Key result
A deep learning method using Residual Network (ResNet) with transfer learning achieved an accuracy of 90.02% in classifying current density vector maps from magnetocardiogram data.
Why the study?
Magnetocardiography is not routinely used clinically due to a lack of data and trained doctors, particularly for interpreting current density vector maps.
Does a Residual Network (ResNet) with transfer learning accurately classify current density vector maps from magnetocardiogram data?
Does a Residual Network (ResNet) with transfer learning accurately classify current density vector maps from magnetocardiogram data?
A deep learning approach using ResNet with transfer learning can accurately classify current density vector maps from magnetocardiograms, potentially aiding in the automated diagnosis of ischemic heart disease.
Supports automated MCG classification feasibility; leaves open clinical utility pending prospective validation.
Ischemia heart disease(IHD) is the leading cause of death in worldwide. Magnetocardiogram( MCG) as a non-invasive detection of heart, takes more important role in clinic detection. However, the MCG technique is not a common diagnosis tool in routine clinical due to 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 by using 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 reconstruct from MCG data. The ResNet exhibits accuracy of 90.02%. This paper suggests a high potential of applying ResNet for CDVMs.
No takes yet. Share an insight, caveat, or question.
Hu et al. (2022) studied Ischemic heart disease. Residual Network (ResNet) with transfer learning was evaluated on Classification accuracy of current density vector maps (CDVM) from category 0 to category 4. A deep learning method using Residual Network (ResNet) with transfer learning achieved an accuracy of 90.02% in classifying current density vector maps from magnetocardiogram data.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: