消息
×
loading..
Hierarchical Symmetric Normalization Registration Using Deformation-Inverse Network
2024
会议录名称INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI (IF:0.402[JCR-2005],0.000[5-Year])
ISSN0302-9743
卷号15002
发表状态已发表
DOI10.1007/978-3-031-72069-7_62
摘要

 Most existing deep learning-based medical image registration methods estimate a single-directional displacement field between the moving and fixed image pair, resulting in registration errors when there  are substantial differences between the to-be-registered image pairs. To solve this issue, we propose a symmetric normalization network to estimate the deformations in a bi-directional way. Specifically, our method learns two bi-directional half-way displacement fields, which warp the moving and fixed images to their mean space. Besides, a symmetric magnitude constraint is designed in the mean space to ensure precise registration. Additionally, a deformation-inverse network is employed to obtain the inverse of the displacement field, which is applied to the inference pipeline to compose the final end-to-end displacement field between the moving and fixed images. During inference, our method first estimates the two half-way displacement fields and then composes one half-way displacement field with the inverse of another half. Moreover, we adopt a multi-level strategy to hierarchically perform registration, for gradually aligning images to their mean space, thereby improving accuracy and smoothness. Experimental results on two datasets demonstrate that the proposed method improves registration performance compared with state-of-the-art algorithms. Our code is available at https://github.com/QingRui-Sha/HSyN.

会议举办国The Kingdom of Morocco
关键词Symmetric normalization registration Inverse displacement field Magnitude constraint Multi-level architecture
会议名称International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI
出版地GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
会议地点MOROCCO
会议日期OCT 06-10, 2024
URL查看原文
收录类别SCI ; CPCI-S ; EI
语种英语
资助项目National Natural Science Foundation of China["62131015","62250710165","U23A20295"] ; Shanghai Municipal Central Guided Local Science and Technology Development Fund[YDZX2023310 0001001] ; Science and Technology Commission of Shanghai Municipality (STCSM)[21010502600] ; Key R&D Program of Guangdong Province, China["2023B0303040001","2021B0101420006"] ; STI 2030-Major Projects[2022ZD0209000]
WOS研究方向Computer Science ; Neurosciences & Neurology ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Neuroimaging ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号WOS:001342225800062
出版者SPRINGER INTERNATIONAL PUBLISHING AG
EISSN1611-3349
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/452303
专题生物医学工程学院_PI研究组_孙开聪组
信息科学与技术学院_硕士生
信息科学与技术学院_博士生
生物医学工程学院_PI研究组_沈定刚组
通讯作者Cao, Xiaohuan; Shen, Dinggang
作者单位
1.School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech, Shanghai, China
2.School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China
3.Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
4.Shanghai Clinical Research and Trial Center, Shanghai, China
第一作者单位上海科技大学
通讯作者单位上海科技大学
第一作者的第一单位上海科技大学
推荐引用方式
GB/T 7714
Sha, Qingrui,Sun, Kaicong,Xu, Mingze,et al. Hierarchical Symmetric Normalization Registration Using Deformation-Inverse Network[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2024.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Sha, Qingrui]的文章
[Sun, Kaicong]的文章
[Xu, Mingze]的文章
百度学术
百度学术中相似的文章
[Sha, Qingrui]的文章
[Sun, Kaicong]的文章
[Xu, Mingze]的文章
必应学术
必应学术中相似的文章
[Sha, Qingrui]的文章
[Sun, Kaicong]的文章
[Xu, Mingze]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。