基于GAN和MS-ResNet的房颤自动检测模型

doi:10.3969/j.issn.0255-8297.2024.01.002

应用科学学报 ›› 2024, Vol. 42 ›› Issue (1): 15-26.doi: 10.3969/j.issn.0255-8297.2024.01.002

基于GAN和MS-ResNet的房颤自动检测模型

秦静¹, 韩悦², 王立永², 季长清^2,3, 刘璐⁴, 汪祖民²

1. 大连大学软件工程学院, 辽宁大连 116622;
2. 大连大学信息工程学院, 辽宁大连 116622;
3. 大连大学物理科学与技术学院, 辽宁大连 116622;
4. 大连大学附属中山医院, 辽宁大连 116001

收稿日期:2023-06-29 出版日期:2024-01-30 发布日期:2024-02-02
通信作者: 秦静,副教授,研究方向为智慧医疗。E-mail:qinjing@dlu.edu.cn E-mail:qinjing@dlu.edu.cn
基金资助:
国家自然科学基金青年科学基金（No.62002038）资助

An Automatic Atrial Fibrillation Detection Model Based on GAN and MS-ResNet

QIN Jing¹, HAN Yue², WANG Liyong², JI Changqing^2,3, LIU Lu⁴, WANG Zumin²

1. College of Software Engineering, Dalian University, Dalian 116622, Liaoning, China;
2. College of Information Engineering, Dalian University, Dalian 116622, Liaoning, China;
3. College of Physical Science and Technology, Dalian University, Dalian 116622, Liaoning, China;
4. Zhongshan Hospital Affiliated to Dalian University, Dalian 116001, Liaoning, China

Received:2023-06-29 Online:2024-01-30 Published:2024-02-02

摘要/Abstract

摘要： 房颤是一种常见的心律失常疾病，针对现有研究工作大多依赖于单尺度信号段而忽略了不同尺度下潜在的互补信息和数据不平衡问题导致诊断性能下降的问题，提出了一种新颖的基于生成对抗网络（generative adversarial network,GAN）和多尺度残差网络（multiscaleresidual net,MS-ResNet）的房颤自动检测模型，该网络使用GAN合成具有高形态相似性的单导联心电数据来解决数据的隐私和不平衡问题。同时，设计了MS-ResNet特征提取策略，从不同尺度提取不同大小信号段的特征，从而有效地捕捉P波消失和RR间期不规则特征。该模型联合这两种策略不仅为房颤自动检测生成高质量心电图（electrocardiogram,ECG）数据，还可以利用多尺度网格提取不同波之间的时序特征。在PhysioNet Challenge2017公开ECG数据集上以及平衡后的数据集上评估了MS-ResNet的性能，并将其与现有的房颤分类模型进行了比较。实验结果表明，MS-ResNet在平衡后的数据集上平均F1值和精确率分别达到0.914 1和91.56%，与不平衡数据集相比，F1提高了4.5%，精确率提高了3.5%。

关键词: 心电图, 房颤, 生成对抗网络, 多尺度, 自动检测

Abstract: Atrial fibrillation (AF) is a common cardiac arrhythmia. However, existing research often relies on single-scale signal segments and overlooks potential complementary information at different scales as well as data imbalance issues, leading to decreased diagnostic performance. This paper proposes a novel AF automatic detection model based on generative adversarial network (GAN) and residual multi-scale network. The model utilizes GAN to synthesize single-lead ECG data with high morphological similarity, hence addressing data privacy and imbalance issues. A multi-scale residual network (MS-ResNet) feature extraction strategy was designed to extract the features of signal segments of different sizes from various scales, so as to effectively capture the features of P wave disappearance and RR interval irregularity. The model combines these two strategies not only to generate high-quality ECG (electrocardiogram) data for the automatic AF detection but also to extract temporal features between different waves using multi-scale grids. The performance of MS-ResNet is evaluated on the PhysioNet Challenge 2017 public ECG dataset and a balanced dataset, comparing it with other existing atrial fibrillation classification models. Experimental results show that the average F1 value and accuracy rate of MS-ResNet on the balanced dataset are 0.914 1 and 91.56%, respectively. Compared with the unbalanced dataset, F1 increases by 4.5%, and the accuracy rate increases by 3.5%.

