Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis

TL;DR

This paper introduces a deep neural generative model for resting-state fMRI data that improves psychiatric disorder diagnosis accuracy and provides interpretable visualizations of disorder-related brain regions.

Contribution

It presents a novel generative modeling approach conditioned on subject state, enhancing diagnosis accuracy and interpretability over existing methods.

Findings

Significantly improved diagnostic accuracy for schizophrenia and bipolar disorder.

Model visualizations highlight brain regions associated with disorders.

Outperforms traditional classification and feature-extraction methods.

Abstract

Accurate diagnosis of psychiatric disorders plays a critical role in improving the quality of life for patients and potentially supports the development of new treatments. Many studies have been conducted on machine learning techniques that seek brain imaging data for specific biomarkers of disorders. These studies have encountered the following dilemma: A direct classification overfits to a small number of high-dimensional samples but unsupervised feature-extraction has the risk of extracting a signal of no interest. In addition, such studies often provided only diagnoses for patients without presenting the reasons for these diagnoses. This study proposed a deep neural generative model of resting-state functional magnetic resonance imaging (fMRI) data. The proposed model is conditioned by the assumption of the subject's state and estimates the posterior probability of the subject's state given the imaging data, using Bayes' rule. This study applied the proposed model to diagnose schizophrenia and bipolar disorders. Diagnostic accuracy was improved by a large margin over competitive approaches, namely classifications of functional connectivity, discriminative/generative models of region-wise signals, and those with unsupervised feature-extractors. The proposed model visualizes brain regions largely related to the disorders, thus motivating further biological investigation.