State-of-the-art deep learning-based registration methods employ three different learning strategies: supervised learning, which requires costly manual annotations, unsupervised learning, which heavily relies on hand-crafted similarity metrics designed by domain experts, or learning from synthetic data, which introduces a domain shift. To overcome the limitations of these strategies, we propose a novel self-supervised learning paradigm for unsupervised registration, relying on self-training. Our idea is based on two key insights. Feature-based differentiable optimizers 1) perform reasonable registration even from random features and 2) stabilize the training of the preceding feature extraction network on noisy labels. Consequently, we propose cyclical self-training, where pseudo labels are initialized as the displacement fields inferred from random features and cyclically updated based on more and more expressive features from the learning feature extractor, yielding a self-reinforcement effect. We evaluate the method for abdomen and lung registration, consistently surpassing metric-based supervision and outperforming diverse state-of-the-art competitors. Source code is available at https://github.com/multimodallearning/reg-cyclical-self-train.

翻译：当前基于深度学习的最先进配准方法采用三种学习策略：监督学习需昂贵的人工标注，无监督学习过度依赖领域专家设计的专业相似性度量，而基于合成数据的学习则引入领域偏移。为突破这些策略的局限性，我们提出一种面向无监督配准的新型自监督学习范式，其核心在于自训练机制。该方法的理论基础包含两个关键发现：基于特征的微分优化器（1）即使采用随机特征也能实现合理的配准效果，（2）能够稳定特征提取网络在含噪声标签上的训练过程。据此，我们提出循环自训练策略，其中伪标签初始化为随机特征推导的位移场，并随着特征提取器表达能力增强而循环更新，最终形成自我强化的正向反馈效应。经腹部与肺部配准实验验证，本方法在一致性上超越基于度量的监督方法，性能全面优于多种现有最先进算法。完整源代码已开源至 https://github.com/multimodallearning/reg-cyclical-self-train。