用流匹配实现两步注册，快速精准配准心脏MRI。
Flow Matching-enabled Test-Time Refinement for Unsupervised Cardiac MR Registration
- 基于位移场空间的流匹配框架，两步完成高精度配准。
- 在六项任务中平均提升0.6%的Dice分数，左心室改善1.09%。
- 无需预训练模型，适合医疗影像实时配准场景。
基于扩散模型的无监督图像配准已被用于心脏电影磁共振成像，但多步推理成本高限制了实际应用。本文提出FlowReg，一种在位移场空间中的流匹配框架，仅需两步即可实现强配准，并支持后续通过更多步骤进一步优化。FlowReg采用warmup-reflow训练：单步网络先作为教师，学生再学习从任意中间状态进行精炼，无需依赖预训练模型。初始猜测策略将模型预测反馈为下一步起点，提升了第二步及之后的精炼效果。在ACDC和MM2数据集上的六项任务（包括跨数据集泛化）中，FlowReg在五项任务上优于现有最先进方法，平均Dice分数提升0.6%，左心室提升达1.09%，所有六项任务的左心室射血分数估计误差均降低2.58个百分点，仅增加0.7%参数量且无需分割标签。代码已开源。
原文摘要 · Abstract (English)
Diffusion-based unsupervised image registration has been explored for cardiac cine MR, but expensive multi-step inference limits practical use. We propose FlowReg, a flow-matching framework in displacement field space that achieves strong registration in as few as two steps and supports further refinement with more steps. FlowReg uses warmup-reflow training: a single-step network first acts as a teacher, then a student learns to refine from arbitrary intermediate states, removing the need for a pre-trained model as in existing methods. An Initial Guess strategy feeds back the model prediction as the next starting point, improving refinement from step two onward. On ACDC and MM2 across six tasks (including cross-dataset generalization), FlowReg outperforms the state of the art on five tasks (+0.6% mean Dice score on average), with the largest gain in the left ventricle (+1.09%), and reduces LVEF estimation error on all six tasks (-2.58 percentage points), using only 0.7% extra parameters and no segmentation labels. Code is available at https://github.com/mathpluscode/FlowReg.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。