Data Driven Classification Using fMRI Network Measures: Application to Schizophrenia

Abstract

Using classification to identify biomarkers for various brain disorders has become a common practice among the functional MR imaging community. Typical classification pipeline includes taking the time series, extracting features from them, and using them to classify a set of patients and healthy controls. The most informative features are then presented as novel biomarkers. In this paper, we compared the results of single and double cross validation schemes on a cohort of 170 subjects with schizophrenia and healthy control subjects. We used graph theoretic measures as our features, comparing the use of functional and anatomical atlases to define nodes and the effect of prewhitening to remove autocorrelation trends. We found that double cross validation resulted in a 20% decrease in classification performance compared to single cross validation. The anatomical atlas resulted in higher classification results. Prewhitening resulted in a 10% boost in classification performance. Overall, a classification performance of 80% was obtained with a double-cross validation scheme using prewhitened time series and an anatomical brain atlas. However, reproducibility of classification within subjects across scans was surprisingly low and comparable to across subject classification rates, indicating that subject state during the short scan significantly influences the estimated features and classification performance.

Schizophrenia Identification Using Multi-View Graph Measures of Functional Brain Networks

“…Nowadays, Magnetic resonance imaging technology has been widely used in various studies related to brain disease diagnosis (Nieuwenhuis et al, 2012;Liu et al, 2016Liu et al, , 2017bLiu et al, ,c, 2018aYang and Wang, 2018). Since SZ is reported to be a functional disease, functional magnetic resonance imaging (fMRI) is increasingly used to study brain dysfunction in patients with mental illness (Castro et al, 2011;Huang et al, 2018;Liu et al, 2018b;Moghimi et al, 2018;Chen et al, 2019). In addition, fMRI provides a database for functional analysis of these brain diseases owing to it's massive spatial and temporal information.…”

“…The most commonly used graph measures include betweenness centrality, degree, local efficiency, participation coefficient, average clustering coefficient, average path length, global efficiency, and small-worldness (Liu et al, 2017a). These topological measures have been applied in the brain disease classifications (Cheng et al, 2015;Khazaee et al, 2015Khazaee et al, , 2017Moghimi et al, 2018). For example, Moghimi et al…”

ISOMAP and machine learning algorithms for the construction of embedded functional connectivity networks of anatomically separated brain regions from resting state fMRI data of patients with Schizophrenia

“…Until today, many studies have proposed several classification/diagnostic biomarkers of schizophrenia [15] – [19] . A typical pipeline for the construction of FCN includes a standard preprocessing routine (e.g.…”

“…Eventually, as stated in [19] , the validation method ( cross-validation) affects both the estimation of accuracy and the identification of the dominant features that could be represented as biomarkers. Indeed, Moghimi et al [19] compared the results of single and double cross-validation schemes to a large dataset comprised of 170 subjects finding that a double cross-validation may lead to even a 20% decrease in the classification performance. The authors assessed more than 19000 global and local network measures and used the Sequential Feature Selection (SFS) algorithm in order to find the most predominant features, that could potentially serve as biomarkers.…”

Machine Learning-Based Identification of Suicidal Risk in Patients With Schizophrenia Using Multi-Level Resting-State fMRI Features

“…Resting state (rs), in turn, is considered highly effective as it captures 60–80% of the brain’s total activity ( Smitha et al, 2017 ). Furthermore, some studies show that it allows monitoring treatment outcomes as well as assessing biomarkers of psychiatric disorders ( Glover, 2011 ; Moghimi et al, 2018 ).…”