Mining fMRI Dynamics with Parcellation Prior for Brain Disease Diagnosis
2023
会议录名称IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI)
ISSN1945-7928
卷号2023-April
发表状态已发表
DOI10.1109/ISBI53787.2023.10230391
摘要To characterize atypical brain dynamics under diseases, prevalent studies investigate functional magnetic resonance imaging (fMRI). However, most of the existing analyses compress rich spatial-temporal information as the brain functional networks (BFNs) and directly investigate the whole-brain network without neurological priors about functional subnetworks. We thus propose a novel graph learning framework to mine fMRI signals with topological priors from brain parcellation for disease diagnosis. Specifically, we 1) detect diagnosis-related temporal features using a 'Transformer'for a higher-level BFN construction, and process it with a following graph convolutional network, and 2) apply an attention-based multiple instance learning strategy to emphasize the disease-affected subnetworks to further enhance the diagnosis performance and interpretability. Experiments demonstrate higher effectiveness of our method than compared methods in the diagnosis of early mild cognitive impairment. More importantly, our method is capable of localizing crucial brain subnetworks during the diagnosis, providing insights into the pathogenic source of mild cognitive impairment. © 2023 IEEE.
会议录编者/会议主办者Flywheel ; Kitware ; Siemens Healthineers ; UCLouvain
关键词Graph neural network Brain disease mild cognitive impairment Transformer Multiple instance learning
会议名称20th IEEE International Symposium on Biomedical Imaging, ISBI 2023
会议地点Cartagena, Colombia
会议日期18-21 April 2023
URL查看原文
收录类别EI
语种英语
出版者IEEE Computer Society
EI入藏号20233914806289
EI主题词Graph neural networks
EISSN1945-8452
EI分类号461.1 Biomedical Engineering ; 461.6 Medicine and Pharmacology ; 701.2 Magnetism: Basic Concepts and Phenomena ; 723.4 Artificial Intelligence ; 746 Imaging Techniques ; 921.4 Combinatorial Mathematics, Includes Graph Theory, Set Theory
原始文献类型Conference article (CA)
来源库IEEE
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/297966
专题生物医学工程学院
信息科学与技术学院_硕士生
信息科学与技术学院_PI研究组_张玉瑶组
生物医学工程学院_PI研究组_沈定刚组
生物医学工程学院_PI研究组_张寒组
作者单位
1.School of Computer Science and Technology, Shanghaitech University, China
2.School of Biomedical Engineering, Shanghaitech University, China
3.Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., China
第一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
Xiaozhao Liu,Mianxin Liu,Lang Mei,et al. Mining fMRI Dynamics with Parcellation Prior for Brain Disease Diagnosis[C]//Flywheel, Kitware, Siemens Healthineers, UCLouvain:IEEE Computer Society,2023.
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
[Xiaozhao Liu]的文章
[Mianxin Liu]的文章
[Lang Mei]的文章
百度学术
百度学术中相似的文章
[Xiaozhao Liu]的文章
[Mianxin Liu]的文章
[Lang Mei]的文章
必应学术
必应学术中相似的文章
[Xiaozhao Liu]的文章
[Mianxin Liu]的文章
[Lang Mei]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。