A5071068569- Service-Oriented Architecture and Web Services
- Caching and Content Delivery
- Web Data Mining and Analysis
- Recommender Systems and Techniques
- Semantic Web and Ontologies
- Data Management and Algorithms
- AI in cancer detection
- Advanced Database Systems and Queries
- Radiomics and Machine Learning in Medical Imaging
- Retinal Imaging and Analysis
- Business Process Modeling and Analysis
- Advanced Software Engineering Methodologies
- Artificial Intelligence in Healthcare and Education
- Peer-to-Peer Network Technologies
- Retinal and Optic Conditions
- Retinal Diseases and Treatments
- Topic Modeling
- Computational Drug Discovery Methods
- Mobile Agent-Based Network Management
- Advanced Neural Network Applications
- COVID-19 diagnosis using AI
- Distributed systems and fault tolerance
- Software Engineering Research
- Machine Learning in Materials Science
- Glaucoma and retinal disorders
Second Affiliated Hospital of Zhejiang University
2021-2025
Zhejiang University
2015-2024
First Affiliated Hospital Zhejiang University
2024
North University of China
2024
Zhejiang Lab
2018-2024
Zhejiang Cancer Hospital
2024
Wenzhou Institute of Industrial Science
2024
University of South Carolina
2024
Zhejiang A & F University
2015-2024
Zhejiang University of Science and Technology
2014-2023
Code summarization provides a high level natural language description of the function performed by code, as it can benefit software maintenance, code categorization and retrieval. To best our knowledge, most state-of-the-art approaches follow an encoder-decoder framework which encodes into hidden space then decode space, suffering from two major drawbacks: a) Their encoders only consider sequential content ignoring tree structure is also critical for task summarization; b) decoders are...
Computed tomography (CT) can provide a 3D view of the patient's internal organs, facilitating disease diagnosis, but it incurs more radiation dose to patient and CT scanner is much cost prohibitive than an X-ray machine too. Traditional reconstruction methods require hundreds projections through full rotational scan body, which cannot be performed on typical machine. In this work, we propose reconstruct from two orthogonal X-rays using generative adversarial network (GAN) framework. A...
Background Deep learning has presented considerable potential and is gaining more importance in computer assisted diagnosis. As the gold standard for pathologically diagnosing cervical intraepithelial lesions invasive cancer, colposcopy-guided biopsy faces challenges improving accuracy efficiency worldwide, especially developing countries. To ease heavy burden of cancer screening, it urgent to establish a scientific, accurate efficient method assisting diagnosis biopsy. Methods The data were...
3D object detection on point clouds finds many applications. However, most known cloud methods did not adequately accommodate the characteristics (e.g., sparsity) of clouds, and thus some key semantic information shape information) is well captured. In this paper, we propose a new graph convolution (GConv) based hierarchical network (HGNet) for detection, which processes raw directly to predict bounding boxes. HGNet effectively captures relationship points utilizes multi-level semantics...
In this paper, we address the large scale variation problem in crowd counting by taking full advantage of multi-scale feature representations a multi-level network. We implement such an idea keeping error patch as small possible with proper level selection strategy, since specific tends to perform better for certain range scales. However, without annotations, it is sub-optimal and error-prone manually assign predictions heads different scales levels. Therefore, propose Scale-Adaptive...
In response to the dual problems of global climate change and economic crisis, concept green economy has spread beyond environmental economics into mainstream politics business. The Belt Road Initiative (BRI) is a critical component achieving transition in regional economy, as well key United Nations 2030 Agenda for Sustainable Development. We used data envelopment analysis system GMM techniques measure association between Government expenditure performance. This method uses panel from 2008...
Abstract Early detection is critical to achieving improved treatment outcomes for child patients with congenital heart diseases (CHDs). Therefore, developing effective CHD techniques using low-cost and non-invasive pediatric electrocardiogram are highly desirable. We propose a deep learning approach detection, CHDdECG, which automatically extracts features from wavelet transformation characteristics, integrates them key human-concept features. Developed on 65,869 cases, CHDdECG achieved...
