Application of Unsupervised Domain Adaptation for Structural MRI Analysis

TL;DR

This paper investigates unsupervised domain adaptation techniques to improve Alzheimer's disease detection and MRI data analysis, achieving state-of-the-art results and establishing benchmarks for anomaly detection in structural MRI.

Contribution

It introduces an unsupervised domain adaptation approach that enhances AD detection and MRI analysis, providing new benchmarks and demonstrating improved performance in both supervised and unsupervised settings.

Findings

Domain adaptation improves AD detection accuracy

Achieves state-of-the-art binary classification performance

Establishes benchmarks for MRI anomaly detection

Abstract

The primary goal of this work is to study the effectiveness of an unsupervised domain adaptation approach for various applications such as binary classification and anomaly detection in the context of Alzheimer's disease (AD) detection for the OASIS datasets. We also explore image reconstruction and image synthesis for analyzing and generating 3D structural MRI data to establish performance benchmarks for anomaly detection. We successfully demonstrate that domain adaptation improves the performance of AD detection when implemented in both supervised and unsupervised settings. Additionally, the proposed methodology achieves state-of-the-art performance for binary classification on the OASIS-1 dataset.