Shuai Wang

ORCID: 0000-0003-2751-0812
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Retinal Imaging and Analysis
  • COVID-19 diagnosis using AI
  • Radiomics and Machine Learning in Medical Imaging
  • Landslides and related hazards
  • Medical Imaging Techniques and Applications
  • Dietary Effects on Health
  • Digital Imaging for Blood Diseases
  • Rock Mechanics and Modeling
  • High-Velocity Impact and Material Behavior
  • Privacy-Preserving Technologies in Data
  • Stochastic Gradient Optimization Techniques
  • Single-cell and spatial transcriptomics
  • Urologic and reproductive health conditions
  • Artificial Intelligence in Healthcare
  • Gene expression and cancer classification
  • AI in cancer detection
  • Topic Modeling
  • Advanced MRI Techniques and Applications
  • MicroRNA in disease regulation
  • Radiation Detection and Scintillator Technologies
  • Imbalanced Data Classification Techniques
  • Sentiment Analysis and Opinion Mining
  • Advanced Neural Network Applications
  • Liver Disease Diagnosis and Treatment
  • Advanced Text Analysis Techniques

China Railway Design Corporation (China)
2023-2024

Shandong University
2022-2023

Zhejiang University
2023

Hangzhou Dianzi University
2023

Suzhou Research Institute
2023

National Institutes of Health Clinical Center
2022

Xidian University
2018-2019

Chinese University of Hong Kong, Shenzhen
2018

University of Illinois Chicago
2018

Huazhong University of Science and Technology
2016

Deep learning has emerged as a powerful machine technique that learns multiple layers of representations or features the data and produces state‐of‐the‐art prediction results. Along with success deep in many application domains, is also used sentiment analysis recent years. This paper gives an overview then provides comprehensive survey its current applications analysis. article categorized under: Fundamental Concepts Data Knowledge > Algorithmic Development Text Mining

10.1002/widm.1253 article EN publisher-specific-oa Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery 2018-03-30

Although artificial intelligence performs promisingly in medicine, few automatic disease diagnosis platforms can clearly explain why a specific medical decision is made.We aimed to devise and develop an interpretable expandable framework for automatically diagnosing multiple ocular diseases providing treatment recommendations the particular illness of patient.As highly depends on observing images, we chose ophthalmic images as research material. All were labeled 4 types or normal (total 5...

10.2196/11144 article EN cc-by Journal of Medical Internet Research 2018-08-02

The common treatment for pediatric cataracts is to replace the cloudy lens with an artificial one. However, patients may suffer complications (severe proliferation into visual axis and abnormal high intraocular pressure; SLPVA AHIP) within 1 year after surgery factors causing these are unknown.Apriori algorithm employed find association rules related complications. We use random forest (RF) Naïve Bayesian (NB) predict datasets preprocessed by SMOTE (synthetic minority oversampling...

10.1186/s12967-018-1758-2 article EN cc-by Journal of Translational Medicine 2019-01-03

Abstract Dynamic failure widely exists in rock engineering, such as excavation, blasting, and rockburst. However, the quantitative measurement of dynamic damage process using experimental methods remains a challenge. In this study, SHPB modeling technique is established based on Voronoi-based DDA to study evolution Fangshan granite under loading. The assessment cracking along artificial joints among Voronoi sub-blocks conducted modified contact constitutive law. A calibration procedure has...

10.1007/s40948-024-00767-9 article EN cc-by Geomechanics and Geophysics for Geo-Energy and Geo-Resources 2024-02-19

Identification of cell subclasses using single-cell RNA-Sequencing (scRNA-Seq) data is paramount importance since it uncovers the hidden biological processes within population. While nonnegative matrix factorization (NMF) model has been reported to be effective in various unsupervised clustering tasks, may still produce inappropriate results for some scRNA-Seq datasets with heterogeneous structures. In this paper, we propose use an orthogonally constrained NMF (ONMF) subclass identification...

10.1109/icassp.2018.8462055 article EN 2018-04-01

Measuring system response matrix (SRM) by Monte Carlo method is time and resource consuming, even with high performance computer nodes. In this paper, we exploited symmetry properties available to drastically reduce the complexity in computing SRM of panel PET, which has two parallel detectors. By extending original simulating 4 voxels every slice PET detector, other on same image can be obtained translation. Without loss generality, voxel size Y Z direction one-quarter crystal pitch...

10.1109/nssmic.2016.8069511 article EN 2016-10-01

The shape and location of the orbital tumor are precious for evaluation, diagnosis, treatment, so it is essential to accurately segment assist clinicians in making reasonable decisions. Nowadays, encoder-decoder-based convolutional neural networks have been widely used medical image segmentation tasks. However, commonly single tensor flow architecture cannot achieve satisfactory performance with significant size variations. In this paper, we propose a size-sensitive deep network named...

10.1109/isbi53787.2023.10230640 article EN 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI) 2023-04-18

Abstract Dynamic failure widely exists in rock engineering, such as excavation, blasting, and rockburst. However, the quantitative measurement of dynamic damage process using experimental methods remains a challenge. In this study, SHPB modeling technique is established based on Voronoi-based DDA to study evolution Fangshan granite under loading. The assessment cracking along artificial joints among Voronoi sub-blocks conducted by employing modified contact constitutive law. A calibration...

10.21203/rs.3.rs-3353670/v1 preprint EN cc-by Research Square (Research Square) 2023-09-25

Retinal disease is one of the primary causes visual impairment, and early diagnosis essential for preventing further deterioration. Nowadays, many works have explored Transformers diagnosing diseases due to their strong representation capabilities. However, retinal exhibit milder forms often present with overlapping signs, which pose great difficulties accurate multi-class classification. Therefore, we propose a new framework named Multi-Scale Patch Message Passing Swin Transformer...

10.48550/arxiv.2311.11669 preprint EN other-oa arXiv (Cornell University) 2023-01-01

<sec> <title>BACKGROUND</title> Although artificial intelligence performs promisingly in medicine, few automatic disease diagnosis platforms can clearly explain why a specific medical decision is made. </sec> <title>OBJECTIVE</title> We aimed to devise and develop an interpretable expandable framework for automatically diagnosing multiple ocular diseases providing treatment recommendations the particular illness of patient. <title>METHODS</title> As highly depends on observing images, we...

10.2196/preprints.11144 preprint EN 2018-05-26
Coming Soon ...