Skip to main content
QUICK REVIEW

[论文解读] Brain Imaging-to-Graph Generation using Adversarial Hierarchical Diffusion Models for MCI Causality Analysis

Qiankun Zuo, Tian, Hao|arXiv (Cornell University)|May 18, 2023
Functional Brain Connectivity Studies被引用 4
一句话总结

该论文提出了一种基于对抗性功能扩散的多分辨率时空增强Transformer去噪(MSETD)网络,用于从4D fMRI生成大脑有效连接(BEC),以实现轻度认知障碍(MCI)的分析。通过利用条件扩散过程以及多尺度Transformer生成器和判别器,该模型在BEC预测方面表现优异,并识别出与临床一致的MCI相关因果连接。

ABSTRACT

Effective connectivity can describe the causal patterns among brain regions. These patterns have the potential to reveal the pathological mechanism and promote early diagnosis and effective drug development for cognitive disease. However, the current methods utilize software toolkits to extract empirical features from brain imaging to estimate effective connectivity. These methods heavily rely on manual parameter settings and may result in large errors during effective connectivity estimation. In this paper, a novel brain imaging-to-graph generation (BIGG) framework is proposed to map functional magnetic resonance imaging (fMRI) into effective connectivity for mild cognitive impairment (MCI) analysis. To be specific, the proposed BIGG framework is based on the diffusion denoising probabilistic models (DDPM), where each denoising step is modeled as a generative adversarial network (GAN) to progressively translate the noise and conditional fMRI to effective connectivity. The hierarchical transformers in the generator are designed to estimate the noise at multiple scales. Each scale concentrates on both spatial and temporal information between brain regions, enabling good quality in noise removal and better inference of causal relations. Meanwhile, the transformer-based discriminator constrains the generator to further capture global and local patterns for improving high-quality and diversity generation. By introducing the diffusive factor, the denoising inference with a large sampling step size is more efficient and can maintain high-quality results for effective connectivity generation. Evaluations of the ADNI dataset demonstrate the feasibility and efficacy of the proposed model. The proposed model not only achieves superior prediction performance compared with other competing methods but also predicts MCI-related causal connections that are consistent with clinical studies.

研究动机与目标

  • 解决现有方法依赖人工fMRI预处理和浅层模型在捕捉复杂因果脑连接方面的局限性。
  • 开发一种端到端框架,将原始fMRI直接映射为有效连接,避免对经验时间序列提取的依赖。
  • 通过对抗性与基于扩散的去噪方法,提升生成的有效连接图的质量、多样性与效率。
  • 识别与临床文献一致的MCI相关因果连接,以期发现潜在生物标志物。

提出的方法

  • 采用条件扩散概率模型(DDPM)逐步将模糊的fMRI时间序列去噪为干净、高质量的ROI基时间序列。
  • 引入一种多分辨率增强Transformer生成器,结合空间/时间多头注意力机制,以在多尺度下提取局部与全局时空特征。
  • 设计一种多尺度扩散式Transformer判别器,以捕捉不同尺度下的时间模式,并稳定对抗训练过程。
  • 使用AAL90脑图谱将3D fMRI划分为90个感兴趣区域(ROIs),实现具有方向边的图结构BEC表示。
  • 采用对抗性策略加速DDPM的缓慢去噪过程,同时保持样本的多样性与质量。
  • 端到端训练模型,直接从4D fMRI生成有效连接图,避免中间预处理瓶颈。

实验结果

研究问题

  • RQ1基于条件扩散的生成模型是否能有效重建高质量的有效连接,而无需人工预处理,从噪声fMRI时间序列中恢复?
  • RQ2多分辨率时空注意力机制在多大程度上提升了生成脑连接图的保真度与多样性?
  • RQ3对抗性训练策略在多大程度上提升了基于扩散的去噪过程的效率与质量?
  • RQ4生成的MCI相关因果连接是否具有生物学合理性,并与阿尔茨海默病及MCI的临床发现一致?

主要发现

  • 所提出的MSETD模型在ADNI数据集上的预测性能优于其他浅层与深度学习方法。
  • 移除对抗性策略(MSETD w/o MDT)后,分类性能显著下降,证实其在提升生成质量与速度方面具有关键作用。
  • 该模型成功识别出12条关键的MCI相关有效连接,包括减弱的HIP.L至PCG.R连接与增强的HIP.L至MOG.R连接,与临床文献中关于记忆与认知衰退的发现一致。
  • SOG.R至PCG.R的有效连接从NC到LMCI阶段减弱,与临床报告中记忆相关网络破坏的发现相符。
  • AMYG、HIP与ANG区域显示出与已知MCI及阿尔茨海默病病理相关的连接模式改变。
  • 该模型在从原始fMRI生成具有生物学可解释性、临床相关性的有效连接模式方面展现出可行性与有效性。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。