Explore the vast range of titles available.

•A review of the adoption of generative adversarial networks in clinical neuroimaging.•We focus on GAN's applications in modeling disease effects of neurologic diseases.•We discuss the pitfalls of current studies and provide future perspectives. Generative adversarial networks (GANs) are one powerful type of deep learning models that have been successfully utilized in numerous fields. They belong to the broader family of generative methods, which learn to generate realistic data with a probabilistic model by learning distributions from real samples. In the clinical context, GANs have shown enhanced capabilities in capturing spatially complex, nonlinear, and potentially subtle disease effects compared to traditional generative methods. This review critically appraises the existing literature on the applications of GANs in imaging studies of various neurological conditions, including Alzheimer's disease, brain tumors, brain aging, and multiple sclerosis. We provide an intuitive explanation of various GAN methods for each application and further discuss the main challenges, open questions, and promising future directions of leveraging GANs in neuroimaging. We aim to bridge the gap between advanced deep learning methods and neurology research by highlighting how GANs can be leveraged to support clinical decision making and contribute to a better understanding of the structural and functional patterns of brain diseases. [Display omitted]

An interpretable machine learning (ML) framework is introduced to enhance the diagnosis of Mild Cognitive Impairment (MCI) and Alzheimer’s disease (AD) by ensuring robustness of the ML models’ interpretations. The dataset used comprises volumetric measurements from brain MRI and genetic data from healthy individuals and patients with MCI/AD, obtained through the Alzheimer’s Disease Neuroimaging Initiative. The existing class imbalance is addressed by an ensemble learning approach, while various attribution-based and counterfactual-based interpretability methods are leveraged towards producing diverse explanations related to the pathophysiology of MCI/AD. A unification method combining SHAP with counterfactual explanations assesses the interpretability techniques’ robustness. The best performing model yielded 87.5% balanced accuracy and 90.8% F1-score. The attribution-based interpretability methods highlighted significant volumetric and genetic features related to MCI/AD risk. The unification method provided useful insights regarding those features’ necessity and sufficiency, further showcasing their significance in MCI/AD diagnosis.

The complex biological mechanisms underlying human brain aging remain incompletely understood. This study investigated the genetic architecture of three brain age gaps (BAG) derived from gray matter volume (GM-BAG), white matter microstructure (WM-BAG), and functional connectivity (FC-BAG). We identified sixteen genomic loci that reached genome-wide significance (P-value < 5×10 −8 ). A gene-drug-disease network highlighted genes linked to GM-BAG for treating neurodegenerative and neuropsychiatric disorders and WM-BAG genes for cancer therapy. GM-BAG displayed the most pronounced heritability enrichment in genetic variants within conserved regions. Oligodendrocytes and astrocytes, but not neurons, exhibited notable heritability enrichment in WM and FC-BAG, respectively. Mendelian randomization identified potential causal effects of several chronic diseases on brain aging, such as type 2 diabetes on GM-BAG and AD on WM-BAG. Our results provide insights into the genetics of human brain aging, with clinical implications for potential lifestyle and therapeutic interventions. All results are publicly available at https://labs.loni.usc.edu/medicine . The biological basis of brain aging is not well understood, but it has implications for human health. Here, the authors explore the genetic basis of human brain aging, finding genetic variants, genes and potential causal relationships with disease.

