English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain

Hofmann, S., Beyer, F., Lapuschkin, S., Goltermann, O., Loeffler, M., Müller, K.-R., et al. (2022). Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain. NeuroImage, 261: 119504. doi:10.1016/j.neuroimage.2022.119504.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-000A-C9F6-E Version Permalink: https://hdl.handle.net/21.11116/0000-000D-DB72-C
Genre: Journal Article

Files

show Files
hide Files
:
Hofmann_2022.pdf (Publisher version), 5MB
View   Save
File Permalink:
https://hdl.handle.net/21.11116/0000-000A-F1DE-C
Name:
Hofmann_2022.pdf
Description:
-
OA-Status:
Gold
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
-
Copyright Info:
-
License:
https://creativecommons.org/licenses/by-nc-nd/4.0/

Locators

show

Creators

show
hide
 Creators:
Hofmann, Simon1, 2, 3, Author                 
Beyer, Frauke1, 3, Author           
Lapuschkin, Sebastian2, Author
Goltermann, Ole1, 4, 5, Author
Loeffler, Markus6, Author
Müller, Klaus-Robert7, 8, 9, 10, 11, Author
Villringer, Arno1, 3, 12, 13, Author           
Samek, Wojciech2, 11, Author
Witte, A. Veronica1, 3, Author           
Affiliations:
1Department Neurology, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_634549              
2Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, Berlin, Germany, ou_persistent22              
3Clinic for Cognitive Neurology, University of Leipzig, Germany, ou_persistent22              
4Max Planck School of Cognition, Leipzig, Germany, ou_persistent22              
5Department of Systems Neuroscience, University Medical Center Hamburg-Eppendorf, Germany, ou_persistent22              
6Institute for Medical Informatics, Statistics and Epidemiology (IMISE), University of Leipzig, Germany, ou_persistent22              
7Department of Machine Learning, TU Berlin, Germany, ou_persistent22              
8Center for Artificial Intelligence, Korea University, Seoul, Republic of Korea, ou_persistent22              
9Brain Team, Google Research, Berlin, Germany, ou_persistent22              
10Max Planck Institute for Informatics, Saarbrücken, Germany, ou_persistent22              
11BIFOLD Berlin Institute for the Foundations of Learning and Data, Germany, ou_persistent22              
12MindBrainBody Institute, Berlin School of Mind and Brain, Germany, ou_persistent22              
13Center for Stroke Research, Charité University Medicine Berlin, Germany, ou_persistent22              

Content

show
hide
Free keywords: Aging; Brain-age; Cardiovascular risk factors; Deep learning; Explainable A.I.; Structural MRI
 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 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.

Details

show
hide
Language(s): eng - English
 Dates: 2022-07-152022-07-212022-07-232022-11-01
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1016/j.neuroimage.2022.119504
Other: epub 2022
PMID: 35882272
 Degree: -

Event

show

Legal Case

show

Project information

show hide
Project name : -
Grant ID : 713-241202; 14505/2470
Funding program : -
Funding organization : LIFE-Leipzig Research Center for Civilization Diseases, University of Leipzig
Project name : -
Grant ID : 209933838
Funding program : -
Funding organization : German Research Foundation (DFG)
Project name : -
Grant ID : 01IS18025A; 01IS18037A; 01IS17058
Funding program : -
Funding organization : Federal Ministry of Education & Research (BMBF)
Project name : -
Grant ID : 965221; 01GQ1115; 01GQ0850
Funding program : -
Funding organization : European Union (EU)
Project name : -
Grant ID : EXC 2046/1; 390685689
Funding program : -
Funding organization : German Research Foundation (DFG)
Project name : -
Grant ID : 2019-0-00079
Funding program : -
Funding organization : Institute for Information & Communication Technology Planning & Evaluation (IITP), Republic of Korea

Source 1

show
hide
Title: NeuroImage
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Orlando, FL : Academic Press
Pages: - Volume / Issue: 261 Sequence Number: 119504 Start / End Page: - Identifier: ISSN: 1053-8119
CoNE: https://pure.mpg.de/cone/journals/resource/954922650166