吉林大学学报(信息科学版) ›› 2024, Vol. 42 ›› Issue (1): 45-50.

• • 上一篇    下一篇

认知障碍脑功能磁共振图像的孪生网络特征工程算法

周丰丰, 王 倩, 董广宇   

  1. 吉林大学 计算机科学与技术学院, 长春 130012
  • 收稿日期:2022-02-23 出版日期:2024-01-29 发布日期:2024-02-04
  • 作者简介: 周丰丰(1977— ), 男, 江苏盐城人, 吉林大学教授, 博士生导师, 主要从事生物医学大数据研究, (Tel)86-431-85166024 (E-mail)FengfengZhou@ gmail. com
  • 基金资助:
    国家自然科学基金资助项目(62072212; U19A2061); 吉林省中青年科技创新创业卓越人才(团队)基金(创新类)资助项目 (20210509055RQ); 吉林省大数据智能计算实验室基金资助项目(20180622002JC) 

Siamese Network Based Feature Engineering Algorithm for Encephalopathy fMRI Images 

ZHOU Fengfeng, WANG Qian, DONG Guangyu    

  1. College of Computer Science and Technology, Jilin University, Changchun 130012, China
  • Received:2022-02-23 Online:2024-01-29 Published:2024-02-04

摘要: 功能磁共振成像技术(fMRI: functional Magnetic Resonance Imaging)是一种高效的脑成像技术研究方法, 为减少 fMRI 数据的冗余, 将其转换为更具分类潜力的特征, 提出一个基于孪生网络( SANet: Siamese Network) 的特征构造算法 SANet, 将多个扫描点下的脑区信息类比为图, 应用改进的 AlexNet 网络进行特征构造, 并结合 增量特征选择策略达到优化分类的目的。 通过实验对比 3 种不同网络结构和 4 种分类器对 SANet 模型的影响, 并进行消融实验, 验证增量特征选择算法对 SANet 构造特征的分类效果。 实验表明, SANet 模型能对 fMRI 数据进行有效构造, 且提高原始特征的分类性能。

关键词: 功能磁共振成像, 特征构造, SANet 模型, 孪生网络, 增量特征选择

Abstract: fMRI ( functional Magnetic Resonance imaging) is an efficient research method for brain imaging technique. In order to reduce the redundancy of the fMRI data and transform the fMRI data to the constructed features with more classification potential, a feature construction method based on the siamese network named as SANet(Siamese Network) is proposed. It engineered the brain regions features under multiple scanning points of an fMRI image. The improved AlexNet is used for feature engineering, and the incremental feature selection strategy is used to find the best feature subset for the encephalopathy prediction task. The effects of three different network structures and four classifiers on the SANet model are evaluated for their prediction efficiencies, and the ablation experiment is conducted to verify the classification effect of the incremental feature selection algorithm on the SANet features. The experimental data shows that the SANet model can construct features from the fMRI data effectively, and improve the classification performance of original features.

Key words:  functional magnetic resonance imaging ( fMRI), feature engineering, siamese network ( SANet) model, siamese network, incremental feature selection

中图分类号: 

  • TP399