A5027873106- Cardiac Imaging and Diagnostics
- Coronary Interventions and Diagnostics
- Radiomics and Machine Learning in Medical Imaging
- Metallurgy and Material Forming
- Visual perception and processing mechanisms
- AI in cancer detection
- Acute Myocardial Infarction Research
- Multisensory perception and integration
- Image Processing and 3D Reconstruction
- Biochemical Acid Research Studies
- Cancer, Hypoxia, and Metabolism
- Emotion and Mood Recognition
- Medical Imaging and Analysis
- Knowledge Management and Sharing
- Visual Attention and Saliency Detection
- Islanding Detection in Power Systems
- Tactile and Sensory Interactions
- Enhanced Oil Recovery Techniques
- Venous Thromboembolism Diagnosis and Management
- Petroleum Processing and Analysis
- Advanced X-ray and CT Imaging
- Video Surveillance and Tracking Methods
- Artificial Intelligence in Healthcare and Education
- Advanced Neural Network Applications
- Cerebrovascular and Carotid Artery Diseases
National Yang Ming Chiao Tung University
2023-2025
Beijing University of Posts and Telecommunications
2021-2025
Henan University of Technology
2024
Sun Yat-sen University
2021
Liaoning University of Technology
2020
Beihua University
2016
Dalian University of Technology
2014
Background: In recent years, the use of deep learning has become more commonplace in biomedical field and its development will greatly assist clinical imaging data interpretation. Most existing machine methods for coronary angiography analysis are limited to a single aspect. Aims: We aimed achieve an automatic multimodal recognise quantify angiography, integrating multiple aspects, including identification artery segments recognition lesion morphology. Methods: A set 20,612 angiograms was...
As a core technique to quantitatively assess the stenosis severity of coronary arteries, quantitative analysis (QCA) is urgently supposed become more automated and intelligent, especially for regions lacking expertise technology. The existing QCA methods highly depend on manual operation, which time-consuming subject personal experience. This study innovatively proposes fully automatic workflow based artificial intelligence (AI-QCA), can quickly accurately make assessment severity. whole...
Background: Ovarian cancer (OC) is the third among most common gynecological cancers. Effective biomarkers are required for OC as in case of other Therefore, here we explored whether plasma proteolytic products could serve potential biomarkers. Methods: We devised a platform that incorporates CyDye labeling, macroporous reversed-phase liquid chromatography, reducing/non-reducing SDS-PAGE, and fluorescence imaging. Paired preoperative postoperative samples from four patients were used to...
Abstract Background Conventional approaches for major depressive disorder (MDD) screening rely on two effective but subjective paradigms: self-rated scales and clinical interviews. Artificial intelligence (AI) can potentially contribute to psychiatry, especially through the use of objective data such as audiovisual signals. Objective This study aimed evaluate efficacy different paradigms using AI analysis Methods We recruited 89 participants (mean age, 37.1 years; male: 30/89, 33.7%; female:...
Renal fibrosis is a hallmark of diabetic nephropathy (DN) and characterized by an epithelial-to-mesenchymal transition (EMT) program aberrant glycolysis. The underlying mechanisms renal are still poorly understood, existing treatments only marginally effective. Therefore, it crucial to comprehend the pathophysiological behind development generate novel therapeutic approaches. Acrolein, α-,β-unsaturated aldehyde, endogenously produced during lipid peroxidation. Acrolein shows high reactivity...
Thyroid ultrasound (US) image segmentation is of great significance for both doctors and patients. However, it a challenging task because the low quality, contrast complex background in each US image. In recent years, some researchers have done thyroid nodule tasks, but results achieved are not particularly satisfactory. this paper, we broadened targets interest included nodules capsules into our research scope. We propose method that implements C-MMDetection to detect extract region (ROI),...
Aiming at the problem of low pedestrian target detection accuracy, we propose a algorithm based on optimized Mask R-CNN which uses latest research results deep learning to improve accuracy and speed results. Due influence illumination, posture, background, other factors human in natural scene image, complexity information is high. SKNet used replace part convolution module depth residual network model order extract features better so that can adaptively select best kernel during training. In...
Drawing upon institutional theory, this article develops an extended model to test and verify the effects of external pressures on Secure Software Development (SSD) assimilation roles internal critical factors. The empirical results are based 86 survey data from respondents related organizations in United Kingdom, Hong Kong, Mainland China who have project experience about SSD. Results partial least squares (PLS) analysis suggest that both mimetic coercive indirect SSD with distal mediation...
Objective To establish an artificial intelligence model based on B-mode thyroid ultrasound images to predict central compartment lymph node metastasis(CLNM)in patients with papillary carcinoma(PTC). Methods We retrieved the clinical manifestations and of tumors in 309 surgical histologically confirmed PTC treated First Medical Center PLA General Hospital from January December 2018.The datasets were split into training set test set.We established a deep learning-based computer-aided for...
Due to adopting of a large number power electronic devices, microgrids are often rich in harmonic content, and suffer serious waveform distortion. The grid frequency also fluctuates along with the load variations or supply fluctuations. All these factors increase difficulty filtering. This paper briefly introduces structure, hybrid filter circuit design working principle passive filter. impact on performance is analyzed studied detail verified simulation. study results provide some...
Temperature fluctuations significantly affect microorganism growth and pest activity in grain stacks. Thus, precise monitoring forecasting of stack temperature are essential for maintaining the quality safety storage. This paper proposes a multi-model fusion approach to predict using historical data stored grains meteorological from region. Based on proposed approaches, four distinct machine learning models, namely Adaboost, decision tree, extra trees, random forest, first developed. These...
<title>Abstract</title> Recently, the advancement of deep learning has led to considerable breakthroughs in automated detection ActionUnits (AUs). Nevertheless, this field is still faced with various challenges, including limited subjects shared datasetsand difficulty collecting AU data as domain knowledge required for annotating AUs. These issues make it arduousfor model generalize across different and attain satisfactory performance on all To address thesechallenges, we propose two...
We sought to propose an innovative vessel blood flow tracking (VBFT) method extract coronary artery tree (CAT) and assess the effectiveness of this VBFT versus single-frame method. Construction a CAT from segmented is basis artificial intelligence-aided angiographic diagnosis. However, construction using single frame remains challenging, due bifurcations overlaps in two-dimensional angiograms. Overall, 13,222 angiograms, including 28,539 vessels, were retrospectively collected 3275 patients...
The vanilla fusion methods still dominate a large percentage of mainstream audio-visual tasks. However, the effectiveness from theoretical perspective is worth discussing. Thus, this paper reconsiders signal fused in multimodal case bionics and proposes simple, plug-and-play, attention module for based on fundamental theory uncertainty theory. In addition, previous work dynamic gradient modulation relies decoupling modalities. So, decoupling-free scheme has been designed conjunction with...
Throwing performance, throwability perception and subjectively felt heaviness all depend on object size weight. Here we investigate how weight must be detected to perceive throwability. In previous studies, the size-weight relation was by hefting an in hand looking at it. Thus, it could that detecting perceiving entail a visual-kinesthetic multisensory process. On other hand, may task-specific, action-relevant perceptual organization is required, meaning perform hand-arm action analogous...