去噪扩散网络在神经影像规范建模中的应用
Denoising diffusion networks for normative modeling in neuroimaging
AI总结：
本文提出基于去噪扩散概率模型（DDPMs）的神经影像规范建模方法，通过统一条件密度估计器实现多变量依赖关系建模，提升高维数据下的校准性能和可扩展性。
摘要：
规范建模通过将生物测量的参考分布条件在协变量上进行估计，使分位数和具有临床解释的偏差分数得以推导。大多数神经影像流水线为每个影像衍生表型（IDP）拟合一个模型，这种做法可扩展性良好，但会丢弃多变量依赖关系，这种依赖关系可能编码协调模式。我们提出去噪扩散概率模型（DDPMs）作为统一的条件密度估计器，用于表格化IDP，从而通过采样推导单变量分位数和偏差分数。我们利用两种去噪器主干：（i）基于特征线性调节（FiLM）的条件多层感知机（MLP）和（ii）具有特征自注意力和跨样本注意力（SAINT）的表格变压器，通过学习嵌入对协变量进行条件化。我们在具有异方差性和多模式年龄效应的合成基准以及UK Biobank FreeSurfer表型上进行评估，从2到200维进行扩展。我们的评估套件包括分位数校准（绝对分位数误差、经验覆盖和概率积分变换）、分布忠实性（Kolmogorov-Smirnov检验）、多变量依赖诊断和最近邻记忆分析。对于低维情况，扩散模型在单个IDP输出上表现良好，与传统基线相当，同时联合建模现实的依赖结构。在高维情况下，变压器主干比MLP更显著更校准，且更好地保持高阶依赖关系，使可扩展的联合规范模型得以实现，仍能与标准单IDP流水线兼容。这些结果支持基于扩散的规范建模作为在神经影像中获得校准的多变量偏差剖面的实用途径。
英文摘要：
Normative modeling estimates reference distributions of biological measures conditional on covariates, enabling centiles and clinically interpretable deviation scores to be derived. Most neuroimaging pipelines fit one model per imaging-derived phenotype (IDP), which scales well but discards multivariate dependence that may encode coordinated patterns. We propose denoising diffusion probabilistic models (DDPMs) as a unified conditional density estimator for tabular IDPs, from which univariate centiles and deviation scores are derived by sampling. We utilise two denoiser backbones: (i) a feature-wise linear modulation (FiLM) conditioned multilayer perceptron (MLP) and (ii) a tabular transformer with feature self-attention and intersample attention (SAINT), conditioning covariates through learned embeddings. We evaluate on a synthetic benchmark with heteroscedastic and multimodal age effects and on UK Biobank FreeSurfer phenotypes, scaling from dimension of 2 to 200. Our evaluation suite includes centile calibration (absolute centile error, empirical coverage, and the probability integral transform), distributional fidelity (Kolmogorov-Smirnov tests), multivariate dependence diagnostics, and nearest-neighbour memorisation analysis. For low dimensions, diffusion models deliver well-calibrated per-IDP outputs comparable to traditional baselines while jointly modeling realistic dependence structure. At higher dimensions, the transformer backbone remains substantially better calibrated than the MLP and better preserves higher-order dependence, enabling scalable joint normative models that remain compatible with standard per-IDP pipelines. These results support diffusion-based normative modeling as a practical route to calibrated multivariate deviation profiles in neuroimaging.
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。
