基于小样本功能磁共振数据的偏头痛时序特征分类研究  

Research on migraine time-series features classification based on small-sample functional magnetic resonance imaging data

作　　者：孙昂 陈宁[2] 何俐[2] 张俊然[1] SUN Ang;CHEN Ning;HE Li;ZHANG Junran(College of Electrical Engineering,Sichuan University,Chengdu 610065,P.R.China;Department of Neurology,West China Hospital of Sichuan University,Chengdu 610041,P.R.China)

机构地区：[1]四川大学、电气工程学院,成都610065 [2]四川大学华西医院、神经内科,成都610041

出　　处：《生物医学工程学杂志》2023年第1期110-117,共8页Journal of Biomedical Engineering

基　　金：国家自然科学基金项目(81500959);四川大学华西医院1.3.5卓越学科项目(ZYJC21041);成都市科技计划项目(2021-YF05-D0916-SN);德阳科技局“揭榜挂帅”项目(2021JBJZ007)。

摘　　要：提取偏头痛患者等的神经影像特征并进行识别模型的设计对相关疾病的辅助诊断具有重要意义。相较于常用的影像特征,本研究直接采用时间序列信号表征偏头痛患者组和健康对照组的大脑功能状态,可有效利用时间信息并减小分类模型训练计算量。首先,本研究针对小样本群体运用组水平独立成分分析和字典学习划分不同脑区后,提取区域平均时间序列信号;其次,将提取的时间序列平均划分成多个子时间序列,以扩充模型输入样本;最后,使用双向长短期记忆网络对时间序列建模,学习每个时间序列内部的前后时序信息来刻画周期性大脑状态变化以提高偏头痛的诊断准确率。研究结果显示,偏头痛患者组与健康对照组的分类准确率为96.94%、曲线下面积为0.98,且计算时间相对较短。实验表明,本文方法具有较强的适用性,时序特征提取和双向长短期记忆网络模型结合能较好地用于偏头痛的分类诊断;这项工作为基于小样本的神经影像数据的轻量化诊断模型提供了新的思路,并有助于相关疾病神经鉴别机制的探索。The extraction of neuroimaging features of migraine patients and the design of identification models are of great significance for the auxiliary diagnosis of related diseases. Compared with the commonly used image features,this study directly uses time-series signals to characterize the functional state of the brain in migraine patients and healthy controls, which can effectively utilize the temporal information and reduce the computational effort of classification model training. Firstly, Group Independent Component Analysis and Dictionary Learning were used to segment different brain areas for small-sample groups and then the regional average time-series signals were extracted. Next, the extracted time series were divided equally into multiple subseries to expand the model input sample. Finally, the time series were modeled using a bi-directional long-short term memory network to learn the pre-and-post temporal information within each time series to characterize the periodic brain state changes to improve the diagnostic accuracy of migraine. The results showed that the classification accuracy of migraine patients and healthy controls was 96.94%, the area under the curve was 0.98, and the computation time was relatively shorter. The experiments indicate that the method in this paper has strong applicability, and the combination of time-series feature extraction and bi-directional long-short term memory network model can be better used for the classification and diagnosis of migraine. This work provides a new idea for the lightweight diagnostic model based on small-sample neuroimaging data, and contributes to the exploration of the neural discrimination mechanism of related diseases.

关 键 词：偏头痛 时间序列 小样本 字典学习 双向长短期记忆网络 

分 类 号：R445.2[医药卫生—影像医学与核医学] R747.2[医药卫生—诊断学]