Key result
Image-based ECG deep learning framework classifies six arrhythmia categories with ~90% accuracy.
Why the study?
Automated ECG analysis requires standardized preprocessing and classification methods to support screening of cardiac rhythm abnormalities.
A 2D image-based CNN can successfully classify basic normal and abnormal ECG rhythms end-to-end, but distinguishing specific structural abnormalities remains challenging under high class imbalance and low image resolution.
ECG image CNNs require caution before clinical use due to abnormal rhythm confusion; leaves open refinement needs for imbalanced, low-resolution datasets.
Automated electrocardiogram (ECG) analysis can support the screening of cardiac rhythm abnormalities when standardized preprocessing and classification are applied. This work presents an image-based ECG arrhythmia classification framework for six rhythm categories: Left Bundle Branch Block (LBBB), Normal, Premature Atrial Contraction (PAC), Premature Ventricular Contractions (PVC), Right Bundle Branch Block (RBBB), and Ventricular Fibrillation. The dataset contains 22,166 ECG waveform images divided into training and test subsets. Images are resized to 64 × 64 pixels and intensity-scaled, while shear, zoom, and horizontal-flip augmentation are applied to the training subset. A sequential CNN comprising three convolutionpooling stages, a 128-unit dense layer, dropout, and a six-unit softmax output performs multiclass classification. The trained network is stored in HDF5 and native Keras formats and deployed through a Flask-based image-upload interface. Experimental evaluation includes epoch-wise learning behavior and three interface-level classification cases. A Normal ECG is classified as Normal and mapped to a healthy-rhythm status, a Ventricular Fibrillation input is classified as Ventricular Fibrillation and mapped to an abnormal-rhythm status, and an LBBB input is classified as PVC and mapped to an abnormal-rhythm status. The results demonstrate the complete inference pipeline from ECG image input to multiclass prediction and user-facing rhythm interpretation, while also revealing class-level confusion among abnormal rhythms.
No takes yet. Share an insight, caveat, or question.
Anuhya et al. (2026) studied Arrhythmia (n=22,166). Sequential CNN with 2-D ECG spectral image representation was evaluated on Classification accuracy. An image-based ECG arrhythmia classification CNN framework achieved a maximum validation accuracy of 89.67% across six rhythm categories, though it demonstrated some class-level confusion among abnormal rhythms.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: