A Multi-Domain Feature Fusion CNN for Myocardial Infarction Detection and Localization

• Published in: Biosensors (Basel) Vol. 15; no. 6; p. 392
• Main Authors: Chen, Yunfan, Ye, Jinxing, Li, Yuting, Luo, Zhe, Luo, Jieqiang, Wan, Xiangkui
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 17.06.2025; MDPI
• Subjects: Accuracy; Angina pectoris; Artificial neural networks; Cardiology; Cardiovascular disease; Cardiovascular diseases; Datasets; Deep learning; ECG; EKG; Electrocardiogram; Electrocardiography; Evaluation; Fatalities; Fourier transforms; Frequency domain analysis; Heart attack; Heart attacks; Humans; Localization; Machine learning; Medical prognosis; Medical research; Medicine, Experimental; Mortality; multi-domain features; Myocardial infarction; Myocardial Infarction - diagnosis; Necrosis; Neural networks; Neural Networks, Computer; Patients; Signal processing; Support vector machines; Time domain analysis; Time-frequency analysis; Wavelet transforms; United States; China; ECG; deep learning; multi-domain features; myocardial infarction
• ISSN: 2079-6374; 2079-6374
• DOI: 10.3390/bios15060392

Myocardial infarction (MI) is a critical cardiovascular disease characterized by extensive myocardial necrosis occurring within a short timeframe. Traditional MI detection and localization techniques predominantly utilize single-domain features as input. However, relying solely on single-domain features of the electrocardiogram (ECG) proves challenging for accurate MI detection and localization due to the inability of these features to fully capture the complexity and variability in cardiac electrical activity. To address this, we propose a multi-domain feature fusion convolutional neural network (MFF–CNN) that integrates the time domain, frequency domain, and time-frequency domain features of ECG for automatic MI detection and localization. Initially, we generate 2D frequency domain and time-frequency domain images to combine with single-dimensional time domain features, forming multi-domain input features to overcome the limitations inherent in single-domain approaches. Subsequently, we introduce a novel MFF–CNN comprising a 1D CNN and two 2D CNNs for multi-domain feature learning and MI detection and localization. The experimental results demonstrate that in rigorous inter-patient validation, our method achieves 99.98% detection accuracy and 84.86% localization accuracy. This represents a 3.43% absolute improvement in detection and a 16.97% enhancement in localization over state-of-the-art methods. We believe that our approach will greatly benefit future research on cardiovascular disease.