Data Integration with Fusion Searchlight: Classifying Brain States from Resting-state fMRI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wein, Simon, Riebel, Marco, Brunner, Lisa-Marie, Nothdurfter, Caroline, Rupprecht, Rainer, Schwarzbach, Jens V.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912369210294272
author Wein, Simon
Riebel, Marco
Brunner, Lisa-Marie
Nothdurfter, Caroline
Rupprecht, Rainer
Schwarzbach, Jens V.
author_facet Wein, Simon
Riebel, Marco
Brunner, Lisa-Marie
Nothdurfter, Caroline
Rupprecht, Rainer
Schwarzbach, Jens V.
contents Resting-state fMRI captures spontaneous neural activity characterized by complex spatiotemporal dynamics. Various metrics, such as local and global brain connectivity and low-frequency amplitude fluctuations, quantify distinct aspects of these dynamics. However, these measures are typically analyzed independently, overlooking their interrelations and potentially limiting analytical sensitivity. Here, we introduce the Fusion Searchlight (FuSL) framework, which integrates complementary information from multiple resting-state fMRI metrics. We demonstrate that combining these metrics enhances the accuracy of pharmacological treatment prediction from rs-fMRI data, enabling the identification of additional brain regions affected by sedation with alprazolam. Furthermore, we leverage explainable AI to delineate the differential contributions of each metric, which additionally improves spatial specificity of the searchlight analysis. Moreover, this framework can be adapted to combine information across imaging modalities or experimental conditions, providing a versatile and interpretable tool for data fusion in neuroimaging.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10161
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data Integration with Fusion Searchlight: Classifying Brain States from Resting-state fMRI
Wein, Simon
Riebel, Marco
Brunner, Lisa-Marie
Nothdurfter, Caroline
Rupprecht, Rainer
Schwarzbach, Jens V.
Neurons and Cognition
Machine Learning
Resting-state fMRI captures spontaneous neural activity characterized by complex spatiotemporal dynamics. Various metrics, such as local and global brain connectivity and low-frequency amplitude fluctuations, quantify distinct aspects of these dynamics. However, these measures are typically analyzed independently, overlooking their interrelations and potentially limiting analytical sensitivity. Here, we introduce the Fusion Searchlight (FuSL) framework, which integrates complementary information from multiple resting-state fMRI metrics. We demonstrate that combining these metrics enhances the accuracy of pharmacological treatment prediction from rs-fMRI data, enabling the identification of additional brain regions affected by sedation with alprazolam. Furthermore, we leverage explainable AI to delineate the differential contributions of each metric, which additionally improves spatial specificity of the searchlight analysis. Moreover, this framework can be adapted to combine information across imaging modalities or experimental conditions, providing a versatile and interpretable tool for data fusion in neuroimaging.
title Data Integration with Fusion Searchlight: Classifying Brain States from Resting-state fMRI
topic Neurons and Cognition
Machine Learning
url https://arxiv.org/abs/2412.10161