A5101885726- Gastric Cancer Management and Outcomes
- Esophageal Cancer Research and Treatment
- Gastrointestinal Bleeding Diagnosis and Treatment
- Colorectal Cancer Screening and Detection
- Lung Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Metastasis and carcinoma case studies
- Sparse and Compressive Sensing Techniques
- Advanced Data Compression Techniques
- Gastrointestinal Tumor Research and Treatment
- Image and Signal Denoising Methods
- Esophageal and GI Pathology
- Cancer-related molecular mechanisms research
- Random lasers and scattering media
- Gastrointestinal disorders and treatments
- Inflammatory Bowel Disease
- Advanced Image Processing Techniques
- Circular RNAs in diseases
- Pancreatic and Hepatic Oncology Research
- Ferroptosis and cancer prognosis
- Image Retrieval and Classification Techniques
- Advanced Image Fusion Techniques
- Cancer, Lipids, and Metabolism
- Domain Adaptation and Few-Shot Learning
- Gastroesophageal reflux and treatments
Sichuan University
2016-2025
West China Hospital of Sichuan University
2016-2025
Fourth Affiliated Hospital of Guangxi Medical University
2023-2024
Gannan Medical University
2018-2023
University of Electronic Science and Technology of China
2006-2022
Second Hospital of Anhui Medical University
2022
Anhui Medical University
2022
The First People's Hospital of Shunde
2022
Guangzhou University of Chinese Medicine
2022
Kwame Nkrumah University of Science and Technology
2021
Abstract Background Appendicitis is the most common abdominal surgical emergency worldwide, and its burden has been changing. We report level trends of appendicitis prevalence, incidence; years lived with disability (YLD) in 204 countries territories from 1990 to 2019, based on data Global Burden Diseases, Injuries, Risk Factors Study (GBD) 2019. Methods The numbers age-standardized incidence, YLD rates per 100,000 population were estimated across regions by age, sex, sociodemographic index...
Gastrointestinal (GI) disease is one of the most common diseases and primarily examined by GI endoscopy. Recently, deep learning (DL), in particular convolutional neural networks (CNNs) have made achievements endoscopy image analysis. This review focuses on applications DL methods analysis images. We summarized compared latest published literature related to clinical covers key detection, classification, segmentation, recognition, location, other tasks. At end, we give a discussion...
Background Hepatocellular carcinoma (HCC) is one of the most lethal malignancies worldwide. PANoptosis a recently unveiled programmed cell death pathway, Nonetheless, precise implications within context HCC remain incompletely elucidated. Methods We conducted comprehensive bioinformatics analysis to evaluate both expression and mutation patterns PANoptosis-related genes (PRGs). categorized into two clusters identified differentially expressed (DEPRGs). Next, risk model was constructed using...
Wireless capsule endoscopy (WCE) has become a widely used diagnostic technique to examine inflammatory bowel diseases and disorders. As one of the most common human helminths, hookworm is kind small tubular structure with grayish white or pinkish semi-transparent body, which number 600 million people infection around world. Automatic detection challenging task due poor quality images, presence extraneous matters, complex gastrointestinal, diverse appearances in terms color texture. This...
Pancreatic cancer (PC) is among the most aggressive malignancies associated with a 5-year survival rate of <9%, and treatment options remain limited. Antibody-drug conjugates (ADCs) are new class anticancer agents superior efficacy safety profiles. We studied antitumor activity Oba01 ADC mechanism underlying targeting death receptor 5 (DR5) in preclinical PC models. Our data revealed that DR5 was highly expressed on plasma membrane cells showed potent vitro panel human DR5-positive cell...
Gastrointestinal (GI) diseases constitute a leading problem in the human digestive system. Consequently, several studies have explored automatic classification of GI as means minimizing burden on clinicians and improving patient outcomes, for both diagnostic treatment purposes. The challenge using deep learning-based (DL) approaches, specifically convolutional neural network (CNN), is that spatial information not fully utilized due to inherent mechanism CNNs. This paper proposes application...
Accurate segmentation of lesions is crucial for diagnosis and treatment early esophageal cancer (EEC). However, neither traditional nor deep learning-based methods up to today can meet the clinical requirements, with mean Dice score - most important metric in medical image analysis hardly exceeding 0.75. In this paper, we present a novel learning approach segmenting EEC lesions. Our method stands out its uniqueness, as it relies solely on single input from patient, forming so-called...
INTRODUCTION: Lugol chromoendoscopy (LCE) is valuable, cost-effective, and widely used in early esophageal cancer screening, yet it suffers from low compliance because of adverse events after LCE. In addition, the reflux iodine during staining upper esophagus brings risk bucking aspiration. We introduced a new model called distance countdown (DC) aimed to reduce METHODS: this randomized controlled trial, 204 patients were into DC No-DC groups. The primary end point was difference incidence...
This letter presents an adaptive denoising method based on the singular value decomposition (SVD). By incorporating a global subspace analysis into scheme of local basis selection, problems previous methods are effectively tackled. Experimental results show that proposed achieves outstanding preservation image details, and at high noise levels it provides improvements in both objective subjective quality denoised when compared to state-of-the-art methods.
The accurate diagnosis of various esophageal diseases at different stages is crucial for providing precision therapy planning and improving 5-year survival rate cancer patients. Automatic classification in gastroscopic images can assist doctors to improve the efficiency accuracy. existing deep learning-based method only classify very few categories same time. Hence, we proposed a novel efficient channel attention dense convolutional neural network (ECA-DDCNN), which into four main including...
Invasive mechanical ventilation plays an important role in the prognosis of patients with sepsis. However, there are, currently, no tools specifically designed to assess weaning from invasive The aim our study was develop a practical model predict sepsis.We extracted patient information Medical Information Mart for Intensive Care Database-IV (MIMIC-IV) and eICU Collaborative Research Database (eICU-CRD). Kaplan-Meier curves were plotted compare 28-day mortality between who successfully...
Vibration has a great influence on the working accuracy of flexible-link manipulators. In this paper, an online trajectory planning method for manipulator is proposed to suppress vibration. Firstly, vibration dynamic model planar established, and actual solved by reasonable simplification. Then, taking residual energy as objective function, optimizer based Particle Swarm Optimization(PSO) intelligent search algorithm employed motion with best suppression effect. Finally, back propagation...
Wireless Capsule Endoscopy (WCE) is a relative novel technology, which can view entire gastrointestinal (GI) tract without invasiveness and sedation. The main disadvantage associated with WCE that the huge number of recorded images must be examined by clinicians. It tedious time consuming task. Developing an automatic computer-aided detection system to alleviate burden clinicians required. In this paper, we proposed new hookworm image algorithm. A gradient space, named Hybrid Color Gradient...
images for the rarely-encountered lesions were difficult to differentiate from normal images.However, number of screened by IPS was 5000 on average, and only 10%-15% original left behind.As a result, large excluded, reading time decreased 5 h 1 average.CONCLUSION: Though total accuracy specificity rates computer-aided screening enteric with are much lower than those CE readers, diagnosis can exclude confine which reduce workload readers in scanning images.This technique make correct as...
Ancylostomiasis is a fairly common small bowel parasite disease identified by capsule endoscopy (CE) for which computer-aided clinical detection method has not been established. We sought to develop an artificial intelligence system with convolutional neural network (CNN) automatically detect hookworms in CE images. trained deep CNN based on YOLO-V4 (You Look Only Once-Version4) detector using 11236 images of hookworms. assessed its performance calculating the area under receiver operating...