Accurate brain age prediction with lightweight deep neural networks

IdenBAT: Disentangled representation learning for identity-preserved brain age transformation

Brain age transformation aims to convert reference brain images into synthesized images that accurately reflect the age-specific features of a target age group. The primary objective of this task is to modify only the age-related attributes of the reference image while preserving all other age-irrelevant attributes. However, achieving this goal poses substantial challenges due to the inherent entanglement of various image attributes within features extracted from a backbone encoder, resulting in simultaneous alterations during image generation. To address this challenge, we propose a novel architecture that employs disentangled representation learning for identity-preserved brain age transformation, called IdenBAT. This approach facilitates the decomposition of image features, ensuring the preservation of individual traits while selectively transforming age-related characteristics to match those of the target age group. Through comprehensive experiments conducted on both 2D and full-size 3D brain datasets, our method adeptly converts input images to target age while retaining individual characteristics accurately. Furthermore, our approach demonstrates superiority over existing state-of-the-art regarding performance fidelity. The code is available at: https://github.com/ku-milab/IdenBAT.

Encoding 3D information in 2D feature maps for brain CT-Angiography

We propose learnable 3D pooling (L3P), a CNN module designed to compress 3D information into 2D feature maps using anisotropic convolutions and unidirectional max pooling. Specifically, we used L3P followed by a 2D network to generate predictions from 3D brain CT-Angiography (CTA) in the context of large vessel occlusion (LVO). To further demonstrate its versatility, we extended its application to 3D brain MRI analysis for brain age prediction. First, we designed an experiment to classify the LVO-affected hemisphere (left or right), projecting the input CTA into the sagittal plane, which allowed to assess the ability of L3P to encode the 3D location where the location information was in the 3D-to-2D compression axis. Second, we evaluated the use of L3P on LVO detection as a binary classification (presence or absence). We compared the L3P models performance to that of 2D and stroke-specific 3D models. L3P models achieved results equivalent to stroke-specific 3D models while requiring fewer parameters and resources and provided better results than 2D models using maximum intensity projection images as input. The generalizability of L3P approach was evaluated on the LVO-affected hemisphere detection using data from a single site for training/validation and data from 36 other sites for testing, achieving an AUC of 0.83 on the test set. L3P also performed comparably or better than a fully 3D network on a brain age prediction task with a separate T1 MRI dataset, demonstrating its versatility across different tasks and imaging modalities. Additionally, L3P models generated more interpretable feature maps.

Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicing

Brain age gap, the difference between estimated brain age and chronological age via magnetic resonance imaging, has emerged as a pivotal biomarker in the detection of brain abnormalities. While deep learning is accurate in estimating brain age, the absence of uncertainty estimation may pose risks in clinical use. Moreover, current 3D brain age models are intricate, and using 2D slices hinders comprehensive dimensional data integration. Here, we introduced Spectral-normalized Neural Gaussian Process (SNGP) accompanied by 2.5D slice approach for seamless uncertainty integration in a single network with low computational expenses, and extra dimensional data integration without added model complexity. Subsequently, we compared different deep learning methods for estimating brain age uncertainty via the Pearson correlation coefficient, a metric that helps circumvent systematic underestimation of uncertainty during training. SNGP shows excellent uncertainty estimation and generalization on a dataset of 11 public datasets (N = 6327), with competitive predictive performance (MAE=2.95). Besides, SNGP demonstrates superior generalization performance (MAE=3.47) on an independent validation set (N = 301). Additionally, we conducted five controlled experiments to validate our method. Firstly, uncertainty adjustment in brain age estimation improved the detection of accelerated brain aging in adolescents with ADHD, with a 38% increase in effect size after adjustment. Secondly, the SNGP model exhibited OOD detection capabilities, showing significant differences in uncertainty across Asian and non-Asian datasets. Thirdly, the performance of DenseNet as a backbone for SNGP was slightly better than ResNeXt, attributed to DenseNet's feature reuse capability, with robust generalization on an independent validation set. Fourthly, site effect harmonization led to a decline in model performance, consistent with previous studies. Finally, the 2.5D slice approach significantly outperformed 2D methods, improving model performance without increasing network complexity. In conclusion, we present a cost-effective method for estimating brain age with uncertainty, utilizing 2.5D slicing for enhanced performance, showcasing promise for clinical applications.

Hyperfusion: A hypernetwork approach to multimodal integration of tabular and medical imaging data for predictive modeling

The integration of diverse clinical modalities such as medical imaging and the tabular data extracted from patients' Electronic Health Records (EHRs) is a crucial aspect of modern healthcare. Integrative analysis of multiple sources can provide a comprehensive understanding of the clinical condition of a patient, improving diagnosis and treatment decision. Deep Neural Networks (DNNs) consistently demonstrate outstanding performance in a wide range of multimodal tasks in the medical domain. However, the complex endeavor of effectively merging medical imaging with clinical, demographic and genetic information represented as numerical tabular data remains a highly active and ongoing research pursuit. We present a novel framework based on hypernetworks to fuse clinical imaging and tabular data by conditioning the image processing on the EHR's values and measurements. This approach aims to leverage the complementary information present in these modalities to enhance the accuracy of various medical applications. We demonstrate the strength and generality of our method on two different brain Magnetic Resonance Imaging (MRI) analysis tasks, namely, brain age prediction conditioned by subject's sex and multi-class Alzheimer's Disease (AD) classification conditioned by tabular data. We show that our framework outperforms both single-modality models and state-of-the-art MRI tabular data fusion methods. A link to our code can be found at https://github.com/daniel4725/HyperFusion.

Brain age in multiple sclerosis: a study with deep learning and traditional machine learning

'Brain age' is a numerical estimate of the biological age of the brain and an overall effort to measure neurodegeneration, regardless of disease type. In multiple sclerosis, accelerated brain ageing has been linked to disability accrual. Artificial intelligence has emerged as a promising tool for the assessment and quantification of the impact of neurodegenerative diseases. Despite the existence of numerous AI models, there is a noticeable lack of comparative imaging data for traditional machine learning versus deep learning in conditions such as multiple sclerosis. A retrospective observational study was initiated to analyse clinical and MRI data (4584 MRIs) from various scanners in a large longitudinal cohort (n = 1516) of people with multiple sclerosis collected from two institutions (Karolinska Institute and Oslo University Hospital) using a uniform data post-processing pipeline. We conducted a comparative assessment of brain age using a deep learning simple fully convolutional network and a well-established traditional machine learning model. This study was primarily aimed to validate the deep learning brain age model in multiple sclerosis. The correlation between estimated brain age and chronological age was stronger for the deep learning estimates (r = 0.90, P < 0.001) than the traditional machine learning estimates (r = 0.75, P < 0.001). An increase in brain age was significantly associated with higher expanded disability status scale scores (traditional machine learning: t = 5.3, P < 0.001; deep learning: t = 3.7, P < 0.001) and longer disease duration (traditional machine learning: t = 6.5, P < 0.001; deep learning: t = 5.8, P < 0.001). No significant inter-model difference in clinical correlation or effect measure was found, but significant differences for traditional machine learning-derived brain age estimates were found between several scanners. Our study suggests that the deep learning-derived brain age is significantly associated with clinical disability, performed equally well to the traditional machine learning-derived brain age measures, and may counteract scanner variability.

WMH-DualTasker: A Weakly Supervised Deep Learning Model for Automated White Matter Hyperintensities Segmentation and Visual Rating Prediction

White matter hyperintensities (WMH) are neuroimaging markers linked to an elevated risk of cognitive decline. WMH severity is typically assessed via visual rating scales and through volumetric segmentation. While visual rating scales are commonly used in clinical practice, they offer limited descriptive power. In contrast, supervised volumetric segmentation requires manually annotated masks, which are labor-intensive and challenging to scale for large studies. Therefore, our goal was to develop an automated deep-learning model that can provide accurate and holistic quantification of WMH severity with minimal supervision. We developed WMH-DualTasker, a deep learning model that simultaneously performs voxel-wise segmentation and visual rating score prediction. The model employs self-supervised learning with transformation-invariant consistency constraints, using WMH visual ratings (ARWMC scale, range 0-30) from clinical settings as the sole supervisory signal. Additionally, we assessed its clinical utility by applying it to identify individuals with mild cognitive impairment (MCI) and to predict dementia conversion. The volumetric quantification performance of WMH-DualTasker was either superior to or on par with existing supervised methods, as demonstrated on the MICCAI-WMH dataset (N = 60, Dice = 0.602) and the SINGER dataset (N = 64, Dice = 0.608). Furthermore, the model exhibited strong agreement with clinical visual rating scales on an external dataset (SINGER, MAE = 1.880, K = 0.77). Importantly, WMH severity metrics derived from WMH-DualTasker improved predictive performance beyond conventional clinical features for MCI classification (AUC = 0.718, p < 0.001) and MCI conversion prediction (AUC = 0.652, p < 0.001) using the ADNI dataset. WMH-DualTasker substantially reduces the reliance on labor-intensive manual annotations, facilitating more efficient and scalable quantification of WMH severity in large-scale population studies. This innovative approach has the potential to advance preventive and precision medicine by enhancing the assessment and management of vascular cognitive impairment associated with WMH.

