Artificial intelligence (AI) is rarely directly used in patent foramen ovale (PFO) diagnosis. In this study, an AI model was developed to detect the presence of PFO automatically in both contrast transthoracic echocardiography (cTTE) images and videos. The whole intelligent diagnosis neural network framework consists of two functional modules of image segmentation (Unet, = 1866) and image classification (ResNet 101, = 9152).
View Article and Find Full Text PDFBackground: Conventional approach to myocardial strain analysis relies on a software designed for the left ventricle (LV) which is complex and time-consuming and is not specific for right ventricular (RV) and left atrial (LA) assessment. This study compared this conventional manual approach to strain evaluation with a novel semi-automatic analysis of myocardial strain, which is also chamber-specific.
Methods: Two experienced observers used the AutoStrain software and manual QLab analysis to measure the LV, RV and LA strains in 152 healthy volunteers.
Background: We investigated the application value of no-invasive myocardial work in evaluating left ventricular (LV) function in patients with hyperthyroidism.
Methods: Sixty-five patients with an initial hyperthyroidism diagnosis were sorted into tachycardia (group TH1, n=31) and without tachycardia (group TH2, n=34) groups. Thirty healthy participants served as the control group (group CON).
In this study, we aimed to develop a prediction model to assist surgeons in choosing an appropriate surgical approach for mitral valve disease patients. We retrospectively analyzed a total of 143 patients who underwent surgery for mitral valve disease. The XGBoost algorithm was used to establish a predictive model to decide a surgical approach (mitral valve repair or replacement) based on the echocardiographic features of the mitral valve apparatus, such as leaflets, the annulus, and sub-valvular structures.
View Article and Find Full Text PDFObjective: By using ultrasound strain rate (SR) imaging to evaluate the left atrial (LA) reservoir and pump function after catheter ablation (CA) with persistent atrial fibrillation (PAF).
Methods: A total of 45 patients with PAF underwent echocardiography examination before and after ablation as well as during 6 months of follow-up. Peak SR was measured at each LA segment (septal, lateral, anterior, inferior and posterior) during systole (LAs) and late diastole (LAa).
Background: To investigate the feasibility of quantitatively assessing left ventricular function and synchronization and diagnose subclinical myocardial injury in patients with systemic lupus erythematosus (SLE) using two-dimensional (2D) longitudinal layer speckle tracking imaging (STI).
Methods: This was a single-center prospective study. A total of 69 patients with SLE were included in the case group and further divided into 2 subgroups, a nonactive and an active group, according to the Systemic Lupus Erythematosus Disease Activity Index (SLEDAI) 2000 scoring standard.
(1) Objective: To evaluate myocardial injury by observing the different parameters of global myocardial work (MW) by left ventricular pressure-strain loop (PSL) analysis in patients with chronic kidney disease (CKD). (2) Methods: According to the left ventricular mass index, the study patients with CKD were further divided into two groups: the left ventricular normal group (CKD, 59) and left ventricular hypertrophy group (CKD, 46). Thirty-three healthy controls (CON) matched in age and sex with the CKD group were recruited.
View Article and Find Full Text PDFObjective: Noninvasive myocardial work (MW) is a new technology which is based on strain after considering the load influence on myocardial deformation. We aimed to investigate the feasibility of quantitatively assessing left ventricular myocardial work (LVMW) in patients with systemic lupus erythematosus (SLE) using a left ventricular pressure-strain loop (LVPSL).
Methods: 76 patients with SLE were included in the study (A), further divided into two subgroups according to the presence of lupus nephritis (LN).
Zhonghua Wei Chang Wai Ke Za Zhi
March 2015
Objective: To assess the correlation of primary colorectal cancer (CRC) lesions' maximum standardized uptake value (SUVmax) and tumor to normal tissue SUVmax ratio (T/N ratio) detected by ¹⁸F-deoxyglucose positron emission computed tomography (¹⁸F-FDG PET-CT) imaging with the postoperative prognosis.
Methods: Clinicopathological data of 92 CRC patients who underwent curative resection after the PET-CT examination and received ¹⁸F-FDG PET-CT examination from January 2009 to December 2013 in the First Affiliated Hospital of Sun Yat-sen University were reviewed retrospectively. The correlation of SUVmax and T/N ratio in primary lesions with clinicopathological factors was analyzed.