Joint spatio-temporal features constrained self-supervised electrocardiogram representation learning.

The electrocardiogram (ECG) measurements with clinical diagnostic labels are intrinsically limited. We propose a generative learning based self-supervised method for general ECG representations applicable to various downstream tasks, thus achieving the goal of reducing the dependence on labeled data. However, existing self-supervised methods either fail to provide satisfactory ECG representations or require too much effort to curate a large amount of expert-annotated datasets. We propose a spatio-temporal joint detection based self-supervised method with little or no human supervision to label massive datasets. Considering the spatio-temporal characteristics of ECG signals, we dynamically randomly mask the original signal (temporal detection) and disrupt the order of leads (spatial detection) to complete the learning through reconstructing the original signal and predicting the lead numbers. To validate the effectiveness of the proposed method, we use several publicly available ECG databases as well as a private ECG data of ventricular tachycardia to pre-train our model. We use diagnostic classification of 27 arrhythmia types and localization of ventricular tachycardia origin sites as two downstream tasks, respectively. The results show that learning ECG representations with this method is effective. This effort demonstrates the feasibility of learning representations from ECG data by self-supervised learning. Our self-supervised method uses only 60% of the labeled data used by the supervised method to achieve the same performance. Using the same amount of data, our self-supervised approach shows 1.3% and 8.6% improvement in classification and localization accuracy compared to the model with random initialization on two types of downstream tasks, respectively.

Neural network aided extended Kalman filtering for inverse imaging of cardiac transmembrane potential.

Objective.The aim of this study is to address the limitations in reconstructing the electrical activity of the heart from the body surface electrocardiogram, which is an ill-posed inverse problem. Current methods often assume values commonly used in the literature in the absence ofa prioriknowledge, leading to errors in the model. Furthermore, most methods ignore the dynamic activation process inherent in cardiomyocytes during the cardiac cycle.Approach.To overcome these limitations, we propose an extended Kalman filter (EKF)-based neural network approach to dynamically reconstruct cardiac transmembrane potential (TMP). Specifically, a recurrent neural network is used to establish the state estimation equation of the EKF, while a convolutional neural network is used as the measurement equation. The Jacobi matrix of the network undergoes a correction feedback process to obtain the Kalman gain.Main results.After repeated iterations, the final estimated state vector, i.e. the reconstructed image of the TMP, is obtained. The results from both the final simulation and real experiments demonstrate the robustness and accurate quantification of the model.Significance.This study presents a new approach to cardiac TMP reconstruction that offers higher accuracy and robustness compared to traditional methods. The use of neural networks and EKFs allows dynamic modelling that takes into account the activation processes inherent in cardiomyocytes and does not requirea prioriknowledge of inputs such as forward transition matrices.

Nonlocal based FISTA network for noninvasive cardiac transmembrane potential imaging.

Objective. The primary aim of our study is to advance our understanding and diagnosis of cardiac diseases. We focus on the reconstruction of myocardial transmembrane potential (TMP) from body surface potential mapping.Approach. We introduce a novel methodology for the reconstruction of the dynamic distribution of TMP. This is achieved through the integration of convolutional neural networks with conventional optimization algorithms. Specifically, we utilize the subject-specific transfer matrix to describe the dynamic changes in TMP distribution and ECG observations at the body surface. To estimate the TMP distribution, we employ LNFISTA-Net, a learnable non-local regularized iterative shrinkage-thresholding network. The coupled estimation processes are iteratively repeated until convergence.Main results. Our experiments demonstrate the capabilities and benefits of this strategy. The results highlight the effectiveness of our approach in accurately estimating the TMP distribution, thereby providing a reliable method for the diagnosis of cardiac diseases.Significance. Our approach demonstrates promising results, highlighting its potential utility for a range of applications in the medical field. By providing a more accurate and dynamic reconstruction of TMP, our methodology could significantly improve the diagnosis and treatment of cardiac diseases, thereby contributing to advancements in healthcare.

GREM2 maintains stem cell-like phenotypes in gastric cancer cells by regulating the JNK signaling pathway.

Gastric cancer (GC) is one of the major malignancies worldwide. This study was conducted to explore the mechanism by which GREM2 maintains biological properties of GC stem cells (GCSCs), and proved that GREM2 could potentially regulate the proliferation, apoptosis, invasion, migration and tumorigenic ability of GCSCs through the regulation of the JNK signaling pathway. In silico analysis was utilized to retrieve expression microarray related to GC, and differential analysis was conducted. The cell line with the highest GREM2 expression was overexpressed with GREM2 mimic, silencing GREM2 by siRNA, or treated with activator or inhibitor of the JNK signaling pathway. Subsequently, expression of GREM2, JNK signaling pathway-, apoptosis- or migration and invasion-associated factors were determined. Proliferation, migration, invasion, apoptosis of GCSCs in vitro and tumorigenic ability and lymph node metastasis of GCSCs in vivo were determined. Based on the in silico analysis of GSE49051, GREM2 was determined to be overexpressed in GC and its expression was the highest in the MKN-45 cell line, which was selected for the subsequent experiments. Silencing of GREM2 or inhibition of the JNK signaling pathway suppressed the proliferation, migration and invasion, while promoting apoptosis of GCSCs in vitro as well as inhibiting tumorigenesis and lymph node metastasis in vivo. In conclusion, the aforementioned findings suggest that the silencing of GREM2 suppresses the activation of the JNK signaling pathway, thereby inhibiting tumor progression. Therefore, GREM2-mediated JNK signaling pathway was expected to be a new therapeutic strategy for GC.