This research explores a novel approach in the realm of learning-based image registration, addressing the limitations inherent in weakly-supervised and unsupervised methods. Weakly-supervised techniques depend heavily on scarce labeled data, while unsupervised strategies rely on indirect measures of accuracy through image similarity. Notably, traditional supervised learning is not utilized due to the lack of precise deformation ground-truth in medical imaging. Our study introduces a unique training framework with On-the-Fly Guidance (OFG) to enhance existing models. This framework, during training, generates pseudo-ground truth a few steps ahead by refining the current deformation prediction with our custom optimizer. This pseudo-ground truth then serves to directly supervise the model in a supervised learning context. The process involves optimizing the predicted deformation with a limited number of steps, ensuring training efficiency and setting achievable goals for each training phase. OFG notably boosts the precision of existing image registration techniques while maintaining the speed of learning-based methods. We assessed our approach using various pseudo-ground truth generation strategies, including predictions and optimized outputs from established registration models. Our experiments spanned three benchmark datasets and three cutting-edge models, with OFG demonstrating significant and consistent enhancements, surpassing previous state-of-the-arts in the field. OFG offers an easily integrable plug-and-play solution to enhance the training effectiveness of learning-based image registration models. Code at https://github.com/miraclefactory/on-the-fly-guidance.

翻译：本研究探索了基于学习的图像配准领域中的一种新方法，旨在解决弱监督和无监督方法固有的局限性。弱监督技术严重依赖稀缺的标注数据，而无监督策略则通过图像相似性这一间接准确性指标进行评估。值得注意的是，由于医学成像中缺乏精确的变形金标准，传统的监督学习无法直接应用。我们的研究提出了一种独特的训练框架——实时引导（OFG），用于增强现有模型。在训练过程中，该框架通过自定义优化器对当前变形预测进行几步迭代优化，生成超前几步的伪金标准。随后，这些伪金标准在监督学习场景中直接用于监督模型。该过程涉及对预测变形进行有限步骤的优化，从而保证训练效率并为每个训练阶段设定可实现的目标。OFG显著提升了现有图像配准技术的精度，同时保持了基于学习方法的速度。我们采用多种伪金标准生成策略（包括现有配准模型的预测结果和优化输出）评估了该方法。实验覆盖三个基准数据集和三种前沿模型，结果表明OFG带来了显著且一致的性能提升，超越了该领域先前的最优结果。OFG提供了一种易于集成的即插即用解决方案，可有效提升基于学习的图像配准模型的训练效果。代码详见 https://github.com/miraclefactory/on-the-fly-guidance。