Log In Sign Up

BIRNet: Brain Image Registration Using Dual-Supervised Fully Convolutional Networks

by   Jingfan Fan, et al.

In this paper, we propose a deep learning approach for image registration by predicting deformation from image appearance. Since obtaining ground-truth deformation fields for training can be challenging, we design a fully convolutional network that is subject to dual-guidance: (1) Coarse guidance using deformation fields obtained by an existing registration method; and (2) Fine guidance using image similarity. The latter guidance helps avoid overly relying on the supervision from the training deformation fields, which could be inaccurate. For effective training, we further improve the deep convolutional network with gap filling, hierarchical loss, and multi-source strategies. Experiments on a variety of datasets show promising registration accuracy and efficiency compared with state-of-the-art methods.


page 5

page 6

page 9

page 10

page 12

page 13

page 15

page 16


An Auto-Context Deformable Registration Network for Infant Brain MRI

Deformable image registration is fundamental to longitudinal and populat...

Unsupervised Multimodal Image Registration with Adaptative Gradient Guidance

Multimodal image registration (MIR) is a fundamental procedure in many i...

Constraining Volume Change in Learned Image Registration for Lung CTs

Deep-learning-based registration methods emerged as a fast alternative t...

Dual-Stream Pyramid Registration Network

We propose a Dual-Stream Pyramid Registration Network (referred as Dual-...

IGCN: Image-to-graph Convolutional Network for 2D/3D Deformable Registration

Organ shape reconstruction based on a single-projection image during tre...

Fast Predictive Image Registration

We present a method to predict image deformations based on patch-wise im...