Prediction of Brain Connectivity Map in Resting-State Fmri Data Using Shrinkage Estimator

Introduction: in recent years, brain functional connectivity studies are extended using the advanced statistical methods. functional connectivity is identified by synchronous activation in a spatially distinct region of the brain in restingstate functional magnetic resonance imaging (mri) data. for this purpose there are several methods such as seedbased correlation analysis based on temporal correlation between different regions of interests (rois) or between brain rsquo;s voxels of prior seed.methods: in the current study, testretest resting state functional mri (rsfmri) data of 21 healthy subjects were analyzed to predict second replication connectivity map using first replication data. a potential estimator is ldquo;raw estimator rdquo; that uses the first replication data from each subject to predict the second replication connectivity map of the same subject. the second estimator, ldquo;mean estimator rdquo; uses the average of all sample subjects' connectivity to estimate the correlation map. shrinkage estimator is made by shrinking raw estimator towards the average connectivity map of all subjects' first replicate. prediction performance of the second replication correlation map is evaluated by mean squared error (mse) criteria.results: by the employment of seedbased correlation analysis and choosing precentral gyrus as the roi over 21 subjects in the study, on average mse for raw, mean and shrinkage estimator were 0.2169, 0.1118, and 0.1103, respectively. also, percent reduction of mse for shrinkage and mean estimator in comparison with raw estimator is 49.14 and 48.45, respectively.conclusion: shrinkage approach has the positive effect on the prediction of functional connectivity. when data has a large between session variability, prediction of connectivity map can be improved by shrinking towards population mean.