Brain structure ages—A new biomarker for multi‐disease classification

Human Brain Mapping, Journal Year: 2024, Volume and Issue: 45(1)

Published: Jan. 1, 2024

Age is an important variable to describe the expected brain's anatomy status across normal aging trajectory. The deviation from that normative trajectory may provide some insights into neurological diseases. In neuroimaging, predicted brain age widely used analyze different However, using only gap information (i.e., difference between chronological and estimated age) can be not enough informative for disease classification problems. this paper, we propose extend notion of global by estimating structure ages structural magnetic resonance imaging. To end, ensemble deep learning models first estimate a 3D map voxel-wise estimation). Then, segmentation mask obtain final ages. This biomarker in several situations. First, it enables accurately purpose anomaly detection at population level. situation, our approach outperforms state-of-the-art methods. Second, compute process each structure. feature multi-disease task accurate differential diagnosis subject Finally, deviations individuals visualized, providing about abnormality helping clinicians real medical contexts.

Language: Английский

---

AgeNet-SHAP: An explainable AI approach for optimally mapping multivariate regional brain age and clinical severity patterns in Alzheimer disease

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: March 4, 2025

Age is a significant risk factor for mild cognitive impairment (MCI) and Alzheimer's disease (AD) identifying brain age patterns critical comprehending the normal aging MCI/AD processes. Prior studies have widely established univariate relationships between regions age, while multivariate associations remain largely unexplored. Herein, various artificial intelligence (AI) models were employed to perform prediction using an MRI dataset (n=668). Then optimal AI model was integrated with Shapley additive explanations (SHAP) feature importance technique identify involved in this prediction. Our results indicated that deep learning (referred as AgeNet) tremendously outperformed conventional machine prediction, AgeNet SHAP AgeNet-SHAP) identified all ground-truth perturbed key predictors of semi-simulation, proved validity our methodology. In experimental dataset, compared cognitively (CN) participants, MCI exhibited moderate differences regions, whereas AD had highly robust distributed regional differences. The individualized AgeNet-SHAP features further showed clinical severity scores continuum. These collectively facilitate data-driven predictive modelling approaches progression, diagnostics, prognostics, personalized medicine efforts.

Language: Английский

---

Association of Psychological Resilience with Decelerated Brain Aging in Cognitively Healthy World Trade Center Responders

Biological Psychiatry Global Open Science, Journal Year: 2025, Volume and Issue: unknown, P. 100489 - 100489

Published: March 1, 2025

Language: Английский

---

Novel brain biomarkers of obesity in young adult women based on statistical measurements of white matter tracts

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(4), P. e0319936 - e0319936

Published: April 10, 2025

Objective Novel brain biomarkers of obesity were sought by studying statistical measurements on fractional anisotropy (FA) images different white matter (WM) tracts from young adult women. Methods Tract chosen that showed differences between two groups (normal weight and overweight/obese) correlated with BMI. From these measurements, a simple novel process was applied to select those would allow the creation models quantify classify state individuals. The created tract used in models. Results Positive correlations found WM integrity BMI, mainly involved motor functions. results, built status, whose regression coefficients formed proposed associated biomarkers. Conclusion A for selection proposed, such determine status subjects individually. models, created. These results generate new knowledge field, intended be future clinical environment as prevention treatment tool changes obesity. Significance After women, opposed some previous reported literature. consisted positive also precise quantification classification status. All this allows generation its probable subsequent application.

Language: Английский

---

Brain Age Prediction in Type II GM1 Gangliosidosis

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: April 25, 2025

GM1 gangliosidosis is an inherited, progressive, and fatal neurodegenerative lysosomal storage disorder with no approved treatment. We calculated a predicted brain ages Brain Structures Age Gap Estimation (BSAGE) for 81 MRI scans from 41 Type II patients 897 556 neurotypical controls (NC) utilizing BrainStructuresAges , machine learning analysis pipeline. NC showed whole aging at rate of 0.83 per chronological year compared 1.57 in juvenile 12.25 late-infantile patients, accurately reflecting the clinical trajectories two disease subtypes. Accelerated distinct was also observed throughout midbrain structures including thalamus caudate nucleus, hindbrain cerebellum brainstem, ventricles to NC. Predicted age BSAGE both correlated cross-sectional longitudinal assessments, indicating their importance as surrogate neuroimaging outcome measures trials gangliosidosis.

