ShiftMorph: A Fast and Robust Convolutional Neural Network for 3D Deformable Medical Image Registration

Deformable image registration (DIR) is crucial for many medical image applications. In recent years, learning-based methods utilizing the convolutional neural network (CNN) or the Transformer have demonstrated their superiority in image registration, dominating a new era for DIR. However, very few of these methods can satisfy the demands of real-time applications due to the high spatial resolution of 3D volumes and the high complexity of 3D operators. To tackle this, we propose losslessly downsampling by shifting the strided convolution. A grouping strategy is then used to reduce redundant computations and support self-consistency learning. As an inherent regularizer of the network design, self-consistency learning improves the deformation quality and enables halving the proposed network after training. Furthermore, the proposed shifted connection converts the decoding operations into a lower-dimensional space, significantly reducing decoding overhead. Extensive experimental results on medical image registration demonstrate that our method is competitive with state-of-the-art methods in terms of registration performance, and additionally, it achieves over 3× the speed of most of them.