Using deep clustering to improve fMRI dynamic functional connectivity analysis

Neuroimage. 2022 Aug 15;257:119288. doi: 10.1016/j.neuroimage.2022.119288. Epub 2022 May 10.

Abstract

Dynamic functional connectivity (dFC) analysis of resting-state fMRI data is commonly performed by calculating sliding-window correlations (SWC), followed by k-means clustering in order to assign each window to a given state. Studies using synthetic data have shown that k-means performance is highly dependent on sliding window parameters and signal-to-noise ratio. Additionally, sources of heterogeneity between subjects may affect the accuracy of group-level clustering, thus affecting measurements of dFC state temporal properties such as dwell time and fractional occupancy. This may result in spurious conclusions regarding differences between groups (e.g. when comparing a clinical population to healthy controls). Therefore, is it important to quantify the ability of k-means to estimate dFC state temporal properties when applied to cohorts of multiple subjects, and to explore ways in which clustering performance can be maximised. Here, we explore the use of dimensionality reduction methods prior to clustering in order to map high-dimensional data to a lower dimensional space, providing salient features to the subsequent clustering step. We assess the use of deep autoencoders for dimensionality reduction prior to applying k-means clustering to the encoded data. We compare this deep clustering method to dimensionality reduction using principle component analysis (PCA), uniform manifold approximation and projection (UMAP), as well as applying k-means to the original feature space using either L1 or L2 distance. We provide extensive quantitative evaluation of clustering performance using synthetic datasets, representing data from multiple heterogeneous subjects. In synthetic data we find that deep clustering gives the best performance, while other approaches are often insufficient to capture temporal properties of dFC states. We then demonstrate the application of each method to real-world data from human subjects and show that the choice of dimensionality reduction method has a significant effect on group-level measurements of state temporal properties.

Keywords: Autoencoders; Deep learning; Dimensionality reduction; Dynamic functional connectivity; Sliding window correlations.

Publication types

  • Research Support, Non-U.S. Gov't
  • Research Support, N.I.H., Extramural

MeSH terms

  • Brain / diagnostic imaging
  • Brain Mapping* / methods
  • Cluster Analysis
  • Humans
  • Magnetic Resonance Imaging* / methods
  • Principal Component Analysis