Elastic Registration of Medical Images With GANs

05/07/2018
by   Dwarikanath Mahapatra, et al.
0

Conventional approaches to image registration consist of time consuming iterative methods. Most current deep learning (DL) based registration methods extract deep features to use in an iterative setting. We propose an end-to-end DL method for registering multimodal images. Our approach uses generative adversarial networks (GANs) that eliminates the need for time consuming iterative methods, and directly generates the registered image with the deformation field. Appropriate constraints in the GAN cost function produce accurately registered images in less than a second. Experiments demonstrate their accuracy for multimodal retinal and cardiac MR image registration.

READ FULL TEXT
research
03/25/2019

Combining Transfer Learning And Segmentation Information with GANs for Training Data Independent Image Registration

Registration is an important task in automated medical image analysis. A...
research
10/18/2019

Generative Adversarial Networks And Domain Adaptation For Training Data Independent Image Registration

Medical image registration is an important task in automated analysis of...
research
04/24/2022

Deep Learning for Medical Image Registration: A Comprehensive Review

Image registration is a critical component in the applications of variou...
research
11/12/2020

Unimodal Cyclic Regularization for Training Multimodal Image Registration Networks

The loss function of an unsupervised multimodal image registration frame...
research
06/06/2022

Bayesian intrinsic groupwise registration via explicit hierarchical disentanglement

Previous methods on multimodal groupwise registration typically require ...
research
07/26/2019

Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images

Segmenting coronary arteries is challenging, as classic unsupervised met...
research
09/26/2021

Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration

Deterministic approaches using iterative optimisation have been historic...

Please sign up or login with your details

Forgot password? Click here to reset