Background Understanding brain aging heterogeneity is critical for early detection of neurodegeneration related to underlying neuropathologies and effective recruitment for clinical trials. Machine learning techniques have shown potential in this domain but often rely on cross‐sectional data, neglecting dynamic observations of pathological changes. This study applies Coupled Cross‐sectional and Longitudinal Non‐negative Matrix Factorization (CCL‐NMF), a novel framework integrating static and dynamic brain changes, to analyze aging‐related brain atrophy heterogeneity in a large, diverse dataset from 12 neuroimaging studies consolidated by the iSTAGING consortium (Skampardoni et al., 2024). Method CCL‐NMF uses a mutually constrained NMF framework to identify brain aging components, combining population‐level aging effects from cross‐sectional data with individual‐specific dynamics from longitudinal data. Individual expression levels (loadings) for each component are estimated, optimizing the reconstruction of both data types to capture the interplay between static and dynamic aspects of brain alterations. Structural MRI data from 48,949 individuals ≥50 years were analyzed. Comparative analyses were conducted against a weakly‐supervised generative adversarial network model, Surreal‐GAN (Yang et al., 2024), which relies solely on cross‐sectional data. Predictive performance for biomarkers, clinical variables, and disease progression was assessed using regression and Cox proportional hazards models with 5‐fold stratified cross‐validation. To facilitate application to external datasets without retraining or harmonization, out‐of‐sample regression‐based estimation of CCL‐NMF loadings was implemented via NiChart (https://cbica.github.io/NiChart_Project/) with reliability validated through Pearson correlations with original loadings. Result CCL‐NMF identified seven distinct brain atrophy components associated with Alzheimer's disease (AD), cognitive decline, and cardiovascular risk factors. Comparative analyses with the five Surreal‐GAN components revealed consistent representations between the two models, elucidating well‐reproducible brain atrophy components (Figure 1A). Importantly, CCL‐NMF provided a richer representation and demonstrated improved predictive performance across various outcomes, including AD, cardiovascular disease markers, and disease progression (Figure 1B). Furthermore, Spearman correlations between original and approximated CCL‐NMF loadings demonstrated high reliability, enabling seamless out‐of‐sample usage (Figure 2). Conclusion CCL‐NMF offers a robust, interpretable framework for understanding brain aging and neurodegeneration by integrating cross‐sectional and longitudinal data. It outperforms cross‐sectional approaches, delivering richer representations with superior predictive accuracy, and supports easy application to external datasets through regression‐based loadings estimation under a web‐accessible server (neuroimagingchart.com).

Understanding brain aging heterogeneity is critical for early detection of neurodegeneration related to underlying neuropathologies and effective recruitment for clinical trials. Machine learning techniques have shown potential in this domain but often rely on cross-sectional data, neglecting dynamic observations of pathological changes. This study applies Coupled Cross-sectional and Longitudinal Non-negative Matrix Factorization (CCL-NMF), a novel framework integrating static and dynamic brain changes, to analyze aging-related brain atrophy heterogeneity in a large, diverse dataset from 12 neuroimaging studies consolidated by the iSTAGING consortium (Skampardoni et al., 2024). CCL-NMF uses a mutually constrained NMF framework to identify brain aging components, combining population-level aging effects from cross-sectional data with individual-specific dynamics from longitudinal data. Individual expression levels (loadings) for each component are estimated, optimizing the reconstruction of both data types to capture the interplay between static and dynamic aspects of brain alterations. Structural MRI data from 48,949 individuals ≥50 years were analyzed. Comparative analyses were conducted against a weakly-supervised generative adversarial network model, Surreal-GAN (Yang et al., 2024), which relies solely on cross-sectional data. Predictive performance for biomarkers, clinical variables, and disease progression was assessed using regression and Cox proportional hazards models with 5-fold stratified cross-validation. To facilitate application to external datasets without retraining or harmonization, out-of-sample regression-based estimation of CCL-NMF loadings was implemented via NiChart (https://cbica.github.io/NiChart_Project/) with reliability validated through Pearson correlations with original loadings. CCL-NMF identified seven distinct brain atrophy components associated with Alzheimer's disease (AD), cognitive decline, and cardiovascular risk factors. Comparative analyses with the five Surreal-GAN components revealed consistent representations between the two models, elucidating well-reproducible brain atrophy components (Figure 1A). Importantly, CCL-NMF provided a richer representation and demonstrated improved predictive performance across various outcomes, including AD, cardiovascular disease markers, and disease progression (Figure 1B). Furthermore, Spearman correlations between original and approximated CCL-NMF loadings demonstrated high reliability, enabling seamless out-of-sample usage (Figure 2). CCL-NMF offers a robust, interpretable framework for understanding brain aging and neurodegeneration by integrating cross-sectional and longitudinal data. It outperforms cross-sectional approaches, delivering richer representations with superior predictive accuracy, and supports easy application to external datasets through regression-based loadings estimation under a web-accessible server (neuroimagingchart.com).

Machine learning can unravel heterogeneous patterns of brain aging and neurodegeneration, but existing methods offer limited insights into disease progression due to reliance on cross-sectional data. We introduce Coupled Cross-sectional and Longitudinal Non-negative Matrix Factorization (CCL-NMF) to capture dominant brain aging patterns by simultaneously leveraging cross-sectional and longitudinal neuroimaging data. CCL-NMF allows individuals to co-express multiple patterns, capturing mixed neuropathologic processes. Applied to neuroimaging data from 48,949 individuals from the harmonized iSTAGING study, CCL-NMF identifies seven distinct, reproducible, and biologically relevant neuroanatomical patterns. Subject-specific loading coefficients quantifying the individual expression of these patterns show distinct associations with cognition, genetic, and lifestyle factors. To support broader application, a regression-based tool was developed to estimate loadings in external cohorts without rerunning the full framework. By enabling individualized estimation of distinct brain aging patterns, these findings may improve risk assessment and therapeutic evaluation in neurodegenerative diseases. Although demonstrated using structural MRI, this framework is generalizable to other imaging modalities and biomarker types.

