Thyroid ultrasound diagnosis improvement via multi-view self-supervised learning and two-stage pre-training.

Thyroid nodule classification and segmentation in ultrasound images are crucial for computer-aided diagnosis; however, they face limitations owing to insufficient labeled data. In this study, we proposed a multi-view contrastive self-supervised method to improve thyroid nodule classification and segmentation performance with limited manual labels. Our method aligns the transverse and longitudinal views of the same nodule, thereby enabling the model to focus more on the nodule area.

Automated identification of protein expression intensity and classification of protein cellular locations in mouse brain regions from immunofluorescence images.

Knowledge of protein expression in mammalian brains at regional and cellular levels can facilitate understanding of protein functions and associated diseases. As the mouse brain is a typical mammalian brain considering cell type and structure, several studies have been conducted to analyze protein expression in mouse brains. However, labeling protein expression using biotechnology is costly and time-consuming.

The characteristics of invasive cardiac lipoma: case report and literature review.

Invasive cardiac lipoma is a rare type of primary cardiac tumor that is composed of adipose tissue but infiltrating the adjacent structures. It is a benign tumor that can cause significant morbidity and mortality due to its size and location within the heart. We describe a giant invasive intracardiac lipoma across atrial wall extending to the ascending aorta and the superior vena cava.

Automatic recognition of protein subcellular location patterns in single cells from immunofluorescence images based on deep learning.

With the improvement of single-cell measurement techniques, there is a growing awareness that individual differences exist among cells, and protein expression distribution can vary across cells in the same tissue or cell line. Pinpointing the protein subcellular locations in single cells is crucial for mapping functional specificity of proteins and studying related diseases. Currently, research about single-cell protein location is still in its infancy, and most studies and databases do not annotate proteins at the cell level.

Long Noncoding RNA SNHG4 Attenuates the Injury of Myocardial Infarction via Regulating miR-148b-3p/DUSP1 Axis.

Objective: Long noncoding RNAs (lncRNAs), including some members of small nucleolar RNA host gene (SNHG), are important regulators in myocardial injury, while the role of SNHG4 in myocardial infarction (MI) is rarely known. This study is aimed at exploring the regulatory role and mechanisms of SNHG4 on MI.

Methods: Cellular and rat models of MI were established.

Rosendaal linear interpolation method appraising of time in therapeutic range in patients with 12-week follow-up interval after mechanical heart valve replacement.

Background: The objective of this study was to evaluate the quality of anticoagulation by the time in therapeutic range (TTR) for patients with 12-week INR follow-up interval.

Materials And Methods: From January 2018 to December 2020, a selective group of patients who underwent mechanical valve replacement and followed up at our anticoagulation clinic for adjustment of warfarin dose were enrolled. The incidences of complications of anticoagulation therapy were reported by linearized rates.

Improving segmentation and classification of renal tumors in small sample 3D CT images using transfer learning with convolutional neural networks.

Purpose: Computed tomography (CT) images can display internal organs of patients and are particularly suitable for preoperative surgical diagnoses. The increasing demands for computer-aided systems in recent years have facilitated the development of many automated algorithms, especially deep convolutional neural networks, to segment organs and tumors or identify diseases from CT images. However, performances of some systems are highly affected by the amount of training data, while the sizes of medical image data sets, especially three-dimensional (3D) data sets, are usually small.

DULoc: quantitatively unmixing protein subcellular location patterns in immunofluorescence images based on deep learning features.

Motivation: Knowledge of subcellular locations of proteins is of great significance for understanding their functions. The multi-label proteins that simultaneously reside in or move between more than one subcellular structure usually involve with complex cellular processes. Currently, the subcellular location annotations of proteins in most studies and databases are descriptive terms, which fail to capture the protein amount or fractions across different locations.

CircUBXN7 mitigates H/R-induced cell apoptosis and inflammatory response through the miR-622-MCL1 axis.

Background: Hypoxia/reoxygenation (H/R)-mediated apoptosis and inflammation are major causes of tissue injury in acute myocardial infarction (AMI). Exploring the underlying mechanisms of cardiomyocyte injury induced by H/R is important for AMI treatment. Circular RNAs have been demonstrated to paly vital roles in the pathogenesis of AMI.

Atrial fibrillation detection based on multi-feature extraction and convolutional neural network for processing ECG signals.

Background And Objective: The incidence of atrial fibrillation is increasing annually. We develop an automatic detection system, which is of great significance for the early detection and treatment of atrial fibrillation. This can lead to the reduction of the incidence of critical illnesses and mortality.

Comparative analysis of active contour and convolutional neural network in rapid left-ventricle volume quantification using echocardiographic imaging.

In cardiology, ultrasound is often used to diagnose heart disease associated with myocardial infarction. This study aims to develop robust segmentation techniques for segmenting the left ventricle (LV) in ultrasound images to check myocardium movement during heartbeat. The proposed technique utilizes machine learning (ML) techniques such as the active contour (AC) and convolutional neural networks (CNNs) for segmentation.

