通过MIND特征空间转换提升深度学习形变配准的泛化能力
Strategies for Robust Deep Learning Based Deformable Registration
- 将图像转为MIND特征空间再输入模型，增强鲁棒性
- 在跨模态、跨对比度测试中显著提升配准性能
- 适合需要高泛化能力的医学图像配准场景
近年来基于深度学习的形变配准方法广受欢迎，但其在超出训练数据分布时的泛化能力较差，严重限制了实际应用。LUMIR脑图像配准挑战赛（Learn2Reg 2025）旨在评估模型在训练集未包含的对比度和模态下的表现。本文提交方案提出一种简单有效的方法：在输入模型前将图像转换至MIND特征空间，显著提升鲁棒性；同时设计一种特殊集成策略，带来小幅但稳定的性能提升。
原文摘要 · Abstract (English)
Deep learning based deformable registration methods have become popular in recent years. However, their ability to generalize beyond training data distribution can be poor, significantly hindering their usability. LUMIR brain registration challenge for Learn2Reg 2025 aims to advance the field by evaluating the performance of the registration on contrasts and modalities different from those included in the training set. Here we describe our submission to the challenge, which proposes a very simple idea for significantly improving robustness by transforming the images into MIND feature space before feeding them into the model. In addition, a special ensembling strategy is proposed that shows a small but consistent improvement.
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。