Behavior Score-Embedded Brain Encoder Network for Improved Classification of Alzheimer Disease Using Resting State fMRI

TL;DR

This paper introduces BSEN, a novel brain encoding network that incorporates behavioral scores from psychological tests into fMRI data analysis, improving classification of Alzheimer's Disease, MCI, and healthy controls.

Contribution

The study presents a behavior score-embedded encoder network (BSEN) that integrates psychological test data into fMRI encoding for better disease classification, a novel approach in neuroimaging analysis.

Findings

Achieved 59.44% accuracy in 3-class classification of AD, MCI, and healthy controls.

Identified key brain regions discriminative between healthy and AD patients.

Demonstrated the effectiveness of integrating behavioral scores into fMRI analysis.

Abstract

The ability to accurately detect onset of dementia is important in the treatment of the disease. Clinically, the diagnosis of Alzheimer Disease (AD) and Mild Cognitive Impairment (MCI) patients are based on an integrated assessment of psychological tests and brain imaging such as positron emission tomography (PET) and anatomical magnetic resonance imaging (MRI). In this work using two different datasets, we propose a behavior score-embedded encoder network (BSEN) that integrates regularly adminstrated psychological tests information into the encoding procedure of representing subject's restingstate fMRI data for automatic classification tasks. BSEN is based on a 3D convolutional autoencoder structure with contrastive loss jointly optimized using behavior scores from MiniMental State Examination (MMSE) and Clinical Dementia Rating (CDR). Our proposed classification framework of using BSEN achieved an overall recognition accuracy of 59.44% (3-class classification: AD, MCI and Healthy Control), and we further extracted the most discriminative regions between healthy control (HC) and AD patients.