Research Paper Volume 12, Issue 6 pp 4822—4835

Prediction of cognitive performance in old age from spatial probability maps of white matter lesions

Figure 4. Flow chart for analysis in the present study. First, FLAIR images were registered to the corresponding individual’s T1 space. Then, the k-nearest neighbor (KNN) classification algorithm was used to segment the white matter lesions (WMLs) automatically. Finally, a machine learning model, relevance vector regression (RVR), was used to predict cognitive performance based on the spatial probability maps of the WMLs.