返回
CycleMorph: Cycle consistent unsupervised deformable image registration
DOI:10.1016/j.media.2021.102036.png)
摘要
En 中文
Image registration is a fundamental task in medical image analysis. Recently, many deep learning based image registration methods have been extensively investigated due to their comparable performance with the state-of-the-art classical approaches despite the ultra-fast computational time. However, the existing deep learning methods still have limitations in the preservation of original topology during the deformation with registration vector fields. To address this issues, here we present a cycle-consistent de formable image registration, dubbed CycleMorph. The cycle consistency enhances image registration performance by providing an implicit regularization to preserve topology during the deformation. The proposed method is so flexible that it can be applied for both 2D and 3D registration problems for various applications, and can be easily extended to multi-scale implementation to deal with the memory issues in large volume registration. Experimental results on various datasets from medical and non-medical applications demonstrate that the proposed method provides effective and accurate registration on diverse image pairs within a few seconds. Qualitative and quantitative evaluations on deformation fields also verify the effectiveness of the cycle consistency of the proposed method. (c) 2021 Elsevier B.V. All rights reserved.
Keyword:
Cycle consistency
Image registration
Deep learning
Unsupervised learning
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
11.8
论文数:
3.9K
被引数:
2.4W
机构
引用论文
Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain具有互相关的对称微分图像配准: 评估老年人和神经退行性脑的自动标记
MEDICAL IMAGE ANALYSIS
IF11.8
VoxelMorph: A Learning Framework for Deformable Medical Image RegistrationVoxelMorph: 可变形医学图像配准的学习框架
‘Ray Ruby’ Grapefruit Affected by Huanglongbing I. Planting Density and Soil Nutrient Management
HortScience
IF0

