ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases
This work addresses the need for synthetic ECG data to aid training, privacy, and annotation in medical diagnosis, but it is incremental as it builds on existing generative models by adding multi-view and disease-conditioning capabilities.
The paper tackled the problem of synthesizing multi-view ECG signals conditioned on heart diseases, which previous methods did not address, and proposed ME-GAN to achieve this with trusty morbid manifestations as verified in experiments.
Electrocardiogram (ECG) is a widely used non-invasive diagnostic tool for heart diseases. Many studies have devised ECG analysis models (e.g., classifiers) to assist diagnosis. As an upstream task, researches have built generative models to synthesize ECG data, which are beneficial to providing training samples, privacy protection, and annotation reduction. However, previous generative methods for ECG often neither synthesized multi-view data, nor dealt with heart disease conditions. In this paper, we propose a novel disease-aware generative adversarial network for multi-view ECG synthesis called ME-GAN, which attains panoptic electrocardio representations conditioned on heart diseases and projects the representations onto multiple standard views to yield ECG signals. Since ECG manifestations of heart diseases are often localized in specific waveforms, we propose a new "mixup normalization" to inject disease information precisely into suitable locations. In addition, we propose a view discriminator to revert disordered ECG views into a pre-determined order, supervising the generator to obtain ECG representing correct view characteristics. Besides, a new metric, rFID, is presented to assess the quality of the synthesized ECG signals. Comprehensive experiments verify that our ME-GAN performs well on multi-view ECG signal synthesis with trusty morbid manifestations.