Prediction of Brain Functional Connectivity Based on Bayesian Model

摘要: Aiming at the complex spatiotemporal correlation of longitudinal neuroimaging data, this paper proposes a brain function connection prediction method based on spatial and dynamic features. The uses conditional autoregressive model to capture between adjacent voxels combines it with Bayesian overcome existing method, considering only time correlation, predicting single period, avoiding simultaneous consider defects voxel-level connections. This selects data in ADNI database verify method. experimental results show that proposed can obtain robust accurate AD group control group, thus achieving implementation mental illness. Early intervention helps doctors make clinical decisions prevent serious consequences