A novel Gramian angular field-based 2D-CNN approach using lead II ECG achieved up to 99.84% average classification accuracy in differentiating healthy subjects from those with inferior myocardial infarction.
Does a Gramian angular field-based 2D-CNN approach using lead II ECG accurately detect inferior myocardial infarction?
A novel 2D-CNN approach using Gramian angular fields on lead II ECG signals achieves >99.6% accuracy in detecting inferior myocardial infarction, demonstrating potential for early detection via wearable devices.
This letter presents a novel method for inferior myocardial infarction (MI) detection using lead II of electrocardiogram (ECG). We evaluate our proposed method on a public dataset, namely, Physikalisch Technische Bundesanstalt (PTB) ECG dataset from PhysioNet. Under our proposed method, we first clean the noisy ECG signals using db4 wavelet, followed by an R-peak detection algorithm to segment the ECG signals into beats. We then translate the ECG timeseries dataset to an equivalent dataset of grayscale images using Gramian angular summation field (GASF) and Gramian angular difference field (GADF) operations. Subsequently, the grayscale images are fed into a custom 2-D convolutional neural network (CNN), which efficiently differentiates between a healthy subject and a subject with MI. Our proposed approach achieves an average classification accuracy of 99.68%, 99.80%, 99.82%, and 99.84% under GASF dataset with noise and baseline wander, GADF dataset with noise and baseline wander, GASF dataset with noise and baseline wander removed, and GADF dataset with noise and baseline wander removed, respectively. Most importantly, this work opens the floor for innovation in wearable devices to measure lead II ECG (e.g., by a smart watch worn on right wrist, along with a smart patch on left leg), in order to do accurate, real-time, and early detection of inferior wall MI.
Yousuf et al. (Mon,) conducted a other in Inferior myocardial infarction. Gramian angular field-based 2D-CNN approach for ECG analysis was evaluated on Classification accuracy for differentiating between healthy subjects and subjects with MI. A novel Gramian angular field-based 2D-CNN approach using lead II ECG achieved up to 99.84% average classification accuracy in differentiating healthy subjects from those with inferior myocardial infarction.