Findings in resting-state fMRI by differences from K-means clustering

Area of Science:

• Neuroimaging
• Computational Neuroscience
• Psychiatry

Background:

• Resting-state functional magnetic resonance imaging (fMRI) is widely used to study brain functional connectivity.
• Traditional methods for analyzing resting-state fMRI data are computationally intensive and sensitive to noise.
• Exploring efficient analytical approaches is crucial for advancing neuroimaging research.

Purpose of the Study:

• To evaluate K-means clustering as a computationally efficient exploratory method for resting-state fMRI analysis.
• To identify functional connectivity biomarkers in schizophrenia patients.
• To investigate differences in functional connectivity patterns between schizophrenia patients with and without auditory hallucinations.

Main Methods:

• Applied K-means clustering to resting-state fMRI data.
• Utilized efficient, readily available implementations of the K-means algorithm.
• Analyzed a dataset comprising schizophrenia patients.

Main Results:

• K-means clustering provided meaningful results with minimal computational cost.
• Distinct functional connectivity patterns were identified between patient subgroups.
• Significant differences were found between schizophrenia patients with and without auditory hallucinations.

Conclusions:

• K-means clustering is a viable and efficient exploratory tool for resting-state fMRI analysis.
• This approach can aid in identifying neuroimaging biomarkers for psychiatric conditions like schizophrenia.
• The findings highlight the potential of clustering methods for understanding brain connectivity in clinical populations.