GPR-SCSANet: Unequal-Length Time Series Normalization with Split-Channel Residual Convolution and Self-Attention for Brain Age Prediction
Sun F, Liang C, Adali T, Zhang D, Jiang R, Calhoun V, Qi S. GPR-SCSANet: Unequal-Length Time Series Normalization with Split-Channel Residual Convolution and Self-Attention for Brain Age Prediction. 2024, 00: 5097-5103. DOI: 10.1109/bibm62325.2024.10822453.Peer-Reviewed Original ResearchSelf-attention mechanismResidual convolutionGaussian process regressionFunctional magnetic resonance imagingReal-world scenariosAge prediction taskSelf-attentionPrediction taskBrain age estimationAge predictionInherent informationBrain age predictionFMRI time coursesLength of time seriesProcess regressionVariables conflictBrain functional alterationsConvolutionPrediction accuracyUnequal-lengthTraditional methodsMotion artifactsDownstream applicationsTime series normalizationPrediction modelA deep spatio-temporal attention model of dynamic functional network connectivity shows sensitivity to Alzheimer’s in asymptomatic individuals
Wei Y, Abrol A, Lah J, Qiu D, Calhoun V. A deep spatio-temporal attention model of dynamic functional network connectivity shows sensitivity to Alzheimer’s in asymptomatic individuals. Annual International Conference Of The IEEE Engineering In Medicine And Biology Society (EMBC) 2024, 00: 1-4. PMID: 40039841, DOI: 10.1109/embc53108.2024.10781740.Peer-Reviewed Original ResearchConceptsDynamic functional network connectivityFunctional magnetic resonance imagingSpatio-temporal attention modelNetwork connectivityMild cognitive impairmentDeep learning advancesFunctional network connectivityMachine learning methodsSelf-attentionAttention modelAt-risk subjectsLearning methodsLearning advancesAlzheimer's diseaseNetwork dependence
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply