Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker

By James H. Cole, Rudra P. K. Poudel, Dimosthenis Tsagkrasoulis, Matthan W. A. Caan, Claire J. Steves, Tim D. Spector, Giovanni Montana. 2016

828 citations recorded by the source corpus.

&NA; Machine learning analysis of neuroimaging data can accurately predict chronological age in healthy people. Deviations from healthy brain ageing have been associated with cognitive impairment and disease. Here we sought to further establish the credentials of ‘brain‐predicted age’ as a biomarker of individual differences in the brain ageing process, using a predictive modelling approach based on deep learning, and specifically convolutional neural networks (CNN), and applied to both pre‐processed and raw T1‐weighted MRI data. Firstly, we aimed to demonstrate the accuracy of CNN brain‐predicted age using a large dataset of healthy adults (N = 2001). Next, we sought to establish the heritability of brain‐predicted age using a sample of monozygotic and dizygotic female twins (N = 62). Thirdly, we examined the test‐retest and multi‐centre reliability of brain‐predicted age using two samples (within‐scanner N = 20; between‐scanner N = 11). CNN brain‐predicted ages were generated and compared to a Gaussian Process Regression (GPR) approach, on all datasets. Input data were grey matter (GM) or white matter (WM) volumetric maps generated by Statistical Parametric Mapping (SPM) or raw data. CNN accurately predicted chronological age using GM (correlation between brain‐predicted age and chronological age r = 0.96, mean absolute error [MAE] = 4.16 years) and raw (r = 0.94, MAE = 4.65 years) data. This was comparable to GPR brain‐predicted age using GM data (r = 0.95, MAE = 4.66 years). Brain‐predicted age was a heritable phenotype for all models and input data (h2 ≥ 0.5). Brain‐predicted age showed high test‐retest reliability (intraclass correlation coefficient [ICC] = 0.90–0.99). Multi‐centre reliability was more variable within high ICCs for GM (0.83–0.96) and poor‐moderate levels for WM and raw data (0.51–0.77). Brain‐predicted age represents an accurate, highly reliable and genetically‐influenced phenotype, that has potential to be used as a biomarker of brain ageing. Moreover, age predictions can be accurately generated on raw T1‐MRI data, substantially reducing computation time for novel data, bringing the process closer to giving real‐time information on brain health in clinical settings. HighlightsChronological age can be accurately predicted using convolutional neural networks.Age predicted is accurate even using raw structural neuroimaging data.Brain‐predicted age can be generated in a clinically applicable timeframe.Brain‐predicted age is significantly heritable.Brain‐predicted age is highly reliable, both within and between scanners.

Subfields: Cognitive Neuroscience, Health, Toxicology and Mutagenesis, Psychiatry and Mental health

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Health, Toxicology and Mutagenesis

In Psychiatry and Mental health

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, methodology): “Brain age [273] Chronological age prediction from raw brain T1-MRI data, also testing the heritability of brain-predicted age”
Predicting Age Using Neuroimaging: Innovative Brain Ageing Biomarkers. (2017, positive): “In particular, deep learning methods show [344_TD$DIFF]considerable promise [9].”
Brain age prediction using deep learning uncovers associated sequence variants (2019, methodology): “And predictably our h is lower than the narrow-sense heritability estimate of PAD estimated by Cole et al. 12 ( h 2 ¼ 0 : 66 [SE ¼ 0 : 09]) using a twin study sample.”
Brain Imaging Generation with Latent Diffusion Models (2022, methodology): “In our study, we used the 3D convolution neural network proposed in [6], trained on the same training set used in the LDM training.”
Medical Image Analysis using Convolutional Neural Networks: A Review (2017, background): “Some recent studies have shown that deep learning algorithms are successfully used for medical imaging applications [78-81].”
Tensor Regression Networks (2017, background): “Predicting age is an important task as the difference between true and predicted age is a biomarker that has a number of clinical applications (Cole et al., 2017; Kolenic et al., 2018; Franke et al., 2018).”
Accurate brain age prediction with lightweight deep neural networks (2019, methodology): “For example, existing studies have observed that the brain-age delta is an effective biomarker that shows differences between different clinical groups (Kaufmann et al., 2019) and is predictive for mortality (Cole et al., 2018).”
A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, background): “In recent years, a large amount of work has been published on deep learning based prediction tasks such as brain age prediction [124], [125], [126], Alzheimer’s disease classiﬁcation and trajectory modeling [127], [128], [129], [130], and schizophrenia classiﬁcation [131], [132].”