arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.05630q-bio.NCcs.AI

BrainCSD：一种层次一致性驱动的 MoE 基础模型，用于统一连接组合成与多任务脑特质预测

BrainCSD: A Hierarchical Consistency-Driven MoE Foundation Model for Unified Connectome Synthesis and Multitask Brain Trait Prediction

Department of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术系）；School of Intelligence Science and Engineering, College of Artificial Intelligence, Harbin Institute of Technology（哈尔滨工业大学智能科学与工程学院）；School of Biomedical Engineering, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical, Measurements and Ultrasound Imaging, Shenzhen University Medical School, Shenzhen University（深圳大学医学院生物医学工程学院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）

Xiongri Shen, Jiaqi Wang, Yi Zhong, Zhenxi Song, Leilei Zhao, Liling Li, Yichen Wei, Lingyan Liang, Shuqiang Wang, Baiying Lei, Demao Deng, Zhiguo Zhang

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

BrainCSD 提出层次一致性驱动的 MoE 基础模型，通过 ROI 特异性、编码-激活和网络感知细化三个组件联合合成 FC/SC 并支持多任务预测，在缺失模态下取得 SOTA 性能。

摘要：

功能连接与结构连接（FC/SC）是脑分析中关键的多模态生物标志物，但其临床效用受到采集成本高、预处理复杂以及模态频繁缺失的制约。现有基础模型要么只处理单一模态，要么缺乏显式的跨模态和跨尺度一致性机制。我们提出 BrainCSD，一种层次化混合专家（MoE）基础模型，可联合合成 FC/SC 生物标志物并支持下游解码任务（诊断与预测）。BrainCSD 包含三个基于神经解剖学的组件：（1）ROI 特异性 MoE，通过对比一致性将来自典型网络（如 DMN、FPN）的区域激活与全局图谱对齐；（2）编码-激活 MoE，对 fMRI/dMRI 中跨时间/梯度的动态依赖关系进行建模；（3）网络感知细化 MoE，在个体和群体层面施加结构先验与对称性约束。在完整和缺失模态设置下的数据集上评估，BrainCSD 取得了 SOTA 结果：在无 FC 条件下 MCI 与 CN 分类准确率为 95.6%，合成误差低（FC RMSE：0.038；SC RMSE：0.006），脑龄预测 MAE 为 4.04 年，MMSE 评分估计 MAE 为 1.72 分。代码可在 https://github.com/SXR3015/BrainCSD 获取。

英文摘要：

Functional and structural connectivity (FC/SC) are key multimodal biomarkers for brain analysis, yet their clinical utility is hindered by costly acquisition, complex preprocessing, and frequent missing modalities. Existing foundation models either process single modalities or lack explicit mechanisms for cross-modal and cross-scale consistency. We propose BrainCSD, a hierarchical mixture-of-experts (MoE) foundation model that jointly synthesizes FC/SC biomarkers and supports downstream decoding tasks (diagnosis and prediction). BrainCSD features three neuroanatomically grounded components: (1) a ROI-specific MoE that aligns regional activations from canonical networks (e.g., DMN, FPN) with a global atlas via contrastive consistency; (2) a Encoding-Activation MOE that models dynamic cross-time/gradient dependencies in fMRI/dMRI; and (3) a network-aware refinement MoE that enforces structural priors and symmetry at individual and population levels. Evaluated on the datasets under complete and missing-modality settings, BrainCSD achieves SOTA results: 95.6\% accuracy for MCI vs. CN classification without FC, low synthesis error (FC RMSE: 0.038; SC RMSE: 0.006), brain age prediction (MAE: 4.04 years), and MMSE score estimation (MAE: 1.72 points). Code is available in \href{https://github.com/SXR3015/BrainCSD}{BrainCSD}

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