Detecting Abnormal Brain Regions in Schizophrenia Using Structural MRI via Machine Learning

Abstract

Utilizing neuroimaging and machine learning (ML) to differentiate schizophrenia (SZ) patients from normal controls (NCs) and for detecting abnormal brain regions in schizophrenia has several benefits and can provide a reference for the clinical diagnosis of schizophrenia. In this study, structural magnetic resonance images (sMRIs) from SZ patients and NCs were used for discriminative analysis. is study proposed an ML framework based on coarse-to-fine feature selection. e proposed framework used two-sample t-tests to extract the differences between groups first, then further eliminated the nonrelevant and redundant features with recursive feature elimination (RFE), and finally utilized the support vector machine (SVM) to learn the decision models with selected gray matter (GM) and white matter (WM) features. Previous studies have tended to report differences at the group level instead of at the individual level and cannot be widely applied. e method proposed in this study extends the diagnosis to the individual level and has a higher recognition rate than previous methods. e experimental results of this study demonstrate that the proposed framework distinguishes SZ patients from NCs, with the highest classification accuracy reaching over 85%. e identified biomarkers are also consistent with previous literature findings. As a universal method, the proposed framework can be extended to diagnose other diseases.

Effects of Brain Atlases and Machine Learning Methods on the Discrimination of Schizophrenia Patients: A Multimodal MRI Study

“…Schizophrenia (SZ) is a chronic psychiatric disorder, characterized by disabling mental symptoms such as auditory delusions, hallucinations and disrupted higher-order cognitive functions ( Austin, 2005 ; Leucht et al, 2007 ). With the development of machine learning methods, both structural and functional magnetic resonance imaging (MRI) data have been applied into the discriminative analyses of SZ patients ( Kasparek et al, 2011 ; Deanna et al, 2012 ; Ota et al, 2012 ; Liu Y. et al, 2017 ; Chen et al, 2020 ). For example, support vector machine (SVM) is the most widely used method to distinguish SZ patients from normal controls (NCs) ( Liu Y. et al, 2017 ; Chen et al, 2020 ) or to differentiate illness stages of SZ, such as first-episode schizophrenia (FESZ) and chronic schizophrenia (CSZ) ( Lu et al, 2018 ; Wu et al, 2018 ).…”

“…With the development of machine learning methods, both structural and functional magnetic resonance imaging (MRI) data have been applied into the discriminative analyses of SZ patients ( Kasparek et al, 2011 ; Deanna et al, 2012 ; Ota et al, 2012 ; Liu Y. et al, 2017 ; Chen et al, 2020 ). For example, support vector machine (SVM) is the most widely used method to distinguish SZ patients from normal controls (NCs) ( Liu Y. et al, 2017 ; Chen et al, 2020 ) or to differentiate illness stages of SZ, such as first-episode schizophrenia (FESZ) and chronic schizophrenia (CSZ) ( Lu et al, 2018 ; Wu et al, 2018 ). Similarly, other classifiers such as random forest ( Deanna et al, 2012 ) and linear discriminant analysis (LDA) ( Kasparek et al, 2011 ; Ota et al, 2012 ) have also been utilized in discriminative analyses of SZ patients.…”

Statistical disease mapping for heterogeneous neuroimaging studies

“…Specifically, both local and global hypothesis‐testing problems are investigated, and the resampling method (i.e., wild bootstrap) is adopted to construct the empirical null distribution of test statistics. Furthermore, both simulation studies and real data analysis reveal that SDM can efficiently delineate imaging heterogeneity at both global and local scales. Our SDM has several potential applications in neuroimaging data analysis, for example, the abnormal brain region detection for different brain‐related diseases, including Alzheimer's disease (Ota et al, 2004), schizophrenia (Chen et al, 2020), traumatic brain injury (Shaker et al, 2017), autism (Salmond et al, 2003), and others. Furthermore, the Python package for our SDM is freely available online (https://github.com/BIG‐S2).…”

Stability Evaluation of Brain Changes in Parkinson's Disease Based on Machine Learning

“…In order to address these issues, machine learning methods have been increasingly applied to neuroimaging in recent years (ChenZhiHong et al, 2020 ; Liu et al, 2020 ). Machine learning methods have been widely used for classification studies aiming to distinguish between PD and HC controls (Duchesne et al, 2009 ; Long et al, 2012 ; Lei et al, 2018 ).…”

“…According to the different attributes of the features, supervised feature selection methods can be divided into three categories: (1) filter methods (Biesiada and Duch, 2005 ; Sánchezmaroño et al, 2007 ), which are based on simple statistical parameters (mean value, variation and correlation coefficient, etc.) and rank them in terms of their ability to detect group-level differences; (2) wrapper methods, which are based on the cost function, and sort all features based on their degree of correlation (Kohavi and John, 1997 ; ChenZhiHong et al, 2020 ); and (3) embedded methods (Wang et al, 2015 ), which select relevant features by imposing certain “penalties” to obtain a subset of relevant features. Filtering methods have the benefit of low computational cost, while wrapper methods are superior to filtering methods in performance due to their discriminative ability (Lee and Verleysen, 2007 ; Chu et al, 2011 ; Adeli et al, 2016 ; Cigdem et al, 2018 ).…”