基于DenseNet的心电数据自动诊断算法  

A DenseNet-based diagnosis algorithm for automated diagnosis using clinical ECG data

作　　者：赖杰伟 陈韵岱[3] 韩宝石[3] 季磊[3] 石亚君[3] 黄志聪 阳维[1,2] 冯前进 LAI Jiewei;CHEN Yundai;HAN Baoshi;JI Lei;SHI Yajun;HUANG Zhicong;YANG Wei;FENG Qianjin(School of Biomedical Engineering, Guangzhou 510515, China;Guangdong Provincial Key Laboratory of Medical Image Processing, Southern MedicalUniversity, Guangzhou 510515, China;Department of Cardiology, Chinese PLA General Hospital, Beijing 100853,China;Cardiocloud Medical Technology (Beijing) Co., Ltd., Beijing 100094, China)

机构地区：[1]南方医科大学生物医学工程学院,广东广州510515 [2]广东省医学图像处理重点实验室,广东广州510515 [3]中国人民解放军总医院心血管内科,北京100853 [4]心韵恒安医疗科技(北京)有限公司,北京100094

出　　处：《南方医科大学学报》2019年第1期69-75,共7页Journal of Southern Medical University

基　　金：国家重点研发计划(2018YFC2001203);国家自然科学基金联合基金重点支持项目(U1501256);广东省应用型科技研发专项(2015B010131011)

摘　　要：目的使用卷积网络训练多导联心电图数据,并将新的心电数据准确地分类,为医生提供可靠的辅助诊断信息。方法先用带通滤波器对数据进行预处理,使用信号分帧的方式调整不同长度的数据处于同样的大小,便于网络的训练测试;同时采用增加样本的方法扩充数据整体,增加异常样本的检出率;针对不同导联的差异性使用深度可分离卷积更有针对性地提取不同通道的特征。使用基于DenseNet的分类模型对多个标签分别训练二分类器,完成多标签分类任务。结果对数据的正异常识别准确率可以达到80.13%,灵敏度,特异度和F1分别为80.38%,79.91%和79.35%。结论本文提出的模型能快速并有效地对心电数据进行预测,在GPU上单个数据的运行时间约在33.59 ms,实时预测结果能满足应用需求。Objective To train convolutional networks using multi-lead ECG data and classify new data accurately to provide reliable information for clinical diagnosis. Methods The data were pre-processed with a bandpass filter, and signal framing was adopted to adjust the data of different lengths to the same size to facilitate network training and prediction. The dataset was expanded by increasing the sample size to improve the detection rate of abnormal samples. A depth-wise separable convolution structure was used for more specific feature extraction for different channels of twelve-lead ECG data. We trained the two classifiers for each label using the improved DenseNet to classify different labels. Results The propose model showed an accuracy of 80.13% for distinguishing between normal and abnormal ECG with a sensitivity of 80.38%, a specificity of 79.91% and a F1 score of 79.35%. Conclusion The model proposed herein can rapidly and effectively classify the ECG data. The running time of a single dataset on GPU is 33.59 ms, which allows real-time prediction to meet the clinical requirements.

关 键 词：心电预处理 信号分帧 深度可分离卷积 密集连接型卷积网络 

分 类 号：R540.41[医药卫生—心血管疾病]