A System for Differentiation of Schizophrenia and Bipolar Disorder based on rsfMRI

TL;DR

This paper introduces a rsfMRI-based system utilizing 1D CNNs to differentiate schizophrenia from bipolar disorder, achieving promising diagnostic accuracy and highlighting potential for improved psychiatric diagnosis.

Contribution

The study develops a novel rsfMRI analysis method using 1D CNNs to distinguish between schizophrenia and bipolar disorder, demonstrating high classification performance.

Findings

Achieved 0.7078 AUC in differentiating disorders

Used intrinsic connectivity time courses from rsfMRI

Showed potential for improved psychiatric diagnosis

Abstract

Schizophrenia and bipolar disorder are debilitating psychiatric illnesses that can be challenging to diagnose accurately. The similarities between the diseases make it difficult to differentiate between them using traditional diagnostic tools. Recently, resting-state functional magnetic resonance imaging (rsfMRI) has emerged as a promising tool for the diagnosis of psychiatric disorders. This paper presents several methods for differentiating schizophrenia and bipolar disorder based on features extracted from rsfMRI data. The system that achieved the best results, uses 1D Convolutional Neural Networks to analyze patterns of Intrinsic Connectivity time courses obtained from rsfMRI and potentially identify biomarkers that distinguish between the two disorders. We evaluate the system's performance on a large dataset of patients with schizophrenia and bipolar disorder and demonstrate that the system achieves a 0.7078 Area Under Curve (AUC) score in differentiating patients with these disorders. Our results suggest that rsfMRI-based classification systems have great potential for improving the accuracy of psychiatric diagnoses and may ultimately lead to more effective treatments for patients with this disorder.