Language: Английский

---

Pathological Aging of Patients With Amyotrophic Lateral Sclerosis: A Preliminary Longitudinal Study

Brain and Behavior, Journal Year: 2025, Volume and Issue: 15(5)

Published: May 1, 2025

ABSTRACT Objective This longitudinal study investigated pathological brain aging in amyotrophic lateral sclerosis (ALS) by evaluating disparities between chronological age and deep learning‐derived structure (BSA) exploring associations with cognitive functional decline. Methods Ten limb‐onset ALS patients (seven males) 10 demographically matched healthy controls (HCs) underwent structural magnetic resonance imaging (sMRI) assessments at baseline follow‐up. The BSA was estimated using the validated volBrain platform. Cognitive domains (language, verbal fluency, executive function, memory, visuospatial skills) global cognition (Persian adaptive Edinburgh Behavioral Screen [ECAS] total score) were assessed along status (ALSFRS‐R). Results exhibited significant BSA‐chronological (Δ = +7.31 years, p 0.009) follow‐up +8.39 0.003), accelerated progression over time ( 0.004). HCs showed no such 0.931). Longitudinal increases correlated function decline r −0.651, 0.042). Higher education predicted preserved language 0.831, 0.003) fluency 0.738, 0.015). ALSFRS‐R paralleled 0.642, 0.045) deterioration 0.667, 0.035). Conclusions is characterized that progresses independently of dysfunction. Education may mitigate decline, while motor aligns impairments. has emerged as a potential biomarker for tracking trajectories ALS, warranting validation larger cohorts.

Language: Английский

---

Clinical applications of deep learning in neuroinflammatory diseases: A scoping review

Revue Neurologique, Journal Year: 2024, Volume and Issue: unknown

Published: May 1, 2024

Deep learning (DL) is an artificial intelligence technology that has aroused much excitement for predictive medicine due to its ability process raw data modalities such as images, text, and time series of signals. Here, we intend give the clinical reader elements understand this technology, taking neuroinflammatory diseases illustrative use case translation efforts. We reviewed scope rapidly evolving field get quantitative insights about which applications concentrate efforts are most commonly used. queried PubMed database articles reporting DL algorithms in radiology.healthairegister.com website commercial algorithms. The review included 148 published between 2018 2024 five could be grouped computer-aided diagnosis, individual prognosis, functional assessment, segmentation radiological structures, optimization acquisition. Our highlighted important discrepancies structures diagnosis currently with overrepresentation imaging. Various model architectures have addressed different applications, relatively low volume data, diverse modalities. report high-level technical characteristics synthesize narratively applications. Predictive performances some common a priori on topic finally discussed. reported position information processing enhancing existing paraclinical investigations bringing perspectives make innovative ones actionable healthcare.

Language: Английский

---

Beyond Accuracy: Refining Brain-Age Models for Enhanced Disease Detection

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: March 29, 2024

Abstract This study critically reevaluates the utility of brain-age models within context detecting neurological and psychiatric disorders, challenging conventional emphasis on maximizing chronological age prediction accuracy. Our analysis T1 MRI data from 46,381 UK Biobank participants reveals a paradox: simpler machine learning models, notably those with excessive regularization, demonstrate superior sensitivity to disease-relevant changes compared their more complex counterparts. counterintuitive discovery suggests that traditionally deemed less accurate in predicting might, fact, offer meaningful biomarker for brain health by capturing variations pertinent disease states. findings challenge traditional understanding as normative modeling, emphasizing inadvertent identification non-normative pathological markers over precise prediction.

Language: Английский

---

Rate of abnormalities in quantitative MR neuroimaging of persons with chronic traumatic brain injury

BMC Neurology, Journal Year: 2024, Volume and Issue: 24(1)

Published: July 5, 2024

Mild traumatic brain injury (mTBI) can result in lasting damage that is often too subtle to detect by qualitative visual inspection on conventional MR imaging. Although a number of FDA-cleared neuroimaging tools have demonstrated changes associated with mTBI, they are still under-utilized clinical practice.

Language: Английский

---

Feature attention graph neural network for estimating brain age and identifying important neural connections in mouse models of genetic risk for Alzheimer’s disease

Imaging Neuroscience, Journal Year: 2024, Volume and Issue: 2, P. 1 - 22

Published: Jan. 1, 2024

Abstract Alzheimer’s disease (AD), a widely studied neurodegenerative disorder, poses significant research challenges due to its high prevalence and complex etiology. Age, critical risk factor for AD, is typically assessed by comparing physiological estimated brain ages. This study utilizes mouse models expressing human alleles of APOE nitric oxide synthase 2 (hNOS2), replicating genetic risks AD alongside human-like immune response. We developed multivariate model that incorporates structural connectomes, genotypes, demographic traits (age sex), environmental factors such as diet, behavioral data estimate age. Our methodology employs Feature Attention Graph Neural Network (FAGNN) integrate these diverse datasets. Behavioral are processed using 2D convolutional neural network (CNN), via 1D CNN, connectomes through graph equipped with quadrant attention module accentuates connections. The FAGNN demonstrated mean absolute error in age prediction 31.85 days root squared 41.84 days, significantly outperforming simpler models. analysis further focused on the delta, which assesses accelerated or delayed aging age, predicted FAGNN, chronological A high-fat diet presence NOS2 gene were identified accelerators old group. Key connections those between cingulum, corpus callosum, striatum, hippocampus, thalamus, hypothalamus, cerebellum, piriform cortex, found be process. Validation diffusion MRI-based metrics, including fractional anisotropy return-to-origin probability measures across connections, revealed age-related differences. These findings suggest white matter degradation highlighted plays key role aging. interplay genotype sex, immunity, modulates enhance our understanding

Language: Английский

---