A5107270420- Cardiovascular Function and Risk Factors
- Cardiac Valve Diseases and Treatments
- Cardiac Imaging and Diagnostics
- Advanced Neural Network Applications
- Liver Disease Diagnosis and Treatment
- Cardiac pacing and defibrillation studies
- Retinal Imaging and Analysis
- Cutaneous Melanoma Detection and Management
- Diabetes, Cardiovascular Risks, and Lipoproteins
- COVID-19 diagnosis using AI
- Artificial Intelligence in Healthcare and Education
- Human Mobility and Location-Based Analysis
- Acute Ischemic Stroke Management
- Industrial Vision Systems and Defect Detection
- Infrared Target Detection Methodologies
- Educational Technology and Pedagogy
- Photoacoustic and Ultrasonic Imaging
- Natural Language Processing Techniques
- Ultrasound and Hyperthermia Applications
- Remote Sensing and LiDAR Applications
- Cardiac electrophysiology and arrhythmias
- Cerebrovascular and Carotid Artery Diseases
- Advanced Vision and Imaging
- Cardiac Structural Anomalies and Repair
- Medical Image Segmentation Techniques
Eye & ENT Hospital of Fudan University
2025
Chinese Academy of Medical Sciences & Peking Union Medical College
2025
Nanjing Drum Tower Hospital
2022-2025
Nanjing University
2023-2025
Nanjing Medical University
2025
Tongji University
2021-2023
Southwest Jiaotong University
2022
Tongji Hospital
2021
Dalian Neusoft University of Information
2020
Dalian Naval Academy
2013
BACKGROUNDLeft bundle branch block (LBBB) represents a frequently encountered conduction system disorder. Despite its widespread occurrence, continual dilemma persists regarding intricate association with underlying cardiomyopathy and pivotal role in the initiation of dilated cardiomyopathy. The pathological alterations linked to LBBB-induced (LBBB-CM) have remained elusive.OBJECTIVEThis study sought investigate chronologic dynamics LBBB left ventricular dysfunction mechanism...
BACKGROUND: Approximately half of the patients with acute ischemic stroke who receive intravenous thrombolysis (IVT) do not achieve an excellent outcome. Remote conditioning (RIC) as a promising neuroprotective treatment may improve clinical outcomes in this population. This study aimed to assess efficacy and safety RIC IVT. METHODS: multicenter, participant-blinded, blinded end point, randomized controlled trial included 558 underwent IVT 18 hospitals from August 2021 May 2023. After IVT,...
Chatbot-based multimodal AI holds promise for collecting medical histories and diagnosing ophthalmic diseases using textual imaging data. This study developed evaluated the ChatGPT-powered Intelligent Ophthalmic Multimodal Interactive Diagnostic System (IOMIDS) to enable patient self-diagnosis self-triage. IOMIDS included a text model three models (text + slit-lamp, smartphone, slit-lamp smartphone). The performance was through two-stage cross-sectional across centers involving 10...
Echocardiography (echo) has become an indispensable tool in modern cardiology, offering real-time imaging that helps clinicians evaluate heart function and identify abnormalities. Despite these advantages, the acquisition of high-quality echo is time-consuming, labor-intensive, highly subjective. The objective this study to introduce a comprehensive system for automated quality control (QC) videos. This focuses on monitoring key parameters, reducing variability associated with manual QC...
Abstract Background End‐to‐end automatic detection of cardiac phase in multibeat echocardiograms is crucial for measuring parameters clinical scenarios. However, existing studies face limitations due to the high cost data annotation and collection, time‐consuming processes. Purpose This study introduces a novel echocardiographic network, EchoPhaseNet, perform fast accurate variable‐length sequences, with low costs limited data. Materials methods Five datasets were used this study, including...
Echocardiography is an essential examination for cardiac disease diagnosis, from which anatomical structures segmentation the key to assessing various functions. However, obscure boundaries and large shape deformations due motion make it challenging accurately identify in echocardiography, especially automatic segmentation. In this study, we propose a dual-branch shape-aware network (DSANet) segment left ventricle, atrium, myocardium echocardiography. Specifically, elaborate architecture...
