Published on Thu Sep 26 2019

Dual-Stream Pyramid Registration Network

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

We propose a Dual-Stream Pyramid Registration Network for unsupervised 3D medical image registration. We design a two-stream architecture able to compute multi-scale registration fields from convolutional feature pyramids. The proposed Dual-PRNet is evaluated on two standard benchmarks for brain MRI registration.

0
0
0
Abstract

We propose a Dual-Stream Pyramid Registration Network (referred as Dual-PRNet) for unsupervised 3D medical image registration. Unlike recent CNN-based registration approaches, such as VoxelMorph, which explores a single-stream encoder-decoder network to compute a registration fields from a pair of 3D volumes, we design a two-stream architecture able to compute multi-scale registration fields from convolutional feature pyramids. Our contributions are two-fold: (i) we design a two-stream 3D encoder-decoder network which computes two convolutional feature pyramids separately for a pair of input volumes, resulting in strong deep representations that are meaningful for deformation estimation; (ii) we propose a pyramid registration module able to predict multi-scale registration fields directly from the decoding feature pyramids. This allows it to refine the registration fields gradually in a coarse-to-fine manner via sequential warping, and enable the model with the capability for handling significant deformations between two volumes, such as large displacements in spatial domain or slice space. The proposed Dual-PRNet is evaluated on two standard benchmarks for brain MRI registration, where it outperforms the state-of-the-art approaches by a large margin, e.g., having improvements over recent VoxelMorph [2] with 0.683->0.778 on the LPBA40, and 0.511->0.631 on the Mindboggle101, in term of average Dice score.

Thu Nov 22 2018
Computer Vision
FAIM -- A ConvNet Method for Unsupervised 3D Medical Image Registration
"FAIM" is a new unsupervised learning algorithm for 3D medical image registration. It takes a pair of full image volumes and predicts the displacement fields needed to register source to target. FAIM has fewer trainable parameters but can achieve higher registration accuracy.
0
0
0
Fri Sep 14 2018
Computer Vision
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
We present VoxelMorph, a fast learning-based framework for deformable,pairwise medical image registration. Traditional registration methods optimize an objective function for each pair of images. We formulate registration as a function that maps an input image pair to a deformation field that aligns these images.
0
0
0
Wed Feb 07 2018
Computer Vision
An Unsupervised Learning Model for Deformable Medical Image Registration
We present a fast learning-based algorithm for deformable, pairwise 3D medical image registration. The proposed method does not require supervised information such as ground truth registration fields or anatomical landmarks. We demonstrate registration accuracy comparable to state-of-the-art 3D image registration, while operating
0
0
0
Thu Jul 25 2019
Machine Learning
Closing the Gap between Deep and Conventional Image Registration using Probabilistic Dense Displacement Networks
Nonlinear image registration continues to be a fundamentally important tool in medical image analysis. When labelled scans are scarce and anatomical differences large, conventional registration has often remained superior to deep learning methods. We propose to design a network with approximate min-convolutions and mean field inference.
0
0
0
Wed Nov 04 2020
Computer Vision
FDRN: A Fast Deformable Registration Network for Medical Images
Deformable image registration is a fundamental task in medical imaging. In the experiments, we show FDRN outperforms the existing state-of-the-art registration methods for brain MR images. FDRN is ageneralized framework for image registration which is not confined to a particular type of medical images or anatomy.
0
0
0
Mon Jun 29 2020
Computer Vision
Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks
0
0
0