ECG PTB CLASSIFICATION DATASET

Electrocardiogram (ECG) interpretation is critical for diagnosing a wide range of cardiovascular conditions. To streamline and accelerate the development of deep learning models in this domain, we present a novel, image-based version of the PTB Diagnostic ECG Database tailored for use with convolutional neural networks (CNNs), vision transformers (ViTs), and other image classification architectures. This enhanced dataset consists of 516 grayscale .png images, each representing a 12-lead ECG signal arranged as a 2D matrix (12 × T, where T is the number of time steps). The conversion pipeline transforms raw time-series signals from PhysioNet’s original dataset into normalized image representations by extracting diagnosis metadata, mapping SNOMED CT codes to diagnostic classes, and organizing images into labeled directories for supervised learning. Eight diagnostic categories are included, encompassing conditions such as myocardial infarction, cardiomyopathy, dysrhythmia, and healthy controls. By bypassing traditional time-series preprocessing and enabling plug-and-play compatibility with popular computer vision models, this dataset significantly lowers the barrier to entry for medical AI development and supports applications in transfer learning, prototyping, and educational use. The resulting dataset not only preserves the diagnostic richness of multi-lead ECGs but also enhances their accessibility for rapid deployment in machine learning pipelines.