World-class AI Team

JF Healthcare ranked the first place twice in a row on Stanford's MURA leaderboard in 2018, and CheXpert leaderboard in 2019. We are the first and only team so far to outperform all three radiologists on the CheXpert test set, demonstrating the role that AI can play in providing precise medical diagnostics. The development of JF’s TB AI detection solution is granted and supported by the State Key Project of Science and Technology, and is listed in the “Frontier Science and Technology Achievements, 2019” by Chinese Association for Science and Technology.

Using neural architecture search, a technique Google developed to automatically design neural networks with neural networks, the JF Healthcare AI team designs a novel deep convolutional backbone and loss function to model the specific image features of chest X-rays. The new model can characterize different types of thorax diseases.

Lean more about us

Deep Synergy between Radiologists and AI Scientists

JF Health possesses deep synergy between radiologists and AI scientists. A team of more than 30 certified radiologists led by Professor Xiao Xiangzuo, director of Jiangxi Institute of Medical Imaging and vice chairman of Jiangxi Radiological Society. The radiologist team is dedicated to the AI algorithm development for image data labeling and annotation. JF has developed its own cloud-based annotation tool. Senior radiologists and AI scientists jointly define labeling and annotation standards, and the annotation team strictly executes the standards. Screening results of all AI algorithms are also reviewed by the radiologist team. The current human-machine consistency has reached more than 90%.

Medical Imaging Big Data

JF Healthcard has accumulated approximately 3 million medical imaging big data, more than 300,000 of which have been annotated. The data are from hundreds of primary care facilities in China, and the National Intelligent Telemedicine TB Imaging Big Data Platform which is co-established by the Chinese Anti-TB Association and JF Healthcare. This collaborative platform collected TB DR imaging data from multiple centers in China with unified standard of data collection and annotation to support the research and development of AI technology to empower TB detection.