数据日期 2026-10-29 · 生成时间 2026-10-29 06:03
证据级别：摘要级。本条依据 PubMed 结构化摘要与元数据撰写，付费墙全文未获取、未逐节核验，本站未做任何数值推算补全。
研究问题
Brain aging involves widespread reorganization of functional networks, yet characterizing these changes across the lifespan remains challenging.
方法
This study presents an innovative application of a Vision Transformer (ViT) to resting-state fMRI (rs-fMRI) functional connectivity for age group classification using the Human Connectome Project (HCP) Lifespan datasets.
核心结论
A ViT model was fine-tuned on [Formula: see text] ROI-to-ROI connectivity matrices to perform three binary age group classifications (Young versus Old, Adult versus Aging, Young versus Aging).；The model achieved accuracies of 91%, 71%, and 93%, respectively, under five-fold cross-validation.；To interpret model decisions, attention weight maps from the final transformer encoder layer were extracted using attention rollout and thresholded with a scree plot analysis, identifying 48 high-salience connections across 28 brain regions.；These features were analyzed across the lifespan using generalized additive models (GAM), and k-means clustering of the trajectories revealed three dominant lifespan connectivity patterns: Age-Declining, Mid-Life Peaking, and Age-Increasing. ‖ 结论：This study demonstrates the viability of the ViT for functional connectome analysis and shows that attention-based interpretability combined with GAM trajectory analysis can enrich insights into age-related changes in brain network connectivity, offering a framework for interpretable brain-age modeling.
局限
未能获取全文，具体设计细节、失访与统计学处理无法核验。
对本项目的价值
★★☆☆☆ 脑老化是最大未满足需求，也是终点最难量化的领域；biomarker 与认知读数选择最敏感。
原文题录
- 英文标题：Mapping Lifespan Functional Connectivity with Vision Transformer and Attention-Guided Trajectory Analysis.
- 期刊与标识：Int J Neural Syst · PMID 42935467 · DOI 10.1142/S0129065727500304**
A 级证据分级：A 级（同行评议人体研究）
本文属人体研究证据，但需注意：观察性或小样本干预的结论不等于已证实临床获益；效应量与长期安全性仍需更大规模、更长随访的试验验证。
关于本文的文献来源：本站依据 IMA 知识库「五刊监控·深度文献卡片」（SOP §4.2 摘要级）撰写，依据期刊公开摘要与 PubMed 元数据；付费墙全文未获取之处已标注「待补全文」，未做任何数值推算补全。