让脑部MRI配准网络具备旋转等变性，提升精度与效率
Rotation Equivariant Convolutions in Deformable Registration of Brain MRI
- 用旋转等变卷积替代标准编码器，利用解剖结构的旋转对称性
- 在旋转输入下仍保持高精度，参数更少，训练数据需求更低
- 适合临床图像配准，尤其对方向不固定的医学影像有优势
图像配准是将不同图像中的解剖结构对齐的基础任务。尽管卷积神经网络表现良好，但缺乏旋转等变性——输入旋转后输出不会相应旋转，这导致无法利用脑部MRI中固有的旋转对称性。本文将旋转等变卷积融入可变形脑部MRI配准网络，在三种基准架构中替换标准编码器，并在多个公开脑部MRI数据集上进行测试。实验表明，等变编码器具有三大优势：1）在减少网络参数的同时实现更高配准精度，验证了解剖先验的有效性；2）在旋转输入对上优于基线模型，表现出对临床中常见方向变化的鲁棒性；3）在较少训练数据下表现更优，体现更高的样本效率。结果表明，引入几何先验是构建更鲁棒、准确、高效配准模型的关键。
原文摘要 · Abstract (English)
Image registration is a fundamental task that aligns anatomical structures between images. While CNNs perform well, they lack rotation equivariance - a rotated input does not produce a correspondingly rotated output. This hinders performance by failing to exploit the rotational symmetries inherent in anatomical structures, particularly in brain MRI. In this work, we integrate rotation-equivariant convolutions into deformable brain MRI registration networks. We evaluate this approach by replacing standard encoders with equivariant ones in three baseline architectures, testing on multiple public brain MRI datasets. Our experiments demonstrate that equivariant encoders have three key advantages: 1) They achieve higher registration accuracy while reducing network parameters, confirming the benefit of this anatomical inductive bias. 2) They outperform baselines on rotated input pairs, demonstrating robustness to orientation variations common in clinical practice. 3) They show improved performance with less training data, indicating greater sample efficiency. Our results demonstrate that incorporating geometric priors is a critical step toward building more robust, accurate, and efficient registration models.
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。