MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14 468 individuals worldwide

Abstract

Deep learning has emerged as a powerful approach to constructing imaging signatures of normal brain ageing as well as of various neuropathological processes associated with brain diseases. In particular, MRI-derived brain age has been used as a comprehensive biomarker of brain health that can identify both advanced and resilient ageing individuals via deviations from typical brain ageing. Imaging signatures of various brain diseases, including schizophrenia and Alzheimer’s disease, have also been identified using machine learning. Prior efforts to derive these indices have been hampered by the need for sophisticated and not easily reproducible processing steps, by insufficiently powered or diversified samples from which typical brain ageing trajectories were derived, and by limited reproducibility across populations and MRI scanners. Herein, we develop and test a sophisticated deep brain network (DeepBrainNet) using a large (n = 11 729) set of MRI scans from a highly diversified cohort spanning different studies, scanners, ages and geographic locations around the world. Tests using both cross-validation and a separate replication cohort of 2739 individuals indicate that DeepBrainNet obtains robust brain-age estimates from these diverse datasets without the need for specialized image data preparation and processing. Furthermore, we show evidence that moderately fit brain ageing models may provide brain age estimates that are most discriminant of individuals with pathologies. This is not unexpected as tightly-fitting brain age models naturally produce brain-age estimates that offer little information beyond age, and loosely fitting models may contain a lot of noise. Our results offer some experimental evidence against commonly pursued tightly-fitting models. We show that the moderately fitting brain age models obtain significantly higher differentiation compared to tightly-fitting models in two of the four disease groups tested. Critically, we demonstrate that leveraging DeepBrainNet, along with transfer learning, allows us to construct more accurate classifiers of several brain diseases, compared to directly training classifiers on patient versus healthy control datasets or using common imaging databases such as ImageNet. We, therefore, derive a domain-specific deep network likely to reduce the need for application-specific adaptation and tuning of generic deep learning networks. We made the DeepBrainNet model freely available to the community for MRI-based evaluation of brain health in the general population and over the lifespan.

Accelerated MRI-predicted brain ageing and its associations with cardiometabolic and brain disorders

“…This highlights the importance of the completely held-out test set such as has been used here www.nature.com/scientificreports/ for generalisability and comparisons with other work. 2D CNNs have been used effectively 8 and trade spatial information for the ability to leverage models pre-trained on natural images. Here, we opted for a 3D CNN that retains and leverages the entire MRI volume.…”

“…More recently, studies have taken advantage of large-scale population-based data including those in UK Biobank and have used neural networks and other advanced methods to analyse MRI imaging data [7][8][9][10][11][12][13] . Here we build on these recent studies using a deep convolutional neural network (CNN) with T1-weighted brain MRI data from 21,382 volunteers in the UK Biobank.…”

Accurate brain age prediction with lightweight deep neural networks

“…There are several researches mitigating this issue (e.g.) by downsampling the input (Korolev et al, 2017), taking patches (Kamnitsas et al, 2017;Liu et al, 2018) or 2D slices (Bashyam et al, 2020;Lin et al, 2018) as input instead of the 3D full brain, or using a reversible architecture (Brügger et al, 2019), yet involving trade-offs between the GPU memory restriction and the information/performance loss. Further, deep networks usually require a large sample size for model fitting, but neuroimaging datasets often have relatively few samples compared to existing million-sample natural image datasets (Raghu et al, 2019;Russakovsky et al, 2015), which could limit the ability to learn image features effectively, and result in overfitting problems.…”

Accurate brain age prediction using recurrent slice-based networks

“…In addition, the lack of models that have been pre-trained with large-scale 3D imaging datasets inhibits effective transfer learning. Networks pretrained with ImageNet have been shown to learn more generalizable features 6 and networks trained with 2D slices have shown significant performance improvements on BrainAge estimation and Alzheimer's disease classification tasks [7][8] . Logistically, the number of parameters in these models requires large GPU memory and the models typically take a long time to train.…”