政府新闻
中国瑞金医院、华为推出人工智能病理模型 2025-02-19
China's Ruijin Hospital, Huawei launch AI pathology model
Ruijin Hospital, an affiliate of the Shanghai Jiao Tong University School of Medicine, and Chinese tech giant Huawei Technologies have unveiled an artificial intelligence pathology model expected to significantly improve diagnostic efficiency and accuracy.
It took around three years to develop RuiPath, Ruijin Hospital said at the 2025 Medical AI and Precision Diagnosis Development Forum on Tuesday. The model is based on Huawei's DCS AI solutions, with technical support from AI startup SenseTime Group and Shanghai Hengdao Medical Pathology Diagnosis Center, it added.
RuiPath features many data modalities, including images and text, covering the clinical, imaging, pathology, and other fields. In addition, its data dimensions are extensive and based on multiple disciplines covering patients' entire lifecycle and providing a comprehensive reflection of disease characteristics.
The model's data labels are complete, including images, examinations, pathology, and others conducive to accurate model training. Leveraging Ruijin Hospital's comprehensive disciplinary advantages,
RuiPath constructs accurate specialized disease data to enhance the diagnosis of specific diseases.
"RuiPath is a clinical grade, domestically developed multimodal interactive pathology model built on the comprehensive business processes of the digital smart pathology department of Ruijin Hospital," said Ning Guang, president of the hospital and academician at the Chinese Academy of Engineering. It achieves multimodal integration and can complete single-slide AI diagnosis within seconds, significantly improving efficiency and quality, Ning added.
Ruijin Hospital commits to being an "innovation laboratory" for medical AI, Ning noted. "More important than technology is upholding the principle of putting life first. We only use technologies that can withstand verification."
Many Chinese hospitals have sped up the adoption of AI. Huashan Hospital, which is affiliated with Shanghai's Fudan University, has deployed and tested DeepSeek's large language model on different platforms, while Shanghai Sixth People's Hospital has set up a localized deployment environment for DeepSeek-R1, focusing on the medical health sector to enhance the intelligence of services and management.
Source: Yicai Global
