Classification of Current Density Vector Maps for Heart Failures Using a Transfer Convolutional Neural Network

Abstract

Ischemic heart disease (IHD) is the leading cause of death worldwide. Magnetocardiogram (MCG) as a non-invasive detection of the heart, takes a more important role in clinic detection. However, the MCG technique is not a common diagnostic tool in routine clinical practice because of the lack of MCG data and trained doctors for MCG data, especially for current density vector map (CDVM). Therefore, we propose an automatic method to analyze MCG data using the deep learning method. Here, we propose a deep learning method called Residual Network (ResNet) with transfer learning to classify CDVM from category 0 to category 4, which is reconstructed from MCG data. The ResNet exhibited an accuracy of 90.02%. This paper suggests a high potential for applying ResNet to CDVMs.

Keywords

• Current density vector map (CDVM)
• magnetocardiogram (MCG)
• residual network (ResNet)
• transfer learning