The present study addresses the cardiac arrhythmia (CA) classification problem using the deep learning (DL)-based method for electrocardiography (ECG) data analysis. Recently, various DL techniques have been utilized to classify arrhythmias, with one typical approach to developing a one-dimensional (1D) convolutional neural network (CNN) model to handle the ECG signals in the time domain. Although the CA classification in the time domain is very prevalent, current methods’ performances are still not robust or satisfactory. This study aims to develop a solution for CA classification in two dimensions by introducing the recurrence plot (RP) combined with an Inception-ResNet-v2 network. The proposed method for nine types of CA classification was tested on the 1st China Physiological Signal Challenge 2018 dataset. During implementation, the optimal leads (lead II and lead aVR) were selected, and then 1D ECG segments were transformed into 2D texture images by the RP approach. These RP-based images as input signals were passed into the Inception-ResNet-v2 for CA classification. In the CPSC, Georgia, and the PTB_XL ECG databases of the PhysioNet/Computing in Cardiology Challenge 2020, the RP-based method achieved an average F1-score of 0.8521, 0.8529, and 0.8862, respectively. The results suggested the excellent generalization ability of the proposed method. To further assess the performance of the proposed method, we compared the 2D RP-image-based solution with the published 1D ECG-based works on the same dataset. Also, it was compared with two traditional ECG transform into 2D image methods, including the time waveform of the ECG recordings and time-frequency images based on continuous wavelet transform (CWT). The proposed method achieved the highest average F1-score of 0.844, with only two leads of the 12-lead ECG original data, which outperformed other works. Therefore, the promising results indicate that the 2D RP-based method has a high clinical potential for CA classification using fewer lead ECG signals.

This paper describes a biventricular model, which couples the electrical and mechanical properties of the heart, and computer simulations of ventricular wall motion and deformation by means of a biventricular model. In the constructed electromechanical model, the mechanical analysis was based on composite material theory and the finite-element method; the propagation of electrical excitation was simulated using an electrical heart model, and the resulting active forces were used to calculate ventricular wall motion. Regional deformation and Lagrangian strain tensors were calculated during the systole phase. Displacements, minimum principal strains and torsion angle were used to describe the motion of the two ventricles. The simulations showed that during the period of systole, (1) the right ventricular free wall moves towards the septum, and at the same time, the base and middle of the free wall move towards the apex, which reduces the volume of the right ventricle; the minimum principle strain (E3) is largest at the apex, then at the middle of the free wall and its direction is in the approximate direction of the epicardial muscle fibres; (2) the base and middle of the left ventricular free wall move towards the apex and the apex remains almost static; the torsion angle is largest at the apex; the minimum principle strain E3 is largest at the apex and its direction on the surface of the middle wall of the left ventricle is roughly in the fibre orientation. These results are in good accordance with results obtained from MR tagging images reported in the literature. This study suggests that such an electromechanical biventricular model has the potential to be used to assess the mechanical function of the two ventricles, and also could improve the accuracy of ECG simulation when it is used in heart-torso model-based body surface potential simulation studies.

This paper presents a new passive shimming (PS) design scheme for the correction of static magnetic-field inhomogeneities in magnetic resonance imaging (MRI) systems. In MRI, the PS procedure usually employs magnetic-field-based or harmonic-based methods to find an optimal iron-piece configuration to improve the uniformity of the static magnetic field in the imaging region. For the field-based PS technique, the peak-to-peak field inhomogeneity is minimized, and the harmonic components are inherently unconstrained; in the harmonic-based scheme, selected unwanted harmonics are minimized, and the overall field uniformity is consequently reduced. The field approach usually provides good field homogeneity but lacks flexibility in managing all terms of spherical harmonic field expansion; the harmonic approach is capable of controlling targeted low-order harmonic terms but can have difficulty in producing optimal overall field homogeneity and in controlling high-order harmonics. The new algorithm proposed herein attempts to combine the strengths of these two methods for a better PS solution. During the PS implementation, an explicit expression of the system matrix with both the field and harmonic sensitivities is generated, and then, an optimization procedure is performed for the determination of shim-piece thicknesses and locations. A case study presented shows that the hybrid method provides good quality, flexible solutions for controlling individual harmonic impurities, and also overall field uniformity. This method is not only applicable to conventional MRI magnets, but also, its flexibility means that it can be easily used to shim unconventional electromagnets.