Advanced Brain Age Prediction Using Multi-Head Self-Attention: A Comparative Analysis of Western and Middle Eastern MRI Datasets

Brain age estimation is a critical biomarker for early detection of neurodegenerative diseases, but existing models are primarily trained on Western datasets, limiting their applicability to diverse populations. Recent studies suggest that brain aging patterns vary across ethnic groups, highlighting the need for more inclusive and adaptable AI-driven neuroimaging models. We trained our model on 4,635 healthy individuals (40-80 years) from ADNI, OASIS-3, Cam-CAN, and IXI, using 80% of data (n=3700) for training and 20% (n=935) for testing. The model was further tested on a Middle Eastern dataset (107 subjects, Tehran, Iran). It integrates multi-head self-attention along with residual connections to enhance long-range spatial feature learning, improving upon previous CNN models. Performance was evaluated using mean absolute error (MAE). The model achieved state-of-the-art accuracy (MAE = 1.99 years) on the Western test set, while being much lighter than previous models (approximately 3 million parameters); however, it performed significantly worse on the ME dataset (best MAE = 4.35 years, final = 5.83 years). Bias correction did not improve performance, indicating population-specific brain aging differences. These findings emphasize the need for diverse training datasets and cross-population adaptation techniques.

Multi-center brain age prediction via dual-modality fusion convolutional network

Accurate prediction of brain age is crucial for identifying deviations between typical individual brain development trajectories and neuropsychiatric disease progression. Although current research has made progress, the effective application of brain age prediction models to multi-center datasets, particularly those with small-sample sizes, remains a significant challenge that is yet to be addressed. To this end, we propose a multi-center data correction method, which employs a domain adaptation correction strategy with Wasserstein distance of optimal transport, along with maximum mean discrepancy to improve the generalizability of brain-age prediction models on small-sample datasets. Additionally, most of the existing brain age models based on neuroimage identify the task of predicting brain age as a regression or classification problem, which may affect the accuracy of the prediction. Therefore, we propose a brain dual-modality fused convolutional neural network model (BrainDCN) for brain age prediction, and optimize this model by introducing a joint loss function of mean absolute error and cross-entropy, which identifies the prediction of brain age as both a regression and classification task. Furthermore, to highlight age-related features, we construct weighting matrices and vectors from a single-center training set and apply them to multi-center datasets to weight important features. We validate the BrainDCN model on the CamCAN dataset and achieve the lowest average absolute error compared to state-of-the-art models, demonstrating its superiority. Notably, the joint loss function and weighted features can further improve the prediction accuracy. More importantly, our proposed multi-center correction method is tested on four neuroimaging datasets and achieves the lowest average absolute error compared to widely used correction methods, highlighting the superior performance of the method in cross-center data integration and analysis. Furthermore, the application to multi-center schizophrenia data shows a mean accelerated aging compared to normal controls. Thus, this research establishes a pivotal methodological foundation for multi-center brain age prediction studies, exhibiting considerable applicability in clinical contexts, which are predominantly characterized by small-sample datasets.

Maintaining Brain Health: The Impact of Physical Activity and Fitness on the Aging Brain-A UK Biobank Study

The growing prevalence of physical and neurological disorders linked to aging poses significant challenges for society. Many of these disorders are closely linked to changes in brain structure and function, highlighting the importance of identifying protective factors that can preserve brain structure in later life and mitigate age-related decline. Physical activity (PA) is consistently linked to physical health and was found to mitigate age-related disorders. However, its effects on markers of brain aging remain inconclusive, partly due to reliance on underpowered studies and self-reported data. We investigated the effects of accelerometer-measured PA and physical fitness on BrainAGE, a machine-learning-derived marker of brain aging, in a large UK Biobank cohort. Using cortical and subcortical neuroimaging-derived features, a BrainAGE model was trained on 21,442 participants (mean absolute error: 3.75 years) and applied to predict BrainAGE for an independent sample of 10,874 participants. Accelerometer-measured moderate-intensity PA, but not self-reported PA, was associated with decelerated brain aging, indicated by a negative BrainAGE. Further, higher hand grip strength, along with lower body mass index (BMI), diastolic blood pressure (DBP), and resting heart rate, was linked to decelerated aging. These fitness measures impacted BrainAGE independently of PA. Additionally, fitness partially accounted for the relationship between PA and BrainAGE. Specifically, BMI, DBP, and resting heart rate showed a significant mediating effect, while grip strength did not. These findings highlight the interplay between PA and fitness in maintaining brain health and provide valuable insights for neuroscience and preventive health measures.

Unveiling Alzheimer's disease through brain age estimation using multi-kernel regression network and magnetic resonance imaging

BACKGROUND AND OBJECTIVE

Structural magnetic resonance imaging (MRI) studies have unveiled age-related anatomical changes across various brain regions. The disparity between actual age and estimated age, known as the Brain-Predicted Age Difference (Brain-PAD), serves as an indicator for predicting neurocognitive ailments or brain abnormalities resulting from diseases. This study aims to develop an accurate brain age prediction model that can assist in identifying potential neurocognitive impairments.

METHODS

The present study implemented a brain age prediction model using a ResNet-50 deep network and a multi-kernel extreme learning machine (MKELM) regression network, relying on MRI images. Kernel methods translate input information into higher-dimensional space by introducing nonlinearity and enabling the model to grasp complicated data patterns. A multi-kernel function combines the Gaussian and polynomial kernels and is incorporated into the brain age regression model. The model effectively utilizes the benefits of both kernel functions to estimate the ages accurately. MRI scans are segmented into gray matter (GM) and white matter (WM) maps preprocessed and extracted of significant features using the ResNet-50 deep network. Extracted features of the WM and GM datasets are fed into the MKELM regression model for brain age prediction.

RESULTS

The proposed age estimation framework achieved 3.06 years of mean absolute error (MAE) and 4.12 years of root mean square error (RMSE) on healthy controls (HC) WM scans, and on GM scans, 2.73 years of MAE and 3.65 years of RMSE values. To further validate the importance of Brain-PAD as a biomarker for identifying brain health conditions, an independent testing dataset of mild cognitive impairment (MCI) and Alzheimer's disease (AD) subjects age is predicted. The Brain-PAD values for AD subjects' GM images are significantly higher compared to those of HC and MCI subjects, indicating distinct brain health conditions. Furthermore, variations in GM and WM tissue were identified in AD subjects, revealing that the parahippocampus and corpus callosum were notably affected.

CONCLUSION

Our findings underscore the potential of Brain-PAD as a significant biomarker for assessing brain health, with implications for early detection of neurocognitive diseases. The developed framework effectively estimates brain age using MRI, contributing valuable insights into the relationship between brain structure and cognitive health.

A lightweight generative model for interpretable subject-level prediction

Recent years have seen a growing interest in methods for predicting an unknown variable of interest, such as a subject's diagnosis, from medical images depicting its anatomical-functional effects. Methods based on discriminative modeling excel at making accurate predictions, but are challenged in their ability to explain their decisions in anatomically meaningful terms. In this paper, we propose a simple technique for single-subject prediction that is inherently interpretable. It augments the generative models used in classical human brain mapping techniques, in which the underlying cause-effect relations can be encoded, with a multivariate noise model that captures dominant spatial correlations. Experiments demonstrate that the resulting model can be efficiently inverted to make accurate subject-level predictions, while at the same time offering intuitive visual explanations of its inner workings. The method is easy to use: training is fast for typical training set sizes, and only a single hyperparameter needs to be set by the user. Our code is available at https://github.com/chiara-mauri/Interpretable-subject-level-prediction.

Enhancing Brain Age Prediction and Neurodegeneration Detection with Contrastive Learning on Regional Biomechanical Properties

The aging process affects brain structure and function, yet its biomechanical properties remain underexplored. Magnetic Resonance Elastography (MRE) provides a unique perspective by mapping brain tissue stiffness and damping ratio, observables that correlate with age and disease. Using a self-supervised contrastive regression framework, we demonstrate that MRE surpasses conventional structural magnetic resonance imaging (MRI) in sensitivity. Specifically, stiffness captures Alzheimer's disease (AD), while damping ratio detects subtle changes associated with mild cognitive impairment (MCI). Our regional analysis identifies deep brain structures, particularly the caudate and thalamus, as key biomarkers of aging. The greater age sensitivity of MRE translates to superior differentiation of AD and MCI from healthy individuals, pinpointing regions where significant biomechanical alterations occur, notably the thalamus in AD and hippocampus in MCI. Furthermore, our results reveal biomechanical alterations in cognitively healthy individuals whose aging profiles closely resemble patients with MCI and AD. These findings highlight MRE's potential as a biomarker for early neurodegenerative changes, aiding dementia risk detection and early intervention.

