A5026488862- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Nausea and vomiting management
- Transportation and Mobility Innovations
- Sharing Economy and Platforms
- Photoacoustic and Ultrasonic Imaging
- Digital Economy and Work Transformation
- Imbalanced Data Classification Techniques
- Advanced Image Processing Techniques
- Medical Image Segmentation Techniques
- 3D Shape Modeling and Analysis
- Advanced Image Fusion Techniques
- Patient Satisfaction in Healthcare
- Colorectal Cancer Screening and Detection
- Explainable Artificial Intelligence (XAI)
- Hospital Admissions and Outcomes
Tsinghua University
2012-2025
University Town of Shenzhen
2022-2023
Abstract Objective 
Liver cancer has a high incidence rate, but experienced doctors are lacking in primary healthcare settings. The development of large models offers new possibilities for diagnosis. However, liver diagnosis, face certain limitations, such as insufficient understanding specific medical images, inadequate consideration vessel factors, and inaccuracies reasoning logic. Therefore, this study proposes diagnostic assistance tool to enhance the capabilities care...
This paper proposes an adaptive window-setting scheme for noninvasive detection and segmentation of bladder tumor surface in T(1)-weighted magnetic resonance (MR) images. The inner border the wall is first covered by a group ball-shaped detecting windows with different radii. By extracting candidate excluding false positive (FP) candidates, entire detected segmented remaining windows. Different from previous methods that are mostly focusing on existence tumor, this emphasizes segmenting...
With the increase of aging population, old-age care industry faces new challenges. Mutual support for elderly as a model has attracted much attention. Although Time Banks have provided mutual assistance pension solution, still, there are some problems. This paper combines blockchain with time bank to build bank, and solves problems faced by current banks. At same time, article innovates help broadens user base participating institutions, which makes system more complete rich.
Ultrasound is one of the preferred choices for early screening dense breast cancer. Clinically, doctors have to manually write report, which time-consuming and laborious, it easy miss miswrite.We proposed a new pipeline automatically generate AI ultrasound reports based on images, aiming assist in improving efficiency clinical reducing repetitive report writing.AI efficiently generated personalized preliminary reports, especially benign normal cases, account majority. Doctors then make...
This paper focuses on the classification task of breast ultrasound images and researches reliability measurement results. We proposed a dual-channel evaluation framework based inference predictive scores. For evaluation, human-aligned doctor-agreed rationales improved feature attribution algorithm SP-RISA are gracefully applied. Uncertainty quantification is used to evaluate via Test Time Enhancement. The effectiveness this has been verified our clinical dataset YBUS, its robustness public...
In some hospitals in remote areas, due to the lack of MRI scanners with high magnetic field intensity, only low-resolution images can be obtained, hindering doctors from making correct diagnoses. our study, higher-resolution were obtained through images. Moreover, as algorithm is a lightweight small number parameters, it carried out areas under condition computing resources. great clinical significance providing references for doctors' diagnoses and treatment areas.We compared different...
Abstract Since the government of China began to emphasize innovation medical service mode in recent years and advocate implementation day surgery at national policy level, given hospital located Jiangsu province implemented 2019. This study investigates impact introduction Surgery on length stay (LOS) expenses for patients undergoing laparoscopic cholecystectomy (LC). An interrupted time series (ITS) analysis was conducted based a sample 5487 from January 2017 May 2022. The factors surveyed...