Deep learning-based deformable registration methods have been widely investigated in diverse medical applications. Learning-based deformable registration relies on weighted objective functions trading off registration accuracy and smoothness of the deformation field. Therefore, they inevitably require tuning the hyperparameter for optimal registration performance. Tuning the hyperparameters is highly computationally expensive and introduces undesired dependencies on domain knowledge. In this study, we construct a registration model based on the gradient surgery mechanism, named GSMorph, to achieve a hyperparameter-free balance on multiple losses. In GSMorph, we reformulate the optimization procedure by projecting the gradient of similarity loss orthogonally to the plane associated with the smoothness constraint, rather than additionally introducing a hyperparameter to balance these two competing terms. Furthermore, our method is model-agnostic and can be merged into any deep registration network without introducing extra parameters or slowing down inference. In this study, We compared our method with state-of-the-art (SOTA) deformable registration approaches over two publicly available cardiac MRI datasets. GSMorph proves superior to five SOTA learning-based registration models and two conventional registration techniques, SyN and Demons, on both registration accuracy and smoothness.

翻译：基于深度学习的可变形配准方法已在多种医学应用中受到广泛研究。基于学习的可变形配准依赖于加权目标函数，需要在配准精度与变形场平滑性之间进行权衡。因此，此类方法不可避免地需要对超参数进行调优以获得最佳配准性能。超参数调优计算成本极高，并且引入了对领域知识的不良依赖。本研究基于梯度剪枝机制构建了一种名为GSMorph的配准模型，实现了多损失间无需超参数的平衡。在GSMorph中，我们将相似性损失的梯度正交投影到与平滑性约束相关的平面上，从而重构优化流程，而非额外引入超参数来平衡这两个竞争项。此外，我们的方法具有模型无关性，可无缝集成到任何深度配准网络中，且不会增加额外参数或降低推理速度。本研究在两个公开心脏MRI数据集上，将所提方法与当前最先进的可变形配准方法进行了对比。GSMorph在配准精度和平滑性上均优于五种基于学习的最新配准模型及两种传统配准技术（SyN和Demons）。