A5060638031- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Digital Imaging for Blood Diseases
- Colorectal Cancer Screening and Detection
- Topic Modeling
- Machine Learning in Healthcare
- Image Retrieval and Classification Techniques
- Biomedical Text Mining and Ontologies
- Pneumonia and Respiratory Infections
- Advanced Neural Network Applications
- Remote Sensing and Land Use
- Cellular Automata and Applications
- Herpesvirus Infections and Treatments
- Chaos-based Image/Signal Encryption
- Software Engineering Research
- Remote-Sensing Image Classification
- Medical Image Segmentation Techniques
- Advanced X-ray and CT Imaging
- COVID-19 diagnosis using AI
- Advanced Malware Detection Techniques
- Influenza Virus Research Studies
- Advanced Steganography and Watermarking Techniques
- Advanced Data Storage Technologies
- Web Application Security Vulnerabilities
- MRI in cancer diagnosis
University of Cambridge
2024-2025
Institute of Zoology
2024-2025
Chinese Academy of Sciences
2024-2025
Affiliated Hospital of Jining Medical University
2025
Xi'an Jiaotong University
2008-2024
State Key Laboratory of Membrane Biology
2024
Wuhan Institute of Technology
2024
Center for Disease Control
2024
Huzhou University
2023
State Key Laboratory of Crystal Materials
2022-2023
Abstract The gut microbiome has emerged as a potential target for the treatment of cardiovascular disease. Ischemia/reperfusion (I/R) after myocardial infarction is serious complication and whether certain bacteria can serve option remains unclear. Lactobacillus reuteri ( L. ) well‐studied probiotic that colonize mammals including humans with known cholesterol‐lowering properties anti‐inflammatory effects. Here, prophylactic cardioprotective effects or its metabolite γ‐aminobutyric acid...
Potholes are a structural damage to the road with hollow which can cause severe traffic accidents and impact efficiency. In this paper, we propose an efficient pothole detection system using deep learning algorithms detect potholes on automatically. Four models trained tested preprocessed dataset, including YOLO V3, SSD, HOG SVM Faster R-CNN. phase one, initial images non-potholes collected labeled. two, four for accuracy loss comparison processed image dataset. Finally, performance of all...
Leukemia classification relies on a detailed cytomorphological examination of Bone Marrow (BM) smear. However, applying existing deep-learning methods to it is facing two significant limitations. Firstly, these require large-scale datasets with expert annotations at the cell level for good results and typically suffer from poor generalization. Secondly, they simply treat BM as multi-class task, thus failing exploit correlation among leukemia subtypes over different hierarchies. Therefore,...
Abstract Emerging evidence has demonstrated the profound impact of gut microbiome on cardiovascular diseases through production diverse metabolites. Using an animal model myocardial ischemia–reperfusion (I/R) injury, we found that prophylactic administration a well‐known probiotic, Bifidobacterium infantis ( B. ), exhibited cardioprotective effects in terms preserving cardiac contractile function and preventing adverse remodeling following I/R these were recapitulated by its metabolite...
Hyperspectral images (HSIs) provide invaluable information in both spectral and spatial domains for image classification tasks. In this paper, we use semantic representation as a middle-level feature to describe pixels' characteristics. Deriving effective is critical achieving good performance. Since different descriptors depict characteristics from perspectives, combining multiple features the same space makes more meaningful. First, probabilistic support vector machine used generate...
Web image analysis has witnessed an AI renaissance. The ILSVRC benchmark been instrumental in providing a corpus and standardized evaluation. NVIDIA City Challenge is envisioned to provide similar impetus the of video data that helps make cities smarter safer. In its first year, this focused on traffic data. While millions cameras around world capture data, albeit low-quality, very little automated value creation results. Lack labeled trained models can be deployed at edge city fabric,...
Pathological primary tumor (pT) stage focuses on the infiltration degree of to surrounding tissues, which relates prognosis and treatment choices. The pT staging relies field-of-views from multiple magnifications in gigapixel images, makes pixel-level annotation difficult. Therefore, this task is usually formulated as a weakly supervised whole slide image (WSI) classification with slide-level label. Existing weakly-supervised methods mainly follow instance learning paradigm, takes patches...
Artificially making clinical decisions for patients with multi-morbidity has long been considered a thorny problem due to the complexity of disease. Drug recommendations can assist doctors in automatically providing effective and safe drug combinations conducive treatment reducing adverse reactions. However, existing recommendation works ignored two critical information. (i) Different types medical information their interrelationships patient's visit history be used construct comprehensive...
Hearing loss poses a significant threat to human health, with its prevalence increasing annually. Niacin (vitamin B3) is an essential B vitamin that plays crucial role in energy metabolism and cellular repair the body. Additionally, it exerts protective influence on cells of inner ear. A correlation between dietary niacin hearing has been reported; however, results remain controversial, requiring further investigation. This study aimed examine potential association intake United States...
Abstract Myocardial ischemia/reperfusion (I/R) injury is a major contributor to myocardial damage, leading adverse cardiac remodeling and dysfunction. Recent studies have highlighted the potential of gut microbiota‐derived metabolites in modulating outcomes. Here, cardioprotective effects commensal bacterium Flavonifractor plautii ( F. ) its metabolite desaminotyrosine (DAT) against I/R are investigated. We showed that prophylactic gavage attenuates as evidenced by improved function reduced...
We examined the impact of one-dose vs. two-dose vaccination strategies on epidemiology varicella zoster virus (VZV) in Australia, using a mathematical model. Strategies were assessed terms (natural and breakthrough) incidence, morbidity, average age infection vaccine effectiveness (VE). Our modelling results suggest that compared to strategy (Australia's current schedule), is expected not only produce less natural cases (5% 13% pre-vaccination state, respectively) but also considerably fewer...
This paper presents a new spectral-spatial feature learning method for hyperspectral image classification, which integrates spectral and spatial information into group sparse coding (GSC) via clusters, each of is an adaptive partition pixels. The clusters derived from the segmentation maps by mean-shift algorithm are regarded as groups in GSC, where pixels within same simultaneously represented linear combination few common atoms given dictionary, thus enforcing smoothness across region to...
Tissue segmentation is an essential task in computational pathology. However, relevant datasets for such a pixel-level classification are hard to obtain due the difficulty of annotation, bringing obstacles training deep learning-based model. Recently, contrastive learning has provided feasible solution mitigating heavy reliance models on annotation. Nevertheless, applying loss most abstract image representations, existing frameworks focus global features, therefore, less capable encoding...