Abstract
At present, the diagnosis of brain disease is mainly based on the self-reported symptoms and clinical signs of the patient, which can easily lead to psychiatrists' bias. The purpose of this study is to develop a brain network clustering model to accurately identify brain diseases based on resting state functional magnetic resonance imaging (fMRI) in the absence of clinical information. We use cosine similarity and sub-network kernels to measure attribute similarity and structure similarity, respectively. By integrating the structure similarity and attribute similarity into one matrix, spectral clustering is used to achieve brain network clustering. Finally, we evaluate this method on three diseases: Alzheimer's disease, Bipolar disorder patients, and Schizophrenia. The performance of methods is evaluated by measuring clustering consistency. Clustering consistency is similar to clustering accuracy, which is used to evaluate the consistency between the clustering labels and clinical diagnostic labels of the subjects. The experimental results show that our proposed method can significantly improve clustering performance, with a consistency of 60.6% for Alzheimer's disease, with a consistency of 100% for Schizophrenia, with a consistency of 100% for Bipolar disorder patients.
Highlights
In recent years, graph mining has become a popular research field and has been widely used in computer networks (Zou et al, 2017), social network analysis (Halder et al, 2016) and computational biology (Zhang et al, 2017)
According to a certain proportion, the attribute similarity matrix and the structure similarity matrix were combined to form a similarity matrix which is used for clustering
In order to evaluate the clustering performance of our proposed method, we compared our method with methods that use a different similarity measure for the same dataset, including: TABLE 4 | Clustering performance of different similarity measure
Summary
Graph mining has become a popular research field and has been widely used in computer networks (Zou et al, 2017), social network analysis (Halder et al, 2016) and computational biology (Zhang et al, 2017). Using fMRI data we can construct the brain functional connectivity network in which each node represents a brain region and each edge represents the functional connectivity between two brain regions (Kong and Yu, 2014). These brain networks provide us with a means to explore the function of the human brain and provide valuable information for clinical diagnosis of neurological diseases, such as Alzheimer’s disease (AD), Bipolar disorder patients (BD), and Schizophrenia (SC). Brain network analysis based on graph mining has become a new research hotspot and attracted increasingly more researchers. Some brain network of subjects were given, some of whom suffered from certain brain diseases (such as AD or BD), while the other group was a normal control group
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call