Plasma proteomics identify biomarkers and undulating changes of brain aging

Nature Aging, Год журнала: 2024, Номер unknown

Опубликована: Дек. 9, 2024

Язык: Английский

---

Transformer based multi-modal MRI fusion for prediction of post-menstrual age and neonatal brain development analysis

Medical Image Analysis, Год журнала: 2024, Номер 94, С. 103140 - 103140

Опубликована: Март 7, 2024

Язык: Английский

---

Brain Age Prediction Using Multi-Hop Graph Attention Combined with Convolutional Neural Network

Bioengineering, Год журнала: 2024, Номер 11(3), С. 265 - 265

Опубликована: Март 8, 2024

Convolutional neural networks (CNNs) have been used widely to predict biological brain age based on magnetic resonance (MR) images. However, CNNs focus mainly spatially local features and their aggregates barely the connective information between distant regions. To overcome this issue, we propose a novel multi-hop graph attention (MGA) module that exploits both global connections of image when combined with CNNs. After insertion convolutional layers, MGA first converts convolution-derived feature map into graph-structured data by using patch embedding embedding-distance-based scoring. Multi-hop nodes are modeled Markov chain process. performing attention, re-converts an updated transfers it next layer. We sSE (spatial squeeze excitation)-ResNet18 for our final prediction model (MGA-sSE-ResNet18) performed various hyperparameter evaluations identify optimal parameter combinations. With 2788 three-dimensional T1-weighted MR images healthy subjects, verified effectiveness MGA-sSE-ResNet18 comparisons four established, general-purpose two representative models. The proposed yielded performance mean absolute error 2.822 years Pearson’s correlation coefficient (PCC) 0.968, demonstrating potential improve accuracy prediction.

Язык: Английский

---

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

Briefings in Functional Genomics, Год журнала: 2024, Номер unknown

Опубликована: Окт. 22, 2024

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

Язык: Английский

---

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

Computer Methods and Programs in Biomedicine, Год журнала: 2025, Номер 261, С. 108617 - 108617

Опубликована: Янв. 30, 2025

Язык: Английский

---

Predicting brain age using partition modeling strategy and atlas-based attentional enhancement in the Chinese population

Cerebral Cortex, Год журнала: 2024, Номер 34(2)

Опубликована: Янв. 31, 2024

As a biomarker of human brain health during development, age is estimated based on subtle differences in structure from those under typical developmental. Magnetic resonance imaging (MRI) routine diagnostic method neuroimaging. Brain prediction MRI has been widely studied. However, few studies Chinese population have reported. This study aimed to construct predictive model for the across its lifespan. We developed partition transfer learning and atlas attention enhancement. The participants were separated into four groups, deep was trained each group identify regions most critical prediction. Atlas attention-enhancement also used help models focus only regions. proposed validated using 354 domestic datasets. For performance testing sets, mean absolute error 2.218 ± 1.801 years, Pearson correlation coefficient (r) 0.969, exceeding previous results wide-range In conclusion, could provide estimation assist assessing status health.

Язык: Английский

---

Multimodal brain age prediction using machine learning: combining structural MRI and 5-HT2AR PET-derived features

GeroScience, Год журнала: 2024, Номер 46(5), С. 4123 - 4133

Опубликована: Апрель 26, 2024

To better assess the pathology of neurodegenerative disorders and efficacy neuroprotective interventions, it is necessary to develop biomarkers that can accurately capture age-related biological changes in human brain. Brain serotonin 2A receptors (5-HT2AR) show a particularly profound decline are also reduced disorders, such as Alzheimer's disease. This study investigates whether 5-HT2AR binding, measured vivo using positron emission tomography (PET), be used biomarker for brain aging. Specifically, we aim (1) predict age binding outcomes, (2) compare 5-HT2AR-based predictions based on gray matter (GM) volume, determined with structural magnetic resonance imaging (MRI), (3) investigate combining GM volume data improves prediction. We PET MR images from 209 healthy individuals aged between 18 85 years (mean = 38, std 18) estimated 14 cortical subcortical regions. Different machine learning algorithms were applied chronological combined measures. The mean absolute error (MAE) cross-validation approach evaluation model comparison. find both cerebral MAE 6.63 years, 0.74 years) 6.95 0.83 accurately. Combining two measures prediction further 5.54 0.68). In conclusion, might useful improving quantification

Язык: Английский

---

Brain age monotonicity and functional connectivity differences of healthy subjects

PLoS ONE, Год журнала: 2024, Номер 19(5), С. e0300720 - e0300720

Опубликована: Май 30, 2024

Alterations in the brain’s connectivity or interactions among brain regions have been studied with aid of resting state (rs)fMRI data attained from large numbers healthy subjects various demographics. This has instrumental providing insight into how a phenotype as fundamental age affects brain. Although machine learning (ML) techniques already deployed such studies, novel questions are investigated this work. We study whether young brains develop properties that progressively resemble those aged brains, and if aging dynamics older provide information about trajectory subjects. The degree prospective monotonic relationship will be quantified, hypotheses trajectories tested via ML. Furthermore, functional across spectrum three datasets compared at population level sexes. findings scrutinize similarities differences male female greater detail than previously performed.

Язык: Английский

---

Complementary value of molecular, phenotypic, and functional aging biomarkers in dementia prediction

GeroScience, Год журнала: 2024, Номер unknown

Опубликована: Окт. 24, 2024

Abstract DNA methylation age (MA), brain (BA), and frailty index (FI) are putative aging biomarkers linked to dementia risk. We investigated their relationship combined potential for prediction of cognitive impairment future risk using the ADNI database. Of several MA algorithms, DunedinPACE GrimAge2, associated with memory, were in a composite alongside BA data-driven FI predictive analyses. Pairwise correlations between age- sex-adjusted measures (aMA), aBA, aFI low. outperformed all diagnostic tasks. A model including age, sex, achieved an area under curve (AUC) 0.94 differentiating cognitively normal controls (CN) from patients held-out test set. When clinical (apolipoprotein E ε4 allele count, executive function), aBA predicted 5-year among MCI out-of-sample AUC 0.88. In prognostic model, offered complementary value (both β s 0.50). The tested MAs did not improve predictions. Results consistent across health deficit selection yielding best performance. had stronger adverse effect on prognosis males, while BA’s impact was greater females. Our findings highlight prediction. results support multidimensional view dementia, intertwined biomarkers, prognosis. MA’s limited contribution suggests caution use individual assessment dementia.

Язык: Английский

---

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

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Ноя. 10, 2024

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, targeted regions may differ. Additionally, given AD's strong association aging, we propose specific are influenced by both AD pathology exhibiting correlations both. To test these hypotheses, developed 3D convolutional network mixed-attention mechanism to recognize subjects from structural magnetic resonance imaging (sMRI) data utilize methods pinpoint significantly correlated AD, MMSE, CDR age. All models were trained internally validated on 417 samples Disease Neuroimaging Initiative (ADNI), classification model was externally 382 Australian Imaging Lifestyle flagship (AIBL). This approach provided robust support for using MMSE assessing progression visually illustrated relationship between aging AD. The analysis revealed among four identification tasks (AD, age) highlighted asymmetric lesions aging. Notably, found accelerate some extent, correlation exists rate of scores. offers new insights into

Язык: Английский

---