A5100659916- AI in cancer detection
- Cutaneous Melanoma Detection and Management
- COVID-19 diagnosis using AI
- Nonmelanoma Skin Cancer Studies
- Radiomics and Machine Learning in Medical Imaging
- Glaucoma and retinal disorders
- Artificial Intelligence in Healthcare and Education
- Ocular Oncology and Treatments
- Retinal Imaging and Analysis
- Retinal Diseases and Treatments
Beijing Tongren Hospital
2022-2025
Capital Medical University
2022-2025
Ministry of Industry and Information Technology
2023-2025
Qujiang People's Hospital
2021
Data privacy mechanisms are essential for rapidly scaling medical training databases to capture the heterogeneity of patient data distributions toward robust and generalizable machine learning systems. In current COVID-19 pandemic, a major focus artificial intelligence (AI) is interpreting chest CT, which can be readily used in assessment management disease. This paper demonstrates feasibility federated method detecting related CT abnormalities with external validation on patients from...
The coronavirus disease 2019 (COVID-19) has become a severe worldwide health emergency and is spreading at rapid rate. Segmentation of COVID lesions from computed tomography (CT) scans great importance for supervising progression further clinical treatment. As labeling COVID-19 CT labor-intensive time-consuming, it essential to develop segmentation method based on limited labeled data conduct this task. In paper, we propose self-ensembled co-training framework, which trained by large-scale...
Early detection, regular monitoring of eyelid tumors and post-surgery recurrence are crucial for patients. However, frequent hospital visits burdensome patients with poor medical conditions. This study validates a novel deep learning-based mobile application, based on YOLOv5 Efficient-Net v2-B architectures, self-diagnosing tumors, enabling improved health support systems such 1195 preprocessed clinical ocular photographs biopsy results were collected model training. The best-performing was...
Abstract Eyelid tumors accounts for 5–10% of skin tumors. It is important but difficult to identify malignant eyelid from benign lesions in a cost-effective way. Traditional screening methods malignancy require laborious and time-consuming histopathological process. Therefore, we aimed develop deep learning (DL)-based image analysis system automatic identification Using common digital camera, collected clinical images patients who were histopathologically diagnosed with We trained 8...