Towards the Interpretability of Deep Learning Models for Multi-modal Neuroimaging: Finding Structural Changes of the Ageing Brain

Description: Brain-age (BA) estimates based on deep learning are increasingly used as neuroimaging biomarker for brain health; however, the underlying neural features have remained unclear. We combined ensembles of convolutional neural networks with Layer-wise Relevance Propagation (LRP) to detect which brain features contribute to BA. Trained on magnetic resonance imaging (MRI) data of a population-based study (n=2637, 18-82 years), our models estimated age accurately based on single and multiple modalities, regionally restricted and whole-brain images (mean absolute errors 3.37-3.86 years). We find that BA estimates capture aging at both small and large-scale changes, revealing gross enlargements of ventricles and subarachnoid spaces, as well as white matter lesions, and atrophies that appear throughout the brain. Divergence from expected aging reflected cardiovascular risk factors and accelerated aging was more pronounced in the frontal lobe. Applying LRP, our study demonstrates how superior deep learning models detect brain-aging in healthy and at-risk individuals throughout adulthood. This collection contains statistical maps from the analysis of the above mentioned LRP relevance maps.

Related article:

Source data:

View ID Name Type
View ID Name Type
Field Value
Compact Identifier
Add DateJuly 27, 2022, 12:08 p.m.
Uploaded bySiMHof
Related article DOI10.1016/j.neuroimage.2022.119504
Related article authorsSimon M. Hofmann, Frauke Beyer, Sebastian Lapuschkin, Ole Goltermann, Markus Loeffler, Klaus-Robert Müller, Arno Villringer, Wojciech Samek and A. Veronica Witte
Citation guidelines

If you use the data from this collection please include the following persistent identifier in the text of your manuscript:

This will help to track the use of this data in the literature. In addition, consider also citing the paper related to this collection.