Background: Functional magnetic resonance imaging (fMRI) analysis is commonly done with cross-correlation\r\nanalysis (CCA) and the General Linear Model (GLM). Both CCA and GLM techniques, however, typically perform\r\ncalculations on a per-voxel basis and do not consider relationships neighboring voxels may have. Clustered voxel\r\nanalyses have then been developed to improve fMRI signal detections by taking advantages of relationships of\r\nneighboring voxels. Mean-shift clustering (MSC) is another technique which takes into account properties of\r\nneighboring voxels and can be considered for enhancing fMRI activation detection.\r\nMethods: This study examines the adoption of MSC to fMRI analysis. MSC was applied to a Statistical Parameter\r\nImage generated with the CCA technique on both simulated and real fMRI data. The MSC technique was then\r\ncompared with CCA and CCA plus cluster analysis. A range of kernel sizes were used to examine how the\r\ntechnique behaves.\r\nResults: Receiver Operating Characteristic curves shows an improvement over CCA and Cluster analysis. False\r\npositive rates are lower with the proposed technique. MSC allows the use of a low intensity threshold and also\r\ndoes not require the use of a cluster size threshold, which improves detection of weak activations and highly\r\nfocused activations.\r\nConclusion: The proposed technique shows improved activation detection for both simulated and real Blood\r\nOxygen Level Dependent fMRI data. More detailed studies are required to further develop the proposed technique.
Loading....