Abstract
An electrocardiogram (ECG) consists of complex segments, such as P-QRS-T waves. Manual ECG annotation is challenging and time-consuming, even for specialist physicians. The shortage of labelled ECG data is one of the essential factors that affect ECG intelligent analysis's long-term development. This study proposes an intelligent ECG-assisted annotation system, that not only supplements labelled data, but also significantly reduces the workload compared with manual annotation. Since beat annotation is the most basic and important part, a GAN-based generation model that can generate 14 types of simulation beats and a CNN-based beat pre-annotation model are proposed. The experimental results show that the simulation beat has high similarity to real beat and the accuracy of the pre-annotation model on the test set of 14 classes of beats is 99.28%. The proposed ECG intelligent annotation system's self-learning mechanism could improve pre-annotation performance and annotation efficiency by generating more labelled data. The proposed annotation system can also be extended to other data annotation applications.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have