Imaging the Topology of Dynamic Brain Connectivity

TL;DR

This paper introduces a novel imaging framework for dynamic brain connectivity that leverages topological data analysis to improve learning and diagnosis of neurological conditions like Alzheimer's.

Contribution

It presents a new topological image representation of evolving brain networks using persistent graph homology and Wasserstein embeddings, enabling effective deep learning applications.

Findings

Achieves clinically meaningful accuracy in early Alzheimer's detection

Provides stable embeddings under resolution changes

Enables transfer learning with limited data

Abstract

Functional brain connectivity changes dynamically over time, making its representation challenging for learning on non-Euclidean data. We present a framework that encodes dynamic functional connectivity as an image representation of evolving network topology. Persistent graph homology summarizes global organization across scales, yielding Wasserstein distance-preserving embeddings stable under resolution changes. Stacking these embeddings forms a topological image that captures temporal reconfiguration of brain networks. This design enables convolutional architectures and transfer learning from pretrained foundational models to operate effectively under limited and imbalanced data. Applied to early Alzheimer's detection, the approach achieves clinically meaningful accuracy, establishing a principled foundation for imaging dynamic brain topology.