On-the-Fly Guidance Training for Medical Image Registration

This study introduces a novel On-the-Fly Guidance (OFG) training framework for enhancing existing learning-based image registra- tion models, addressing the limitations of weakly-supervised and un- supervised methods. Weakly-supervised methods struggle due to the scarcity of labeled data, and unsupervised methods directly depend on image similarity metrics for accuracy. Our method proposes a supervised fashion for training registration models, without the need for any labeled data. OFG generates pseudo-ground truth during training by refining de- formation predictions with a differentiable optimizer, enabling direct su- pervised learning. OFG optimizes deformation predictions efficiently, im- proving the performance of registration models without sacrificing infer- ence speed. Our method is tested across several benchmark datasets and leading models, it significantly enhanced performance, providing a plug- and-play solution for training learning-based registration models. Code available at: https://github.com/cilix-ai/on-the-fly-guidance