Coronary angiography image segmentation based on PSPNet.

Purpose: Coronary artery disease (CAD) is known to have high prevalence, high disability and mortality. The incidence and mortality of cardiovascular disease are also gradually increasing worldwide. Therefore, our paper proposes to use a more efficient image processing method to extract accurate vascular structures from vascular images by combining computer vision and deep learning.

Knockdown of Long Noncoding RNA SNHG14 Protects H9c2 Cells Against Hypoxia-induced Injury by Modulating miR-25-3p/KLF4 Axis in Vitro.

Cyanotic congenital heart disease (CCHD) is the main cause of death in infants worldwide. Long noncoding RNAs (lncRNAs) have been pointed to exert crucial roles in development of CHD. The current research is designed to illuminate the impact and potential mechanism of lncRNA SNHG14 in CCHD in vitro.

Human umbilical cord blood-derived MSCs exosome attenuate myocardial injury by inhibiting ferroptosis in acute myocardial infarction mice.

The exosome of MSCs derived from human umbilical cord blood (HUCB-MSC) has been reported to have cardioprotective effects on mouse models of acute myocardial infarction (AMI) and cardiomyocyte hypoxia injury, but the exact mechanisms involved require further investigation. This paper aimed to study the role of HUCB-MSC-exosomes in inhibiting ferroptosis to attenuate myocardial injury. Compared with sham or normoxia groups, RT-PCR and western blotting showed that divalent metal transporter 1 (DMT1) expression was significantly increased, and Prussian blue staining, ferrous iron (Fe), MDA, and GSH level detection demonstrated that ferroptosis occurred in the infraction myocardium and in cardiomyocyte following hypoxia-induced injury.

The circular RNA TLK1 exacerbates myocardial ischemia/reperfusion injury via targeting miR-214/RIPK1 through TNF signaling pathway.

Purpose: Myocardial ischemia/reperfusion injury (IRI) induces cardiomyocytes death and leads to loss of cardiac function. Circular RNAs (circRNA) have gain increasing interests in modulating myocardial IRI. In this study, we aim to investigate the role and exact mechanism of circTLK1 in the pathogenesis of myocardial IRI.

LncRNA OIP5-AS1 inhibits osteoblast differentiation of valve interstitial cells via miR-137/TWIST11 axis.

OIP5-AS1, a highly abundant imprinted long non-coding RNA (lncRNA), has been implicated in calcific aortic valve disease (CAVD). However, the function and underlying mechanism of OIP5-AS1 in CAVD progression remains unknown. In this study, osteoblastic differentiation of valve interstitial cells (VICs) isolated from human calcific aortic valves was induced by osteogenic medium.

Primary malignant schwannoma of the heart.

Primary malignant schwannoma of the heart is an extremely rare disease. We, herein, report a 42-year-old female who underwent successful surgical excision of such a tumor.

MicroRNA-26b relieves inflammatory response and myocardial remodeling of mice with myocardial infarction by suppression of MAPK pathway through binding to PTGS2.

Background: Myocardial infarction (MI) is a common cardiovascular disease caused by myocardial ischemia. Also, microRNA (miRNA) participates in the pathophysiology of many cardiovascular diseases, which can affect stem cell transplantation in the treatment of MI. In this study, our aim is to explore effect of miR-26b on inflammatory response and myocardial remodeling through the MAPK pathway by targeting PTGS2 in mice with MI.

Ten-year experience of tricuspid valve replacement with the St. Jude medical valve.

Bioprosthetic valves for tricuspid valve replacement (TVR) have become increasingly popular in recent years, but mechanical valves remain valuable, particularly for the patients who want to avoid reoperation for bioprostheses malfunction. The aim of this study was to review our 10-year experience in adult patients who underwent TVR with the St. Jude Medical (SJM) valve.

Influence of vascular geometry on local hemodynamic parameters: phantom and small rodent study.

Background: Many studies have demonstrated that the geometry of the carotid bifurcation enables prediction of blood flow variation associated with atherosclerotic plaque formation. The phase angle between the arterial wall circumferential strain and its instantaneous wall shear stress is known as stress phase angle (SPA). This parameter is used to evaluate hemodynamic factors of atherogenesis.

Echocardiographic assessment of long-term hemodynamic characteristics of mechanical mitral valve prostheses with different mitral valvular diseases.

Mitral stenosis (MS) and mitral insufficiency (MI) have different pre-operative hemodynamic characteristics. However, it is unclear if there are differences in long-term echocardiographic characteristics of MS and MI patients after mechanical mitral valve replacement. This study is to compare long-term echocardiographic results of mechanical mitral valve prostheses between MS and MI patients.

A Simplified Arch Debranching Technique for Hybrid Repair of Complicated Type B Aortic Dissection.

Convenient procedures and fewer postoperative adverse events of an arch debranching technique are important factors that need to be considered for assured outcomes of hybrid repair. In this report we describe our hybrid repair with a simplified arch debranching technique. It was used for patients with complicated type B aortic dissection who had undergone previous operations for type A aortic dissection.