FlowLet: 使用小波流匹配的条件性三维脑部MRI合成

摘要

脑磁共振成像（MRI）在神经发育、衰老及疾病研究中扮演核心角色。其中一项关键应用是脑年龄预测（BAP），即通过MRI数据估算个体生物学脑年龄。有效的BAP模型需要规模庞大、多样性高且年龄分布均衡的数据集，而现有3D MRI数据集存在人口统计学偏差，限制了模型的公平性与泛化能力。获取新数据成本高昂且受伦理约束，因此推动了生成式数据增强技术的发展。当前生成方法多基于潜变量扩散模型，这类模型在学得的低维潜空间中运行，以应对体积MRI数据的内存需求。然而，这些方法在推理时通常速度较慢，可能因潜空间压缩引入伪影，且很少以年龄为条件，从而影响BAP性能。本文提出FlowLet——一种条件生成框架，通过在可逆3D小波域中利用流匹配方法合成年龄条件化的3D MRI，有助于避免重建伪影并降低计算需求。实验表明，FlowLet仅需少量采样步骤即可生成高保真体积数据。使用FlowLet生成的数据训练BAP模型可提升对低年龄组人群的性能，而基于区域的分析证实了解剖结构的保留。

English

Brain Magnetic Resonance Imaging (MRI) plays a central role in studying neurological development, aging, and diseases. One key application is Brain Age Prediction (BAP), which estimates an individual's biological brain age from MRI data. Effective BAP models require large, diverse, and age-balanced datasets, whereas existing 3D MRI datasets are demographically skewed, limiting fairness and generalizability. Acquiring new data is costly and ethically constrained, motivating generative data augmentation. Current generative methods are often based on latent diffusion models, which operate in learned low dimensional latent spaces to address the memory demands of volumetric MRI data. However, these methods are typically slow at inference, may introduce artifacts due to latent compression, and are rarely conditioned on age, thereby affecting the BAP performance. In this work, we propose FlowLet, a conditional generative framework that synthesizes age-conditioned 3D MRIs by leveraging flow matching within an invertible 3D wavelet domain, helping to avoid reconstruction artifacts and reducing computational demands. Experiments show that FlowLet generates high-fidelity volumes with few sampling steps. Training BAP models with data generated by FlowLet improves performance for underrepresented age groups, and region-based analysis confirms preservation of anatomical structures.