Multiscale Community-Based Fingerprinting of Signed Functional Networks
Authors: Sema Athamnah, Selin Aviyente
Organizations: Department of Biomedical Engineering, Michigan State University, USA. · Department of Electrical and Computer Engineering, Michigan State University, USA.
Objective: Recent studies demonstrate that functional connectomes contain subject-specific signatures, or fingerprints, that can identify individuals across repeated sessions and tasks. Existing methods mostly rely on edge-level features that are sensitive to noise, difficult to interpret, and limited in their ability to generalize across tasks and datasets. Methods: We propose a multiscale community-based functional connectome fingerprinting framework that characterizes each individual by the mesoscale structure of their functional networks. We introduce a signed multilayer community detection framework that incorporates both correlated and anti-correlated brain activity to identify subject-specific community structures across tasks and sessions. Graph-theoretic metrics are then computed from the resulting joint community structures to derive low-dimensional community-level fingerprint representations. Results: The proposed framework is evaluated on 810 healthy control subjects from the Human Connectome Project (HCP). The results show that community-based fingerprints provide a reliable and interpretable substrate for individualized brain characterization across sessions and tasks. Conclusion: Mesoscale community structure provides meaningful and discriminative subject-specific fingerprints. Significance: The proposed framework offers a promising foundation for precision neuroimaging and personalized neuroscience applications.
Figures & tables
Notations
Explanations
G±
Signed graph.
N
Number of nodes.
V
Set of nodes.
E
Set of edges.
A±
Positive (negative) adjacency matrix.
P±
Positive (negative) null-model adjacency matrix.
Table 1: Notation definitions.
Figure 1: Overview of the proposed community-based fingerprinting framework. (a) Multiscale Community Detection: A signed multilayer modularity (SMM) optimization framework is applied to generate a set of multiscale partitions by varying the resolution ( γ ) and interlayer coupling ( ω ) parameters (Section 3.1 ). (b) Fingerprint Extraction: For each partition, community-level graph-theoretic features are extracted from each subject’s functional connectivity (FC) network to construct community-based fingerprint (CBF) vectors (Section 3.2 ). (c) Partition Selection: The resulting partitions are ranked according to the mean pairwise Euclidean distance (MPED) of their corresponding CBF vectors, and the top- L partitions are selected (Section 3.3 ). (d) Subject Identification: The selected top- L partitions are used to construct the training and testing CBFs from the corresponding training and testing FC networks. For each selected partition and feature type, each testing CBF vector is matched to its corresponding training CBF vector using a distance-based nearest-neighbor classifier for subject identification (Section 3.4 ).
Figure 2: Within-task fingerprinting results for a sample size of S=100 , averaged across 10 randomly selected subject groups.
Figure 3: Within-task fingerprinting results across different methods for sample sizes (a) S=200 , (b) 300 , and (c) 400 .
Figure 4: Between-task fingerprinting results across different methods for a sample size of S=400 . Results for S=200 , and 300 are provided in the Supplementary Materials.
Figure 5: Discriminative connectivity maps illustrating the spatial distribution of the top-1% discriminative community-based fingerprints (first and third rows), with the corresponding contributions of the seven Yeo functional brain systems (second and fourth rows) for each HCP task ( S=400 ).
Effect
DF
F-value
p -value
p -value (GG)
fMRI task
7,63
1181.60
2.79×10−64∗
1.08×10−31∗
Method
7,63
5834.68
4.89×10−86∗
6.48×10−28∗
fMRI task × Method
49,441
180.61
1.47×10−260∗
1.74×10−30∗
Table 2: Results of the two-way repeated-measures ANOVA for sample size S =100.
Table 3: Bonferroni-corrected post-hoc comparisons for the method factor, for sample size S =100.
Effect
DF
F-value
p -value
fMRI task
7,98
2531.54
1.03×10−107
Sample Size
2,98
373.31
1.46×10−46
Method
7,98
2269.96
2.09×10−105
Method × Sample Size
14,98
13.77
1.90×10−17
Method × fMRI task
49,98
77.45
1.68×10−60
Sample Size × fMRI task
14,98
4.13
1.27×10−5
Table 4: Results of the three-way ANOVA for sample size S =200, 300, and 400.
Table 5: Bonferroni-corrected post-hoc comparisons for the method factor for sample size S =200, 300, and 400.
School of Medicine, University of Dundee, UK · College of Medicine and Biological Information Engineering, Northeastern University, China · School of Airspace Science and Engineering, Shandong University, China +5