Key words: electrocardiogram (ECG), atrial fibrillation (AF), generative adversarial network (GAN), multi-scale, automatic detection

中图分类号:

TP391.1

秦静, 韩悦, 王立永, 季长清, 刘璐, 汪祖民. 基于GAN和MS-ResNet的房颤自动检测模型[J]. 应用科学学报, 2024, 42(1): 15-26.

QIN Jing, HAN Yue, WANG Liyong, JI Changqing, LIU Lu, WANG Zumin. An Automatic Atrial Fibrillation Detection Model Based on GAN and MS-ResNet[J]. Journal of Applied Sciences, 2024, 42(1): 15-26.

参考文献

[1] Ma F Y, Zhang J Y, Liang W, et al. Automated classification of atrial fibrillation using artificial neural network for wearable devices [J]. Mathematical Problems in Engineering, 2020, 12: 1-6.
[2] Ciaccio E J, Biviano, A B,Wan E Y, et al. Development of an automaton model of rotational activity driving atrial fibrillation [J]. Computers in Biology and Medicine, 2017, 83: 166-181.
[3] Kishore A, Vail A, Majid A, et al. Detection of atrial fibrillation after ischemic stroke or transient ischemic attack: a systematic review and meta-analysis [J]. Stroke, 2014, 45(2): 520-526.
[4] Buda M, Maki A, Mazurowski M A. A systematic study of the class imbalance problem in convolutional neural networks [J]. Neural Networks, 2018, 106: 249-259.
[5] Falk R H. Atrial fibrillation [J]. New England Journal of Medicine, 2001, 344(14): 1067-1078.
[6] Bahrami M, Forouzanfar M. Sleep apnea detection from single-lead ECG: a comprehensive analysis of machine learning and deep learning algorithms [J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-11.
[7] Chen S W, Wang S L, Qi X Z, et al. Review of ECG detection and classification based on deep learning: coherent taxonomy, motivation, open challenges and recommendations [J]. Biomedical Signal Processing and Control, 2022, 74: 103493.
[8] Sobahi N, Sengur A, Tan R S, et al. Attention-based 3D CNN with residual connections for efficient ECG-based COVID-19 detection [J]. Computers in Biology and Medicine, 2022, 143: 105335.
[9] Rai H M, Chatterjee K. Hybrid CNN-LSTM deep learning model and ensemble technique for automatic detection of myocardial infarction using big ECG data [J]. Applied Intelligence, 2022, 52(5): 5366-5384.
[10] Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks [DB/OL]. 2015[2023-06-29]. https:// arxiv.org/abs/1511.06434.
[11] Li W Q, Tang Y M, Yu K M, et al. SLC-GAN: an automated myocardial infarction detection model based on generative adversarial networks and convolutional neural networks with singlelead electrocardiogram synthesis [J]. Information Sciences, 2022, 589: 738-750.
[12] Rafi T H, Ko Y W. HeartNet: self multihead attention mechanism via convolutional network with adversarial data synthesis for ECG-based arrhythmia classification [J]. IEEE Access, 2022, 10: 100501-100512.
[13] Ma K, Zhan C A, Yang F. Multi-classification of arrhythmias using ResNet with CBAM on CWGAN-GP augmented ECG Gramian angular summation field [J]. Biomedical Signal Processing and Control, 2022, 77, 103684.
[14] Wang R, Yao Q, Fan X, et al. Multi-class arrhythmia detection based on neural network with multi-stage features fusion [C]//2019 IEEE International Conference on Systems, 2019: 4082-4087.
[15] Fan X M, Yao Q H, Cai Y P, et al. Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ECG recordings [J]. IEEE Journal of Biomedical and Health Informatics, 2018, 22(6): 1744-1753.
[16] Prabhakararao E, Dandapat S. Multiscale convolutional neural network for detecting paroxysmal atrial fibrillation from single lead ECG signals [C]//IEEE Applied Signal Processing Conference (ASPCON), 2020: 339-343.
[17] Prabhakararao E, Dandapat S. Multi-scale convolutional neural network ensemble for multiclass arrhythmia classification [J]. IEEE Journal of Biomedical and Health Informatics, 2021, 26(8): 3802-3812.
[18] Gao Y, Wang H, Liu Z. An end-to-end atrial fibrillation detection by a novel residualbased temporal attention convolutional neural network with exponential nonlinearity loss [J]. Knowledge-Based Systems, 2020, 212(1): 106589.
[19] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting [J]. Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
[20] Lourenço A, Silva H, Carreiras C, et al. Outlier detection in non-intrusive ECG biometric system [C]//International Conference Image Analysis and Recognition. Springer, 2013: 43-52.
[21] Clifford G D, Liu C Y, Moody B, et al. AF classification from a short single lead ECG recording: the physionet/computing in cardiology challenge 2017[C]//Computing in Cardiology (CinC), 2017: 1-4.
[22] Shark L K, Yu C. Denoising by optimal fuzzy thresholding in wavelet domain [J]. Electronics Letters, 2000, 36(6): 581-582.
[23] Wang R X, Fan J P, Li Y. Deep multi-scale fusion neural network for multi-class arrhythmia detection [J]. IEEE Journal of Biomedical and Health Informatics, 2020, 24(9): 2461-2472.
[24] Xie Q Y, Wang X R, Sun H Y, et al. ECG signal detection and classification of heart rhythm diseases based on ResNet and LSTM [J]. Advances in Mathematical Physics, 2021, 2021(4): 1-11.
[25] Rohr M, Reich C, Höhl A, et al. Exploring novel algorithms for atrial fibrillation detection by driving graduate level education in medical machine learning [J]. Physiological Measurement, 2022, 43(7): 074001.
[26] Wu Q, Sun Y F, Yan H, et al. ECG signal classification with binarized convolutional neural network [J]. Computers in Biology and Medicine, 2020, 121: 103800.