A new boundary element method (BEM) based method is described for the design of coils for magnetic resonance imaging (MRI) systems. BEM is an effective approach for solving the electromagnetic forward problem and has been used in the design of MRI gradient coils. However, BEM-based gradient coil design faces an ill-posed mathematical problem, which is conventionally handled by means of a Lagrange multiplication method. This work attempts to improve the BEM method for MRI coil designs by applying the Tikhonov regularization scheme to solve the ill-posed matrix system formulated by the BEM forward model. The objective of the study is not to design some specific gradient or radio-frequency (RF) coils for MRI system, but to discuss the design scheme with practical regularization and constraints. The proposed approach was explained in the design of MRI coils including biplanar transverse gradient coils and RF phased array coils. With the consideration of the practical engineering requirements, physical constraints such as wire intervals are transformed into mathematical constraints and formulated into BEM equations. The examples demonstrate that the proposed method is efficient and flexible for the design of MRI coils with arbitrary geometries and engineering constraints.

Background:Myocardial ischemia is a common early symptom of cardiovascular disease (CVD). Reliable detection of myocardial ischemia using computer-aided analysis of electrocardiograms (ECG) provides an important reference for early diagnosis of CVD. The vectorcardiogram (VCG) could improve the performance of ECG-based myocardial ischemia detection by affording temporal-spatial characteristics related to myocardial ischemia and capturing subtle changes in ST-T segment in continuous cardiac cycles. We aim to investigate if the combination of ECG and VCG could improve the performance of machine learning algorithms in automatic myocardial ischemia detection.Methods:The ST-T segments of 20-second, 12-lead ECGs, and VCGs were extracted from 377 patients with myocardial ischemia and 52 healthy controls. Then, sample entropy (SampEn, of 12 ECG leads and of three VCG leads), spatial heterogeneity index (SHI, of VCG) and temporal heterogeneity index (THI, of VCG) are calculated. Using a grid search, fourSampEnand two features are selected as input signal features for ECG-only and VCG-only models based on support vector machine (SVM), respectively. Similarly, three features (S_I,THI, andSHI, whereS_Iis theSampEnof lead I) are further selected for the ECG + VCG model. 5-fold cross validation was used to assess the performance of ECG-only, VCG-only, and ECG + VCG models. To fully evaluate the algorithmic generalization ability, the model with the best performance was selected and tested on a third independent dataset of 148 patients with myocardial ischemia and 52 healthy controls.Results:The ECG + VCG model with three features (S_I,THI, andSHI) yields better classifying results than ECG-only and VCG-only models with the average accuracy of 0.903, sensitivity of 0.903, specificity of 0.905, F1 score of 0.942, and AUC of 0.904, which shows better performance with fewer features compared with existing works. On the third independent dataset, the testing showed an AUC of 0.814.Conclusion:The SVM algorithm based on the ECG + VCG model could reliably detect myocardial ischemia, providing a potential tool to assist cardiologists in the early diagnosis of CVD in routine screening during primary care services.

This paper proposes a finite-difference (FD)-based method for the design of gradient coils in MRI. The design method first uses the FD approximation to describe the continuous current density of the coil space and then employs the stream function method to extract the coil patterns. During the numerical implementation, a linear equation is constructed and solved using a regularization scheme. The algorithm details have been exemplified through biplanar and cylindrical gradient coil design examples. The design method can be applied to unusual coil designs such as ultrashort or dedicated gradient coils. The proposed gradient coil design scheme can be integrated into a FD-based electromagnetic framework, which can then provide a unified computational framework for gradient and RF design and patient-field interactions.