2023
Multi-model order spatially constrained ICA reveals highly replicable group differences and consistent predictive results from resting data: A large N fMRI schizophrenia study
Meng X, Iraji A, Fu Z, Kochunov P, Belger A, Ford J, McEwen S, Mathalon D, Mueller B, Pearlson G, Potkin S, Preda A, Turner J, van Erp T, Sui J, Calhoun V. Multi-model order spatially constrained ICA reveals highly replicable group differences and consistent predictive results from resting data: A large N fMRI schizophrenia study. NeuroImage Clinical 2023, 38: 103434. PMID: 37209635, PMCID: PMC10209454, DOI: 10.1016/j.nicl.2023.103434.Peer-Reviewed Original ResearchConceptsIndependent component analysisData-driven approachData miningF1 scoreClassification modelReference algorithmNetwork connectivityMagnetic resonance imaging dataNetworkImaging dataPredictive resultsPatient dataFunctional magnetic resonance imaging (fMRI) dataData acquisition timeConnectivity networksFrameworkConnectivityPromising approachNew subjectMiningAnalytic approachAlgorithmDatasetAcquisition timeComponent analysis
2015
Classification of Schizophrenia and Bipolar Patients Using Static and Time-Varying Resting-State FMRI Brain Connectivity
Rashid B, Arbabshirani M, Damaraju E, Millar R, Cetin M, Pearlson G, Calhoun V. Classification of Schizophrenia and Bipolar Patients Using Static and Time-Varying Resting-State FMRI Brain Connectivity. 2015, 251-254. DOI: 10.1109/isbi.2015.7163861.Peer-Reviewed Original ResearchClassification of schizophreniaHigh-dimensional dataAutomatic differential diagnosisAutomatic classificationAccurate classifierDimensional dataChallenging taskNetwork connectivityDiscriminative analysisHigh accuracyPowerful informationClassificationTraining subjectsLarge amountPrevious workDynamic functional network connectivityConnectivityClassifierFunctional network connectivityFNC analysisTaskBrain connectivityRobustnessFrameworkAccuracy