Brain-fingerprinting

Author: Jason da Silva Castanheira

This tutorial introduces the concept and method of neurophysiological brain-fingerprinting. Using the outputs of the OMEGA tutorial, we will derrive spectral brain-fingerprints, as detailed below, for the five example participants.

Introduction

Brain-fingerprinting is a method to assess inter-individual differences in brain activity. It was first proposed by Finn and colleagues in 2015. The present tutorial will demonstrate the method's functionality using Brainstorm outputs.

This demonstration uses sample data from the OMEGA dataset , and can be followed by completing all steps of the OMEGA tutorial.

Preparing the data for brain-fingerprinting

The brain-fingerprinting method requires features of interest to define the so-called brain-fingerprint. These features can be derrived from functional connectomes or from neural power spectrum, as detailed in da Silva Castanheira et al., 2021.

This tutorial will focus on derriving brain-fingerprints using neural power spectra at every parcel of the Destrieux atlas.

To do so, we compute the spectrum (i.e., PSD) using the Welch method at every vertex of the cortical surface, and average the resulting values within each region defined by the Destrieux atlas. Note, this is done to downsample the spatial features of the brain-fingerprint. If we did not downsample the PSD to a cortical atlas, the resulting feature space would be too large to work with (e.g., 15,000 vertecies by 300 frequncies).

{attachment:Tutorials/BrainFingerprint/bfp_code.png|AlternativeText|width="100%"}

Brain-fingerprinting require at least two data segments for every individual. For the purposes of this demonstartion, we will split the OMEGA recordings in half (i.e., within-session fingerprinting).

The brain-fingerpinting method

Brain-fingerprinting is a method based on the correlational similarity of participants across data segments. For each participant in a given cohort, we compute the Pearson correlation coefficient between the brain-fingerprint (in the case of this demonstration, the regional PSD) of the first segment and the second brain-fingerprint of all participants in the cohort, including the probe participant. This yeilds a participant similarity matrix, where off-diagonal elements represent the similarity of a participant i to all other participant and diagonal elements represent the similarity of a participant's brain-fingerprint across data segments.

INSERT IMAGE HERE

Participant differentiation consists of a lookup procedure along the rows or columns of the participant similarity correlation matrix. A participant is said to be correctly differentiated if a participant's brain-fingerprint is most similar to themselves (self-similarity) than all other participants in the cohort (other-similarity). In other words, if the largest correlation coefficient between the first brain-fingerprint and the second matches the probe participant.

Differentiation accuracy

Differentiation accuracy represent the percent ratio of the number of participants correctly differentiated across the cohort (i.e., differentiation accuracy). Brain-fingerprinting is typically repreated for all possible pairs of data segments. In the case of this tutorial, we only have two data segments (the first and second half of the recording) and therefore only have two differentiation accuracies--obtained by a lookup procedure along the rows and columns respectively.

Differentiability

We previously defined differentiability to describe how easy any given participant is to differentiate from a cohort of individuals. This measure consists of the autocorrelation 9self-similarity) of the spectral brain-fingerprint of participanti (data segment 1 to data segment 2), z-scored to the mean and standard deviation of the cross-correlation 9other-similarity) of participanti data segment 1 with the data segment 2 of all others in the cohort (see 9 for details). A participant with a high differentiability score will have a higher autocorrelation relative to their cross-correlation to others in the cohort, and therefore be easier to accurately identify.

Quantifying the most salient features of the brain-fingerprint

SPRiNT is performed on time series, so we will first prepare some data from our notch-filtered dataset

Applications of the brain-fingerprint

SPRiNT is performed on time series, so we will first prepare some data from our notch-filtered dataset

Additional documentation

SPRiNT is performed on time series, so we will first prepare some data from our notch-filtered dataset