DeepECG: Image-based electrocardiogram interpretation with deep convolutional neural networks

被引：12

作者：

Li, Changling ^{[1
]}

Zhao, Hang ^{[2
]}

Lu, Wei ^{[2
]}

Leng, Xiaochang ^{[2
]}

Wang, Li ^{[2
]}

Lin, Xintan ^{[2
]}

Pan, Yibin ^{[3
]}

Jiang, Wenbing ^{[4
]}

Jiang, Jun ^{[1
]}

Sun, Yong ^{[1
]}

Wang, Jianan ^{[1
]}

Xiang, Jianping ^{[2
]}

机构：

[1] Zhejiang Univ, Affiliated Hosp 2, Dept Cardiol, Sch Med, Hangzhou, Peoples R China

[2] ArteryFlow Technol Co Ltd, Hangzhou, Peoples R China

[3] Jinhua Municipal Cent Hosp, Dept Cardiol, Hangzhou, Peoples R China

[4] Wenzhou Peoples Hosp, Dept Cardiol, Hangzhou, Peoples R China

来源：

BIOMEDICAL SIGNAL PROCESSING AND CONTROL | 2021年 / 69卷

关键词：

Electrocardiogram; Arrhythmia; Deep learning; Convolutional neural networks; Transfer learning; HEARTBEAT CLASSIFICATION;

D O I：

10.1016/j.bspc.2021.102824

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

Electrocardiogram (ECG) plays a critical role in the diagnosis of cardiovascular disease (CVDs). In this paper, we develop DeepECG, a system that diagnoses 7 kinds of arrhythmia from 51,579 ECGs. DeepECG takes ECG images as inputs, and performs arrhythmia classification using deep convolutional neural network models (DCNN) and transfer learning. We conduct a comprehensive study of different neural network architectures, where the best model Inception-V3 achieves mean balanced accuracy of 98.46 %, recall of 95.43 %, and specificity of 96.75 %. The experimental results have successfully validated that our system can achieve excellent multi-label classification based on image formats, making it possible for cardiologists to use image-based ECG interpretation with DCNN to aid diagnosis and reduce misdiagnosis rates.

引用

下载

页数：6

共 50 条

[21] Deep Image Matching Based on Siamese Convolutional Neural Networks
J. Dou
Z. Tu
Pattern Recognition and Image Analysis, 2025, 35 (1) : 1 - 15
[22] IMAGE-BASED AIR QUALITY ANALYSIS USING DEEP CONVOLUTIONAL NEURAL NETWORK
Chakma, Avijoy
Vizena, Ben
Cao, Tingting
Lin, Jerry
Zhang, Jing
2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3949 - 3952
[23] Quantized Deep Residual Convolutional Neural Network for Image-Based Dietary Assessment
Tan, Ren Zhang
Chew, Xinying
Khaw, Khai Wah
IEEE ACCESS, 2020, 8 : 111875 - 111888
[24] Image-based time series forecasting: A deep convolutional neural network approach
Semenoglou, Artemios-Anargyros
Spiliotis, Evangelos
Assimakopoulos, Vassilios
NEURAL NETWORKS, 2023, 157 : 39 - 53
[25] A Deep Separable Convolutional Neural Network for Multiscale Image-Based Smoke Detection
Yinuo Huo
Qixing Zhang
Yang Jia
Dongcai Liu
Jinfu Guan
Gaohua Lin
Yongming Zhang
Fire Technology, 2022, 58 : 1445 - 1468
[26] A Deep Separable Convolutional Neural Network for Multiscale Image-Based Smoke Detection
Huo, Yinuo
Zhang, Qixing
Jia, Yang
Liu, Dongcai
Guan, Jinfu
Lin, Gaohua
Zhang, Yongming
FIRE TECHNOLOGY, 2022, 58 (03) : 1445 - 1468
[27] Deep Convolutional Generative Adversarial Networks in Image-Based Android Malware Detection
Mercaldo, Francesco
Martinelli, Fabio
Santone, Antonella
COMPUTERS, 2024, 13 (06)
[28] Image-based species identification of wild bees using convolutional neural networks
Buschbacher, Keanu
Ahrens, Dirk
Espeland, Marianne
Steinhage, Volker
ECOLOGICAL INFORMATICS, 2020, 55
[29] Learning image-based spatial transformations via convolutional neural networks: A review
Tustison, Nicholas J.
Avants, Brian B.
Gee, James C.
MAGNETIC RESONANCE IMAGING, 2019, 64 : 142 - 153
[30] Efficient single image-based dehazing technique using convolutional neural networks
Gade, Harish Babu
Odugu, Venkata Krishna
Janardhana Rao, B.
Satish, B.
Venkatram, N.
Revathi, K.
MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (34) : 80727 - 80749

← 1 2 3 4 5 →