Adversarial Learning Based Structural Brain-network Generative Model for Analyzing Mild Cognitive Impairment

TL;DR

This paper introduces an adversarial learning model to generate and analyze structural brain networks directly from diffusion tensor images, aiding early detection of mild cognitive impairment with high accuracy.

Contribution

The study presents a novel adversarial learning-based generative model for structural brain networks that bypasses traditional tools, enabling direct analysis from imaging data.

Findings

Structural brain networks show a progressive weakening from NC to EMCI to LMCI.

The model achieves 83.33% classification accuracy on ADNI data.

Structural connectivity declines as cognitive impairment worsens.

Abstract

Mild cognitive impairment(MCI) is a precursor of Alzheimer's disease(AD), and the detection of MCI is of great clinical significance. Analyzing the structural brain networks of patients is vital for the recognition of MCI. However, the current studies on structural brain networks are totally dependent on specific toolboxes, which is time-consuming and subjective. Few tools can obtain the structural brain networks from brain diffusion tensor images. In this work, an adversarial learning-based structural brain-network generative model(SBGM) is proposed to directly learn the structural connections from brain diffusion tensor images. By analyzing the differences in structural brain networks across subjects, we found that the structural brain networks of subjects showed a consistent trend from elderly normal controls(NC) to early mild cognitive impairment(EMCI) to late mild cognitive impairment(LMCI): structural connectivity progressed in a progressively weaker direction as the condition worsened. In addition, our proposed model tri-classifies EMCI, LMCI, and NC subjects, achieving a classification accuracy of 83.33\% on the Alzheimer's Disease Neuroimaging Initiative(ADNI) database.