A Novel Metabolic Connectome Method to Predict Progression to Mild Cognitive Impairment

Figure 2

The framework for the estimation of metabolic connectivity (MC) between pairwise regions from individual FDG-PET image. Firstly, the FDG-PET image was divided into 90 ROIs, and the metabolic intensity values of voxels with random ROI were extracted. Then, kernel density estimation was employed to estimate the probability density function (PDF) of each ROI. Lastly, the KLSE algorithm was implemented to measure the metabolic correlation by the similarity among PDFs.