orcid":"0000-0003-2285-5627","position":10,"is_corresponding":false},{"id":667616,"name":"Jerome Engel","orcid":"0000-0001-6324-5716","position":11,"is_corresponding":false},{"id":241711,"name":"William Speier","orcid":"0000-0002-0890-8684","position":12,"is_corresponding":false},{"id":667617,"name":"Vwani Roychowdhury","orcid":"0000-0003-0832-6489","position":13,"is_corresponding":false},{"id":488243,"name":"Hiroki Nariai","orcid":"0000-0002-8318-2924","position":14,"is_corresponding":false},{"id":667613,"name":"Yipeng Zhang","orcid":"0000-0003-2869-4692","position":0,"is_corresponding":true}],"reference_count":53,"raw_metadata":null,"created_at":"2026-07-18T23:44:30.791367Z","pmid":"35169696","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":[]}