Original title: From the Quarter Hour to Several Seconds, China's First Artificial Intelligence Bone Age Reader is Put into Use
News reporter: Wang Yingying
Over the past two weeks, the Department of Radiology at the Children’s Hospital of Zhejiang University School of Medicine has quietly integrated an artificial intelligence (AI) software system. This new tool can automatically analyze a child's hand X-ray and determine their bone age within just a few seconds. The difference between the AI's results and those of senior doctors is no more than three months.
This marks the first time an AI-based bone age reader has been implemented in a hospital in China. On September 25, the Children’s Hospital of Zhejiang University School of Medicine (Zhejiang Children’s Hospital) and Yitu Technology announced a strategic partnership aimed at advancing medical AI applications.
The AI model was developed using bone age data from over 10,000 healthy children’s physical exams conducted at Zhejiang Children’s Hospital. Yitu Technology applied deep learning techniques to train the system, making it capable of accurately identifying and analyzing skeletal development patterns.
Shu Qiang, dean of the Children’s Hospital of Zhejiang University School of Medicine and deputy secretary of the Party Committee, described the collaboration as “a very standardized and formal AI project.†Fu Junfen, the deputy dean and project director, emphasized that the initiative was carried out through a formal research project with approval from the hospital ethics committee and other relevant parties.
According to Fu Junfen, the AI system is already operational and will soon be tested in broader settings such as schools. The goal is to eventually deploy the technology across hospitals nationwide. Fu and Niu Hao, president of ETO Medical, expressed their ambition to “set new standards for bone age interpretation in China.â€
The Bone Age Determination Dilemma
Dr. Fu Junfen, who entered the field of pediatric endocrinology in 2000, has long been interested in improving the accuracy of bone age determination. Bone age is a crucial measure of a child’s growth and development, used to diagnose and monitor conditions like growth disorders and endocrine diseases.
However, traditional methods of measuring bone age face a major challenge: balancing speed and accuracy. In clinical practice, the GP map method is commonly used, where doctors compare a child’s X-ray to images from the 1950s. While this method is quick, it lacks consistency—different doctors may give widely varying results, sometimes differing by up to two years.
There are more accurate methods, such as the TW3 technique, which involves detailed analysis of 20 bones in the hand. However, this process is time-consuming and requires complex calculations. Even with software assistance, it can take 15–30 minutes to complete—a significant burden for busy clinics.
Artificial intelligence offers a solution. It can quickly and accurately perform the same tasks as the TW3 method, reducing the time needed to just a few seconds.
"Hello" a Ruler
Several months ago, Fujitsu Fukui began exploring how AI could transform medical imaging. Now, AI-powered bone age determination is becoming a key area of focus in the industry. Imaging professionals see great potential in AI-driven tools, and hospital IT companies are also investing in related technologies.
Lin Qiang, responsible for the IBG project, emphasized that high-quality labeled data is essential for AI success. “You need to feed the data,†he said. “It’s not enough to throw data at the algorithm—it needs to be properly labeled.â€
Niu Hao noted that the most expensive part of developing an AI bone age reader is the initial labeling of data. “You can’t read the labels until they’re accurate,†he said. This requires radiologists and endocrinologists to carefully label thousands of X-rays manually.
To protect patient privacy, the hospital’s Information Department desensitized more than 10,000 bone age X-rays before providing them to Yitu Technology. The AI system then learns from these data points, iteratively refining its model. Human experts review the results, helping the system improve over time.
Ultimately, the AI system became a fast and reliable tool for bone age determination. It can complete the entire TW3 process in seconds, identifying bone features, ranking them, and calculating the final age. In real-world use, the final decision is still made by a doctor, but the AI significantly speeds up the process.
“China lacks 200,000 pediatricians,†Fu Junfen said. “This technology helps save a lot of time for doctors.â€
Laptop Standing Desk Adjustable,Laptop Standing Desk Adjustable Height,Laptop Standing Desk Cart,Laptop Standing Desk Foldable,etc.
Shenzhen Chengrong Technology Co.ltd is a high-quality enterprise specializing in metal stamping and CNC production for 12 years. The company mainly aims at the R&D, production and sales of Notebook Laptop Stands and Mobile Phone Stands. From the mold design and processing to machining and product surface oxidation, spraying treatment etc ,integration can fully meet the various processing needs of customers. Have a complete and scientific quality management system, strength and product quality are recognized and trusted by the industry, to meet changing economic and social needs .
Laptop Standing Desk Adjustable,Laptop Standing Desk Adjustable Height,Laptop Standing Desk Cart,Laptop Standing Desk Foldable
Shenzhen ChengRong Technology Co.,Ltd. , https://www.laptopstandsupplier.com