《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (5): 1403-1409.DOI: 10.11772/j.issn.1001-9081.2024050684

• 第十届中国数据挖掘会议 • 上一篇    

融合时序相关信息的脑功能网络估计与分类

杨俊1, 庞梦雪1, 乔立山1,2()   

  1. 1.聊城大学 数学科学学院,山东 聊城 252000
    2.山东建筑大学 计算机科学与技术学院,济南 250101
  • 收稿日期:2024-05-27 修回日期:2024-06-22 接受日期:2024-06-28 发布日期:2024-07-25 出版日期:2025-05-10
  • 通讯作者: 乔立山
  • 作者简介:杨俊(2000—),女,山东新泰人,硕士研究生,主要研究方向:智能医学、脑功能数据分析、机器学习
    庞梦雪(1999—),女,山东惠民人,硕士研究生,主要研究方向:智能医学、脑功能数据分析、机器学习
    乔立山(1979—),男,山东邹平人,教授,博士,CCF会员,主要研究方向:人工智能、模式识别、智能医学、脑功能数据分析、机器学习。
  • 基金资助:
    国家自然科学基金面上项目(61976110);国家自然科学基金重点项目(11931008)

Estimation and classification of brain functional networks based on temporal correlation information fusion

Jun YANG1, Mengxue PANG1, Lishan QIAO1,2()   

  1. 1.School of Mathematical Science,Liaocheng University,Liaocheng Shandong 252000,China
    2.School of Computer Science and Technology,Shandong Jianzhu University,Jinan Shandong 250101,China
  • Received:2024-05-27 Revised:2024-06-22 Accepted:2024-06-28 Online:2024-07-25 Published:2025-05-10
  • Contact: Lishan QIAO
  • About author:YANG Jun, born in 2000, M. S. candidate. Her research interests include intelligent medicine, brain functional data analysis, machine learning.
    PANG Mengxue, born in 1999, M. S. candidate. Her research interests include intelligent medicine, brain functional data analysis, machine learning.
    QIAO Lishan, born in 1979. Ph. D., professor. His research interests include artificial intelligence, pattern recognition, intelligent medicine, brain functional data analysis, machine learning.
  • Supported by:
    National Natural Science Foundation of China — General Project(61976110);National Natural Science Foundation of China — Key Project(11931008)

摘要:

脑功能网络在神经或精神类脑疾病的早期诊断中发挥着重要作用,而估计一个高质量的脑功能网络是其中最关键的问题之一。尽管目前已有众多脑功能网络估计方法,但多数仅考虑了脑区间的相关性,忽视了时间点间可能存在的依赖关系。最近的研究发现,引入潜变量编码时间点间的依赖性可以有效提高脑功能网络的判别性;但该方法仅基于相邻时间点的依赖关系,并未有效利用不相邻时间点的信息,无法全面反映脑功能网络的时序特性。因此,提出一种新的脑功能网络估计方法,通过引入相似性矩阵编码不相邻时间点间的依赖关系,旨在提高脑功能网络估计的质量;并设计了交替优化学习算法快速求解该方法的模型。为了评估所提方法的有效性,在3个公开数据集ADNI(Alzheimer's Disease Neuroimaging Initiative)、ABIDE(Autism Brain Imaging Data Exchange)和REST-MDD(REST-meta-MDD Consortium)上分别进行了轻度认知障碍、孤独症与抑郁症的识别实验,实验结果表明,基于所提方法估计的脑功能网络能够获得更优的分类性能。

关键词: 脑功能网络, 相似性矩阵, 隐变量, 静息态功能磁共振成像, 时序信息

Abstract:

Brain functional networks play a crucial role in the early diagnosis of neurological or encephaloid diseases, and the estimation of a high-quality brain functional network is one of the most critical challenges. Although numerous brain functional network estimation methods have been proposed, most of them only focus on the correlations among brain regions while ignoring potential dependencies among time points. Recent studies have found that encoding dependencies among time points can effectively improve the discriminative properties of brain functional networks; however, this method only relies on the dependencies between adjacent time points and fails to effectively utilize information from non-adjacent time points, thereby inadequately capturing the temporal characteristics of the brain functional network. To address this limitation, a new brain functional network estimation method was proposed, which introduced a similarity matrix to encode the dependencies among non-adjacent time points, aiming to improve the quality of the estimation. Additionally, an alternating optimization learning algorithm was designed to solve the model quickly. To evaluate the effectiveness of the proposed method, experiments were conducted on three public datasets — ADNI (Alzheimer's Disease Neuroimaging Initiative), ABIDE (Autism Brain Imaging Data Exchange), and REST-MDD (REST-meta-MDD Consortium) — for mild cognitive impairment, autism and depression, respectively. Experimental results demonstrate that the brain functional network estimated by the proposed method achieves superior classification performance.

Key words: brain functional network, similarity matrix, latent variable, resting-state functional Magnetic Resonance Imaging (rs-fMRI), temporal information

中图分类号: