Key result
ImECGnet, using image-based ECG data and a multibranch convolutional neural network, achieved classification accuracies of 97.91%, 99.62%, and 98.70% on three benchmark databases.
Why the study?
Time-series ECG processing methods are highly dependent on input noise and sequence length, and cannot always effectively correlate lead data from different sensors.
Does ImECGnet improve cardiovascular disease classification accuracy compared to time series-based approaches using ECG data?
Does ImECGnet improve cardiovascular disease classification accuracy compared to time series-based approaches using ECG data?
Representing ECG signals as a single image and processing them with a specialized multibranch CNN achieves high classification accuracy for cardiovascular diseases, outperforming traditional time-series methods.
Should not yet change practice; hypothesis-generating for image-based ECG CNNs in cardiovascular classification.
Reliable Cardiovascular Disease (CVD) classification performed by a smart system can assist medical doctors in recognizing heart illnesses in patients more efficiently and effectively. Electrocardiogram (ECG) signals are an important diagnostic tool as they are already available early in the patients’ health diagnosis process and contain valuable indicators for various CVDs. Most ECG processing methods represent ECG data as a time series, often as a matrix with each row containing the measurements of a sensor lead; and/or the transforms of such time series like wavelet power spectrums. While methods processing such time-series data have been shown to work well in benchmarks, they are still highly dependent on factors like input noise and sequence length, and cannot always correlate lead data from different sensors well. In this paper, we propose to represent ECG signals incorporating all lead data plotted as a single image, an approach not yet explored by literature. We will show that such an image representation combined with our newly proposed convolutional neural network specifically designed for CVD classification can overcome the aforementioned shortcomings. The proposed (Convolutional Neural Network) CNN is designed to extract features representing both the proportional relationships of different leads to each other and the characteristics of each lead separately. Empirical validation on the publicly available PTB, MIT-BIH, and St.-Petersburg benchmark databases shows that the proposed method outperforms time seriesbased state-of-the-art approaches, yielding classification accuracy of 97.91%, 99.62%, and 98.70%, respectively.
No takes yet. Share an insight, caveat, or question.
Ghahremani et al. (2023) studied Cardiovascular Disease. ImECGnet (image-based ECG representation with a multibranch convolutional neural network) vs. Time series-based state-of-the-art approaches was evaluated on Classification accuracy. ImECGnet, using image-based ECG data and a multibranch convolutional neural network, achieved classification accuracies of 97.91%, 99.62%, and 98.70% on three benchmark databases.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: