M2LG-DG：用于跨站点重度抑郁症分类的多模态局部-全局域泛化框架
M2LG-DG: A Multi-modal Local-Global Domain Generalization Framework for Cross-site Major Depressive Disorder Classification
查看机构详情
- Griffith University（格里菲斯大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
提出M2LG-DG多模态局部-全局域泛化框架，通过双流编码器、共享/私有分解及跨站点对比学习，提升跨站点重度抑郁症分类性能，AUC达69.48%。
中文摘要 AI 辅助
基于静息态功能磁共振成像（rs-fMRI）的分类模型在模型开发时未包含的影像站点上通常表现出较低的性能，这可能限制其在临床环境中的使用。域泛化（DG）通过从源站点学习对未见目标站点仍然有效的表示来解决这一问题。然而，现有的用于精神疾病分类的域泛化方法通常依赖单一影像模态，并且可能未充分考虑站点特定的采集效应对学习到的表示空间的影响。在同一站点扫描的受试者共享扫描仪硬件、采集设置和预处理特征，这可能导致表示反映采集条件而非诊断信息。在本工作中，我们提出了M2LG-DG，一个仅使用源数据的多模态局部-全局框架，用于跨站点重度抑郁症（MDD）分类。该框架采用双流rs-fMRI编码器，其中全局路径通过自注意力建模区域间依赖关系，局部路径在基于功能连接导出的脑图上执行图约束聚合。影像和非影像表示被分解为共享和私有成分，并通过带有学习到的模态门控的双向交叉注意力进行整合。跨站点监督对比目标从不同源站点获取的同类受试者形成正样本对，鼓励融合表示在跨采集域中保留诊断信息。在四个保留的REST-meta-MDD站点上，M2LG-DG实现了69.48%的AUC，并超过最接近的比较方法2.18个百分点。在自闭症脑影像数据交换（ABIDE）数据集上的实验进一步支持了其在其他精神神经影像分类任务中的适用性。
英文摘要
Classification models based on resting-state functional magnetic resonance imaging (rs-fMRI) often show lower performance at imaging sites not included during model development, which can limit their use in clinical settings. Domain generalization (DG) addresses this issue by learning representations from source sites that remain effective for unseen target sites. However, existing DG approaches for psychiatric disorder classification commonly rely on a single imaging modality and may not fully account for site-specific acquisition effects on the learned representation space. Subjects scanned at the same site share scanner hardware, acquisition settings, and preprocessing characteristics, which can cause representations to reflect acquisition conditions rather than diagnostic information. In this work, we present M2LG-DG, a source-only multimodal local-global framework for cross-site major depressive disorder (MDD) classification. The framework employs a dual-stream rs-fMRI encoder, where the global pathway models inter-regional dependencies through self-attention and the local pathway performs graph-constrained aggregation over functional connectivity-derived brain graphs. Imaging and non-imaging representations are decomposed into shared and private components and integrated through bidirectional cross-attention with a learned modality gate. A cross-site supervised contrastive objective forms positive pairs from same-class subjects acquired at different source sites, encouraging the fused representation to preserve diagnostic information across acquisition domains. On four held-out REST-meta-MDD sites, M2LG-DG achieves an AUC of 69.48% and exceeds the closest comparison method by 2.18 percentage points. Experiments on the Autism Brain Imaging Data Exchange (ABIDE) dataset further support its applicability to other psychiatric neuroimaging classification tasks.