Abstract Aims/Introduction The triglyceride‐glucose (TyG) index is a simple and reliable indicator of insulin resistance, associated with the development poor outcomes cardiovascular disease. Subclinical left ventricular dysfunction (SLVD) frequently detected in approximately one‐third diabetes patients, but it has not been established whether TyG correlates SLVD. We carried out this research to evaluate relationship between SLVD type 2 mellitus patients. Materials Methods This was...
Purpose: Accurate prediction of the progression to severe stroke in initially diagnosed nonsevere patients with acute-subacute anterior circulation nonlacuna ischemic infarction (ASACNLII) is important making clinical decision. This study aimed apply a machine learning method predict if ASACNLII would progress by using diffusion-weighted images and information on admission. Methods: retrospective enrolled 344 from June 2017 August 2020 admission, 108 cases progressed during hospitalization...
Abstract In the context of artificial intelligence, natural language processing technology has matured and it is a key for foreign teaching research direction. The application intelligence to Japanese essentially that combines computer science intelligence. Based on this, this article will analyze in teaching, hoping have certain reference significance teachers’ educational research.
Abstract Automatic skin lesion segmentation is the most critical and relevant task in computer‐aided cancer diagnosis. Methods based on convolutional neural networks (CNNs) are mainly used current segmentation. The requirement of huge pixel‐level labels a significant obstacle to achieve semantic by CNNs. In this paper, novel weakly supervised framework for presented, which generates high‐quality annotations optimizes network. A hierarchical image algorithm can predict boundary map training...
We present a unique case of left atrial (LA) dissection in 46-year-old man following aortic surgery. The LA was attributed to coronary sinus catheter-related injury. This report highlights the importance recognizing this rare complication and crucial role transesophageal echocardiography its diagnosis. discuss pathogenesis, diagnostic criteria, management strategies for dissection.
This study aimed to establish standard transesophageal echocardiographic (TEE) measurements of left ventricular (LV) morphology, function, and myocardial work parameters in healthy Beagle dogs using pressure-strain loops (PSL). Additionally, it sought standardize optimal TEE imaging techniques explore the potiential application analyis veterinary medicine. Thirty-seven male were anesthetized, intubated, mechanically ventilated for examinations. LV systolic diastolic function evaluated, with...
Left ventricular global longitudinal strain (GLS) is considered to be the first marker of diabetes mellitus-related subclinical cardiac dysfunction, but whether it attributable fat mass and distribution remains uncertain. In this study, we explored mass, especially in android area, associated with systolic dysfunction before onset disease. We conducted a single-center prospective cross-sectional study between November 2021 August 2022 on inpatients Department Endocrinology, Nanjing Drum...
Driving scene understanding is to obtain compre-hensive information through the sensor data and provide a basis for downstream tasks, which indispensable safety of self-driving vehicles. Specific perception such as object detection graph generation, are commonly used. However, results these tasks only equivalent characterization sampling from high-dimensional features, not sufficient represent scenario. In addition, goal inconsistent with human driving that just focuses on what may affect...
Deep learning-based skin lesion segmentation methods have achieved promising results in the community. However, they are usually based on fully supervised learning and require many high-quality ground truths. Labeling truths takes a lot of labor, material, financial resources. We propose novel semi-supervised method to solve this problem. First, hierarchical image algorithm is used generate optimal maps. Then, training performed small part images with The resulting pseudo masks generated...
To reduce the computational complexity of JPDA and resolve closely-spaced targets efficiently, decompose into parallel PDA algorithms without regarding correlation targets. For a target, measurements are all clutter except ones originated from itself. The algorithm to track every single target with fixed covariance states. When got closed within thick clutter, try avoid coalescence association, maintaining independence through neglecting assignment association model measurement-to-track...
Abstract Purpose: Quantitative assessment of liver function reserve (LFR) plays an important role in clinical management hepatocellular carcinoma (HCC) patients. Reduced LFR is closely related to increased level fibrosis. Virtual Touch Quantification (VTQ) a non-invasive ultrasonic imaging technique. In this study, we aimed explore the correlation between VTQ parameters and levels different stages Methods: From January 2016 October 2018, 145 patients (114 males 31 females) scheduled for...