Lea Baecker

TL;DR: Neuroharmony, a harmonization tool for images from unseen scanners, was able to reduce scanner-related bias from unseen scans and represents a significant step towards imaging-based clinical tools.

TL;DR: A review of the state-of-the-art methods and potential clinical applications of brain age prediction can be found in this paper, where a regression machine learning model of age-related neuroanatomical changes in healthy people is used to predict brain age.

TL;DR: In this paper, the authors compared the performance of support vector regression, relevance vector regression and Gaussian process regression on whole-brain region-based or voxel-based structural magnetic resonance imaging data with or without dimensionality reduction through principal component analysis.

TL;DR: This systematic review describes and compares the technical characteristics of the available tools, and proposes a checklist of pivotal characteristics that should be included in an “ideal” neuroimaging-based clinical tool for brain disorders.

TL;DR: In this article, the authors used deep autoencoders to assess how individuals deviated from the healthy norm and established which brain regions were associated with this deviation. And they found that patients exhibited deviations according to the severity of their clinical condition.