2025
An Explainable Unified Framework of Spatio-Temporal Coupling Learning With Application to Dynamic Brain Functional Connectivity Analysis
Gao B, Yu A, Qiao C, Calhoun V, Stephen J, Wilson T, Wang Y. An Explainable Unified Framework of Spatio-Temporal Coupling Learning With Application to Dynamic Brain Functional Connectivity Analysis. IEEE Transactions On Medical Imaging 2025, 44: 941-951. PMID: 39320999, DOI: 10.1109/tmi.2024.3467384.Peer-Reviewed Original ResearchSpatio-temporal informationDeep learning networkInter-node connectivitySpatio-temporal correlationMachine learning modelsNode representationsPoor explainabilityCoupling learningLearning frameworkDeep learningLearning networkLearning modelsExplainabilityTime series dataExperimental resultsCoupling associationFramework constructionLearningDynamic functional connectivityFrameworkBrain functional connectivity analysisBrain dynamic functional connectivityInformationConnectionNetwork
2024
Brain networks and intelligence: A graph neural network based approach to resting state fMRI data
Thapaliya B, Akbas E, Chen J, Sapkota R, Ray B, Suresh P, Calhoun V, Liu J. Brain networks and intelligence: A graph neural network based approach to resting state fMRI data. Medical Image Analysis 2024, 101: 103433. PMID: 39708510, PMCID: PMC11877132, DOI: 10.1016/j.media.2024.103433.Peer-Reviewed Original ResearchConceptsGraph neural networksNeural networkGraph isomorphism networkGraph convolutional layersGraph convolutional networkMachine learning modelsNetwork connectivity matrixCognitive processesConvolutional layersConvolutional networkPrediction taskModel architectureGraph architectureAdolescent Brain Cognitive Development datasetResting-state functional magnetic resonance imagingFunctional magnetic resonance imagingLearning modelsMiddle frontal gyrusPredicting individual differencesResting state fMRI dataPredictive intelligenceIntelligenceNetworkFunctional network connectivity matricesArchitectureA simple but tough-to-beat baseline for fMRI time-series classification
Popov P, Mahmood U, Fu Z, Yang C, Calhoun V, Plis S. A simple but tough-to-beat baseline for fMRI time-series classification. NeuroImage 2024, 303: 120909. PMID: 39515403, PMCID: PMC11625415, DOI: 10.1016/j.neuroimage.2024.120909.Peer-Reviewed Original ResearchConceptsComplex machine learning modelsBlack-box natureMulti-layer perceptronMachine learning modelsPrediction accuracyBlack-box modelsFMRI classificationComplex classifiersClassification accuracySequential informationHuman fMRI dataLearning modelsBlack-boxRich modelsSuperior performanceComplex model developmentFMRI dataTime-series fMRI dataTime series dataClassifierStand-alone pieceClassificationAccuracyDesign modelSeries dataBrain networks and intelligence: A graph neural network based approach to resting state fMRI data
Thapaliya B, Akbas E, Chen J, Sapkota R, Ray B, Suresh P, Calhoun V, Liu J. Brain networks and intelligence: A graph neural network based approach to resting state fMRI data. Medical Image Analysis 2024, 101: 103433. PMID: 37986729, PMCID: PMC10659448, DOI: 10.1016/j.media.2024.103433.Peer-Reviewed Original ResearchGraph neural networksNeural networkGraph isomorphism networkGraph convolutional layersGraph convolutional networkMachine learning modelsMean square errorNetwork connectivity matrixCognitive processesConvolutional layersConvolutional networkPrediction taskModel architectureGraph architectureAdolescent Brain Cognitive Development datasetResting-state functional magnetic resonance imagingFunctional magnetic resonance imagingLearning modelsMiddle frontal gyrusPredicting individual differencesResting state fMRI dataPredictive intelligenceIntelligenceNetworkFunctional network connectivity matricesIdentifying Reproducibly Important EEG Markers of Schizophrenia with an Explainable Multi-Model Deep Learning Approach
Sancho M, Ellis C, Miller R, Calhoun V. Identifying Reproducibly Important EEG Markers of Schizophrenia with an Explainable Multi-Model Deep Learning Approach. Annual International Conference Of The IEEE Engineering In Medicine And Biology Society (EMBC) 2024, 00: 1-4. PMID: 40039893, DOI: 10.1109/embc53108.2024.10781959.Peer-Reviewed Original ResearchConceptsDeep learning approachLearning-based studiesMachine learning methodsMachine learning modelsMachine learning-based studiesExplainability approachesCross-validation foldsLearning methodsLearning approachLearning modelsDevelopment of robust approachesMachineDiagnosis of schizophreniaDiverse symptom presentationsPower dataBiomarkers of SZRobust approachFrequency bandLeft hemisphereSpectral power dataMultimodal active subspace analysis for computing assessment oriented subspaces from neuroimaging data
Batta I, Abrol A, Calhoun V, Initiative A. Multimodal active subspace analysis for computing assessment oriented subspaces from neuroimaging data. Journal Of Neuroscience Methods 2024, 406: 110109. PMID: 38494061, PMCID: PMC11100582, DOI: 10.1016/j.jneumeth.2024.110109.Peer-Reviewed Original ResearchConceptsBrain subspacesStandard machine learning algorithmsHigh-dimensional neuroimaging dataTrain machine learning modelsUnsupervised decompositionMachine learning algorithmsMachine learning modelsFunctional sub-systemsSubspace analysisSubspace componentsLearning algorithmsSupervised approachBiological traitsLearning modelsSub-systemsAlzheimer's diseaseSubspaceComputational frameworkActive subspaceCross-validation procedureNeuroimaging dataAD-related brain regionsAutomated identificationPredictive performanceOrientation subspaces
2023
Deep learning with explainability for characterizing age-related intrinsic differences in dynamic brain functional connectivity
Qiao C, Gao B, Liu Y, Hu X, Hu W, Calhoun V, Wang Y. Deep learning with explainability for characterizing age-related intrinsic differences in dynamic brain functional connectivity. Medical Image Analysis 2023, 90: 102941. PMID: 37683445, DOI: 10.1016/j.media.2023.102941.Peer-Reviewed Original ResearchFunctional connectivityBrain functional connectivityBrain networksDynamic brain functional connectivityDeep networksFunctional brain networksInformation processing abilityBrain development studiesEmotional processingDeep learning approachFeature selection strategyMachine learning modelsProcessing abilityBrain developmentCognitive activityDeep learningAccuracy-orientedSound processingBrainDevelopmental patternsLearning approachLearning modelsMental regulationSelection strategyInformation transmission mechanismEffective Training Strategy for NN Models of Working Memory Classification with Limited Samples
Suresh P, Ray B, Thapaliya B, Farahdel B, Kazemivash B, Chen J, Duan K, Calhoun V, Liu J. Effective Training Strategy for NN Models of Working Memory Classification with Limited Samples. 2023, 00: 1-4. DOI: 10.1109/isbi53787.2023.10230722.Peer-Reviewed Original ResearchTraining strategyNeural networkData-hungry techniquesNN modelImage featuresSets of hyperparametersMachine learning methodsMachine learning modelsTrained NN modelModel performanceHigh memory capacityImbalanced samplesLearning methodsMemory capacityBrain imaging featuresSuboptimal solutionLearning modelsNetwork configurationEffective training strategyEfficient reuseWorking memory capacityTask-specificData conditionsBiomedical imagingNetwork
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply