Dual-stream pyramid registration network

Miao Kang, Xiaojun Hu, Weilin Huang, Matthew R. Scott, Mauricio Reyes

Abstract: Highlights•We propose a Dual-stream Pyramid Registration Network (referred as Dual-PRNet) for unsupervised 3D medical image registration.•We design a two-stream 3D encoder-decoder network that computes two convolutional feature pyramids separately from two input volumes.•We propose sequential pyramid registration where a sequence of pyramid registration (RP) modules is designed to predict multi-level registration fields directly from the decoding feature pyramids.•The PR modules can be further enhanced by computing local 3D correlations between the feature pyramids, resulting in the improved Dual-PRNet++.•Our Dual-PRNet++ can be integrated into a 3D segmentation framework for joint registration and segmentation, by precisely warping voxel-level annotations.