Recognition of brain activities via graph-based long short-term memory-convolutional neural network

Introduction

Human brain activities are always difficult to recognize due to its diversity and susceptibility to disturbance. With its unique capability of measuring brain activities, magnetoencephalography (MEG), as a high temporal and spatial resolution neuroimaging technique, has been used to identify multi-task brain activities. Accurately and robustly classifying motor imagery (MI) and cognitive imagery (CI) from MEG signals is a significant challenge in the field of brain-computer interface (BCI).

Methods

In this study, a graph-based long short-term memory-convolutional neural network (GLCNet) is proposed to classify the brain activities in MI and CI tasks. It was characterized by implementing three modules of graph convolutional network (GCN), spatial convolution and long short-term memory (LSTM) to effectively extract time-frequency-spatial features simultaneously. For performance evaluation, our method was compared with six benchmark algorithms of FBCSP, FBCNet, EEGNet, DeepConvNets, Shallow ConvNet and MEGNet on two public datasets of MEG-BCI and BCI competition IV dataset 3.

Results

The results demonstrated that the proposed GLCNet outperformed other models with the average accuracies of 78.65% and 65.8% for two classification and four classification on the MEG-BCI dataset, respectively.

Discussion

It was concluded that the GLCNet enhanced the model's adaptability in handling individual variability with robust performance. This would contribute to the exploration of brain activates in neuroscience.

Construction of brain age models based on structural and white matter information

Brain aging is an inevitable process in adulthood, yet there is a lack of objective measures to accurately assess its extent. This study aims to develop brain age prediction model using magnetic resonance imaging (MRI), which includes structural information of gray matter and integrity information of white matter microstructure. Multiparameter MRI was performed on two population cohorts. We collected structural MRI data from T1- and T2-sequences, including gray matter volume, surface area, and thickness in different areas. For diffusion tensor imaging (DTI), we derived four white matter parameters: fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity. To achieve reliable brain age prediction based on structure and white matter integrity, we employed LASSO regression. We successfully constructed a brain age prediction model based on multiparameter brain MRI (Mean absolute error of 3.87). Using structural and diffusion metrics, we identified and visualized which brain areas were notably involved in brain aging. Simultaneously, we discovered that lateralization during brain aging is a significant factor in brain aging models. We have successfully developed a brain age estimation model utilizing white matter and gray matter metrics, which exhibits minimal errors and is suitable for adults.

Genetically supported targets and drug repurposing for brain aging: A systematic study in the UK Biobank

Brain age gap (BAG), the deviation between estimated brain age and chronological age, is a promising marker of brain health. However, the genetic architecture and reliable targets for brain aging remains poorly understood. In this study, we estimate magnetic resonance imaging (MRI)-based brain age using deep learning models trained on the UK Biobank and validated with three external datasets. A genome-wide association study for BAG identified two unreported loci and seven previously reported loci. By integrating Mendelian Randomization (MR) and colocalization analysis on eQTL and pQTL data, we prioritized seven genetically supported druggable genes, including MAPT, TNFSF12, GZMB, SIRPB1, GNLY, NMB, and C1RL, as promising targets for brain aging. We rediscovered 13 potential drugs with evidence from clinical trials of aging and prioritized several drugs with strong genetic support. Our study provides insights into the genetic basis of brain aging, potentially facilitating drug development for brain aging to extend the health span.

Unravelling pathological ageing with brain age gap estimation in Alzheimer's disease, diabetes and schizophrenia

Brain age gap estimation (BrainAGE), the difference between predicted brain age and chronological age, might be a putative biomarker aiming to detect the transition from healthy to pathological brain ageing. The biomarker primarily models healthy ageing with machine learning models trained with structural magnetic resonance imaging (MRI) data. BrainAGE is expected to translate the deviations in neural ageing trajectory and has been shown to be increased in multiple pathologies, such as Alzheimer's disease (AD), schizophrenia and Type 2 diabetes (T2D). Thus, accelerated ageing seems to be a general feature of neuropathological processes. However, neurobiological constraints remain to be identified to provide specificity to this biomarker. Explainability might be the key to uncovering age predictions and understanding which brain regions lead to an elevated predicted age on a given pathology compared to healthy controls. This is highly relevant to understanding the similarities and differences in neurodegeneration in AD and T2D, which remains an outstanding biological question. Sensitivity maps explain models by computing the importance of each voxel on the final prediction, thereby contributing to the interpretability of deep learning approaches. This paper assesses whether sensitivity maps yield different results across three conditions related to pathological neural ageing: AD, schizophrenia and T2D. Five deep learning models were considered, each model trained with different MRI data types: minimally processed T1-weighted brain scans, and corresponding grey matter, white matter, cerebrospinal fluid tissue segmentation and deformation fields (after spatial normalization). Our results revealed an increased BrainAGE in all pathologies, with a different mean, which is the smallest in schizophrenia; this is in line with the observation that neural loss is secondary in this early-onset condition. Importantly, our findings suggest that the sensitivity, indexing regional weights, for all models varies with age. A set of regions were shown to yield statistical differences across conditions. These sensitivity results suggest that mechanisms of neurodegeneration are quite distinct in AD and T2D. For further validation, the sensitivity and the morphometric maps were compared. The findings outlined a high congruence between the sensitivity and morphometry maps for age and clinical group conditions. Our evidence outlines that the biological explanation of model predictions is vital in adding specificity to the BrainAGE and understanding the pathophysiology of chronic conditions affecting the brain.

Deep learning to quantify the pace of brain aging in relation to neurocognitive changes

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.

Dimensionality reduction in 3D causal deep learning for neuroimage generation: an evaluation study

Purpose

Causal deep learning (DL) using normalizing flows allows the generation of true counterfactual images, which is relevant for many medical applications such as explainability of decisions, image harmonization, and in-silico studies. However, such models are computationally expensive when applied directly to high-resolution 3D images and, therefore, require image dimensionality reduction (DR) to efficiently process the data. The goal of this work was to compare how different DR methods affect counterfactual neuroimage generation.

Approach

Five DR techniques [2D principal component analysis (PCA), 2.5D PCA, 3D PCA, autoencoder, and Vector Quantised-Variational AutoEncoder] were applied to 23,692 3D brain images to create low-dimensional representations for causal DL model training. Convolutional neural networks were used to quantitatively evaluate age and sex changes on the counterfactual neuroimages. Age alterations were measured using the mean absolute error (MAE), whereas sex changes were assessed via classification accuracy.

Results

The 2.5D PCA technique achieved the lowest MAE of 4.16 when changing the age variable of an original image. When sex was changed, the autoencoder embedding led to the highest classification accuracy of 97.84% while also significantly impacting the age variable predictions, increasing the MAE to 5.24 years. Overall, 3D PCA provided the best balance, with an age prediction MAE of 4.57 years while maintaining 94.01% sex classification accuracy when altering the age variable and 94.73% sex classification accuracy and the lowest age prediction MAE (3.84 years) when altering the sex variable.

Conclusions

3D PCA appears to be the best-suited DR method for causal neuroimage analysis.

White matter injuries mediate brain age effects on cognitive function in cerebral small vessel disease

PURPOSE

This study aims to investigate the potential effect of compromised structural integrity on cerebral aging and cognitive function in cerebral small vessel disease (CSVD).

METHODS

Fifty-five CSVD patients and 42 controls underwent three-dimensional T1-weighted imaging and diffusion tensor imaging. Relative brain age (RBA) was computed to assess cerebral aging. Variables of structural integrity included cortical thickness, cortical volume, white matter hyperintensity (WMH) volume, peak width of skeletonized mean diffusivity (PSMD), ventricular volume, and choroid plexus volume. Mini-Mental State Examination (MMSE) was conducted to assess general cognition. Trail Making Test (TMT) and Auditory Verbal Learning Test were administered to evaluate executive function and episodic memory, respectively. Mediation analysis and multivariate linear regression with interaction terms were performed to explore the differential impacts of RBA on cognitive function and structural integrity between CSVD patients and controls.

RESULTS

RBA was significantly increased in CSVD patients compared to controls (p < 0.001). White matter injuries as assessed with PSMD (mediation magnitude: 41.1%) and WMH volume (mediation magnitude: 56.9%) significantly mediated the relationship between CSVD pathologies and RBA (p < 0.001). Higher RBA was significantly correlated with poorer scores of MMSE, TMT-A, and TMT-B in CSVD patients (p < 0.01). Additionally, PSMD (mediation magnitude: 57.8% in MMSE, 48.3% in TMT-A, and 28.8% in TMT-B) and WMH volume (mediation magnitude: 55.1% in MMSE) significantly mediated the relationship between RBA and cognitive function (p < 0.05).

