Gaussian Process Uncertainty in Age Estimation as a Measure of Brain Abnormality

TL;DR

This paper introduces a novel approach using Gaussian process uncertainty metrics to detect brain abnormalities by measuring deviations from normal aging patterns, outperforming traditional age prediction errors across various neuroimaging features and diseases.

Contribution

It proposes a new uncertainty-based method for brain abnormality detection that does not rely on the assumption that pathology mimics accelerated aging, demonstrating improved differentiation between healthy and diseased subjects.

Findings

Uncertainty measures outperform prediction error in distinguishing diseased from healthy subjects.

The approach is versatile across different diseases and neuroimaging features.

Differences in disease patterns compared to normal aging are effectively captured.

Abstract

Multivariate regression models for age estimation are a powerful tool for assessing abnormal brain morphology associated to neuropathology. Age prediction models are built on cohorts of healthy subjects and are built to reflect normal aging patterns. The application of these multivariate models to diseased subjects usually results in high prediction errors, under the hypothesis that neuropathology presents a similar degenerative pattern as that of accelerated aging. In this work, we propose an alternative to the idea that pathology follows a similar trajectory than normal aging. Instead, we propose the use of metrics which measure deviations from the mean aging trajectory. We propose to measure these deviations using two different metrics: uncertainty in a Gaussian process regression model and a newly proposed age weighted uncertainty measure. Consequently, our approach assumes that pathologic brain patterns are different to those of normal aging. We present results for subjects with autism, mild cognitive impairment and Alzheimer's disease to highlight the versatility of the approach to different diseases and age ranges. We evaluate volume, thickness, and VBM features for quantifying brain morphology. Our evaluations are performed on a large number of images obtained from a variety of publicly available neuroimaging databases. Across all features, our uncertainty based measurements yield a better separation between diseased subjects and healthy individuals than the prediction error. Finally, we illustrate differences in the disease pattern to normal aging, supporting the application of uncertainty as a measure of neuropathology.