Name
Abstract | ||
|---|---|---|
Deep-learning frameworks have been widely used in deformable image registration(DIR), which is a fun-damental step in medical image analysis. In traditional deep-learning-based DIR methods, pairwise reg-istration is conducted for each image, cooperated with a dual-input structure. They only considered that the registered images need to be as similar as possible to the target image, while ignored that all reg-istered images to the same target image should have similar appearance too. Therefore, in this paper we add the deformation constraints between different registered images to the registration network in order to enhance the appearance consistency of the registered images and improve the registration accu-racy. Specifically, a Triple-Input-Unsupervised neural Network (TIUNet) is proposed to register two source images to a common target image at the same time. Then, a novel deformation-strengthened loss is de-signed to simulate the deformation constraint between the two warped source images. Finally, the defor-mation constraints between the source images and the target image are jointly optimized to obtain the deformation field model. The experimental results on the available tissue segmentation database demon-strate that our proposed TIUNet method shows a superior performance of deformation field model over several other advanced deformable image registration algorithms. Moreover, benefited from the triple-input structure, our proposed TIUNet method could expand the available training sets naturally and is suitable for the registration task with fewer training data. (c) 2021 Elsevier B.V. All rights reserved. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1016/j.patrec.2021.08.032 | PATTERN RECOGNITION LETTERS |
Keywords | DocType | Volume |
Image registration, Triple-input structure, Convolutional neural networks, Deformation-strengthen loss | Journal | 151 |
ISSN | Citations | PageRank |
0167-8655 | 0 | 0.34 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lei Qu | 1 | 1 | 1.03 |
| Wan Wan | 2 | 0 | 0.34 |
| Kaixuan Guo | 3 | 0 | 0.34 |
| Yu Liu | 4 | 492 | 30.80 |
| Jun Tang | 5 | 1 | 2.38 |
| Xiaolei Li | 6 | 1 | 0.69 |
| Jun Wu | 7 | 0 | 0.34 |