基于GAN和MS-ResNet的房颤自动检测模型

An Automatic Atrial Fibrillation Detection Model Based on GAN and MS-ResNet

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	阚亚亚, 张孙杰, 熊娟, 祖奕. 结合transformer多尺度实例交互的稀疏集目标检测[J]. 应用科学学报, 2023, 41(5): 777-788.
[2]	张春森, 朱江乐, 张学芬, 刘旭东, 史书. 融合自注意力机制与生成对抗网络的DEM空洞填充[J]. 应用科学学报, 2023, 41(5): 789-800.
[3]	曾静, 李莹, 戚小莎, 吉根林. 多层记忆增强生成对抗网络二次预测的视频异常检测方法[J]. 应用科学学报, 2023, 41(1): 80-94.
[4]	聂江华, 肖永生, 黄丽贞, 贺丰收. 基于时频分析与深度学习的高分辨距离像雷达目标识别[J]. 应用科学学报, 2022, 40(6): 973-983.
[5]	刘硕, 瞿崇晓, 祝中科, 张福俊, 范长军. 基于MSR和AMSR的红外融合增强算法[J]. 应用科学学报, 2022, 40(3): 423-433.
[6]	雷前慧, 潘丽丽, 邵伟志, 胡海鹏, 黄瑶. 基于三重注意力机制的新冠肺炎病灶分割模型[J]. 应用科学学报, 2022, 40(1): 105-115.
[7]	刘星宏, 王英, 王鑫, 兰书梅. 基于生成对抗网络的异质信息网络表征学习[J]. 应用科学学报, 2021, 39(4): 532-544.
[8]	马飞虎, 徐发东, 孙翠羽. 面向对象的无人机影像地物分类[J]. 应用科学学报, 2021, 39(2): 312-320.
[9]	朱翌明, 陈帆, 和红杰, 陈鸿佑. 基于秘密信息驱动的正交GAN信息隐藏模型[J]. 应用科学学报, 2019, 37(5): 721-732.
[10]	李欣, 唐文莉, 杨博. 利用深度残差网络的高分遥感影像语义分割[J]. 应用科学学报, 2019, 37(2): 282-290.
[11]	冯发杰, 吏军平, 丁亚洲, 朱坤, 崔卫红. 基于多尺度视觉特征组合的高分遥感影像目标检测[J]. 应用科学学报, 2018, 36(3): 471-484.
[12]	刘明明, 张敏情, 刘佳, 高培贤, 张英男. 基于生成对抗网络的无载体信息隐藏[J]. 应用科学学报, 2018, 36(2): 371-382.
[13]	樊敬敬, 张华, 郝明. 面向对象的机载LiDAR数据建筑物提取[J]. 应用科学学报, 2016, 34(1): 84-94.
[14]	王国力，周伟，丛瑜，关键. 多尺度自卷积方差显著性SAR图像目标检测[J]. 应用科学学报, 2013, 31(6): 607-6.
[15]	朱俊杰1,2，杜小平1,2，范湘涛1,2，郭华东1,2. GIS数据约束的海岸带SAR图像多尺度分割[J]. 应用科学学报, 2013, 31(1): 79-83.