A5101884596- Colorectal Cancer Screening and Detection
- Gastric Cancer Management and Outcomes
- Esophageal Cancer Research and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Helicobacter pylori-related gastroenterology studies
- Indoor and Outdoor Localization Technologies
- Force Microscopy Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- Immune cells in cancer
- Gastrointestinal Bleeding Diagnosis and Treatment
- PAPR reduction in OFDM
- COVID-19 diagnosis using AI
- Mechanical and Optical Resonators
- Gait Recognition and Analysis
- AI in cancer detection
- Pancreatic and Hepatic Oncology Research
- Non-Invasive Vital Sign Monitoring
- COVID-19 Clinical Research Studies
- Microfluidic and Bio-sensing Technologies
- Nanopore and Nanochannel Transport Studies
- Hand Gesture Recognition Systems
- Image Processing and 3D Reconstruction
- Iron-based superconductors research
- Superconductivity in MgB2 and Alloys
- 3D Shape Modeling and Analysis
Wuhan University
2020-2025
Renmin Hospital of Wuhan University
2020-2025
Wuhan Prevention and Treatment Center for Occupational Diseases
2024-2025
China Pharmaceutical University
2024
Hubei University of Arts and Science
2024
Qingdao University
2021
Affiliated Hospital of Qingdao University
2021
Wuhan University of Technology
2018-2021
Shenyang Institute of Automation
2005-2013
Chinese Academy of Sciences
2011-2013
Computed tomography (CT) is the preferred imaging method for diagnosing 2019 novel coronavirus (COVID19) pneumonia. We aimed to construct a system based on deep learning detecting COVID-19 pneumonia high resolution CT. For model development and validation, 46,096 anonymous images from 106 admitted patients, including 51 patients of laboratory confirmed 55 control other diseases in Renmin Hospital Wuhan University were retrospectively collected. Twenty-seven prospective consecutive collected...
Abstract Background Computed tomography (CT) is the preferred imaging method for diagnosing 2019 novel coronavirus (COVID19) pneumonia. Our research aimed to construct a system based on deep learning detecting COVID-19 pneumonia high resolution CT, relieve working pressure of radiologists and contribute control epidemic. Methods For model development validation, 46,096 anonymous images from 106 admitted patients, including 51 patients laboratory confirmed 55 other diseases in Renmin Hospital...
Tumor-associated macrophages (TAMs) are indispensable to mediating the connections between cells in tumor microenvironment. In this study, we intended research function and mechanism of Calmodulin2 (CALM2) gastric cancer (GC)-TAM microenvironment.CALM2 expression GC tissues was determined through quantitative real-time PCR (qRT-PCR) immunohistochemistry (IHC). The correlation CALM2 level survival rate patients assessed. overexpression or knockdown model constructed evaluate its role cell...
Hepatitis B virus (HBV) infection is a major etiology of hepatocellular carcinoma (HCC). An interesting question how different are the molecular and phenotypic profiles between HBV-infected (HBV+) non-HBV-infected (HBV-) HCCs? Based on publicly available multi-omics data for HCC, including bulk single-cell data, we collected sequenced, performed comprehensive comparison features HBV+ HBV− HCCs. Our analysis showed that compared to HCCs, HCCs had significantly better clinical outcomes, higher...
White light endoscopy is the most pivotal tool for detecting early gastric neoplasms. Previous artificial intelligence (AI) systems were primarily unexplainable, affecting their clinical credibility and acceptability. We aimed to develop an explainable AI named ENDOANGEL-ED (explainable diagnosis) solve this problem. A total of 4482 images 296 videos with focal lesions from 3279 patients eight hospitals used training, validating, testing ENDOANGEL-ED. traditional sole deep learning (DL)...
Purpose This paper aims to propose a new ultrasonic detection method for stainless steel weld defects based on complex synergetic convolutional calculation solve two problems in the of austenitic defects. These include ignoring nonlinear information imaginary part domain signal and correlation between amplitude real phase subjective dependence diagnosis model parameters. Design/methodology/approach An convolution is proposed this address above issues. By mapping low-density, 1D samples space...
Introduction: The completeness of esophagogastroduodenoscopy (EGD) is a prerequisite for detecting lesions. This study aims to explore whether the quality complete examinations assisted by artificial intelligence (AI) would be comparable those conducted within guideline-recommended inspection time. Methods: Patients referred diagnostic, screening, or surveillance EGD were enrolled at Renmin Hospital Wuhan University. randomly assigned two groups in 1:1 ratio. In AI-assisted group,...
Prompt diagnosis of early gastric cancer (EGC) is crucial for improving patient survival. However, most previous computer-aided-diagnosis (CAD) systems did not concretize or explain diagnostic theories. We aimed to develop a logical anthropomorphic artificial intelligence (AI) system named ENDOANGEL-LA (logical anthropomorphic) EGCs under magnifying image enhanced endoscopy (M-IEE).We retrospectively collected data 692 patients and 1897 images from Renmin Hospital Wuhan University, Wuhan,...
Changes in gastric mucosa caused by Helicobacter pylori (H. pylori) infection affect the observation of early cancer under endoscopy. Although previous researches reported that computer-aided diagnosis (CAD) systems have great potential H. infection, their explainability remains a challenge.We aim to develop an explainable artificial intelligence system for diagnosing (EADHI) and giving diagnostic basis endoscopy.A case-control study.We retrospectively obtained 47,239 images from 1826...
Endoscopic reports are essential for the diagnosis and follow-up of gastrointestinal diseases. This study aimed to construct an intelligent system automatic photo documentation during esophagogastroduodenoscopy (EGD) test its utility in clinical practice.Seven convolutional neural networks trained tested using 210,198 images were integrated endoscopic image reporting (EAIRS). We performance through man-machine comparison at three levels: internal, external, prospective test. Between May 2021...
Abstract Decoding gene regulatory networks is essential for understanding the mechanisms underlying many complex diseases. GENET developed, an automated system designed to extract and visualize extensive molecular relationships from published biomedical literature. Using natural language processing, entities relations are identified a randomly selected set of 1788 scientific articles, visualized in filterable knowledge graph. The performance evaluated compared with existing methods. named...
BackgroundTimely identification and regular surveillance of patients at high risk are crucial for early diagnosis upper gastrointestinal cancer. However, traditional manual method is time-consuming, current rate below 50%. Here, we aimed to develop a system named ENDOANGEL-AS (automatic surveillance) automatic high-risk patients.Methods7874 from Renmin Hospital Wuhan University between May 1 July 31, 2021 were used as the training set, 6762 August October internal test 7570 two other...
This paper reports the fabrication technique of a novel carbon nanotubes (CNTs) based MEMS pressure sensor with piezoresistive gauge factor potentially much greater than polysilicon sensors. By using dielectrophoretic (DEP) nanoassembly CNTs and MEMS-compatible process, we have successfully integrated bundled strands CNT sensing elements on arrays polymethylmethacrylate (PMMA) diaphragms. The effects were preliminarily investigated by measuring pressure-resistance dependency sensors...
Recently, Wi-Fi channel state information (CSI) motion detection systems have been widely researched for applications in human health care and security flat floor environments. However, these disregard the indoor context, which is often complex consists of unique features, such as staircases. Motion on a staircase also meaningful important various applications, fall intruder detection. In this paper, we present difference CSI environments through analysing radio propagation model experiments...
Several recent studies have found that the efficacy of computer-aided polyp detection (CADe) on adenoma rate (ADR) diminished in real-world settings. The role unmeasured factors AI-human interaction, such as monitor approaches, remains unknown. This study aimed to validate effectiveness CADe real world and assess impact approaches.