《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (1): 310-315.DOI: 10.11772/j.issn.1001-9081.2021010132

• 前沿与综合应用 • 上一篇    

3DPCANet在阿尔茨海默症功能磁共振成像图像分类中的应用

贾洪飞, 刘茜, 王瑜(), 肖洪兵, 邢素霞   

  1. 北京工商大学 人工智能学院,北京 100048
  • 收稿日期:2021-01-25 修回日期:2020-05-31 接受日期:2020-06-10 发布日期:2021-07-14 出版日期:2022-01-10
  • 通讯作者: 王瑜
  • 作者简介:贾洪飞(1997—),男,吉林通化人,硕士研究生,主要研究方向:图像处理、模式识别
    刘茜(1996—),女,北京人,硕士研究生,主要研究方向:图像处理、模式识别
    王瑜(1977—),女,北京人,教授,博士生导师,博士,CCF会员,主要研究方向:图像处理、模式识别
    肖洪兵(1968—),男,北京人,副教授,博士,主要研究方向:图像处理、模式识别
    邢素霞(1975—),女,北京人,副教授,博士,主要研究方向:图像处理、模式识别。
  • 基金资助:
    国家自然科学基金资助项目(61671028);北京市自然科学基金-北京市教育委员会科技计划重点项目(KZ202110011015)

Application of 3DPCANet in image classification of functional magnetic resonance imaging for Alzheimer’s disease

Hongfei JIA, Xi LIU, Yu WANG(), Hongbing XIAO, Suxia XING   

  1. School of Artificial Intelligence,Beijing Technology and Business University,Beijing 100048,China
  • Received:2021-01-25 Revised:2020-05-31 Accepted:2020-06-10 Online:2021-07-14 Published:2022-01-10
  • Contact: Yu WANG
  • About author:JIA Hongfei, born in 1997, M. S. candidate. His research interests include image processing, pattern recognition.
    LIU Xi, born in 1996, M. S. candidate. Her research interests include image processing, pattern recognition.
    WANG Yu, born in 1977, Ph. D., professor. Her research interests include image processing, pattern recognition.
    XIAO Hongbing, born in 1968, Ph. D., associate professor. His research interests include image processing, pattern recognition.
    XING Suxia, born in 1975, Ph. D., associate professor. Her research interests include image processing, pattern recognition.
  • Supported by:
    National Natural Science Foundation of China(61671028);Beijing Municipal Natural Science Foundation — Key Project of Science and Technology Plan of Beijing Municipal Education Commission(KZ202110011015)

摘要:

阿尔茨海默症(AD)是一种起病隐匿的进行性神经退行性疾病,会使患者的大脑脑区结构发生改变。为辅助医生对AD患者的病情做出正确判断,提出了一种改进的三维主成分分析网络(3DPCANet)模型,并结合被试者全脑均值低频波动振幅(mALFF)图像来对AD进行分类。首先,对功能磁共振成像(fMRI)数据进行预处理,计算出全脑mALFF图像;然后,利用改进的3DPCANet深度学习模型进行特征提取;最后,使用支持向量机(SVM)对不同阶段的AD患者的特征进行分类。实验结果显示,所提模型简单,鲁棒性好,且其在主观记忆衰退(SMD)与AD、SMD与晚期轻度认知障碍(LMCI)以及LMCI与AD上的分类准确率分别达到了92.42%、91.80%和89.33%,验证了提出方法的有效性和可行性。

关键词: 阿尔茨海默症, 功能磁共振成像, 3DPCANet, 支持向量机, 均值低频波动振幅

Abstract:

Alzheimer’s Disease (AD) is a progressive neurodegenerative disease with hidden causes, and can result in structural changes of patients’ brain regions. For assisting the doctors to make correct judgment on the condition of AD patients, an improved Three-Dimensional Principal Component Analysis Network (3DPCANet) model was proposed to classify AD by combining the mean Amplitude of Low-Frequency Fluctuation (mALFF) image of the whole brain of the subject. Firstly, functional Magnetic Resonance Imaging (fMRI) data were preprocessed, and the mALFF image of the whole brain was calculated. Then, the improved 3DPCANet deep learning model was used for feature extraction. Finally, Support Vector Machine (SVM) was used to classify features of AD patients with different stages. Experimental results show that the proposed model is simple and robust, and has the classification accuracies on Subjective Memory Decline (SMD) vs. AD, SMD vs. Late Mild Cognitive Impairment (LMCI), and LMCI vs. AD reached 92.42%, 91.80% and 89.33% respectively, which verifies the effectiveness and feasibility of the proposed method.

Key words: Alzheimer’s Disease (AD), functional Magnetic Resonance Imaging (fMRI), 3DPCANet, Support Vector Machine (SVM), mean Amplitude of Low-Frequency Fluctuation (mALFF)

中图分类号: