用几何先验解决脑影像模型特征坍塌，提取可解释的阿尔茨海默病预测标志物。
GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
- 基于模型学习的流形结构引导稀疏自编码器，防止深层特征坍塌。
- 仅用2%嵌入维度就实现MCI转AD预测AUC 0.746，且跨队列复现性r=0.97。
- 排除年龄干扰后识别出与Braak分期一致的神经解剖区域特征，适合临床研究者使用。
脑MRI基础模型能学习丰富的解剖表征，但其编码的临床信息仍难以解读。标准稀疏自编码器（SAE）在深度Transformer层中易出现特征坍塌，且阿尔茨海默病（AD）研究中衰老几乎影响所有临床变量，导致简单标注不可靠。我们提出GeoSAE，一种几何引导的SAE框架，利用基础模型的流形结构防止特征坍塌，并通过去年龄混淆的部分相关性标注每个存活特征。该方法应用于来自阿尔茨海默病神经影像计划（ADNI）和澳大利亚影像生物标志物与生活方式（AIBL）队列的约1.4万例T1加权MRI扫描。GeoSAE识别出一组紧凑、完全可解释的特征，仅使用2%的嵌入维度即可预测轻度认知障碍（MCI）向AD转化（AUC 0.746），而共病标注特征表现仅达随机水平。所识别特征在不同队列间无需重新训练即可复现（r=0.97），并定位至与Braak分期一致的神经解剖区域。结果表明，几何引导的SAE可从冻结的脑MRI基础模型中提取可解释的生物标志物。
原文摘要 · Abstract (English)
Brain MRI foundation models learn rich representations of anatomy, but interpreting what clinical information they encode remains an open problem. Standard sparse autoencoders (SAEs) suffer from severe feature collapse in deep transformer layers, and in Alzheimer's disease (AD) research, aging confounds nearly every clinical variable, making naive annotation unreliable. We propose GeoSAE, a geometry-guided SAE framework that uses the foundation model's learned manifold structure to prevent feature collapse and annotates each surviving feature via age-deconfounded partial correlations. Applied to ~14k T1-weighted MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Australian Imaging biomarkers and Lifestyle (AIBL) datasets, GeoSAE identifies a compact, fully interpretable feature set that predicts mild cognitive impairment (MCI)-to-AD conversion (AUC 0.746) using only 2% of the embedding dimensions, while comorbidity-annotated features achieve only chance-level performance. The identified features replicate across cohorts without retraining (r=0.97) and localize to neuroanatomically distinct regions consistent with Braak staging. This shows that geometry-guided SAEs can extract interpretable, biomarkers from frozen brain MRI foundation models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。