Resting state-fMRI approach towards understanding impairments in mTLE

TL;DR

This paper reviews how resting-state fMRI reveals network-level impairments in mesial temporal lobe epilepsy and explores machine learning for diagnosis based on these network patterns.

Contribution

It provides a comprehensive review of recent rs-fMRI studies on mTLE and discusses the application of machine learning for diagnosis.

Findings

Altered regional and global brain networks in mTLE

Resting-state networks can differentiate mTLE patients from healthy controls

Machine learning enables automated diagnosis of mTLE

Abstract

Mesial temporal lobe epilepsy (mTLE) is the most common form of epilepsy. While it is characterized by an epileptogenic focus in the mesial temporal lobe, it is increasingly understood as a network disorder. Hence, understanding the nature of impairments on a network level is essential for its diagnosis and treatment. In this work, we review recent works that apply resting-state functional MRI to provide key insights into the impairments to the functional architecture in mTLE. We discuss changes on both regional and global scales. Finally, we describe how Machine Learning can be applied to rs-fMRI data to extract resting-state networks specific to mTLE and for automated diagnosis of this disease.