期刊
IEEE SIGNAL PROCESSING MAGAZINE
卷 39, 期 2, 页码 87-98出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/MSP.2021.3128348
关键词
Neuroimaging; Deep learning; Sensitivity and specificity; Data models; Reliability; Fuels; Task analysis
资金
- National Institutes of Health [R01EB005846, R01MH117107, R01GM109068, R01MH104680, R01MH107354, R56MH124925]
- National Science Foundation [1539067, 2112455]
- Natural Science Foundation of China [82022035, 61773380, 12090021]
This article discusses the application of deep learning in four important categories in the field of neuroimaging, highlighting recent progress and challenges in each category. It also provides guidelines for using deep learning in neuroimaging data and explores the future directions of deep learning in clinical applications.
Deep learning (DL) has been extremely successful when applied to the analysis of natural images. By contrast, analyzing neuroimaging data presents some unique challenges, including higher dimensionality, smaller sample sizes, multiple heterogeneous modalities, and a limited ground truth. In this article, we discuss DL methods in the context of four diverse and important categories in the neuroimaging field: classification/prediction, dynamic activity/connectivity, multimodal fusion, and interpretation/visualization. We highlight recent progress in each of these categories, discuss the benefits of combining data characteristics and model architectures, and derive guidelines for the use of DL in neuroimaging data. For each category, we also assess promising applications and major challenges to overcome. Finally, we discuss future directions of neuroimaging DL for clinical applications, a topic of great interest, touching on all four categories.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据