Head Motion Degrades Machine Learning Classification of Alzheimer's Disease from Positron Emission Tomography

TL;DR

Head motion during PET scans significantly biases machine learning-based Alzheimer's classification, highlighting the urgent need for effective motion correction to improve diagnostic accuracy in clinical settings.

Contribution

This study demonstrates the impact of head motion on PET-based machine learning classification of Alzheimer's and emphasizes the necessity for portable motion correction solutions.

Findings

Classification accuracy drops by up to 10% without motion correction.

Motion bias affects image interpretation and diagnostic reliability.

Validation across multiple tracers confirms the robustness of findings.

Abstract

Brain positron emission tomography (PET) imaging is broadly used in research and clinical routines to study, diagnose, and stage Alzheimer's disease (AD). However, its potential cannot be fully exploited yet due to the lack of portable motion correction solutions, especially in clinical settings. Head motion during data acquisition has indeed been shown to degrade image quality and induces tracer uptake quantification error. In this study, we demonstrate that it also biases machine learning-based AD classification. We start by proposing a binary classification algorithm solely based on PET images. We find that it reaches a high accuracy in classifying motion corrected images into cognitive normal or AD. We demonstrate that the classification accuracy substantially decreases when images lack motion correction, thereby limiting the algorithm's effectiveness and biasing image interpretation. We validate these findings in cohorts of 128 $^{11}$C-UCB-J and 173 $^{18}$F-FDG scans, two tracers highly relevant to the study of AD. Classification accuracies decreased by 10% and 5% on 20 $^{18}$F-FDG and 20 $^{11}$C-UCB-J testing cases, respectively. Our findings underscore the critical need for efficient motion correction methods to make the most of the diagnostic capabilities of PET-based machine learning.