Enhanced multi-label cardiology diagnosis with channel-wise recurrent fusion
Weimin Wen1, Hongyi Zhang1, Zidong Wang2
1School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen 361024, China.
Insights
This study introduces the Branched Convolution and Channel Fusion Network (BCCF-Net) for advanced electrocardiogram (ECG) analysis. The novel network accurately identifies multiple heart conditions simultaneously from ECG signals.
Area of Science:
- Cardiology
- Artificial Intelligence
- Signal Processing
Background:
- Timely detection of abnormal electrocardiogram (ECG) signals is crucial for preventing heart disease.
- Traditional automated methods struggle with simultaneous multi-disease identification and 12-lead ECG correlations.
Purpose of the Study:
- To present a novel network architecture, the Branched Convolution and Channel Fusion Network (BCCF-Net), for multi-label ECG diagnosis.
- To enable simultaneous identification of multiple cardiac diseases from ECG signals.
- To explore potential correlations within 12-lead ECG signals.
Main Methods:
- Developed the Branched Convolution and Channel Fusion Network (BCCF-Net).
- Incorporated Channel-wise Recurrent Fusion (CRF) to enhance 12-lead correlation analysis.
- Utilized squeeze and excitation (SE) attention mechanism within convolutional neural networks (CNNs).
- Employed multi-branch convolution (MBC) modules for capturing multi-scale spatio-temporal patterns.
Main Results:
- The BCCF-Net demonstrated superior performance compared to state-of-the-art algorithms on two public datasets.
- Achieved high efficacy and robustness in multi-label ECG classification across seven subtasks.
- The framework successfully identified multiple diseases simultaneously from ECG segments.
Conclusions:
- The BCCF-Net offers a significant advancement in automated ECG analysis for multi-label diagnosis.
- The proposed framework has practical clinical applications for refined cardiac arrhythmia diagnosis.
- This approach enhances the diagnostic capabilities for complex cardiovascular conditions using ECG data.
Abstract:
The timely detection of abnormal electrocardiogram (ECG) signals is vital for preventing heart disease. However, traditional automated cardiology diagnostic methods have the limitation of being unable to simultaneously identify multiple diseases in a segment of ECG signals, and do not consider the potential correlations between the 12-lead ECG signals. To address these issues, this paper presents a novel network architecture, denoted as Branched Convolution and Channel Fusion Network (BCCF-Net), designed for the multi-label diagnosis of ECG cardiology to achieve simultaneous identification of multiple diseases. Among them, the BCCF-Net incorporates the Channel-wise Recurrent Fusion (CRF) network, which is designed to enhance the ability to explore potential correlation information between 12 leads. Furthermore, the utilization of the squeeze and excitation (SE) attention mechanism maximizes the potential of the convolutional neural network (CNN). In order to efficiently capture complex patterns in space and time across various scales, the multi branch convolution (MBC) module has been developed. Through extensive experiments on two public datasets with seven subtasks, the efficacy and robustness of the proposed ECG multi-label classification framework have been comprehensively evaluated. The results demonstrate the superior performance of the BCCF-Net compared to other state-of-the-art algorithms. The developed framework holds practical application in clinical settings, allowing for the refined diagnosis of cardiac arrhythmias through ECG signal analysis.
Related Concept Videos
01:30Heart Failure IV: Classification and Diagnostic Evaluation
01:25Cardiomyopathy I: Introduction and Classification
01:30Cardiomyopathy II: Dilated Cardiomyopathy
01:29Cardiomyopathy III: Hypertrophic Cardiomyopathy
01:29Cardiomyopathy IV: Restrictive Cardiomyopathy
01:29Cardiomyopathy V: Interprofessional Care