Kaikai Ye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kaikai Ye has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Zhenghui Hu
Zhejiang University of Technology
2 shared publications Mingzhu Bai
College of Science, Zhejiang University of Technology, Hangzhou, China
1 shared publicationQiang Lin
College of Science, Zhejiang University of Technology, Hangzhou, China
1 shared publication- Qiang Lin
State Key Laboratory of Ocean Sensing, Institute of Quantum Sensing, School of Physics, Zhejiang University, Hangzhou 310058, China
1 shared publication - Yutong Lin
Qianweichang College, Shanghai University, Shanghai 200444, China
1 shared publication Zekuan Yang
College of Science, Zhejiang University of Technology, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 25 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 82766-82775
Classification of Current Density Vector Maps for Heart Failures Using a Transfer Convolutional Neural Network
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.
- 25 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 82766-82775
Open AccessClassification of Current Density Vector Maps for Heart Failures Using a Transfer Convolutional Neural Network
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.
- Open Access
- 20 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 107095-107103
Solving the Magnetocardiography Forward Problem in a Realistic Three-Dimensional Heart-Torso Model
The forward problem in magnetocardiography (MCG) is important for understanding the relationship between the electric activity of the heart and the body surface magnetic field (BSM), and providing insight into the clinical application of MCG. In this paper, we proposed a computational framework based on the finite element method (FEM) to solve the MCG forward problem. For the subject-specific heart-torso geometry established from the medical image, the modified FitzHugh-Nagumo (FHN) equation was used to describe the volumetric myocardial dynamic transmembrane potential (TMP), then the quasi-static Maxwell equations was applied to simulate the propagation of cardiac magnetic field produced by TMP. The two parts were validated on the simplified one-dimensional FHN equation and the source model of the straight wire respectively, in which the analytical solutions exist. Further, under a realistic geometry heart-torso model, the distribution of the body surface magnetic vector field was presented, the component in the direction perpendicular to the body surface ( B y ) of which was in very good agreement with the actual observations from the same subject on a pulse-pumped Rb atomic magnetometer.
- 20 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 107095-107103
Open AccessSolving the Magnetocardiography Forward Problem in a Realistic Three-Dimensional Heart-Torso Model
The forward problem in magnetocardiography (MCG) is important for understanding the relationship between the electric activity of the heart and the body surface magnetic field (BSM), and providing insight into the clinical application of MCG. In this paper, we proposed a computational framework based on the finite element method (FEM) to solve the MCG forward problem. For the subject-specific heart-torso geometry established from the medical image, the modified FitzHugh-Nagumo (FHN) equation was used to describe the volumetric myocardial dynamic transmembrane potential (TMP), then the quasi-static Maxwell equations was applied to simulate the propagation of cardiac magnetic field produced by TMP. The two parts were validated on the simplified one-dimensional FHN equation and the source model of the straight wire respectively, in which the analytical solutions exist. Further, under a realistic geometry heart-torso model, the distribution of the body surface magnetic vector field was presented, the component in the direction perpendicular to the body surface ( B y ) of which was in very good agreement with the actual observations from the same subject on a pulse-pumped Rb atomic magnetometer.