Saved in:
Bibliographic Details
Main Authors: Wu, Jiong, Zhou, Shuang, Lin, Li, Wang, Xin, Tan, Wenxue
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.04244
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914783443288064
author Wu, Jiong
Zhou, Shuang
Lin, Li
Wang, Xin
Tan, Wenxue
author_facet Wu, Jiong
Zhou, Shuang
Lin, Li
Wang, Xin
Tan, Wenxue
contents Diffeomorphic image registration is a fundamental step in medical image analysis, owing to its capability to ensure the invertibility of transformations and preservation of topology. Currently, unsupervised learning-based registration techniques primarily extract features at the image level, potentially limiting their efficacy. This paper proposes a novel unsupervised learning-based fully convolutional network (FCN) framework for fast diffeomorphic image registration, emphasizing feature acquisition at the image patch level. Furthermore, a novel differential operator is introduced and integrated into the FCN architecture for parameter learning. Experiments are conducted on three distinct T1-weighted magnetic resonance imaging (T1w MRI) datasets. Comparative analyses with three state-of-the-art diffeomorphic image registration approaches including a typical conventional registration algorithm and two representative unsupervised learning-based methods, reveal that the proposed method exhibits superior performance in both registration accuracy and topology preservation.
format Preprint
id arxiv_https___arxiv_org_abs_2404_04244
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fast Diffeomorphic Image Registration using Patch based Fully Convolutional Networks
Wu, Jiong
Zhou, Shuang
Lin, Li
Wang, Xin
Tan, Wenxue
Computer Vision and Pattern Recognition
Diffeomorphic image registration is a fundamental step in medical image analysis, owing to its capability to ensure the invertibility of transformations and preservation of topology. Currently, unsupervised learning-based registration techniques primarily extract features at the image level, potentially limiting their efficacy. This paper proposes a novel unsupervised learning-based fully convolutional network (FCN) framework for fast diffeomorphic image registration, emphasizing feature acquisition at the image patch level. Furthermore, a novel differential operator is introduced and integrated into the FCN architecture for parameter learning. Experiments are conducted on three distinct T1-weighted magnetic resonance imaging (T1w MRI) datasets. Comparative analyses with three state-of-the-art diffeomorphic image registration approaches including a typical conventional registration algorithm and two representative unsupervised learning-based methods, reveal that the proposed method exhibits superior performance in both registration accuracy and topology preservation.
title Fast Diffeomorphic Image Registration using Patch based Fully Convolutional Networks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.04244