发表机构
Athinoula A. Martinos Center for Biomedical Imaging; Massachusetts General Hospital; Harvard Medical School（阿西努拉·A.马蒂诺斯生物医学成像中心; 麻省总医院; 哈佛医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出DisMorph框架，通过合成数据训练解耦纵向形变中的技术畸变与生物变化，在模拟、真实畸变及AD数据上均展现出更优的配准与变化检测能力，为临床纵向形态测量提供了更准确的方案。
AI 中文摘要
纵向磁共振成像（MRI）能够灵敏测量大脑结构变化，用于研究衰老和神经退行性疾病。可变形图像配准是估计此类变化的关键工具，它通过计算密集形变来捕捉纵向扫描间的几何差异。然而，MRI扫描仪会引入随采集系统和协议变化的几何畸变，例如梯度非线性（GNL）畸变。现有配准方法会估计一个单一的形变场，将生物效应与技术效应混在一起，若畸变（部分）未被校正，可能会导致下游形态测量结果出现偏差。我们提出了DisMorph，一个完全基于合成数据训练的配准框架，它明确将纵向形变分解为技术变换和解剖变换。该框架会预测两个密集形变，每个形变分别编码一种效应。在训练过程中，一种新型生成模型会分别合成两种效应，以提供解耦监督，同时通过域随机化促进跨成像协议的泛化能力。我们在三个互补的场景中评估了该方法：在具有已知真值的模拟数据上，与传统配准方法相比，我们的方法能更准确、更一致地检测解剖变化；在仅存在GNL畸变差异的真实图像对上，我们的方法将大部分几何变化分配给了畸变场，证明了在无解剖变化时的特异性；在纵向阿尔茨海默病（AD）图像对上，我们的方法能检测AD相关脑结构中的解剖变化，同时识别出标准校正后残留的畸变。通过在纵向形变中解耦MRI诱导的畸变与生物变化，我们的方法为采集一致性难以维持的临床场景中实现更准确的纵向形态测量铺平了道路。
英文摘要
Longitudinal MRI enables sensitive measurement of structural brain change for studying aging and neurodegenerative disease. Deformable image registration is a key tool for estimating such change by computing a dense deformation that captures geometric differences between longitudinal scans. However, MRI scanners introduce geometric distortions that vary across acquisition systems and protocols, such as gradient non-linearity (GNL) distortion. Existing registration methods estimate a single field that conflates biological and technical effects, potentially biasing downstream morphometric measurements if distortions remain (partially) uncorrected. We propose $\texttt{DisMorph}$, a registration framework trained entirely on synthetic data that explicitly decomposes longitudinal deformation into technical and anatomical transforms. It predicts two dense deformations, each encoding one effect. During training, a novel generative model synthesizes both effects separately to provide disentanglement supervision, while domain randomization promotes generalization across imaging protocols. We evaluate our method in three complementary settings. On simulated data with known ground truth, our method detects anatomical change more accurately and consistently than conventional registration. On real image pairs that differ only by GNL distortion, our method assigns most geometric change to the distortion field, demonstrating specificity in the absence of anatomical change. On longitudinal Alzheimer's disease (AD) pairs, our method detects anatomical change in AD-related brain structures while identifying residual distortion left after standard correction. By disentangling MRI-induced distortion from biological change in the longitudinal deformation, our method paves the way for more accurate longitudinal morphometry in clinical settings where maintaining acquisition consistency is challenging.
Comments11 pages, 6 figures, longitudinal morphometry, deformable registration, neuroimaging, domain randomization, gradient non-linearity distortion, accepted by the SASHIMI Workshop at MICCAI 2026
