Deep Learning Approach to Transformer-Based Arrhythmia Classification using Scalogram of Single-Lead ECG

被引:0
|
作者
Ryu, Ji Seung [1 ]
Lee, Solam [2 ,3 ]
Park, Young Jun [4 ]
Chu, Yu-Seong [1 ]
Lee, Sena [1 ]
Jang, Seunghyun [1 ]
Kang, Seung-Young [1 ]
Kang, Hyun Young [1 ]
Yang, Sejung [1 ]
机构
[1] Yonsei Univ, Dept Biomed Engn, Wonju, South Korea
[2] Yonsei Univ, Dept Prevent Med, Wonju Coll Med, Wonju, South Korea
[3] Yonsei Univ, Dept Dermatol, Wonju Coll Med, Wonju, South Korea
[4] Yonsei Univ, Wonju Severance Christian Hosp, Div Cardiol, Dept Internal Med,Wonju Coll Med, Wonju, South Korea
基金
新加坡国家研究基金会;
关键词
Arrhythmia; electrocardiography; scalogram; deep learning; transformer; vision transformer;
D O I
10.1117/12.2648239
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Arrhythmia is the heartbeat losing its regularity or deviating from its average number. Among the types of arrhythmia is atrial fibrillation (AF) and atrial flutter (AFL), which are considered risk factors for development due to high morbidity and mortality. The early detection of AF/AFL is essential because their effects on the heart or complications appear after a considerable time. Electrocardiography (ECG) is a widely used screening method in primary care because of its low cost and convenience. ECG records the heart's electrical activity for a period of time via electrodes attached to the body. Owing to the development of computing power and interest in big data, attempts at deep learning (DL) have increased. The transformer was proposed by Google in 2017 and has achieved state-of-the-art performance in natural language processing. Various transformer-based models have been applied to various tasks beyond natural language processing and have shown promising prospects. However, there have been few cases of vision transformer (ViT) applications in ECG domain. It was difficult to determine whether ViT had sufficient influence in ECG domain. This study determined whether our extensive ECG dataset could make an AF/AFL diagnosis. We also confirmed whether the recently proposed ViT has AF/AFL diagnostic power.
引用
收藏
页数:8
相关论文
共 50 条
  • [41] Classification of Single-Lead ECG Signal to Normal and Abnormal Subjects Using Histogram-based Features
    Al-Yami, Rand R.
    Alotaiby, Turkv N.
    Aljafar, Latifah M.
    Alshebeili, Saleh A.
    Zouhair, Jalila
    2017 INTERNATIONAL CONFERENCE ON ELECTRICAL AND COMPUTING TECHNOLOGIES AND APPLICATIONS (ICECTA), 2017, : 52 - 54
  • [42] An ECG Stitching Scheme for Driver Arrhythmia Classification Based on Deep Learning
    Kim, Do Hoon
    Lee, Gwangjin
    Kim, Seong Han
    SENSORS, 2023, 23 (06)
  • [43] Deep Learning-Based ECG Arrhythmia Classification: A Systematic Review
    Xiao, Qiao
    Lee, Khuan
    Mokhtar, Siti Aisah
    Ismail, Iskasymar
    Pauzi, Ahmad Luqman bin Md
    Zhang, Qiuxia
    Lim, Poh Ying
    APPLIED SCIENCES-BASEL, 2023, 13 (08):
  • [44] Prediction of stroke using single lead ECG signal: A deep learning approach
    Amrutha, Ravva
    Roshni, S.
    Sahana, M.
    Chapparapu, Sai Pranavi
    Balasubramanyam, Adithya
    2024 IEEE INTERNATIONAL CONFERENCE ON DIGITAL HEALTH, ICDH 2024, 2024, : 151 - 160
  • [45] Enhancing Microseismic Signal Classification in Metal Mines Using Transformer-Based Deep Learning
    Peng, Pingan
    Lei, Ru
    Wang, Jinmiao
    SUSTAINABILITY, 2023, 15 (20)
  • [46] MVKT-ECG: Efficient single-lead ECG classification for multi-label arrhythmia by multi-view knowledge transferring
    Qin, Yuzhen
    Sun, Li
    Chen, Hui
    Yang, Wenming
    Zhang, Wei-Qiang
    Fei, Jintao
    Wang, Guijin
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 166
  • [47] Personalizing a Generic ECG Heartbeat Classification for Arrhythmia Detection: A Deep Learning Approach
    Wu, Meng-Hsi
    Chang, Emily J.
    Chu, Tzu-Hsuan
    IEEE 1ST CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2018), 2018, : 92 - 99
  • [48] Detection of Myocardial Infarction and Arrhythmia from Single-Lead ECG Data using Bagging Trees Classifier
    Khatun, Saleha
    Morshed, Bashir I.
    2017 IEEE INTERNATIONAL CONFERENCE ON ELECTRO INFORMATION TECHNOLOGY (EIT), 2017, : 520 - 524
  • [49] Identification of Atrial Fibrillation With Single-Lead Mobile ECG During Normal Sinus Rhythm Using Deep Learning
    Kim, Jiwoong
    Lee, Sun Jung
    Ko, Bonggyun
    Lee, Myungeun
    Lee, Young-Shin
    Lee, Ki Hong
    JOURNAL OF KOREAN MEDICAL SCIENCE, 2024, 39 (05)
  • [50] A review on deep learning methods for ECG arrhythmia classification
    Ebrahimi Z.
    Loni M.
    Daneshtalab M.
    Gharehbaghi A.
    Expert Systems with Applications: X, 2020, 7