An official website of the United States government
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.
more »
« less
This content will become publicly available on April 6, 2026
Controllable Generative Model for Brain Evolution
Today’s generative models can synthesize magnetic resonance images (MRIs) of the brain at specific ages. However, such models can neither map the aging process longitudinally within subjects, nor accommodate its variability across subjects. Such approaches also cannot predict anatomic features of aging in ways that can be validated retrospectively or trusted prospectively. We introduce a three-dimensional hybrid ControlNet + diffusion model that uses the baseline T1-weighted MRIs of healthy adults to predict individual neuroanatomic aging trajectories, as reflected by follow-up MRIs. The approach captures individual anatomical changes with an average predicted voxelwise intensity error of 15% and structural similarity index of 93%. Unlike methods relying on qualitative validation, our approach quantifies the fidelity of prospective MRI synthesis using FreeSurfer volumetrics. Because brain atrophy reflects risk for Alzheimer’s disease (AD), our model’s ability to generate individual-specific prospective MRIs suggests its clinical potential to assist AD risk estimation.
more »
« less
- Award ID(s):
- 1936775
- PAR ID:
- 10626298
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 979-8-3503-6874-1
- Page Range / eLocation ID:
- 1 to 5
- Format(s):
- Medium: X
- Location:
- Hyderabad, India
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Brain age (BA), distinct from chronological age (CA), can be estimated from MRIs to evaluate neuroanatomic aging in cognitively normal (CN) individuals. BA, however, is a cross-sectional measure that summarizes cumulative neuroanatomic aging since birth. Thus, it conveys poorly recent or contemporaneous aging trends, which can be better quantified by the (temporal) pace P of brain aging. Many approaches to map P, however, rely on quantifying DNA methylation in whole-blood cells, which the blood–brain barrier separates from neural brain cells. We introduce a three-dimensional convolutional neural network (3D-CNN) to estimate P noninvasively from longitudinal MRI. Our longitudinal model (LM) is trained on MRIs from 2,055 CN adults, validated in 1,304 CN adults, and further applied to an independent cohort of 104 CN adults and 140 patients with Alzheimer’s disease (AD). In its test set, the LM computes P with a mean absolute error (MAE) of 0.16 y (7% mean error). This significantly outperforms the most accurate cross-sectional model, whose MAE of 1.85 y has 83% error. By synergizing the LM with an interpretable CNN saliency approach, we map anatomic variations in regional brain aging rates that differ according to sex, decade of life, and neurocognitive status. LM estimates of P are significantly associated with changes in cognitive functioning across domains. This underscores the LM’s ability to estimate P in a way that captures the relationship between neuroanatomic and neurocognitive aging. This research complements existing strategies for AD risk assessment that estimate individuals’ rates of adverse cognitive change with age.more » « less
-
Background: The progressive cognitive decline, an integral component of Alzheimer’s disease (AD), unfolds in tandem with the natural aging process. Neuroimaging features have demonstrated the capacity to distinguish cognitive decline changes stemming from typical brain aging and AD between different chronological points. Objective: To disentangle the normal aging effect from the AD-related accelerated cognitive decline and unravel its genetic components using a neuroimaging-based deep learning approach. Methods: We developed a deep-learning framework based on a dual-loss Siamese ResNet network to extract fine-grained information from the longitudinal structural magnetic resonance imaging (MRI) data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study. We then conducted genome-wide association studies (GWAS) and post-GWAS analyses to reveal the genetic basis of AD-related accelerated cognitive decline. Results: We used our model to process data from 1,313 individuals, training it on 414 cognitively normal people and predicting cognitive assessment for all participants. In our analysis of accelerated cognitive decline GWAS, we identified two genome-wide significant loci: APOE locus (chromosome 19 p13.32) and rs144614292 (chromosome 11 p15.1). Variant rs144614292 (G > T) has not been reported in previous AD GWA studies. It is within the intronic region of NELL1, which is expressed in neurons and plays a role in controlling cell growth and differentiation. The cell-type-specific enrichment analysis and functional enrichment of GWAS signals highlighted the microglia and immune-response pathways. Conclusions: Our deep learning model effectively extracted relevant neuroimaging features and predicted individual cognitive decline. We reported a novel variant (rs144614292) within the NELL1 gene.more » « less
-
Recent work suggests that indentations of the cerebral cortex, or sulci, may be uniquely vulnerable to atrophy in aging and Alzheimer's disease (AD) and that posteromedial cortex (PMC) is particularly vulnerable to atrophy and pathology accumulation. However, these studies did not consider small, shallow, and variable tertiary sulci that are located in association cortices and are often associated with human-specific aspects of cognition. Here, we manually defined 4,362 PMC sulci in 432 hemispheres in 216 human participants (50.5% female) and found that these smaller putative tertiary sulci showed more age- and AD-related thinning than larger, more consistent sulci, with the strongest effects for two newly uncovered sulci. A model-based approach relating sulcal morphology to cognition identified that a subset of these sulci was most associated with memory and executive function scores in older adults. These findings lend support to the retrogenesis hypothesis linking brain development and aging, and provide new neuroanatomical targets for future studies of aging and AD. Significance StatementLarge-scale changes in cortical structure in aging suggest sulci are particularly vulnerable to atrophy. However, tertiary sulci, the smallest and most individually variable cortical folds associated with cognitive development, have not been studied in aging. Here, we investigate tertiary sulci for the first time in aging and Alzheimer's disease (AD). We find that these smaller and shallower sulci show more age- and AD-related thinning than larger sulci in posteromedial cortex (PMC), and that the atrophy of a subset of PMC sulci is most associated with cognition in older adults. These findings support classical theories linking developmental and aging trajectories at a novel anatomical resolution and provide insight into relationships between individual differences in structural brain changes and cognitive decline.more » « less
-
null (Ed.)Abstract Depression has been associated with greater risk of Alzheimer’s disease (AD), and existing research has identified structural differences in brain regions in depressed subjects compared to healthy samples, but results have been heterogeneous. We sought to determine the effect of depression on regional brain volumes by cognitive and APOE e4 status. Secondary analysis of the National Alzheimer’s Coordinating Center (NACC) Uniform Data Set was conducted using complete MRI data from 1,371 participants (mean age: 70.5; SD: 11.7). Multiple linear regression was used to estimate the adjusted effect of depression (via the Neuropsychiatric Inventory Questionnaire) on regional brain volumes through measurement of 30 structural MRIs. Depression in the prior two years was associated with lower total brain, cerebrum,, and gray matter volumes and greater total brain white matter hyperintensities (p<.05). Greater volumes were also observed in all ventricular volume measures. Lower mean volumes were observed in six additional frontal lobe and parietal lobe cortical regions. Alternately, depression antecedent to the past 2 years correlated only with occipital lobe gray matter volumes (right, left, total). Our findings suggest that depression in the prior two years is associated with atrophy across multiple brain regions and related ventricular enlargement, even after controlling for intracranial volume and demographic covariates. The duration of depression influences results, however, as depression prior to 2 years before assessment was correlated with significantly fewer and different regional brain volume changes.more » « less
