Related Experiment Video
Updated: Jan 13, 2026
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
A Novel Framework for Cardiovascular Disease Detection Using a Hybrid CWT-SIFT Image Representation and a Lightweight
1Laboratory of Information and Communication Technologies, Abdelmalek Essaadi University, Tangier 90000, Morocco.
Insights
This study introduces a novel framework for cardiovascular disease (CVD) detection using ECG images and a lightweight neural network. The method achieves high accuracy, offering an efficient solution for accessible CVD screening.
Area of Science:
- Biomedical Engineering
- Artificial Intelligence in Healthcare
- Cardiology
Background:
- Cardiovascular diseases (CVD) present a growing global health challenge, necessitating early and accurate diagnosis.
- Existing deep learning models for CVD detection often require extensive datasets, which are scarce in many regions.
- This study addresses the need for effective CVD detection methods with limited data.
Purpose of the Study:
- To develop a novel framework for automated cardiovascular disease identification from ECG signals.
- To overcome data limitations in training predictive models, particularly in resource-constrained settings.
Main Methods:
- A hybrid approach combining Multi-Resolution Wavelet Features and Scale-Invariant Feature Transform (SIFT) keypoint density maps.
- Transformation of 1D ECG signals into 3-channel images using Continuous Wavelet Transform (CWT) and SIFT.
- Utilized a lightweight Residual Attention Neural Network (ResAttNet) for classification.
- Addressed class imbalance with Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbors (ENN), incorporating Focal Loss.
Main Results:
- Achieved high performance metrics: 99.60% accuracy, 97.38% precision, 98.53% recall, and 97.37% F1-score via five-fold cross-validation.
- Demonstrated superior performance compared to current state-of-the-art methods.
Conclusions:
- The proposed framework offers a highly accurate and computationally efficient solution for CVD detection.
- This work represents a significant advancement towards accessible and scalable computer-aided screening tools for cardiovascular diseases.
Abstract:
Background: The mortality and morbidity rates of cardiovascular disease (CVD) are rising sharply in many developed and developing countries. CVD is a fatal disease that requires early and timely diagnosis to prevent further damage and ultimately save patients' lives. In recent years, numerous studies have explored the automated identification of different categories of CVDs using various deep learning classifiers. However, they often rely on a substantial amount of data. The lack of representative training samples in real-world scenarios, especially in developing countries, poses a significant challenge that hinders the successful training of accurate predictive models. In this study, we introduce a framework to address this gap. Methods: The core novelty of our framework is the combination of Multi-Resolution Wavelet Features with Scale-Invariant Feature Transform (SIFT) keypoint density maps and a lightweight residual attention neural network (ResAttNet). Our hybrid approach transforms one-dimensional ECG signals into a three-channel image representation. Specifically, the CWT is used to extract hidden features in the time-frequency domain to create the first two image channels. Subsequently, the SIFT algorithm is implemented to capture additional significant features to generate the third channel. These three-channel images are then fed to our custom residual attention neural network to enhance classification performance. To tackle the challenge of class imbalance present in our dataset, we employed a hybrid strategy combining the Synthetic Minority Over-sampling Technique (SMOTE) with Edited Nearest Neighbors (ENN) to balance class samples and integrated Focal Loss into the training process to help the model focus on hard-to-classify instances. Results: The performance metrics achieved using five-fold cross-validation are 99.60% accuracy, 97.38% precision, 98.53% recall, and 97.37% F1-score. Conclusions: The experimental results showed that our proposed method outperforms current state-of-the-art methods. The primary practical implication of this work is that by combining a novel, information-rich feature representation with a lightweight classifier, our framework offers a highly accurate and computationally efficient solution, making it a significant step towards developing accessible and scalable computer-aided screening tools.
