Wavelet-domain regression and predictive inference in psychiatric neuroimaging

TL;DR

This paper introduces wavelet-domain statistical methods for predictive modeling using neuroimaging data, focusing on psychiatric applications like ADHD diagnosis, and evaluates their effectiveness and confounding factors.

Contribution

It develops and compares wavelet-based regression techniques and extends confounding assessment methods for image predictors in psychiatric neuroimaging.

Findings

Wavelet-domain methods effectively predict ADHD from brain images.

Permutation tests reveal the impact of confounding variables.

Results provide insights into the role of confounding in neuroimaging-based diagnosis.

Abstract

An increasingly important goal of psychiatry is the use of brain imaging data to develop predictive models. Here we present two contributions to statistical methodology for this purpose. First, we propose and compare a set of wavelet-domain procedures for fitting generalized linear models with scalar responses and image predictors: sparse variants of principal component regression and of partial least squares, and the elastic net. Second, we consider assessing the contribution of image predictors over and above available scalar predictors, in particular, via permutation tests and an extension of the idea of confounding to the case of functional or image predictors. Using the proposed methods, we assess whether maps of a spontaneous brain activity measure, derived from functional magnetic resonance imaging, can meaningfully predict presence or absence of attention deficit/hyperactivity disorder (ADHD). Our results shed light on the role of confounding in the surprising outcome of the recent ADHD-200 Global Competition, which challenged researchers to develop algorithms for automated image-based diagnosis of the disorder.