Featured Publications
Development of Expert-Level Automated Detection of Epileptiform Discharges During Electroencephalogram Interpretation
Jing J, Sun H, Kim JA, Herlopian A, Karakis I, Ng M, Halford JJ, Maus D, Chan F, Dolatshahi M, Muniz C, Chu C, Sacca V, Pathmanathan J, Ge W, Dauwels J, Lam A, Cole AJ, Cash SS, Westover MB. Development of Expert-Level Automated Detection of Epileptiform Discharges During Electroencephalogram Interpretation. JAMA Neurology 2020, 77: 103-108. PMID: 31633740, PMCID: PMC6806668, DOI: 10.1001/jamaneurol.2019.3485.Peer-Reviewed Original Research
2022
Deep Learning Applications for Acute Stroke Management
Chavva IR, Crawford AL, Mazurek MH, Yuen MM, Prabhat AM, Payabvash S, Sze G, Falcone GJ, Matouk CC, de Havenon A, Kim JA, Sharma R, Schiff SJ, Rosen MS, Kalpathy‐Cramer J, Gonzalez J, Kimberly WT, Sheth KN. Deep Learning Applications for Acute Stroke Management. Annals Of Neurology 2022, 92: 574-587. PMID: 35689531, DOI: 10.1002/ana.26435.Peer-Reviewed Original ResearchConceptsDeep machine learningDeep learning applicationsMedical image analysisDeep neural networksPixel-wise labelingAcute stroke managementReal-world examplesDL applicationsDL approachMachine learningLearning applicationsDL modelsNeural networkStroke managementLesion segmentationMaximal utilityImage analysisElectronic medical record dataInter-rater variabilityCause of disabilityMedical record dataRelevant clinical featuresStroke detectionAdvanced neuroimaging techniquesDecision making
2020
Deep active learning for Interictal Ictal Injury Continuum EEG patterns
Ge W, Jing J, An S, Herlopian A, Ng M, Struck AF, Appavu B, Johnson EL, Osman G, Haider HA, Karakis I, Kim JA, Halford JJ, Dhakar MB, Sarkis RA, Swisher CB, Schmitt S, Lee JW, Tabaeizadeh M, Rodriguez A, Gaspard N, Gilmore E, Herman ST, Kaplan PW, Pathmanathan J, Hong S, Rosenthal ES, Zafar S, Sun J, Westover M. Deep active learning for Interictal Ictal Injury Continuum EEG patterns. Journal Of Neuroscience Methods 2020, 351: 108966. PMID: 33131680, PMCID: PMC8135050, DOI: 10.1016/j.jneumeth.2020.108966.Peer-Reviewed Original ResearchConceptsConvolutional neural networkIll patientsActive learningLarge labeled datasetExpert-level performanceDeep active learningLarge EEG datasetsPseudo-labeled dataUse of ALElectroencephalography patternsPatient careQuery criteriaLabeled datasetLabel spreadingEEG patternsPatientsExpert labelsClass balancingNeural networkAvailable labelsVector representationQueriesInformative examplesAL approachEEG dataset