CONCLUSION

White matter injuries play a critical role in the cerebral aging and cognitive decline in CSVD patients.

UK Biobank MRI data can power the development of generalizable brain clocks: A study of standard ML/DL methodologies and performance analysis on external databases

In this study, we present a comprehensive pipeline to train and compare a broad spectrum of machine learning and deep learning brain clocks, integrating diverse preprocessing strategies and correction terms. Our analysis also includes established methodologies which have shown success in prior UK Biobank-related studies. For our analysis we used T1-weighted MRI scans and processed de novo all images via FastSurfer, transforming them into a conformed space for deep learning and extracting image-derived phenotypes for our machine learning approaches. We rigorously evaluated these approaches both as robust age predictors for healthy individuals and as potential biomarkers for various neurodegenerative conditions, leveraging data from the UK Biobank, ADNI, and NACC datasets. To this end we designed a statistical framework to assess age prediction performance, the robustness of the prediction across cohort variability (database, machine type and ethnicity) and its potential as a biomarker for neurodegenerative conditions. Results demonstrate that highly accurate brain age models, typically utilising penalised linear machine learning models adjusted with Zhang's methodology, with mean absolute errors under 1 year in external validation, can be achieved while maintaining consistent prediction performance across different age brackets and subgroups (e.g., ethnicity and MRI machine/manufacturer). Additionally, these models show strong potential as biomarkers for neurodegenerative conditions, such as dementia, where brain age prediction achieved an AUROC of up to 0.90 in distinguishing healthy individuals from those with dementia.

Learning-based inference of longitudinal image changes: Applications in embryo development, wound healing, and aging brain

Longitudinal imaging data are routinely acquired for health studies and patient monitoring. A central goal in longitudinal studies is tracking relevant change over time. Traditional methods remove nuisance variation with custom pipelines to focus on significant changes. In this work, we present a machine learning-based method that automatically ignores irrelevant changes and extracts the time-varying signal of interest. Our method, called Learning-based Inference of Longitudinal imAge Changes (LILAC), performs a pairwise comparison of longitudinal images in order to make a temporal difference prediction. LILAC employs a convolutional Siamese architecture to extract feature pairs, followed by subtraction and a bias-free fully connected layer to learn meaningful temporal image differences. We first showcase LILAC's ability to capture key longitudinal changes by simply training it to predict the temporal ordering of images. In our experiments, temporal ordering accuracy exceeded 0.98, and predicted time differences were strongly correlated with actual changes in relevant variables (Pearson Correlation Coefficient r = 0.911 with embryo phase change, and r = 0.875 with time interval in wound healing). Next, we trained LILAC to explicitly predict specific targets, such as the change in clinical scores in patients with mild cognitive impairment. LILAC models achieved over a 40% reduction in root mean square error compared to baseline methods. Our empirical results demonstrate that LILAC effectively localizes and quantifies relevant individual-level changes in longitudinal imaging data, offering valuable insights for studying temporal mechanisms or guiding clinical decisions.

Transformer-based approaches for neuroimaging: an in-depth review of their role in classification and regression tasks

In the ever-evolving landscape of deep learning (DL), the transformer model emerges as a formidable neural network architecture, gaining significant traction in neuroimaging-based classification and regression tasks. This paper presents an extensive examination of transformer's application in neuroimaging, surveying recent literature to elucidate its current status and research advancement. Commencing with an exposition on the fundamental principles and structures of the transformer model and its variants, this review navigates through the methodologies and experimental findings pertaining to their utilization in neuroimage classification and regression tasks. We highlight the transformer model's prowess in neuroimaging, showcasing its exceptional performance in classification endeavors while also showcasing its burgeoning potential in regression tasks. Concluding with an assessment of prevailing challenges and future trajectories, this paper proffers insights into prospective research directions. By elucidating the current landscape and envisaging future trends, this review enhances comprehension of transformer's role in neuroimaging tasks, furnishing valuable guidance for further inquiry.

Judged by your neighbors: Brain structural normativity profiles for large and heterogeneous samples

The detection of norm deviations is fundamental to clinical decision making and impacts our ability to diagnose and treat diseases effectively. Current normative modeling approaches rely on generic comparisons and quantify deviations in relation to the population average. However, generic models interpolate subtle nuances and risk the loss of critical information, thereby compromising effective personalization of health care strategies. To acknowledge the substantial heterogeneity among patients and support the paradigm shift of precision medicine, we introduce Nearest Neighbor Normativity (N3), which is a strategy to refine normativity evaluations in diverse and heterogeneous clinical study populations. We address current methodological shortcomings by accommodating several equally normative population prototypes, comparing individuals from multiple perspectives and designing specifically tailored control groups. Applied to brain structure in 36,896 individuals, the N3 framework provides empirical evidence for its utility and significantly outperforms traditional methods in the detection of pathological alterations. Our results underscore N3's potential for individual assessments in medical practice, where norm deviations are not merely a benchmark, but an important metric supporting the realization of personalized patient care.

ds-FCRN: three-dimensional dual-stream fully convolutional residual networks and transformer-based global-local feature learning for brain age prediction

The brain undergoes atrophy and cognitive decline with advancing age. The utilization of brain age prediction represents a pioneering methodology in the examination of brain aging. This study aims to develop a deep learning model with high predictive accuracy and interpretability for brain age prediction tasks. The gray matter (GM) density maps obtained from T1 MRI data of 16,377 healthy participants aged 45 to 82 years from the UKB database were included in this study (mean age, 64.27 ± 7.52 , 7811 men). We propose an innovative deep learning architecture for predicting brain age based on GM density maps. The architecture combines a 3D dual-stream fully convolutional residual network (ds-FCRN) with a Transformer-based global-local feature learning paradigm to enhance prediction accuracy. Moreover, we employed Shapley values to elucidate the influence of various brain regions on prediction precision. On a test set of 3,276 healthy subjects (mean age, 64.15 ± 7.45 , 1561 men), our 3D ds-FCRN model achieved a mean absolute error of 2.2 years in brain age prediction, outperforming existing models on the same dataset. The posterior interpretation revealed that the temporal lobe plays the most significant role in the brain age prediction process, while frontal lobe aging is associated with the greatest number of lifestyle factors. Our designed 3D ds-FCRN model achieved high predictive accuracy and high decision transparency. The brain age vectors constructed using Shapley values provided brain region-level insights into life factors associated with abnormal brain aging.

A review of artificial intelligence-based brain age estimation and its applications for related diseases

The study of brain age has emerged over the past decade, aiming to estimate a person's age based on brain imaging scans. Ideally, predicted brain age should match chronological age in healthy individuals. However, brain structure and function change in the presence of brain-related diseases. Consequently, brain age also changes in affected individuals, making the brain age gap (BAG)-the difference between brain age and chronological age-a potential biomarker for brain health, early screening, and identifying age-related cognitive decline and disorders. With the recent successes of artificial intelligence in healthcare, it is essential to track the latest advancements and highlight promising directions. This review paper presents recent machine learning techniques used in brain age estimation (BAE) studies. Typically, BAE models involve developing a machine learning regression model to capture age-related variations in brain structure from imaging scans of healthy individuals and automatically predict brain age for new subjects. The process also involves estimating BAG as a measure of brain health. While we discuss recent clinical applications of BAE methods, we also review studies of biological age that can be integrated into BAE research. Finally, we point out the current limitations of BAE's studies.

An optimized ensemble search approach for classification of higher-level gait disorder using brain magnetic resonance images

Higher-Level Gait Disorder (HLGD) is a type of gait disorder estimated to affect up to 6% of the older population. By definition, its symptoms originate from the higher-level nervous system, yet its association with brain morphology remains unclear. This study hypothesizes that there are patterns in brain morphology linked to HLGD. For the first time in the literature, this work investigates whether deep learning, in the form of convolutional neural networks, can capture patterns in magnetic resonance images to identify individuals affected by HLGD. To handle this new classification task, we propose setting up an ensemble of models. This leverages the benefits of combining classifiers instead of determining which network is the most suitable, developing a new architecture, or customizing an existing one. We introduce a computationally cost-effective search algorithm to find the optimal ensemble by leveraging a cost function of both traditional performance scores and the diversity among the models. Using a unique dataset from a large population-based cohort (VESPR), the ensemble identified by our algorithm demonstrated superior performance compared to single networks, other ensemble fusion techniques, and the best linear radiological measure. This emphasizes the importance of implementing diversity into the cost function. Furthermore, the results indicate significant morphological differences in brain structure between HLGD-affected individuals and controls, motivating research about which areas the networks base their classifications on, to get a better understanding of the pathophysiology of HLGD.

