A new approach for heart disease detection using Motif transform-based CWT's time-frequency images with DenseNet deep transfer learning methods
Related Experiment Video
Updated: Jul 1, 2025
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
1Electrical Department, Sirnak University, Sirnak, Türkiye.
Insights
This study introduces a novel algorithm for analyzing electrocardiogram (ECG) signals using Motif Transformation (MT), Continuous Wavelet Transform (CWT), and DenseNET deep learning. The combined approach achieved a 99.31% success rate in cardiac condition diagnosis.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Artificial Intelligence in Healthcare
Background:
- Electrocardiogram (ECG) signals are crucial for diagnosing cardiac conditions like congestive heart failure (CHF) and cardiac arrhythmias (ARR).
- Accurate analysis of ECG signals is vital for timely disease diagnosis and management.
- Advanced computer-aided systems are needed to enhance the analysis of complex ECG data.
Purpose of the Study:
- To develop and evaluate a novel ECG data pattern recognition algorithm for improved cardiac condition diagnosis.
- To address limitations of existing signal preprocessing techniques in ECG analysis.
- To leverage deep learning for accurate classification of ECG patterns.
Main Methods:
- Proposed a novel ECG signal preprocessing model using Continuous Wavelet Transform (CWT).
- Introduced Motif Transformation (MT) to overcome CWT limitations like boundary effects and improve time-frequency localization.
- Classified ECG signals using DenseNET deep transfer learning on scalogram images generated by MT and CWT.
Main Results:
- The integrated MT + CWT + DenseNET approach demonstrated significant effectiveness in ECG data pattern recognition.
- The algorithm achieved a high success rate of 99.31% in classifying cardiac conditions from ECG signals.
- The study highlights the potential of combining signal transformation techniques with deep learning for ECG analysis.
Conclusions:
- The proposed MT + CWT + DenseNET algorithm offers a highly accurate and effective method for ECG signal analysis.
- This approach shows promise for facilitating the early and accurate diagnosis of various cardiac conditions.
- The study validates the synergy between advanced signal processing and deep learning in cardiovascular diagnostics.
Objectives:
Electrocardiogram (ECG) signals are extensively utilized in the identification and assessment of diverse cardiac conditions, including congestive heart failure (CHF) and cardiac arrhythmias (ARR), which present potential hazards to human health. With the aim of facilitating disease diagnosis and assessment, advanced computer-aided systems are being developed to analyze ECG signals.
Methods:
This study proposes a state-of-the-art ECG data pattern recognition algorithm based on Continuous Wavelet Transform (CWT) as a novel signal preprocessing model. The Motif Transformation (MT) method was devised to diminish the drawbacks and limitations inherent in the CWT, such as the issue of boundary effects, limited localization in time and frequency, and overfitting conditions. This transformation technique facilitates the formation of diverse patterns (motifs) within the signals. The patterns (motifs) are constructed by comparing the amplitudes of each individual sample value in the ECG signals in terms of their largeness and smallness. In the subsequent stage, the obtained one-dimensional signals from the MT transformation were subjected to CWT to obtain scalogram images. In the last stage, the obtained scalogram images were subjected to classification using DenseNET deep transfer learning techniques.
Results And Conclusions:
The combined approach of MT + CWT + DenseNET yielded an impressive success rate of 99.31 %.
