Convolution-GRU Based on Independent Component Analysis for fMRI Analysis with Small and Imbalanced Samples
Functional magnetic resonance imaging (fMRI) is a commonly used method of brain research. However, due to the complexity and particularity of the fMRI task, it is difficult to find enough subjects, resulting in a small and, often, imbalanced dataset. A dataset with small samples causes overfitting o...
Main Authors: | Shan Wang, Feng Duan, Mingxin Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/21/7465 |
Similar Items
-
Validation of Shared and Specific Independent Component Analysis (SSICA) for between-group comparisons in fMRI
by: Mona Maneshi, et al.
Published: (2016-09-01) -
Phase fMRI Reveals More Sparseness and Balance of Rest Brain Functional Connectivity Than Magnitude fMRI
by: Zikuan Chen, et al.
Published: (2019-03-01) -
Detection of functional networks within white matter using independent component analysis
by: Yali Huang, et al.
Published: (2020-11-01) -
Dynamic Connectivity States Estimated from Resting fMRI Identify Differences among Schizophrenia, Bipolar Disorder, and Healthy Control Subjects
by: Barnaly eRashid, et al.
Published: (2014-11-01) -
Non-linear ICA Analysis of Resting-State fMRI in Mild Cognitive Impairment
by: Xia-an Bi, et al.
Published: (2018-06-01)