A Modality-Flexible Framework for Alzheimer's Disease Diagnosis Following Clinical Routine

Dementia has high incidence among the elderly, and Alzheimer's disease (AD) is the most common dementia. The procedure of AD diagnosis in clinics usually follows a standard routine consisting of different phases, from acquiring non-imaging tabular data in the screening phase to MR imaging and ultimately to PET imaging. Most of the existing AD diagnosis studies are dedicated to a specific phase using either single or multi-modal data. In this paper, we introduce a modality-flexible classification framework, which is applicable for different AD diagnosis phases following the clinical routine. Specifically, our framework consists of three branches corresponding to three diagnosis phases: 1) a tabular branch using only tabular data for screening phase, 2) an MRI branch using both MRI and tabular data for uncertain cases in screening phase, and 3) ultimately a PET branch for the challenging cases using all the modalities including PET, MRI, and tabular data. To achieve effective fusion of imaging and non-imaging modalities, we introduce an image-tabular transformer block to adaptively scale and shift the image and tabular features according to modality importance determined by the network. The proposed framework is extensively validated on four cohorts containing 6495 subjects. Experiments demonstrate that our framework achieves superior diagnostic performance than the other representative methods across various AD diagnosis tasks, and shows promising performance for all the diagnosis phases, which exhibits great potential for clinical application.

Predicting brain age with global-local attention network from multimodal neuroimaging data: Accuracy, generalizability, and behavioral associations

Brain age, an emerging biomarker for brain diseases and aging, is typically predicted using single-modality T1-weighted structural MRI data. This study investigates the benefits of integrating structural MRI with diffusion MRI to enhance brain age prediction. We propose an attention-based deep learning model that fuses global-context information from structural MRI with local details from diffusion metrics. The model was evaluated using two large datasets: the Human Connectome Project (HCP, n = 1064, age 22-37) and the Cambridge Center for Aging and Neuroscience (Cam-CAN, n = 639, age 18-88). It was tested for generalizability and robustness on three independent datasets (n = 546, age 20-86), reproducibility on a test-retest dataset (n = 44, age 22-35), and longitudinal consistency (n = 129, age 46-92). We also examined the relationship between predicted brain age and behavioral measures. Results showed that the multimodal model improved prediction accuracy, achieving mean absolute errors (MAEs) of 2.44 years in the HCP dataset (sagittal plane) and 4.36 years in the Cam-CAN dataset (axial plane). The corresponding R2 values were 0.258 and 0.914, respectively, reflecting the model's ability to explain variance in the predictions across both datasets. Compared to single-modality models, the multimodal approach showed better generalization, reducing MAEs by 10-76 % and enhancing robustness by 22-82 %. While the multimodal model exhibited superior reproducibility, the sMRI model showed slightly better longitudinal consistency. Importantly, the multimodal model revealed unique associations between predicted brain age and behavioral measures, such as walking endurance and loneliness in the HCP dataset, which were not detected with chronological age alone. In the Cam-CAN dataset, brain age and chronological age exhibited similar correlations with behavioral measures. By integrating sMRI and dMRI through an attention-based model, our proposed approach enhances predictive accuracy and provides deeper insights into the relationship between brain aging and behavior.

EEG-based brain age prediction in infants-toddlers: Implications for early detection of neurodevelopmental disorders

The infant brain undergoes rapid developmental changes in the first three years of life. Understanding these changes through the prediction of chronological age using neuroimaging can provide insights into typical and atypical brain development. We utilized 938 resting-state EEG recordings from 457 typically developing infants, 2 to 38 months old, to develop age prediction models. The multilayer perceptron model demonstrated the highest accuracy with an R2 of 0.83 and a mean absolute error of 91.7 days. Feature importance analysis that combined hierarchical clustering and Shapley values identified two feature clusters describing periodic alpha and low beta activity as key predictors of age. Application of the model to EEG data from infants later diagnosed with autism or Down syndrome revealed significant underestimations of chronological age, supporting its potential as a clinical tool for early identification of alterations in brain development.

Predicting host health status through an integrated machine learning framework: insights from healthy gut microbiome aging trajectory

The gut microbiome, recognized as a critical component in the development of chronic diseases and aging processes, constitutes a promising approach for predicting host health status. Previous research has underscored the potential of microbiome-based predictions, and the rapid advancements of machine learning techniques have introduced new opportunities for exploiting microbiome data. To predict various host nonhealthy conditions, this study proposed an integrated machine learning-based estimation pipeline of Gut Age Index (GAI) by establishing a health aging baseline with the gut microbiome data from healthy individuals. We assessed the performance of GAI pipeline on two extensive cohorts - the Guangdong Gut Microbiome Project (GGMP) and the American Gut Project (AGP). In the GGMP cohort, for 20 common chronic diseases such as metabolic syndrome, obesity, and cardiovascular diseases, the proposed GAI achieved a balanced accuracy, ranging from 66 to 75%, with the prediction performance for atherosclerosis being the highest. In the AGP cohort, the balanced accuracy of GAI ranged from 58 to 72% for 10 diseases. Based on the results from these two datasets, we conclude that our proposed approach in this study can be used to predict individual health status, which offers the potential for scalable, cost-effective, and personalized health insights.

A Multiform Heterogeneity Framework for Alzheimer's Disease Based on Multimodal Neuroimaging

Understanding the heterogeneity of Alzheimer's disease (AD) is crucial for advancing precision medicine specifically tailored to this disorder. Recent research has deepened our understanding of AD heterogeneity; however, translating these insights from bench to bedside via neuroimaging heterogeneity frameworks presents significant challenges. In this review, we systematically revisit prior studies and summarize the existing methodology of data-driven neuroimaging studies for AD heterogeneity. We organized the current methodology into 1) a subtyping clustering strategy for patients with AD, and we also subdivided it into subtyping analysis based on cross-sectional multimodal neuroimaging profiles and the identification of long-term disease progression from short-term datasets; 2) a stratified strategy that integrates neuroimaging measures with biomarkers; and 3) individual-specific abnormal patterns based on the normative model. Then, we evaluated the characteristics of these studies along 2 dimensions: 1) the understanding of pathology and 2) clinical application. We systematically address the limitations, challenges, and future directions of research into AD heterogeneity. Our goal is to enhance the neuroimaging heterogeneity framework for AD, thereby facilitating its transition from bench to bedside.

Explainable brain age prediction: a comparative evaluation of morphometric and deep learning pipelines

Brain age, a biomarker reflecting brain health relative to chronological age, is increasingly used in neuroimaging to detect early signs of neurodegenerative diseases and support personalized treatment plans. Two primary approaches for brain age prediction have emerged: morphometric feature extraction from MRI scans and deep learning (DL) applied to raw MRI data. However, a systematic comparison of these methods regarding performance, interpretability, and clinical utility has been limited. In this study, we present a comparative evaluation of two pipelines: one using morphometric features from FreeSurfer and the other employing 3D convolutional neural networks (CNNs). Using a multisite neuroimaging dataset, we assessed both model performance and the interpretability of predictions through eXplainable Artificial Intelligence (XAI) methods, applying SHAP to the feature-based pipeline and Grad-CAM and DeepSHAP to the CNN-based pipeline. Our results show comparable performance between the two pipelines in Leave-One-Site-Out (LOSO) validation, achieving state-of-the-art performance on the independent test set ( M A E = 3.21 with DNN and morphometric features and M A E = 3.08 with a DenseNet-121 architecture). SHAP provided the most consistent and interpretable results, while DeepSHAP exhibited greater variability. Further work is needed to assess the clinical utility of Grad-CAM. This study addresses a critical gap by systematically comparing the interpretability of multiple XAI methods across distinct brain age prediction pipelines. Our findings underscore the importance of integrating XAI into clinical practice, offering insights into how XAI outputs vary and their potential utility for clinicians.

Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age Estimation

Background/Objectives: A multimodal brain age estimation model could provide enhanced insights into brain aging. However, effectively integrating multimodal neuroimaging data to enhance the accuracy of brain age estimation remains a challenging task. Methods: In this study, we developed an innovative data fusion technique employing a low-rank tensor fusion algorithm, tailored specifically for deep learning-based frameworks aimed at brain age estimation. Specifically, we utilized structural magnetic resonance imaging (sMRI), diffusion tensor imaging (DTI), and magnetoencephalography (MEG) to extract spatial-temporal brain features with different properties. These features were fused using the low-rank tensor algorithm and employed as predictors for estimating brain age. Results: Our prediction model achieved a desirable prediction accuracy on the independent test samples, demonstrating its robust performance. Conclusions: The results of our study suggest that the low-rank tensor fusion algorithm has the potential to effectively integrate multimodal data into deep learning frameworks for estimating brain age.

