Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-scale fMRI time series analysis for understanding neurodegeneration in MCI

Ammu R., Debanjali Bhattacharya, Ameiy Acharya, Ninad Aithal, Neelam Sinha

TL;DR

A technique that spans multi-scale views (global scale and local scale -- examining each individual ROI that constitutes the network) applied to resting-state fMRI volumes is presented, finding reduced activity in ROIs and all ROIs in MCI show greater predictability in time-series.

Abstract

In this study, we present a technique that spans multi-scale views (global scale -- meaning brain network-level and local scale -- examining each individual ROI that constitutes the network) applied to resting-state fMRI volumes. Deep learning based classification is utilized in understanding neurodegeneration. The novelty of the proposed approach lies in utilizing two extreme scales of analysis. One branch considers the entire network within graph-analysis framework. Concurrently, the second branch scrutinizes each ROI within a network independently, focusing on evolution of dynamics. For each subject, graph-based approach employs partial correlation to profile the subject in a single graph where each ROI is a node, providing insights into differences in levels of participation. In contrast, non-linear analysis employs recurrence plots to profile a subject as a multichannel 2D image, revealing distinctions in underlying dynamics. The proposed approach is employed for classification of a cohort of 50 healthy control (HC) and 50 Mild Cognitive Impairment (MCI), sourced from ADNI dataset. Results point to: (1) reduced activity in ROIs such as PCC in MCI (2) greater activity in occipital in MCI, which is not seen in HC (3) when analysed for dynamics, all ROIs in MCI show greater predictability in time-series.

Multi-scale fMRI time series analysis for understanding neurodegeneration in MCI

TL;DR

A technique that spans multi-scale views (global scale and local scale -- examining each individual ROI that constitutes the network) applied to resting-state fMRI volumes is presented, finding reduced activity in ROIs and all ROIs in MCI show greater predictability in time-series.

Abstract

In this study, we present a technique that spans multi-scale views (global scale -- meaning brain network-level and local scale -- examining each individual ROI that constitutes the network) applied to resting-state fMRI volumes. Deep learning based classification is utilized in understanding neurodegeneration. The novelty of the proposed approach lies in utilizing two extreme scales of analysis. One branch considers the entire network within graph-analysis framework. Concurrently, the second branch scrutinizes each ROI within a network independently, focusing on evolution of dynamics. For each subject, graph-based approach employs partial correlation to profile the subject in a single graph where each ROI is a node, providing insights into differences in levels of participation. In contrast, non-linear analysis employs recurrence plots to profile a subject as a multichannel 2D image, revealing distinctions in underlying dynamics. The proposed approach is employed for classification of a cohort of 50 healthy control (HC) and 50 Mild Cognitive Impairment (MCI), sourced from ADNI dataset. Results point to: (1) reduced activity in ROIs such as PCC in MCI (2) greater activity in occipital in MCI, which is not seen in HC (3) when analysed for dynamics, all ROIs in MCI show greater predictability in time-series.
Paper Structure (21 sections, 6 equations, 3 figures, 4 tables)

This paper contains 21 sections, 6 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Results
  3. Discussion
  4. Conclusion
  5. Proposed Methodology
  6. Data availability
  7. Author contributions statement
  8. Competing interests
  9. Additional information

Figures (3)

  • Figure 1: Recurrence plots illustrate the dynamic evolution of ROI 18 within the Default Mode Network, identified as the most active ROI using a Graph-based community detection approach. The analysis reveals a significant difference in activity in the post cingulate 108 region of the brain between subjects with MCI and healthy individuals.
  • Figure 2: Block schematic of proposed multi-scale methodlogy
  • Figure 3: Illustration of conversion of an fMRI time series to recurrence plots. Given a brain region, say, for instance post cingulate 108 belonging to DMN, we have a representative time series data of the BOLD signal from this region. This is converted to recurrence matrix of size $160\times160$ and then resized to uniformly-sized $224\times224$ to visualize the recurrence plot.