计算机应用 ›› 2021, Vol. 41 ›› Issue (2): 590-597.DOI: 10.11772/j.issn.1001-9081.2020060897

所属专题: 前沿与综合应用

• 前沿与综合应用 • 上一篇    下一篇

使用深度学习和不同频率维度的脑功能性连接对轻微认知障碍的诊断

孔伶旭1, 吴海锋1,2, 曾玉1,2, 陆小玲1   

  1. 1. 云南民族大学 电气信息工程学院, 昆明 650500;
    2. 云南省高校智能传感网络及信息系统科技创新团队(云南民族大学), 昆明 650500
  • 收稿日期:2020-06-28 修回日期:2020-10-05 出版日期:2021-02-10 发布日期:2020-12-18
  • 通讯作者: 吴海锋
  • 作者简介:孔伶旭(1995-),男,山西运城人,硕士研究生,CCF会员,主要研究方向:深度学习、生物医学信号处理;吴海锋(1977-),男,云南昆明人,教授,博士,主要研究方向:深度学习、生物医学信号处理、信号处理;曾玉(1981-),女,云南昆明人,讲师,博士研究生,主要研究方向:深度学习;陆小玲(1995-),女,江苏无锡人,硕士研究生,CCF会员,主要研究方向:深度学习、生物医学信号处理。
  • 基金资助:
    国家自然科学基金资助项目(61762093);云南省重点应用和基础研究基金资助项目(2018FA036);云南省教育厅科学研究基金资助项目(2020Y0238);云南省高校科技创新团队。

Diagnosis of mild cognitive impairment using deep learning and brain functional connectivities with different frequency dimensions

KONG Lingxu1, WU Haifeng1,2, ZENG Yu1,2, LU Xiaoling1   

  1. 1. School of Electrical and Information Technology, Yunnan Minzu University, Kunming Yunnan 650500, China;
    2. Intelligent Senor Network&Information System Innovative Research Team in Science and Technology in University of Yunnan Province(Yunnan Minzu University), Kunming Yunnan 650500, China
  • Received:2020-06-28 Revised:2020-10-05 Online:2021-02-10 Published:2020-12-18
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61762093), the Key Application and Basic Research Fund of Yunnan Province (2018FA036), the Science Research Fund of Education Department of Yunnan Province (2020Y0238), the Program for Innovative Research Team in Science and Technology in University of Yunnan Province.

摘要: 准确诊断轻微认知障碍(MCI)对于阿尔兹海默症(AD)的预防和治疗十分关键,目前常使用深度学习和静息态功能核磁共振成像(rs-fMRI)对MCI进行辅助诊断。皮尔逊(Pearson)相关法和加窗的皮尔逊(WP)相关法能在时间维度上表示脑功能性连接(FC),但不能将不同频率维度上的信息进行分解表示。针对这一问题,提出将不同频率维度的FC系数作为现有深度学习的特征输入的方法,以提高MCI分类准确率。首先将被试的数据进行拼接后进行多通道经验模态分解(MEMD),然后通过切割求得不同频率维度上的FC系数,最后使用VGG16和长短期记忆(LSTM)网络进行测试。实验结果表明,使用所提出的FC系数时,MCI的分类准确率最高可达84.33%,相较使用传统FC系数时的准确率提高了18.33~21.00个百分点;而且不同频率维度的FC系数对MCI有着不同的分辨率。

关键词: 静息态功能核磁共振成像, 轻微认知障碍, 功能性连接, 多通道经验模态分解, 深度学习

Abstract: Accurate diagnosis of Mild Cognitive Impairment (MCI) is critical to the prevention and treatment of Alzheimer's Disease (AD). Currently, deep learning and resting-state functional Magnetic Resonance Imaging (rs-fMRI) are often used to assist the diagnosis of MCI. The commonly used Pearson correlation method and Window Pearson (WP) correlation method can represent the brain Functional Connectivity (FC) in the time dimension, but cannot decompose and represent the information in different frequency dimensions. In order to solve this problem, a new method of using FC coefficients in different frequency dimensions as the input features of the existing deep learning was proposed to improve the accuracy of MCI classification. Firstly, the data of the subjects were spliced and then subjected to Multivariate Empirical Model Decomposition (MEMD). Secondly, the FC coefficients in different frequency dimensions were obtained after segmenting. Finally, VGG16 and Long Short-Term Memory (LSTM) network were used for testing. Experimental results show that, when the proposed FC coefficients ars used, the classification accuracy of MCI can reach up to 84.33%, which is 18.33-21.00 percentage points higher than the accuracy with the use of the traditional FC coefficients. In addition, the FC coefficients of different frequency dimensions have different resolutions for MCI.

Key words: resting-state functional Magnetic Resonance Imaging (rs-fMRI), mild cognitive impairment, Functional Connectivity (FC), Multivariate Empirical Model Decomposition (MEMD), deep learning

中图分类号: