%0 Journal Article %1 HOFMANN2022119504 %A Hofmann, Simon M. %A Beyer, Frauke %A Lapuschkin, Sebastian %A Goltermann, Ole %A Loeffler, Markus %A Müller, Klaus-Robert %A Villringer, Arno %A Samek, Wojciech %A Witte, A. Veronica %D 2022 %J NeuroImage %K Ageing, Brain-age, Cardiovascular Explainable Structural a.i., deep factors, learning mri, risk %P 119504 %R https://doi.org/10.1016/j.neuroimage.2022.119504 %T Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain %U https://www.sciencedirect.com/science/article/pii/S1053811922006206 %V 261 %X 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 ageing 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 ageing reflected cardiovascular risk factors and accelerated ageing was more pronounced in the frontal lobe. Applying LRP, our study demonstrates how superior deep learning models detect brain-ageing in healthy and at-risk individuals throughout adulthood.

@article{HOFMANN2022119504, abstract = {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 ageing 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 ageing reflected cardiovascular risk factors and accelerated ageing was more pronounced in the frontal lobe. Applying LRP, our study demonstrates how superior deep learning models detect brain-ageing in healthy and at-risk individuals throughout adulthood.}, added-at = {2024-10-02T10:38:17.000+0200}, author = {Hofmann, Simon M. and Beyer, Frauke and Lapuschkin, Sebastian and Goltermann, Ole and Loeffler, Markus and Müller, Klaus-Robert and Villringer, Arno and Samek, Wojciech and Witte, A. Veronica}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2466889b4a770297b579998244a1f27a7/scadsfct}, doi = {https://doi.org/10.1016/j.neuroimage.2022.119504}, interhash = {1378cf98310e3bf5199b9d606b789ce8}, intrahash = {466889b4a770297b579998244a1f27a7}, issn = {1053-8119}, journal = {NeuroImage}, keywords = {Ageing, Brain-age, Cardiovascular Explainable Structural a.i., deep factors, learning mri, risk}, pages = 119504, timestamp = {2024-10-02T10:38:17.000+0200}, title = {Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain}, url = {https://www.sciencedirect.com/science/article/pii/S1053811922006206}, volume = 261, year = 2022 }