In this study, we examined whether age can be predicted on the basis of different anatomical features obtained from a large sample of healthy subjects (n = 3,144). From this sample we obtained different anatomical feature sets: (1) 11 larger brain regions (including cortical volume, thickness, area, subcortical volume, cerebellar volume, etc.), (2) 148 cortical compartmental thickness measures, (3) 148 cortical compartmental area measures, (4) 148 cortical compartmental volume measures, and (5) a combination of the above-mentioned measures. With these anatomical feature sets, we predicted age using 6 statistical techniques (multiple linear regression, ridge regression, neural network, k-nearest neighbourhood, support vector machine, and random forest). We obtained very good age prediction accuracies, with the highest accuracy being R = 0.84 (prediction on the basis of a neural network and support vector machine approaches for the entire data set) and the lowest being R = 0.40 (prediction on the basis of a k-nearest neighborhood for cortical surface measures). Interestingly, the easy-to-calculate multiple linear regression approach with the 11 large brain compartments resulted in a very good prediction accuracy (R = 0.73), whereas the application of the neural network approach for this data set revealed very good age prediction accuracy (R = 0.83). Taken together, these results demonstrate that age can be predicted well on the basis of anatomical measures. The neural network approach turned out to be the approach with the best results. In addition, it was evident that good prediction accuracies can be achieved using a small but nevertheless age-representative dataset of brain features. Hum Brain Mapp 38:997-1008, 2017. © 2016 Wiley Periodicals, Inc.

We examined whether it is possible to identify individual subjects on the basis of brain anatomical features. For this, we analyzed a dataset comprising 191 subjects who were scanned three times over a period of two years. Based on FreeSurfer routines, we generated three datasets covering 148 anatomical regions (cortical thickness, area, volume). These three datasets were also combined to a dataset containing all of these three measures. In addition, we used a dataset comprising 11 composite anatomical measures for which we used larger brain regions (11LBR). These datasets were subjected to a linear discriminant analysis (LDA) and a weighted K-nearest neighbors approach (WKNN) to identify single subjects. For this, we randomly chose a data subset (training set) with which we calculated the individual identification. The obtained results were applied to the remaining sample (test data). In general, we obtained excellent identification results (reasonably good results were obtained for 11LBR using WKNN). Using different data manipulation techniques (adding white Gaussian noise to the test data and changing sample sizes) still revealed very good identification results, particularly for the LDA technique. Interestingly, using the small 11LBR dataset also revealed very good results indicating that the human brain is highly individual.

No abstract