CCPortal
DOI10.1073/pnas.2021852118
Functional connectome fingerprinting using shallow feedforward neural networks
Sarar G.; Rao B.; Liu T.
发表日期2021
ISSN00278424
卷号118期号:15
英文摘要Although individual subjects can be identified with high accuracy using correlation matrices computed from resting-state functional MRI (rsfMRI) data, the performance significantly degrades as the scan duration is decreased. Recurrent neural networks can achieve high accuracy with short-duration (72 s) data segments but are designed to use temporal features not present in the correlation matrices. Here we show that shallow feedforward neural networks that rely solely on the information in rsfMRI correlation matrices can achieve state-of-the-art identification accuracies (≥ 99.5%) with data segments as short as 20 s and across a range of input data size combinations when the total number of data points (number of regions × number of time points) is on the order of 10,000. © 2021 National Academy of Sciences. All rights reserved.
英文关键词Connectome; Fingerprinting; FMRI; Neural network
语种英语
scopus关键词article; connectome; controlled study; feed forward neural network; functional magnetic resonance imaging; functional magnetic resonance imaging
来源期刊Proceedings of the National Academy of Sciences of the United States of America
文献类型期刊论文
条目标识符http://gcip.llas.ac.cn/handle/2XKMVOVA/179936
作者单位Center for Functional MRI, University of California San Diego, San Diego, CA 92093, United States; Department of Electrical and Computer Engineering, University of California San Diego, San Diego, CA 92093, United States; Department of Radiology, University of California San Diego, San Diego, CA 92093, United States; Department of Psychiatry, University of California San Diego, San Diego, CA 92093, United States
推荐引用方式
GB/T 7714
Sarar G.,Rao B.,Liu T.. Functional connectome fingerprinting using shallow feedforward neural networks[J],2021,118(15).
APA Sarar G.,Rao B.,&Liu T..(2021).Functional connectome fingerprinting using shallow feedforward neural networks.Proceedings of the National Academy of Sciences of the United States of America,118(15).
MLA Sarar G.,et al."Functional connectome fingerprinting using shallow feedforward neural networks".Proceedings of the National Academy of Sciences of the United States of America 118.15(2021).
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Sarar G.]的文章
[Rao B.]的文章
[Liu T.]的文章
百度学术
百度学术中相似的文章
[Sarar G.]的文章
[Rao B.]的文章
[Liu T.]的文章
必应学术
必应学术中相似的文章
[Sarar G.]的文章
[Rao B.]的文章
[Liu T.]的文章
相关权益政策
暂无数据
收藏/分享

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。