Deep neural networks learn general and clinically relevant representations of the ageing brain
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 compil...
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-08-01
|
| Series: | NeuroImage |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811922003342 |
| _version_ | 1811341095333789696 |
|---|---|
| author | Esten H. Leonardsen Han Peng Tobias Kaufmann Ingrid Agartz Ole A. Andreassen Elisabeth Gulowsen Celius Thomas Espeseth Hanne F. Harbo Einar A. Høgestøl Ann-Marie de Lange Andre F. Marquand Didac Vidal-Piñeiro James M. Roe Geir Selbæk Øystein Sørensen Stephen M. Smith Lars T. Westlye Thomas Wolfers Yunpeng Wang |
| author_facet | Esten H. Leonardsen Han Peng Tobias Kaufmann Ingrid Agartz Ole A. Andreassen Elisabeth Gulowsen Celius Thomas Espeseth Hanne F. Harbo Einar A. Høgestøl Ann-Marie de Lange Andre F. Marquand Didac Vidal-Piñeiro James M. Roe Geir Selbæk Øystein Sørensen Stephen M. Smith Lars T. Westlye Thomas Wolfers Yunpeng Wang |
| author_sort | Esten H. Leonardsen |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-13T18:52:34Z |
| format | Article |
| id | doaj.art-40a26a731299428dbed3ac91ab54493b |
| institution | Directory Open Access Journal |
| issn | 1095-9572 |
| language | English |
| last_indexed | 2024-04-13T18:52:34Z |
| publishDate | 2022-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj.art-40a26a731299428dbed3ac91ab54493b2022-12-22T02:34:23ZengElsevierNeuroImage1095-95722022-08-01256119210Deep neural networks learn general and clinically relevant representations of the ageing brainEsten H. Leonardsen0Han Peng1Tobias Kaufmann2Ingrid Agartz3Ole A. Andreassen4Elisabeth Gulowsen Celius5Thomas Espeseth6Hanne F. Harbo7Einar A. Høgestøl8Ann-Marie de Lange9Andre F. Marquand10Didac Vidal-Piñeiro11James M. Roe12Geir Selbæk13Øystein Sørensen14Stephen M. Smith15Lars T. Westlye16Thomas Wolfers17Yunpeng Wang18Corresponding author. Postboks 1094 Blindern, 0317 OSLO.; Department of Psychology, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, NorwayWellcome Centre for Integrative Neuroimaging (WIN FMRIB), University of Oxford, Oxford, OX3 9DU, United KingdomNorwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Psychiatry and Psychotherapy, Tübingen Center for Mental Health, University of Tübingen, GermanyNorwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Psychiatric Research, Diakonhjemmet Hospital, Oslo, Norway; Centre for Psychiatry Research, Department of Clinical Neuroscience, Karolinska Institutet & Stockholm Health Care Services, Stockholm County Council, Stockholm, SwedenNorwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, NorwayDepartment of Neurology, Oslo University Hospital, Norway; Institute of Clinical Medicine, University of Oslo, Oslo, NorwayDepartment of Psychology, University of Oslo, Oslo, Norway; Department of Psychology, Bjørknes University College, Oslo, NorwayDepartment of Neurology, Oslo University Hospital, Norway; Institute of Clinical Medicine, University of Oslo, Oslo, NorwayDepartment of Psychology, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Neurology, Oslo University Hospital, NorwayDepartment of Psychology, University of Oslo, Oslo, Norway; LREN, Centre for Research in Neurosciences-Department of Clinical Neurosciences, CHUV and University of Lausanne, Lausanne, Switzerland; Department of Psychiatry, University of Oxford, Oxford, UKDonders Institute for Brain, Cognition and Behaviour, Radboud University Medical Centre, Nijmegen, NetherlandsDepartment of Psychology, University of Oslo, Oslo, NorwayDepartment of Psychology, University of Oslo, Oslo, NorwayNorwegian National Advisory Unit on Aging and Health, Vestfold Hospital Trust, Tønsberg, Norway; Department of Geriatric Medicine, Oslo University Hospital, Oslo, NorwayDepartment of Psychology, University of Oslo, Oslo, NorwayWellcome Centre for Integrative Neuroimaging (WIN FMRIB), University of Oxford, Oxford, OX3 9DU, United KingdomDepartment of Psychology, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway; KG Jebsen Center for Neurodevelopmental Disorders, University of Oslo, Oslo, NorwayDepartment of Psychology, University of Oslo, Oslo, Norway; Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, NorwayDepartment of Psychology, University of Oslo, Oslo, NorwayThe 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.http://www.sciencedirect.com/science/article/pii/S1053811922003342 |
| spellingShingle | Esten H. Leonardsen Han Peng Tobias Kaufmann Ingrid Agartz Ole A. Andreassen Elisabeth Gulowsen Celius Thomas Espeseth Hanne F. Harbo Einar A. Høgestøl Ann-Marie de Lange Andre F. Marquand Didac Vidal-Piñeiro James M. Roe Geir Selbæk Øystein Sørensen Stephen M. Smith Lars T. Westlye Thomas Wolfers Yunpeng Wang Deep neural networks learn general and clinically relevant representations of the ageing brain NeuroImage |
| title | Deep neural networks learn general and clinically relevant representations of the ageing brain |
| title_full | Deep neural networks learn general and clinically relevant representations of the ageing brain |
| title_fullStr | Deep neural networks learn general and clinically relevant representations of the ageing brain |
| title_full_unstemmed | Deep neural networks learn general and clinically relevant representations of the ageing brain |
| title_short | Deep neural networks learn general and clinically relevant representations of the ageing brain |
| title_sort | deep neural networks learn general and clinically relevant representations of the ageing brain |
| url | http://www.sciencedirect.com/science/article/pii/S1053811922003342 |
| work_keys_str_mv | AT estenhleonardsen deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT hanpeng deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT tobiaskaufmann deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT ingridagartz deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT oleaandreassen deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT elisabethgulowsencelius deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT thomasespeseth deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT hannefharbo deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT einarahøgestøl deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT annmariedelange deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT andrefmarquand deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT didacvidalpineiro deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT jamesmroe deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT geirselbæk deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT øysteinsørensen deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT stephenmsmith deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT larstwestlye deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT thomaswolfers deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain AT yunpengwang deepneuralnetworkslearngeneralandclinicallyrelevantrepresentationsoftheageingbrain |