Deep neural networks learn general and clinically relevant representations of the ageing brain

NeuroImage

卷:256

Didac Vidal-Piñeiro¹  Andre F. Marquand²  Hanne F. Harbo³  Yunpeng Wang⁴  Han Peng⁵  Øystein Sørensen⁶  Thomas Espeseth⁶  Ingrid Agartz⁶  Lars T. Westlye⁶  Ann-Marie de Lange⁶  Tobias Kaufmann⁷  James M. Roe⁸  Esten H. Leonardsen⁹  Stephen M. Smith¹⁰  Thomas Wolfers¹¹  Einar A. Høgestøl¹²  Elisabeth Gulowsen Celius¹²  Geir Selbæk¹²  Ole A. Andreassen¹³ 

[1] Centre for Psychiatry Research, Department of Clinical Neuroscience, Karolinska Institutet &

[2] Department of Psychiatric Research, Diakonhjemmet Hospital, Oslo, Norway;

[3] Department of Psychiatry and Psychotherapy, Tübingen Center for Mental Health, University of Tübingen, Germany;

[4] Department of Psychology, Bjørknes University College, Oslo, Norway;

[5] Department of Psychology, University of Oslo, Oslo, Norway;

[6] Institute of Clinical Medicine, University of Oslo, Oslo, Norway;

[7] Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital &

[8] Stockholm Health Care Services, Stockholm County Council, Stockholm, Sweden;

[9] Corresponding author. Postboks 1094 Blindern, 0317 OSLO.;

[10] Department of Neurology, Oslo University Hospital, Norway;

[11] Wellcome Centre for Integrative Neuroimaging (WIN FMRIB), University of Oxford, Oxford, OX3 9DU, United Kingdom;

关键词: ;   

DOI  :  

来源: DOAJ

【 摘 要 】

The discrepancy between chronological age and the apparent age of the brain based on neuroimaging data — the brain age delta — has emerged as a reliable marker of brain health. With an increasing wealth of data, approaches to tackle heterogeneity in data acquisition are vital. To this end, we compiled raw structural magnetic resonance images into one of the largest and most diverse datasets assembled (n=53542), and trained convolutional neural networks (CNNs) to predict age. We achieved state-of-the-art performance on unseen data from unknown scanners (n=2553), and showed that higher brain age delta is associated with diabetes, alcohol intake and smoking. Using transfer learning, the intermediate representations learned by our model complemented and partly outperformed brain age delta in predicting common brain disorders. Our work shows we can achieve generalizable and biologically plausible brain age predictions using CNNs trained on heterogeneous datasets, and transfer them to clinical use cases.

【 授权许可】

Unknown