基于功能连接矩阵生成式回放的fMRI脑部疾病诊断持续学习框架
Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replay
提出结构感知变分自编码器生成逼真的功能连接矩阵，并结合多级知识蒸馏与分层上下文赌博机自适应回放采样，为视觉领域处理非欧几里得图结构数据的持续学习提供可复用方案。
原文依据 structure-aware variational autoencoder that synthesizes realistic FC matrices
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论功能磁共振成像（fMRI）广泛用于研究和诊断脑部疾病，其中功能连接（FC）矩阵为大规模神经交互提供了强大的表征。然而，现有的诊断模型要么在单一站点上训练，要么在完全多站点访问下训练，这使得它们不适用于临床数据从不同机构顺序到达的真实场景。这导致泛化能力有限和严重的灾难性遗忘。本文提出了首个专门为跨异构临床站点的fMRI诊断设计的持续学习框架。我们的框架引入了一种结构感知的变分自编码器，可为患者组和对照组合成逼真的FC矩阵。基于这一生成主干，我们开发了一种多级知识蒸馏策略，在新站点数据和回放样本之间对齐预测和图表示。为了进一步提高效率，我们采用了一种分层上下文赌博机方案进行自适应回放采样。在针对重度抑郁症（MDD）、精神分裂症（SZ）和自闭症谱系障碍（ASD）的多站点数据集上的实验表明，所提出的生成模型提高了数据增强质量，并且整体持续学习框架在缓解灾难性遗忘方面显著优于现有方法。我们的代码可在https://github.com/4me808/FORGE获取。
英文原文摘要 1489 字符
Functional magnetic resonance imaging (fMRI) is widely used for studying and diagnosing brain disorders, with functional connectivity (FC) matrices providing powerful representations of large-scale neural interactions. However, existing diagnostic models are trained either on a single site or under full multi-site access, making them unsuitable for real-world scenarios where clinical data arrive sequentially from different institutions. This results in limited generalization and severe catastrophic forgetting.This paper presents the first continual learning framework specifically designed for fMRI-based diagnosis across heterogeneous clinical sites. Our framework introduces a structure-aware variational autoencoder that synthesizes realistic FC matrices for both patient and control groups. Built on this generative backbone, we develop a multi-level knowledge distillation strategy that aligns predictions and graph representations between new-site data and replayed samples. To further enhance efficiency, we incorporate a hierarchical contextual bandit scheme for adaptive replay sampling.Experiments on multi-site datasets for major depressive disorder (MDD), schizophrenia (SZ), and autism spectrum disorder (ASD) show that the proposed generative model enhances data augmentation quality, and the overall continual learning framework substantially outperforms existing methods in mitigating catastrophic forgetting. Our code is available at https://github.com/4me808/FORGE.