Deep learning-based brain age prediction in normal aging and dementia

被引：102

作者：

Lee, Jeyeon ^{[1
]}

Burkett, Brian J. ^{[1
]}

Min, Hoon-Ki ^{[1
]}

Senjem, Matthew L. ^{[2
]}

Lundt, Emily S. ^{[3
]}

Botha, Hugo ^{[4
]}

Graff-Radford, Jonathan ^{[4
]}

Barnard, Leland R. ^{[4
]}

Gunter, Jeffrey L. ^{[1
]}

Schwarz, Christopher G. ^{[1
]}

Kantarci, Kejal ^{[1
]}

Knopman, David S. ^{[4
]}

Boeve, Bradley F. ^{[4
]}

Lowe, Val J. ^{[1
]}

Petersen, Ronald C. ^{[4
]}

Jack, Clifford R., Jr. ^{[1
]}

Jones, David T. ^{[1
,4
]}

机构：

[1] Mayo Clin, Dept Radiol, Rochester, MN 55905 USA

[2] Mayo Clin, Dept Informat Technol, Rochester, MN USA

[3] Mayo Clin, Dept Hlth Sci Res, Rochester, MN USA

[4] Mayo Clin, Dept Neurol, Rochester, MN 55905 USA

来源：

NATURE AGING | 2022年 / 2卷 / 05期

基金：

美国国家卫生研究院;

关键词：

POSITRON-EMISSION-TOMOGRAPHY; MILD COGNITIVE IMPAIRMENT; ALZHEIMERS ASSOCIATION WORKGROUPS; FDG-PET; DIAGNOSTIC GUIDELINES; NATIONAL INSTITUTE; AEROBIC GLYCOLYSIS; WHITE-MATTER; GREY-MATTER; DISEASE;

D O I：

10.1038/s43587-022-00219-7

中图分类号：

Q2 [细胞生物学];

学科分类号：

071009 ; 090102 ;

摘要：

Brain aging is accompanied by patterns of functional and structural change. Alzheimer's disease (AD), a representative neurodegenerative disease, has been linked to accelerated brain aging. Here, we developed a deep learning-based brain age prediction model using a large collection of fluorodeoxyglucose positron emission tomography and structural magnetic resonance imaging and tested how the brain age gap relates to degenerative syndromes including mild cognitive impairment, AD, frontotemporal dementia and Lewy body dementia. Occlusion analysis, performed to facilitate the interpretation of the model, revealed that the model learns an age- and modality-specific pattern of brain aging. The elevated brain age gap was highly correlated with cognitive impairment and the AD biomarker. The higher gap also showed a longitudinal predictive nature across clinical categories, including cognitively unimpaired individuals who converted to a clinical stage. However, regions generating brain age gaps were different for each diagnostic group of which the AD continuum showed similar patterns to normal aging.

引用

页码：412 / +

页数：28

共 74 条

[1]

Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265

[2] Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning [J].