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.
Highlights
The process of brain ageing is known to be associated to a general decline in cognitive functions and higher risk of neurodegenerative diseases (Yankner et al, 2008; Denver and McClean, 2018)
Quantile regression does not model the expected value of the outcome of interest given the predictors, but some selected quantiles of the conditional distribution. This model can be adapted for functional covariates: in a functional quantile regression model we explore the linear relationship between a certain quantile of the outcome and the 3D image
For the dataset at hand the B-splines projection with equidistant knots every 12 mm for each dimension allows to represent each image with R2 approximately equal to 0.96
Summary
The process of brain ageing is known to be associated to a general decline in cognitive functions and higher risk of neurodegenerative diseases (Yankner et al, 2008; Denver and McClean, 2018). In some cases, both ageing and dementia affect the same areas in the brain (Lockhart and DeCarli, 2014). A large part of the research in neuroimaging data analysis has been focused on explanatory analyses aimed at describing the relationship between the brain and some variables of interest (such as neurodegenerative diseases, sex, physical activity). With the advent of large imaging databases, a prediction-oriented focus has been considered, in order to detect individual differences among subjects that could be used in clinical practice (for example Yoo et al, 2018; Zhou et al, 2019)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