Signed Curvature Graph Representation Learning of Brain Networks for Brain Age Estimation

Graph Neural Networks (GNNs) play a pivotal role in learning representations of brain networks for estimating brain age. However, the over-squashing impedes interactions between long-range nodes, hindering the ability of message-passing mechanism-based GNNs to learn the topological structure of brain networks. Graph rewiring methods and curvature GNNs have been proposed to alleviate over-squashing. However, most graph rewiring methods overlook node features and curvature GNNs neglect the geometric properties of signed curvature. In this study, a Signed Curvature GNN (SCGNN) was proposed to rewire the graph based on node features and curvature, and learn the representation of signed curvature. First, a Mutual Information Ollivier-Ricci Flow (MORF) was proposed to add connections in the neighborhood of edge with the minimal negative curvature based on the maximum mutual information between node features, improving the efficiency of information interaction between nodes. Then, a Signed Curvature Convolution (SCC) was proposed to aggregate node features based on positive and negative curvature, facilitating the model's ability to capture the complex topological structures of brain networks. Additionally, an Ollivier-Ricci Gradient Pooling (ORG-Pooling) was proposed to select the key nodes and topology structures by curvature gradient and attention mechanism, accurately obtaining the global representation for brain age estimation. Experiments conducted on six public datasets with structural magnetic resonance imaging (sMRI), spanning ages from 18 to 91 years, validate that our method achieves promising performance compared with existing methods. Furthermore, we employed the gaps between brain age and chronological age for identifying Alzheimer's Disease (AD), yielding the best classification performance.

Medical Transformer: Universal Encoder for 3-D Brain MRI Analysis

Transfer learning has attracted considerable attention in medical image analysis because of the limited number of annotated 3-D medical datasets available for training data-driven deep learning models in the real world. We propose Medical Transformer, a novel transfer learning framework that effectively models 3-D volumetric images as a sequence of 2-D image slices. To improve the high-level representation in 3-D-form empowering spatial relations, we use a multiview approach that leverages information from three planes of the 3-D volume, while providing parameter-efficient training. For building a source model generally applicable to various tasks, we pretrain the model using self-supervised learning (SSL) for masked encoding vector prediction as a proxy task, using a large-scale normal, healthy brain magnetic resonance imaging (MRI) dataset. Our pretrained model is evaluated on three downstream tasks: 1) brain disease diagnosis; 2) brain age prediction; and 3) brain tumor segmentation, which are widely studied in brain MRI research. Experimental results demonstrate that our Medical Transformer outperforms the state-of-the-art (SOTA) transfer learning methods, efficiently reducing the number of parameters by up to approximately 92% for classification and regression tasks and 97% for segmentation task, and it also achieves good performance in scenarios where only partial training samples are used.

Disentangling Neurodegeneration From Aging in Multiple Sclerosis Using Deep Learning: The Brain-Predicted Disease Duration Gap

BACKGROUND AND OBJECTIVES

Disentangling brain aging from disease-related neurodegeneration in patients with multiple sclerosis (PwMS) is increasingly topical. The brain-age paradigm offers a window into this problem but may miss disease-specific effects. In this study, we investigated whether a disease-specific model might complement the brain-age gap (BAG) by capturing aspects unique to MS.

METHODS

In this retrospective study, we collected 3D T1-weighted brain MRI scans of PwMS to build (1) a cross-sectional multicentric cohort for age and disease duration (DD) modeling and (2) a longitudinal single-center cohort of patients with early MS as a clinical use case. We trained and evaluated a 3D DenseNet architecture to predict DD from minimally preprocessed images while age predictions were obtained with the DeepBrainNet model. The brain-predicted DD gap (the difference between predicted and actual duration) was proposed as a DD-adjusted global measure of MS-specific brain damage. Model predictions were scrutinized to assess the influence of lesions and brain volumes while the DD gap was biologically and clinically validated within a linear model framework assessing its relationship with BAG and physical disability measured with the Expanded Disability Status Scale (EDSS).

RESULTS

We gathered MRI scans of 4,392 PwMS (69.7% female, age: 42.8 ± 10.6 years, DD: 11.4 ± 9.3 years) from 15 centers while the early MS cohort included 749 sessions from 252 patients (64.7% female, age: 34.5 ± 8.3 years, DD: 0.7 ± 1.2 years). Our model predicted DD better than chance (mean absolute error = 5.63 years, R2 = 0.34) and was nearly orthogonal to the brain-age model (correlation between DD and BAGs: r = 0.06 [0.00-0.13], p = 0.07). Predictions were influenced by distributed variations in brain volume and, unlike brain-predicted age, were sensitive to MS lesions (difference between unfilled and filled scans: 0.55 years [0.51-0.59], p < 0.001). DD gap significantly explained EDSS changes (B = 0.060 [0.038-0.082], p < 0.001), adding to BAG (ΔR2 = 0.012, p < 0.001). Longitudinally, increasing DD gap was associated with greater annualized EDSS change (r = 0.50 [0.39-0.60], p < 0.001), with an incremental contribution in explaining disability worsening compared with changes in BAG alone (ΔR2 = 0.064, p < 0.001).

DISCUSSION

The brain-predicted DD gap is sensitive to MS-related lesions and brain atrophy, adds to the brain-age paradigm in explaining physical disability both cross-sectionally and longitudinally, and may be used as an MS-specific biomarker of disease severity and progression.

Estimated Brain Age in Healthy Aging and Across Multiple Neurological Disorders

BACKGROUND

The brain aging in the general population and patients with neurological disorders is not well understood.

PURPOSE

To characterize brain aging in the above conditions and its clinical relevance.

STUDY TYPE

Retrospective.

POPULATION

A total of 2913 healthy controls (HC), with 1395 females; 331 multiple sclerosis (MS); 189 neuromyelitis optica spectrum disorder (NMOSD); 239 Alzheimer's disease (AD); 244 Parkinson's disease (PD); and 338 cerebral small vessel disease (cSVD).

FIELD STRENGTH/SEQUENCE

3.0 T/Three-dimensional (3D) T1-weighted images.

ASSESSMENT

The brain age was estimated by our previously developed model, using a 3D convolutional neural network trained on 9794 3D T1-weighted images of healthy individuals. Brain age gap (BAG), the difference between chronological age and estimated brain age, was calculated to represent accelerated and resilient brain conditions. We compared MRI metrics between individuals with accelerated (BAG ≥ 5 years) and resilient brain age (BAG ≤ -5 years) in HC, and correlated BAG with MRI metrics, and cognitive and physical measures across neurological disorders.

STATISTICAL TESTS

Student's t test, Wilcoxon test, chi-square test or Fisher's exact test, and correlation analysis. P < 0.05 was considered statistically significant.

RESULTS

In HC, individuals with accelerated brain age exhibited significantly higher white matter hyperintensity (WMH) and lower regional brain volumes than those with resilient brain age. BAG was significantly higher in MS (10.30 ± 12.6 years), NMOSD (2.96 ± 7.8 years), AD (6.50 ± 6.6 years), PD (4.24 ± 4.8 years), and cSVD (3.24 ± 5.9 years) compared to HC. Increased BAG was significantly associated with regional brain atrophy, WMH burden, and cognitive impairment across neurological disorders. Increased BAG was significantly correlated with physical disability in MS (r = 0.17).

DATA CONCLUSION

Healthy individuals with accelerated brain age show high WMH burden and regional volume reduction. Neurological disorders exhibit distinct accelerated brain aging, correlated with impaired cognitive and physical function.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: Stage 2.

MRI-based whole-brain elastography and volumetric measurements to predict brain age

Brain age, as a correlate of an individual's chronological age obtained from structural and functional neuroimaging data, enables assessing developmental or neurodegenerative pathology relative to the overall population. Accurately inferring brain age from brain magnetic resonance imaging (MRI) data requires imaging methods sensitive to tissue health and sophisticated statistical models to identify the underlying age-related brain changes. Magnetic resonance elastography (MRE) is a specialized MRI technique which has emerged as a reliable, non-invasive method to measure the brain's mechanical properties, such as the viscoelastic shear stiffness and damping ratio. These mechanical properties have been shown to change across the life span, reflect neurodegenerative diseases, and are associated with individual differences in cognitive function. Here, we aim to develop a machine learning framework to accurately predict a healthy individual's chronological age from maps of brain mechanical properties. This framework can later be applied to understand neurostructural deviations from normal in individuals with neurodevelopmental or neurodegenerative conditions. Using 3D convolutional networks as deep learning models and more traditional statistical models, we relate chronological age as a function of multiple modalities of whole-brain measurements: stiffness, damping ratio, and volume. Evaluations on held-out subjects show that combining stiffness and volume in a multimodal approach achieves the most accurate predictions. Interpretation of the different models highlights important regions that are distinct between the modalities. The results demonstrate the complementary value of MRE measurements in brain age models, which, in future studies, could improve model sensitivity to brain integrity differences in individuals with neuropathology.

