Show Me Your Brain…

and I’ll tell you who you are. One driving force behind human individuality is individual experience, which shapes our behavior and the neural underpinnings of behavior. Over the past thirty years of his academic career, Lutz Jäncke has studied how these individual experiences, such as training or education, influence the structure and function of the brain. In a longitudinal study, his team now wanted to find out whether individual subjects can be identified based on neuroanatomical features measured with standard MRI techniques.

Over the past eight years, Lutz Jäncke and his team have followed a large cohort of 230 subjects at regular intervals using a range of different MRI and psychological measures. This longitudinal approach was possible within the framework of the University Research Priority Program “Dynamic of Healthy Aging” at the University of Zurich. In collaboration with Seyed Valizadeh from the Department of Cognitive Science at ETH Zurich, basic neuroanatomical measures, such as cortical thickness, volumes of different brain areas were extracted, and a set of statistical classification techniques were applied. Using the newly developed rule-based identification approach (RBIA), sets of neuroanatomical features obtained at baseline were combined by if–then rules and compared to the same set of neuroanatomical features derived from the 7-year follow-up measurement. While linear discriminant analysis (LDA) and Random Forest machine learning (RF) showed satisfying results, the RBIA achieved perfect participant identification for some four-feature sets. The identification results improved substantially when using larger feature sets, with fourteen neuroanatomical features providing perfect identification.

This study shows once more that the human brain is highly individual in terms of neuroanatomical features. Thus, it is possible to recognize individual persons based on only a few anatomical features, even if these anatomical features are already seven years old. The authors assume that these anatomical traits are influenced not only by genetic but also by experience-based influences.

By: Lutz Jäncke, Department of Neuropsychology, University of Zurich and Seyed Valizadeh, Department of Cognitive Science, ETH Zurich.

Reference: Jäncke, L., & Valizadeh, S. A. Identification of individual subjects based on neuroanatomical measures obtained 7 years earlier. The European Journal of Neuroscience (2022).

Further reading:

Valizadeh, S. A., Riener, R., Elmer, S., & Jäncke, L. Decrypting the electrophysiological individuality of the human brain: Identification of individuals based on resting-state EEG activity. NeuroImage (2019).

Valizadeh, S. A., Liem, F., Mérillat, S., Hänggi, J., & Jäncke, L. Identification of individual subjects on the basis of their brain anatomical features. Scientific Reports (2018).

Valizadeh, S. A., Hänggi, J., Mérillat, S., & Jäncke, L. Age prediction on the basis of brain anatomical measures. Human Brain Mapping (2017).