RegionFM：使用基础模型嵌入进行可解释的基于区域的脑MRI分类
RegionFM: Interpretable Region-Based Brain MRI Classification Using Foundation Model Embeddings
浏览论文内容
中文总结 AI 辅助
研究针对脑MRI基础模型预测难解释问题，提出RegionFM框架，将解剖分割与基础模型嵌入结合，通过划分区域、编码嵌入及构建模型组合，用于认知障碍分类评估，在保持性能同时使解释与临床推理更好对齐。
中文摘要 AI 辅助
基础模型为脑MRI分析提供了强大的表征，但它们的预测在解剖学意义上仍难以解释。脑MRI的临床评估通常围绕解剖学定义的结构和区域异常进行，而传统的解释方法通常产生体素或补丁级的重要性图，无法明确量化各个脑区的贡献。为了解决这种不匹配，我们提出了RegionFM，这是一个将解剖分割与脑MRI基础模型嵌入相结合的可解释框架。RegionFM首先将每个MRI扫描划分为解剖区域，并为每个区域构建一个单独的MRI体积。然后，一个冻结的基础模型将每个区域编码为一个嵌入，一个区域加法逻辑模型将这些嵌入组合起来，使得每个解剖区域对最终预测贡献一个明确的标量项。这种公式支持对区域贡献进行个体水平和队列水平的分析。我们使用来自多个预训练脑MRI基础模型的嵌入对RegionFM进行认知障碍分类评估。结果表明，RegionFM在提供基于解剖学的解释的同时，保持了与难以解释的微调方法相当的性能。随机嵌入消融产生接近随机的性能，表明预测依赖于基础模型嵌入捕获的有意义结构，而不是简单的特征统计。总体而言，RegionFM在保持有竞争力的预测性能的同时，使模型解释与基于解剖学的临床推理更好地对齐。
英文摘要
Foundation models provide powerful representations for brain MRI analysis, but their predictions remain difficult to interpret in anatomically meaningful terms. Clinical assessment of brain MRI is commonly organized around anatomically defined structures and regional abnormalities, whereas conventional explanation methods typically produce voxel- or patch-level importance maps that do not explicitly quantify the contributions of individual brain regions. To address this mismatch, we propose RegionFM, an interpretable framework that integrates anatomical segmentation with brain MRI foundation-model embeddings. RegionFM first divides each MRI scan into anatomical regions and constructs a separate MRI volume for each region. A frozen foundation model then encodes each region into an embedding, and a region-additive logistic model combines these embeddings such that every anatomical region contributes an explicit scalar term to the final prediction. This formulation supports both subject-level and cohort-level analyses of regional contributions. We evaluate RegionFM on cognitive-impairment classification using embeddings from multiple pretrained brain MRI foundation models. The results show that RegionFM maintains performance comparable to less interpretable fine-tuning approaches while providing anatomically grounded explanations. Randomized embedding ablations yield near-chance performance, indicating that the predictions rely on meaningful structure captured by the foundation-model embeddings rather than simple feature statistics. Overall, RegionFM better aligns model explanations with anatomy-based clinical reasoning while maintaining competitive predictive performance.
发表机构
- L3S Research Center（L3S研究中心）
机构由 AI 辅助整理，请以论文原文为准。