Adolescent brain maturation associated with environmental factors: a multivariate analysis

Human adolescence marks a crucial phase of extensive brain development, highly susceptible to environmental influences. Employing brain age estimation to assess individual brain aging, we categorized individuals (N = 7,435, aged 9-10 years old) from the Adolescent Brain and Cognitive Development (ABCD) cohort into groups exhibiting either accelerated or delayed brain maturation, where the accelerated group also displayed increased cognitive performance compared to their delayed counterparts. A 4-way multi-set canonical correlation analysis integrating three modalities of brain metrics (gray matter density, brain morphological measures, and functional network connectivity) with nine environmental factors unveiled a significant 4-way canonical correlation between linked patterns of neural features, air pollution, area crime, and population density. Correlations among the three brain modalities were notably strong (ranging from 0.65 to 0.77), linking reduced gray matter density in the middle temporal gyrus and precuneus to decreased volumes in the left medial orbitofrontal cortex paired with increased cortical thickness in the right supramarginal and bilateral occipital regions, as well as increased functional connectivity in occipital sub-regions. These specific brain characteristics were significantly more pronounced in the accelerated brain aging group compared to the delayed group. Additionally, these brain regions exhibited significant associations with air pollution, area crime, and population density, where lower air pollution and higher area crime and population density were correlated to brain variations more prominently in the accelerated brain aging group.

Evaluation of Brain Age as a Specific Marker of Brain Health

Brain age is a powerful marker of general brain health. Furthermore, brain age models are trained on large datasets, thus giving them a potential advantage in predicting specific outcomes - much like the success of finetuning large language models for specific applications. However, it is also well-accepted in machine learning that models trained to directly predict specific outcomes (i.e., direct models) often perform better than those trained on surrogate outcomes. Therefore, despite their much larger training data, it is unclear whether brain age models outperform direct models in predicting specific brain health outcomes. Here, we compare large-scale brain age models and direct models for predicting specific health outcomes in the context of Alzheimer's Disease (AD) dementia. Using anatomical T1 scans from three continents (N = 1,848), we find that direct models outperform brain age models without finetuning. Finetuned brain age models yielded similar performance as direct models, but importantly, did not outperform direct models although the brain age models were pretrained on 1000 times more data than the direct models: N = 53,542 vs N = 50. Overall, our results do not discount brain age as a useful marker of general brain health. However, in this era of large-scale brain age models, our results suggest that small-scale, targeted approaches for extracting specific brain health markers still hold significant value.

Sex differences in brain MRI using deep learning toward fairer healthcare outcomes

This study leverages deep learning to analyze sex differences in brain MRI data, aiming to further advance fairness in medical imaging. We employed 3D T1-weighted Magnetic Resonance images from four diverse datasets: Calgary-Campinas-359, OASIS-3, Alzheimer's Disease Neuroimaging Initiative, and Cambridge Center for Aging and Neuroscience, ensuring a balanced representation of sexes and a broad demographic scope. Our methodology focused on minimal preprocessing to preserve the integrity of brain structures, utilizing a Convolutional Neural Network model for sex classification. The model achieved an accuracy of 87% on the test set without employing total intracranial volume (TIV) adjustment techniques. We observed that while the model exhibited biases at extreme brain sizes, it performed with less bias when the TIV distributions overlapped more. Saliency maps were used to identify brain regions significant in sex differentiation, revealing that certain supratentorial and infratentorial regions were important for predictions. Furthermore, our interdisciplinary team, comprising machine learning specialists and a radiologist, ensured diverse perspectives in validating the results. The detailed investigation of sex differences in brain MRI in this study, highlighted by the sex differences map, offers valuable insights into sex-specific aspects of medical imaging and could aid in developing sex-based bias mitigation strategies, contributing to the future development of fair AI algorithms. Awareness of the brain's differences between sexes enables more equitable AI predictions, promoting fairness in healthcare outcomes. Our code and saliency maps are available at https://github.com/mahsadibaji/sex-differences-brain-dl.

Exploring the relationship among Alzheimer's disease, aging and cognitive scores through neuroimaging-based approach

Alzheimer's disease (AD) is a fatal neurodegenerative disorder, with the Mini-Mental State Examination (MMSE) and Clinical Dementia Rating (CDR) serving significant roles in monitoring its progression. We hypothesize that while cognitive assessment scores can detect AD-related brain changes, the targeted brain regions may differ. Additionally, given AD's strong association with aging, we propose that specific brain regions are influenced by both AD pathology and aging, exhibiting strong correlations with both. To test these hypotheses, we developed a 3D convolutional network with a mixed-attention mechanism to recognize AD subjects from structural magnetic resonance imaging (sMRI) data and utilize 3D convolutional methods to pinpoint brain regions significantly correlated with the AD, MMSE, CDR and age. All models were trained and internally validated on 417 samples from the Alzheimer's Disease Neuroimaging Initiative (ADNI), and the classification model was externally validated on 382 samples from the Australian Imaging and Lifestyle flagship (AIBL). This approach provided robust support for using MMSE and CDR in assessing AD progression and visually illustrated the relationship between aging and AD. The analysis revealed correlations among the four identification tasks (AD, MMSE, CDR and age) and highlighted asymmetric brain lesions in both AD and aging. Notably, we found that AD can accelerate aging to some extent, and a significant correlation exists between the rate of aging and cognitive assessment scores. This offers new insights into the relationship between AD and aging.

Fusing multi-scale functional connectivity patterns via Multi-Branch Vision Transformer (MB-ViT) for macaque brain age prediction

Brain age (BA) is defined as a measure of brain maturity and could help characterize both the typical brain development and neuropsychiatric disorders in mammals. Various biological phenotypes have been successfully applied to predict BA of human using chronological age (CA) as label. However, whether the BA of macaque, one of the most important animal models, can also be reliably predicted is largely unknown. To address this question, we propose a novel deep learning model called Multi-Branch Vision Transformer (MB-ViT) to fuse multi-scale (i.e., from coarse-grained to fine-grained) brain functional connectivity (FC) patterns derived from resting state functional magnetic resonance imaging (rs-fMRI) data to predict BA of macaques. The discriminative functional connections and the related brain regions contributing to the prediction are further identified based on Gradient-weighted Class Activation Mapping (Grad-CAM) method. Our proposed model successfully predicts BA of 450 normal rhesus macaques from the publicly available PRIMatE Data Exchange (PRIME-DE) dataset with lower mean absolute error (MAE) and mean square error (MSE) as well as higher Pearson's correlation coefficient (PCC) and coefficient of determination (R2) compared to other baseline models. The correlation between the predicted BA and CA reaches as high as 0.82 of our proposed method. Furthermore, our analysis reveals that the functional connections predominantly contributing to the prediction results are situated in the primary motor cortex (M1), visual cortex, area v23 in the posterior cingulate cortex, and dysgranular temporal pole. In summary, our proposed deep learning model provides an effective tool to accurately predict BA of primates (macaque in this study), and lays a solid foundation for future studies of age-related brain diseases in those animal models.

A minimalistic approach to classifying Alzheimer's disease using simple and extremely small convolutional neural networks

BACKGROUND

There is a broad interest in deploying deep learning-based classification algorithms to identify individuals with Alzheimer's disease (AD) from healthy controls (HC) based on neuroimaging data, such as T1-weighted Magnetic Resonance Imaging (MRI). The goal of the current study is to investigate whether modern, flexible architectures such as EfficientNet provide any performance boost over more standard architectures.

METHODS

MRI data was sourced from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and processed with a minimal preprocessing pipeline. Among the various architectures tested, the minimal 3D convolutional neural network SFCN stood out, composed solely of 3x3x3 convolution, batch normalization, ReLU, and max-pooling. We also examined the influence of scale on performance, testing SFCN versions with trainable parameters ranging from 720 up to 2.9 million.

RESULTS

SFCN achieves a test ROC AUC of 96.0% while EfficientNet got an ROC AUC of 94.9 %. SFCN retained high performance down to 720 trainable parameters, achieving an ROC AUC of 91.4%.

COMPARISON WITH EXISTING METHODS

The SFCN is compared to DenseNet and EfficientNet as well as the results of other publications in the field.

CONCLUSIONS

The results indicate that using the minimal 3D convolutional neural network SFCN with a minimal preprocessing pipeline can achieve competitive performance in AD classification, challenging the necessity of employing more complex architectures with a larger number of parameters. This finding supports the efficiency of simpler deep learning models for neuroimaging-based AD diagnosis, potentially aiding in better understanding and diagnosing Alzheimer's disease.

