Related Experiment Video
Updated: Aug 14, 2025
Identifying Coronary Artery Calcification on Non-gated Computed Tomography Scans
Published on: August 28, 2018
Identification of Coronary Culprit Lesion in ST Elevation Myocardial Infarction by Using Deep Learning
Li-Ming Tseng1,2,3, Cheng-Yen Chuang4, Su-Kiat Chua4,3
1Department of Emergency MedicineShin Kong Wu Ho-Su Memorial Hospital Taipei 11101 Taiwan.
Insights
Deep learning accurately identifies culprit coronary arteries in ST-elevation myocardial infarction (STEMI) patients using electrocardiograms (ECGs). Continuous wavelet transform (CWT) preprocessing improved accuracy over short-time Fourier transform (STFT).
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Imaging
Background:
- ST-elevation myocardial infarction (STEMI) requires prompt identification of the infarct-related coronary artery.
- Current methods rely on electrocardiogram (ECG) interpretation, which can be challenging.
- Accurate culprit artery identification is crucial for timely and effective revascularization, reducing mortality and morbidity.
Purpose of the Study:
- To develop and evaluate a deep learning model for more accurate prediction of culprit coronary arteries in STEMI patients.
- To compare the efficacy of different ECG signal preprocessing techniques, specifically short-time Fourier transform (STFT) and continuous wavelet transform (CWT), within a deep learning framework.
Main Methods:
- A convolutional neural network (CNN) deep learning model was trained using ECG signals from 384 STEMI patients who underwent primary percutaneous coronary intervention (PCI).
- ECG signals were preprocessed using STFT and CWT (Morlet wavelet) with varying input lengths.
- Model performance was assessed by evaluating sensitivity, specificity, and overall accuracy for predicting the infarct-related artery (LAD, LCX, RCA).
Main Results:
- STFT preprocessing yielded an overall accuracy of 79.3%.
- CWT preprocessing achieved a higher overall accuracy of 83.7%.
- CWT demonstrated superior sensitivity and specificity for predicting all three major coronary arteries (LAD, LCX, RCA) compared to STFT.
Conclusions:
- Deep learning, utilizing CNNs, can significantly aid in identifying the culprit coronary artery in STEMI patients.
- Continuous wavelet transform (CWT) is a more effective ECG signal preprocessing method than STFT for this deep learning application.
- This approach holds promise for improving the diagnostic accuracy and guiding treatment decisions in STEMI management.
Objective:
Early revascularization of the occluded coronary artery in patients with ST elevation myocardial infarction (STEMI) has been demonstrated to decrease mortality and morbidity. Currently, physicians rely on features of electrocardiograms (ECGs) to identify the most likely location of coronary arteries related to an infarct. We sought to predict these culprit arteries more accurately by using deep learning.
Methods:
A deep learning model with a convolutional neural network (CNN) that incorporated ECG signals was trained on 384 patients with STEMI who underwent primary percutaneous coronary intervention (PCI) at a medical center. The performances of various signal preprocessing methods (short-time Fourier transform [STFT] and continuous wavelet transform [CWT]) with different lengths of input ECG signals were compared. The sensitivity and specificity for predicting each infarct-related artery and the overall accuracy were evaluated.
Results:
ECG signal preprocessing with STFT achieved fair overall prediction accuracy (79.3%). The sensitivity and specificity for predicting the left anterior descending artery (LAD) as the culprit vessel were 85.7% and 88.4%, respectively. The sensitivity and specificity for predicting the left circumflex artery (LCX) were 37% and 99%, respectively, and the sensitivity and specificity for predicting the right coronary artery (RCA) were 88.4% and 82.4%, respectively. Using CWT (Morlet wavelet) for signal preprocessing resulted in better overall accuracy (83.7%) compared with STFT preprocessing. The sensitivity and specificity were 93.46% and 80.39% for LAD, 56% and 99.7% for LCX, and 85.9% and 92.9% for RCA, respectively.
Conclusion:
Our study demonstrated that deep learning with a CNN could facilitate the identification of the culprit coronary artery in patients with STEMI. Preprocessing ECG signals with CWT was demonstrated to be superior to doing so with STFT.
Related Concept Videos
01:30Acute Coronary Syndrome I: Introduction
01:30Acute Coronary Syndrome III: Diagnostic Studies