Interpretable deep learning reveals spatiotemporal MRI features of brain aging that align with neurodegeneration.

Nikhil N Chaudhari, Owen M Vega, Phoebe Imms, Jaron M Kawamura, Nahian F Chowdhury, Tamara Jafar, Andrei Irimia

Corwin D. Denney Research Center, Alfred E. Mann Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA. · pubmed

Paper

Abstract

Cortical thinning and atrophy are hallmarks of brain aging that have been characterized using magnetic resonance imaging (MRI). Brain aging involves many neuroanatomic features whose effects on brain structure remain unexplored. To address this challenge, we trained interpretable deep neural networks (DNNs) to estimate brain age (BA) from T

The following analysis is generated by AI and may contain errors. It is separate from the authors’ abstract and is not peer review.

Research summary

The paper claims that interpretable deep learning can identify MRI features that correlate with brain aging and neurodegeneration. This research is relevant as it explores the underlying mechanisms of brain aging, which is a fundamental aspect of longevity and age-related diseases.

Author of this paper? Send a correction.