Anatomic Interpretability in Neuroimage Deep Learning: Saliency Approaches for Typical Aging and Traumatic Brain Injury

The black box nature of deep neural networks (DNNs) makes researchers and clinicians hesitant to rely on their findings. Saliency maps can enhance DNN explainability by suggesting the anatomic localization of relevant brain features. This study compares seven popular attribution-based saliency approaches to assign neuroanatomic interpretability to DNNs that estimate biological brain age (BA) from magnetic resonance imaging (MRI). Cognitively normal (CN) adults ( N = 13,394 , 5,900 males; mean age: 65.82 ± 8.89 years) are included for DNN training, testing, validation, and saliency map generation to estimate BA. To study saliency robustness to the presence of anatomic deviations from normality, saliency maps are also generated for adults with mild traumatic brain injury (mTBI, N = 214 , 135 males; mean age: 55.3 ± 9.9 years). We assess saliency methods' capacities to capture known anatomic features of brain aging and compare them to a surrogate ground truth whose anatomic saliency is known a priori. Anatomic aging features are identified most reliably by the integrated gradients method, which outperforms all others through its ability to localize relevant anatomic features. Gradient Shapley additive explanations, input × gradient, and masked gradient perform less consistently but still highlight ubiquitous neuroanatomic features of aging (ventricle dilation, hippocampal atrophy, sulcal widening). Saliency methods involving gradient saliency, guided backpropagation, and guided gradient-weight class attribution mapping localize saliency outside the brain, which is undesirable. Our research suggests the relative tradeoffs of saliency methods to interpret DNN findings during BA estimation in typical aging and after mTBI.

Analysis and visualization of the effect of multiple sclerosis on biological brain age

Introduction

The rate of neurodegeneration in multiple sclerosis (MS) is an important biomarker for disease progression but can be challenging to quantify. The brain age gap, which quantifies the difference between a patient's chronological and their estimated biological brain age, might be a valuable biomarker of neurodegeneration in patients with MS. Thus, the aim of this study was to investigate the value of an image-based prediction of the brain age gap using a deep learning model and compare brain age gap values between healthy individuals and patients with MS.

Methods

A multi-center dataset consisting of 5,294 T1-weighted magnetic resonance images of the brain from healthy individuals aged between 19 and 89 years was used to train a convolutional neural network (CNN) for biological brain age prediction. The trained model was then used to calculate the brain age gap in 195 patients with relapsing remitting MS (20-60 years). Additionally, saliency maps were generated for healthy subjects and patients with MS to identify brain regions that were deemed important for the brain age prediction task by the CNN.

Results

Overall, the application of the CNN revealed accelerated brain aging with a larger brain age gap for patients with MS with a mean of 6.98 ± 7.18 years in comparison to healthy test set subjects (0.23 ± 4.64 years). The brain age gap for MS patients was weakly to moderately correlated with age at disease onset (ρ = -0.299, p < 0.0001), EDSS score (ρ = 0.206, p = 0.004), disease duration (ρ = 0.162, p = 0.024), lesion volume (ρ = 0.630, p < 0.0001), and brain parenchymal fraction (ρ = -0.718, p < 0.0001). The saliency maps indicated significant differences in the lateral ventricle (p < 0.0001), insula (p < 0.0001), third ventricle (p < 0.0001), and fourth ventricle (p = 0.0001) in the right hemisphere. In the left hemisphere, the inferior lateral ventricle (p < 0.0001) and the third ventricle (p < 0.0001) showed significant differences. Furthermore, the Dice similarity coefficient showed the highest overlap of salient regions between the MS patients and the oldest healthy subjects, indicating that neurodegeneration is accelerated in this patient cohort.

Discussion

In conclusion, the results of this study show that the brain age gap is a valuable surrogate biomarker to measure disease progression in patients with multiple sclerosis.

Adding the third dimension: 3D convolutional neural network diagnosis of temporal lobe epilepsy

Convolutional neural networks (CNN) show great promise for translating decades of research on structural abnormalities in temporal lobe epilepsy into clinical practice. Three-dimensional CNNs typically outperform two-dimensional CNNs in medical imaging. Here we explore for the first time whether a three-dimensional CNN outperforms a two-dimensional CNN for identifying temporal lobe epilepsy-specific features on MRI. Using 1178 T1-weighted images (589 temporal lobe epilepsy, 589 healthy controls) from 12 surgical centres, we trained 3D and 2D CNNs for temporal lobe epilepsy versus healthy control classification, using feature visualization to identify important regions. The 3D CNN was compared to the 2D model and to a randomized model (comparison to chance). Further, we explored the effect of sample size with subsampling, examined model performance based on single-subject clinical characteristics, and tested the impact of image harmonization on model performance. Across 50 datapoints (10 runs with 5-folds each) the 3D CNN median accuracy was 86.4% (35.3% above chance) and the median F1-score was 86.1% (33.3% above chance). The 3D model yielded higher accuracy compared to the 2D model on 84% of datapoints (median 2D accuracy, 83.0%), a significant outperformance for the 3D model (binomial test: P < 0.001). This advantage of the 3D model was only apparent at the highest sample size. Saliency maps exhibited the importance of medial-ventral temporal, cerebellar, and midline subcortical regions across both models for classification. However, the 3D model had higher salience in the most important regions, the ventral-medial temporal and midline subcortical regions. Importantly, the model achieved high accuracy (82% accuracy) even in patients without MRI-identifiable hippocampal sclerosis. Finally, applying ComBat for harmonization did not improve performance. These findings highlight the value of 3D CNNs for identifying subtle structural abnormalities on MRI, especially in patients without clinically identified temporal lobe epilepsy lesions. Our findings also reveal that the advantage of 3D CNNs relies on large sample sizes for model training.

A perspective on brain-age estimation and its clinical promise

Brain-age estimation has gained increased attention in the neuroscientific community owing to its potential use as a biomarker of brain health. The difference between estimated and chronological age based on neuroimaging data enables a unique perspective on brain development and aging, with multiple open questions still remaining in the brain-age research field. This Perspective presents an overview of current advancements in the field and envisions the future evolution of the brain-age framework before its potential deployment in hospital settings.

[18F]FDG PET integrated with structural MRI for accurate brain age prediction

PURPOSE

Brain aging is a complex and heterogeneous process characterized by both structural and functional decline. This study aimed to establish a novel deep learning (DL) method for predicting brain age by utilizing structural and metabolic imaging data.

METHODS

The dataset comprised participants from both the Universal Medical Imaging Diagnostic Center (UMIDC) and the Alzheimer's Disease Neuroimaging Initiative (ADNI). The former recruited 395 normal control (NC) subjects, while the latter included 438 NC subjects, 51 mild cognitive impairment (MCI) subjects, and 56 Alzheimer's disease (AD) subjects. We developed a novel dual-pathway, 3D simple fully convolutional network (Dual-SFCNeXt) to estimate brain age using [18F]fluorodeoxyglucose positron emission tomography ([18F]FDG PET) and structural magnetic resonance imaging (sMRI) images of NC subjects as input. Several prevailing DL models were trained and tested using either MRI or PET data for comparison. Model accuracies were evaluated using mean absolute error (MAE) and Pearson's correlation coefficient (r). Brain age gap (BAG), deviations of brain age from chronologic age, was correlated with cognitive assessments in MCI and AD subjects.

RESULTS

Both PET- and MRI-based models achieved high prediction accuracy. The leading model was the SFCNeXt (the single-pathway version) for PET (MAE = 2.92, r = 0.96) and MRI (MAE = 3.23, r = 0.95) on all samples. By integrating both PET and MRI images, the Dual-SFCNeXt demonstrated significantly improved accuracy (MAE = 2.37, r = 0.97) compared to all single-modality models. Significantly higher BAG was observed in both the AD (P < 0.0001) and MCI (P < 0.0001) groups compared to the NC group. BAG correlated significantly with Mini-Mental State Examination (MMSE) scores (r=-0.390 for AD, r=-0.436 for MCI) and the Clinical Dementia Rating Scale Sum of Boxes (CDR-SB) scores (r = 0.333 for AD, r = 0.372 for MCI).

CONCLUSION

The integration of [18F]FDG PET with structural MRI enhances the accuracy of brain age prediction, potentially introducing a new avenue for related multimodal brain age prediction studies.

Brain age prediction via cross-stratified ensemble learning

As an important biomarker of neural aging, the brain age reflects the integrity and health of the human brain. Accurate prediction of brain age could help to understand the underlying mechanism of neural aging. In this study, a cross-stratified ensemble learning algorithm with staking strategy was proposed to obtain brain age and the derived predicted age difference (PAD) using T1-weighted magnetic resonance imaging (MRI) data. The approach was characterized as by implementing two modules: one was three base learners of 3D-DenseNet, 3D-ResNeXt, 3D-Inception-v4; another was 14 secondary learners of liner regressions. To evaluate performance, our method was compared with single base learners, regular ensemble learning algorithms, and state-of-the-art (SOTA) methods. The results demonstrated that our proposed model outperformed others models, with three metrics of mean absolute error (MAE), root mean-squared error (RMSE), and coefficient of determination (R2) of 2.9405 years, 3.9458 years, and 0.9597, respectively. Furthermore, there existed significant differences in PAD among the three groups of normal control (NC), mild cognitive impairment (MCI) and Alzheimer's disease (AD), with an increased trend across NC, MCI, and AD. It was concluded that the proposed algorithm could be effectively used in computing brain aging and PAD, and offering potential for early diagnosis and assessment of normal brain aging and AD.