Quality-of-service-based (QoS) service selection is an important issue of service-oriented computing. A common premise previous research that the QoS values services to target users are supposed be all known. However, many unknown in reality. This paper presents a neighborhood-based collaborative filtering approach predict such for QoS-based selection. Compared with existing methods, proposed method has three new features: 1) adjusted-cosine-based similarity calculation remove impact...
Neoantigens play important roles in cancer immunotherapy. Current methods used for neoantigen prediction focus on the binding between human leukocyte antigens (HLAs) and peptides, which is insufficient high-confidence prediction. In this study, we apply deep learning techniques to predict neoantigens considering both possibility of HLA-peptide (binding model) potential immunogenicity (immunogenicity peptide-HLA complex (pHLA). The model achieves comparable performance with other...
Colorectal cancer (CRC) is one of the most life-threatening malignancies. Colonoscopy pathology examination can identify cells early-stage colon tumors in small tissue image slices. But, such time-consuming and exhausting on high resolution images. In this paper, we present a new framework for colonoscopy whole slide (WSI) analysis, including lesion segmentation diagnosis. Our contains an improved U-shape network with VGG net as backbone, two schemes training inference, respectively (the...
Extubation failure is a complex and ongoing problem in the intensive care unit (ICU). It refers to patients who require re-intubation after extubation (namely disconnection from mechanical ventilation). In these patients, leads severe risks associated with increased mortalities, longer stay ICU also higher health costs. Many studies have been proposed analyze of identify possible factors or indices that may predict failure. However, used small number for limited their features several vital...
Many known supervised deep learning methods for medical image segmentation suffer an expensive burden of data annotation model training. Recently, few-shot were proposed to alleviate this burden, but such often showed poor adaptability the target tasks. By prudently introducing interactive into strategy, we develop a novel approach called Interactive Few-shot Learning (IFSL), which not only addresses models also tackles common issues methods. First, design new structure, Medical Prior-based...
\beginabstract The trend in the DBMS market is to migrate cloud for elasticity, high availability, and lower costs. traditional, monolithic database architecture difficult meet these requirements. With development of high-speed network new memory technologies, disaggregated data center has become a reality: it decouples various components from servers into separated resource pools (e.g., compute, memory, storage) connects them through network. next generation native databases should be...
Abstract Background The incidence rates of cervical cancer in developing countries have been steeply increasing while the medical resources for prevention, detection, and treatment are still quite limited. Computer-based deep learning methods can achieve high-accuracy fast screening. Such lead to early diagnosis, effective treatment, hopefully successful prevention cancer. In this work, we seek construct a robust convolutional neural network (DCNN) model that assist pathologists screening...
Clinical trials are indispensable for medical research and the development of new treatments. However, clinical often involve thousands participants can span several years to complete, with a high probability failure during process. Recently, there has been burgeoning interest in virtual trials, which simulate real-world scenarios hold potential significantly enhance patient safety, expedite development, reduce costs, contribute broader scientific knowledge healthcare. Existing focuses on...
Abstract Graph neural networks (GNN) has been considered as an attractive modelling method for molecular property prediction, and numerous studies have shown that GNN could yield more promising results than traditional descriptor-based methods. In this study, based on 11 public datasets covering various endpoints, the predictive capacity computational efficiency of prediction models developed by eight machine learning (ML) algorithms, including four (SVM, XGBoost, RF DNN) graph-based (GCN,...
Higher-resolution biopsy slice images reveal many details, which are widely used in medical practice. However, taking high-resolution is more costly than low-resolution ones. In this paper, we propose a joint framework containing novel transfer learning strategy and deep super-resolution to generate from The called SRFBN+ proposed by modifying state-of-the-art SRFBN. Specifically, the structure of feedback block SRFBN was modified be flexible. Besides, it challenging use typical strategies...