发表机构
Hawkes Institute; University College London; Institut Pasteur; Université Paris Cité; AINOSTICS ltd.; Fudan University; Université Libre de Bruxelles (ULB); University of Liège (ULiège)（霍克斯研究所; 伦敦大学学院; 巴斯德研究所; 巴黎西岱大学; AINOSTICS有限公司; 复旦大学; 布鲁塞尔自由大学; 列日大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对dMRI中涡流畸变校正方法计算成本高的问题，提出深度学习框架Eddeep，其通过两阶段网络实现与FSL Eddy相当的校正质量，同时大幅缩短推理时间，为大规模研究和临床部署提供支持。
AI 中文摘要
扩散MRI（dMRI）依赖于扩散加权回波平面成像，该成像极易受涡流诱导的几何畸变影响。这些畸变会根据梯度强度和方向在不同扩散体积间变化，导致体积间配准错位，进而对下游的微观结构分析产生偏差。当前最先进的校正方法，如FSL Eddy，通过迭代预测-校正方案实现高质量校正，但计算成本高昂。我们提出Eddeep，一种用于dMRI中快速涡流畸变校正的深度学习框架。Eddeep将该问题分解为两个阶段：第一，有监督图像转换网络对扩散加权图像和b=0图像的外观进行标准化，消除阻碍可靠配准的对比度差异；第二，无监督配准网络在物理约束的二次畸变模型下，同时估计涡流畸变和体积间头部运动参数，支持单次前向传递完成校正。该方法在UK Biobank数据上训练，并在域内（UK Biobank）和域外（Memodyn）数据集上评估。在体积间抖动、扩散峰度成像残差、信号不规则性及互信息等一系列互补指标上，Eddeep实现了与FSL Eddy相当的校正质量，同时大幅缩短了推理时间。这些结果表明，深度学习可在不依赖迭代优化的情况下提供准确高效的涡流畸变校正，为大规模研究和临床部署开发更快的扩散MRI处理流程提供支持。代码可访问：this https URL。
英文摘要
Diffusion MRI (dMRI) relies on diffusion-weighted echo-planar imaging, which is highly susceptible to eddy-current-induced geometric distortions. These distortions vary across diffusion volumes according to gradient strength and direction, causing between-volume misalignment that can bias downstream microstructural analyses. Current state-of-the-art correction methods, such as FSL Eddy, achieve high-quality correction through iterative prediction-correction schemes but are computationally expensive. We propose Eddeep, a deep-learning framework for fast eddy-current distortion correction in dMRI. Eddeep decomposes the problem into two stages. First, a supervised image translation network standardises the appearance of diffusion-weighted and b=0 images, removing contrast differences that hinder reliable registration. Second, an unsupervised registration network estimates both eddy-current distortion and between-volume head motion parameters under a physics-constrained quadratic distortion model, enabling correction in a single forward pass. The method was trained on UK Biobank data and evaluated on both in-domain (UK Biobank) and out-of-domain (Memodyn) datasets. Across a range of complementary metrics, including between-volume jitter, diffusion kurtosis imaging residuals, signal irregularity, and mutual information, Eddeep achieved correction quality comparable to that of FSL Eddy while substantially reducing inference time. These results demonstrate that deep learning can provide accurate and efficient eddy-current distortion correction without relying on iterative optimisation, supporting the development of faster diffusion MRI processing pipelines for large-scale studies and clinical deployment. The code is available at: https://github.com/CIG-UCL/eddeep.
CommentsAssociated GitHub repo: https://github.com/CIG-UCL/eddeep
