Quantifying uncertainty in brain-predicted age using scalar-on-image quantile regression

Abstract

Prediction of subject age from brain anatomical MRI has the potential to provide a sensitive summary of brain changes, indicative of different neurodegenerative diseases. However, existing studies typically neglect the uncertainty of these predictions. In this work we take into account this uncertainty by applying methods of functional data analysis. We propose a penalised functional quantile regression model of age on brain structure with cognitively normal (CN) subjects in the Alzheimer’s Disease Neuroimaging Initiative (ADNI), and use it to predict brain age in Mild Cognitive Impairment (MCI) and Alzheimer’s Disease (AD) subjects. Unlike the machine learning approaches available in the literature of brain age prediction, which provide only point predictions, the outcome of our model is a prediction interval for each subject.

An uncertainty-aware, shareable, and transparent neural network architecture for brain-age modeling

“…MCCQR outperforms RVR in the MACS and IXI datasets. Note that incorporating epistemic or aleatory uncertainty alone-as has recently been suggested (20) for brain-age models-systematically underestimates uncertainty (see fig. S1).…”

“…A recent study also recognized the issue of uncertainty quantification for brain-age modeling and used quantile regression (QR) to estimate aleatory uncertainty in brain-age prediction (20). While this approach accounts for aleatory uncertainty induced by, e.g., measurement error, it does not consider epistemic uncertainty, i.e., uncertainty in the model weights.…”

“…For high-dimensional inputs, however, uncertainty estimation becomes exceedingly difficult using these methods. This has sparked a plethora of research into alternative approaches, especially for neural networks (18)(19)(20). While interesting, most of these approaches do not consider aleatory and epistemic uncertainty together, and none have been applied to brain-age research.…”

Lactoferrin-Loaded PEG/PLA Block Copolymer Targeted With Anti-Transferrin Receptor Antibodies for Alzheimer Disease

“…Therefore, the establishment of new therapy for AD is important. [1][2][3][4] Alzheimer disease is considered pathologically through the age-related amyloid-beta (Ab) admission, neurofibrillary masses, synapses, and neuronal damage. Aberrant accumulation of Ab, especially its 42 amino acid isoforms (Ab42), is the essential pathogenic mechanism of AD.…”