Investigating the genetic underpinnings of human aging is essential for unraveling the etiology of and developing actionable therapies for chronic diseases. Here, we characterize the genetic architecture of the biological age gap (BAG; the difference between machine learning-predicted age and chronological age) across nine human organ systems in 377,028 participants of European ancestry from the UK Biobank. The BAGs were computed using cross-validated support vector machines, incorporating imaging, physical traits and physiological measures. We identify 393 genomic loci-BAG pairs (P < 5 × 10 ) linked to the brain, eye, cardiovascular, hepatic, immune, metabolic, musculoskeletal, pulmonary and renal systems. Genetic variants associated with the nine BAGs are predominantly specific to the respective organ system (organ specificity) while exerting pleiotropic links with other organ systems (interorgan cross-talk). We find that genetic correlation between the nine BAGs mirrors their phenotypic correlation. Further, a multiorgan causal network established from two-sample Mendelian randomization and latent causal variance models revealed potential causality between chronic diseases (for example, Alzheimer's disease and diabetes), modifiable lifestyle factors (for example, sleep duration and body weight) and multiple BAGs. Our results illustrate the potential for improving human organ health via a multiorgan network, including lifestyle interventions and drug repurposing strategies.

An interpretable machine learning (ML) framework is introduced to enhance the diagnosis of Mild Cognitive Impairment (MCI) and Alzheimer's disease (AD) by ensuring robustness of the ML models' interpretations. The dataset used comprises volumetric measurements from brain MRI and genetic data from healthy individuals and patients with MCI/AD, obtained through the Alzheimer's Disease Neuroimaging Initiative. The existing class imbalance is addressed by an ensemble learning approach, while various attribution-based and counterfactual-based interpretability methods are leveraged towards producing diverse explanations related to the pathophysiology of MCI/AD. A unification method combining SHAP with counterfactual explanations assesses the interpretability techniques' robustness. The best performing model yielded 87.5% balanced accuracy and 90.8% F1-score. The attribution-based interpretability methods highlighted significant volumetric and genetic features related to MCI/AD risk. The unification method provided useful insights regarding those features' necessity and sufficiency, further showcasing their significance in MCI/AD diagnosis.

Machine learning has been increasingly used to obtain individualized neuroimaging signatures for disease diagnosis, prognosis, and response to treatment in neuropsychiatric and neurodegenerative disorders. Therefore, it has contributed to a better understanding of disease heterogeneity by identifying disease subtypes that present significant differences in various brain phenotypic measures. In this review, we first present a systematic literature overview of studies using machine learning and multimodal MRI to unravel disease heterogeneity in various neuropsychiatric and neurodegenerative disorders, including Alzheimer disease, schizophrenia, major depressive disorder, autism spectrum disorder, multiple sclerosis, as well as their potential in transdiagnostic settings. Subsequently, we summarize relevant machine learning methodologies and discuss an emerging paradigm which we call dimensional neuroimaging endophenotype (DNE). DNE dissects the neurobiological heterogeneity of neuropsychiatric and neurodegenerative disorders into a low dimensional yet informative, quantitative brain phenotypic representation, serving as a robust intermediate phenotype (i.e., endophenotype) largely reflecting underlying genetics and etiology. Finally, we discuss the potential clinical implications of the current findings and envision future research avenues.

An interpretable machine learning (ML) framework is introduced to enhance the diagnosis of Mild Cognitive Impairment (MCI) and Alzheimer's disease (AD) by ensuring robustness of the ML models' interpretations. The dataset used comprises volumetric measurements from brain MRI and genetic data from healthy individuals and patients with MCI/AD, obtained through the Alzheimer's Disease Neuroimaging Initiative. The existing class imbalance is addressed by an ensemble learning approach, while various attribution-based and counterfactual-based interpretability methods are leveraged towards producing diverse explanations related to the pathophysiology of MCI/AD. A unification method combining SHAP with counterfactual explanations assesses the interpretability techniques' robustness. The best performing model yielded 87.5% balanced accuracy and 90.8% F1-score. The attribution-based interpretability methods highlighted significant volumetric and genetic features related to MCI/AD risk. The unification method provided useful insights regarding those features' necessity and sufficiency, further showcasing their significance in MCI/AD diagnosis.