A5100948268- Radiation Dose and Imaging
- Radiomics and Machine Learning in Medical Imaging
- Cancer Immunotherapy and Biomarkers
- Pancreatic and Hepatic Oncology Research
- Thyroid Cancer Diagnosis and Treatment
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Neuroendocrine Tumor Research Advances
- Cardiac Imaging and Diagnostics
- Photoacoustic and Ultrasonic Imaging
- Natural product bioactivities and synthesis
- Enhanced Oil Recovery Techniques
- SARS-CoV-2 and COVID-19 Research
- Evacuation and Crowd Dynamics
- Viral gastroenteritis research and epidemiology
- Image Retrieval and Classification Techniques
- Medical Image Segmentation Techniques
- Lattice Boltzmann Simulation Studies
- Natural Compounds in Disease Treatment
- Chronic Lymphocytic Leukemia Research
- Fire dynamics and safety research
- Electrical and Bioimpedance Tomography
- Brain Tumor Detection and Classification
- Lung Cancer Diagnosis and Treatment
- vaccines and immunoinformatics approaches
Southern Medical University
2023-2025
Nanfang Hospital
2023-2025
West China Hospital of Sichuan University
2023-2025
Sichuan University
2023-2025
Changzhou No.2 People's Hospital
2025
Imperial College London
2024
China University of Petroleum, Beijing
2024
BGI Group (China)
2024
Beijing Hua Xin Hospital
2024
First People's Hospital of Foshan
2023
Abstract Objective To evaluate the value of an integrated model incorporating deep learning (DL), hand-crafted radiomics and clinical US imaging features for diagnosing central lymph node metastasis (CLNM) in patients with papillary thyroid cancer (PTC). Methods This retrospective study reviewed 613 clinicopathologically confirmed PTC from two institutions. The DL were developed using primary lesion images then selected by multivariate analysis to generate model. performance was compared...
The objective of this study was to determine whether a new combination immunogens could be more effective than the S–2P design in terms eliciting an immune response. aimed use unified formulation standard make comparison between immunogen design. analyzed published mutation strategies known COVID-19 vaccines and also Spike protein variants RCSB database identify most promising combination. By choosing different variants, we prepared well characterized mRNA preparations administered them...
This study aimed to develop a BI-RADS network (DL-UM) via integrating ultrasound (US) and mammography (MG) images explore its performance in improving breast lesion diagnosis management when collaborating with radiologists, particularly cases discordant US MG Breast Imaging Reporting Data System (BI-RADS) classifications. We retrospectively collected image data from 1283 women lesions who underwent both within one month at two medical centres categorised them into concordant classification...
Abstract Aims Growing clinical evidence suggests that not all patients with rheumatoid arthritis (RA) benefit to the same extent by treatment tripterygium glycoside (TG), which highlights need identify RA‐related genes can be used predict drug responses. In addition, single as markers of RA are sufficiently accurate for use predictors. Therefore, there is a paired expression serve biomarkers predicting therapeutic effects TG tablets in RA. Methods A total 17 pairs co‐expressed were...
Abstract Objective To evaluate the value of an integrated model incorporating deep learning (DL), radiomics and clinical US imaging features for diagnosing central lymph node metastasis (CLNM) in patients with papillary thyroid cancer (PTC). Methods This retrospective study reviewed 613 clinicopathologically confirmed PTC from two institutions. The DL were developed using primary lesion images then selected by multivariate analysis to generate model. performance was compared junior senior...
Visual In-Context Learning (ICL) has emerged as a promising research area due to its capability accomplish various tasks with limited example pairs through analogical reasoning. However, training-based visual ICL limitations in ability generalize unseen and requires the collection of diverse task dataset. On other hand, existing methods inference-based category solely rely on textual prompts, which fail capture fine-grained contextual information from given examples can be time-consuming...
Abstract A gradient‐information‐enhanced image segmentation method using convolutional neural networks is presented, and then combined with contact angle measurement to establish an automated processing workflow. For three‐dimensional X‐ray images, the accuracy at interfaces sparsely distributed small objects directly influences of measurement. Leveraging reliable gradient information train network, this addresses issue inaccurate even low resolution present. Furthermore, memory requirements...
Due to the relatively small, confined space and large occupant loads in railcars, fire protection life safety railcar is greatly concerned public transportation industry. The object of this study evaluate emergency evacuation from railcars a metropolitan railway system United States as part hazard analysis accordance with NFPA 130, "Standard for Fixed Guideway Transit Passenger Rail Systems". time passengers location (station or exit path) was analyzed by using computational egress model...
Objective To investigate the feasibility of using a specific iodine delivery rate in coronary computed tomography angiography(CCTA) to obtain high and uniform image quality patients with different body weight, according latest guideline contrast medium injection protocol. Methods A total 159 consecutive who had undergone CCTA for ruling out heart disease were prospectively enrolled divided into five subgroups weight: ≤60, 60-70, 70-80, 80-90, >90 kg, former three scanned 100 kV tube...
Objective To investigate the feasibility, image quality, and safety of low-tube-voltage, low iodine load iso-osmolar contrast comprehensive cardiac aortoiliac CT angiography (CTA) for transcatheter aortic valve replacement (TAVR) planning. Methods Ninety-eight consecutive TAVR candidates prospectively underwent combined contrast-enhanced CTA root complex vascular access route. Patients were assigned to group A (2nd generation dual-source CT, 100 kV, 270 mgI/ml iodixanol) or B 120 370...