Skip to main content
Brain Informatics
Fig. 5 | Brain Informatics

Fig. 5

From: A comparison of feature extraction methods for prediction of neuropsychological scores from functional connectivity data of stroke patients

Fig. 5

Maps of predictive functional connectivity edges for PCA-based models obtained by back-projecting the regression coefficients. The top 200 edges are projected onto a semitransparent brain: green connections represent positive weights, whereas orange connections represent negative weights. The spheres/nodes represent the cortical parcels linked by the selected edges and are displayed with size proportional to their contribution to the model

Back to article page