Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment
Proceedings of the National Academy of Sciences · 10.01.2023 · 120 (2)
DOI: 10.1073/pnas.2214634120 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 03.01.2023. Verfasst von Chenzhong Yin und 11 weiteren Autor:innen. Beteiligte Einrichtung: Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089. Hauptthemen laut MEDLINE: Deep Learning, Cognitive Dysfunction, Alzheimer Disease. Die Arbeit wurde bisher 126-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIA NIH HHS, NIBIB NIH HHS, NINDS NIH HHS.
Abstract (Originalsprache)
The gap between chronological age (CA) and biological brain age, as estimated from magnetic resonance images (MRIs), reflects how individual patterns of neuroanatomic aging deviate from their typical trajectories. MRI-derived brain age (BA) estimates are often obtained using deep learning models that may perform relatively poorly on new data or that lack neuroanatomic interpretability. This study introduces a convolutional neural network (CNN) to estimate BA after training on the MRIs of 4,681 cognitively normal (CN) participants and testing on 1,170 CN participants from an independent sample. BA estimation errors are notably lower than those of previous studies. At both individual and cohort levels, the CNN provides detailed anatomic maps of brain aging patterns that reveal sex dimorphisms and neurocognitive trajectories in adults with mild cognitive impairment (MCI, N = 351) and Alzheimer’s disease (AD, N = 359). In individuals with MCI (54% of whom were diagnosed with dementia within 10.9 y from MRI acquisition), BA is significantly better than CA in capturing dementia symptom severity, functional disability, and executive function. Profiles of sex dimorphism and lateralization in brain aging also map onto patterns of neuroanatomic change that reflect cognitive decline. Significant associations between BA and neurocognitive measures suggest that the proposed framework can map, systematically, the relationship between aging-related neuroanatomy changes in CN individuals and in participants with MCI or AD. Early identification of such neuroanatomy changes can help to screen individuals according to their AD risk.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089.
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, CA 90089.
- Corwin D. Denney Research Center, Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089.
- Imaging Genetics Center, Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA 90033.
- Department of Quantitative & Computational Biology, Dana & David Dornsife College of Arts & Sciences, University of Southern California, Los Angeles, CA 90089.
- Department of Ophthalmology, Keck School of Medicine, University of Southern California, Los Angeles, CA 90033.
ORCID-Profile: Chenzhong Yin, Phoebe Imms, Mingxi Cheng, Anar Amgalan, Nahian F Chowdhury, Nikhil N Chaudhari, Xinghe Chen, Paul M Thompson, Paul Bogdan, Andrei Irimia
Förderung
- NIA NIH HHS
- NIBIB NIH HHS
- NINDS NIH HHS
- Biotechnology and Biological Sciences Research Council
- NIMH NIH HHS
- Medical Research Council
- HHS | National Institutes of Health
- U.S. Department of Defense
Zitieren
APA
Yin, C., Imms, P., Cheng, M., Amgalan, A., Chowdhury, N. F., Massett, R. J., Chaudhari, N. N., Chen, X., Thompson, P. M., Bogdan, P., Irimia, A., & Alzheimer’s Disease Neuroimaging Initiative (2023). Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment. Proceedings of the National Academy of Sciences, 120(2). https://doi.org/10.1073/pnas.2214634120
Vancouver
Yin C, Imms P, Cheng M, Amgalan A, Chowdhury NF, Massett RJ, et al. Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment. Proceedings of the National Academy of Sciences. 2023;120(2). doi:10.1073/pnas.2214634120
BibTeX
@article{Yin2023,
author = {Yin, Chenzhong and Imms, Phoebe and Cheng, Mingxi and Amgalan, Anar and Chowdhury, Nahian F and Massett, Roy J and Chaudhari, Nikhil N and Chen, Xinghe and Thompson, Paul M and Bogdan, Paul and Irimia, Andrei and Alzheimer’s Disease Neuroimaging Initiative, Alzheimer’s Disease Neuroimaging Initiative},
title = {Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment},
journal = {Proceedings of the National Academy of Sciences},
year = {2023},
volume = {120},
number = {2},
doi = {10.1073/pnas.2214634120}
}
EUVIMED