Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Two-stage Unsupervised Learning Method for Affine and Deformable Registration

Abstract: 

Conventional medical image registration relies on time-consuming iterative optimization. We propose a two-stage unsupervised learning method for 3D medical image registration. In the first stage, we learn a global image-wise affine map by a deep network. In the second stage, we learn a local voxel-wise deformation vector field by an encoder-decoder architecture. The final registered image is acquired by applying the local deformation field to the moved image of the first stage. The two networks are trained in an unsupervised manner by maximizing global and local normalized cross-correlations between the fixed image and moved images in the two stages respectively. The well-trained networks can be directly adopted to register images through forward propagation without iteration. We do not need ground-truth in training stage and aligning images in preprocess step. Experiments on four brain MRI datasets demonstrate that the proposed approach outperforms several state-of-the-art methods in terms of accuracy and efficiency.

up
0 users have voted:

Paper Details

Authors:
Dongdong Gu, Guocai Liu, Juanxiu Tian, Qi Zhan
Submitted On:
12 September 2019 - 1:32am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Dongdong Gu
Paper Code:
1128
Document Year:
2019
Cite

Document Files

poster_icip_reg.pdf

(6)

Subscribe

[1] Dongdong Gu, Guocai Liu, Juanxiu Tian, Qi Zhan, "Two-stage Unsupervised Learning Method for Affine and Deformable Registration", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4600. Accessed: Sep. 15, 2019.
@article{4600-19,
url = {http://sigport.org/4600},
author = {Dongdong Gu; Guocai Liu; Juanxiu Tian; Qi Zhan },
publisher = {IEEE SigPort},
title = {Two-stage Unsupervised Learning Method for Affine and Deformable Registration},
year = {2019} }
TY - EJOUR
T1 - Two-stage Unsupervised Learning Method for Affine and Deformable Registration
AU - Dongdong Gu; Guocai Liu; Juanxiu Tian; Qi Zhan
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4600
ER -
Dongdong Gu, Guocai Liu, Juanxiu Tian, Qi Zhan. (2019). Two-stage Unsupervised Learning Method for Affine and Deformable Registration. IEEE SigPort. http://sigport.org/4600
Dongdong Gu, Guocai Liu, Juanxiu Tian, Qi Zhan, 2019. Two-stage Unsupervised Learning Method for Affine and Deformable Registration. Available at: http://sigport.org/4600.
Dongdong Gu, Guocai Liu, Juanxiu Tian, Qi Zhan. (2019). "Two-stage Unsupervised Learning Method for Affine and Deformable Registration." Web.
1. Dongdong Gu, Guocai Liu, Juanxiu Tian, Qi Zhan. Two-stage Unsupervised Learning Method for Affine and Deformable Registration [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4600