On January 7, according to ByteDance news, ByteDance's medical brand "Xiaohe Health" has developed an AI-assisted diagnosis software for colonoscopy.
It can use artificial intelligence technology to assist clinicians in real-time detection and identification of colorectal cancer lesions.
At present, the software's sensitivity and specificity (two key indicators reflecting the level of medical screening) for colorectal cancer-related standard diagnosis have increased to more than 95%.
It is understood that the colonoscopy AI-assisted diagnosis software is Xiaohe Health's first medical research project.
During the research and development process, a number of domestic top three hospitals provided support to Xiaohe Health, authorizing it to analyze more than 500,000 medical cases and more than 14 million medical pictures and other data.
The project developers said that based on the technical advantages of ByteDance in the field of machine learning and image recognition, the colonoscopy AI software developed this time has strong deep learning capabilities, processing capabilities and processing speed of colorectal cancer medical images and data. were greatly improved.
According to the data, ByteDance has applied for 15 invention patents for related AI technologies, mainly in the fields of polyp identification, polyp typing, and endoscopic image analysis and processing.
After comprehensive application of these technologies, this AI colonoscopy software can realize self-supervised training without adding additional data, and continuously improve its own learning ability and clinical use accuracy.
When processing colonoscopy videos in real time, it can analyze 30 to 50 medical images per second, and provide real-time feedback and diagnostic prompts to doctors during the inspection process.
Compared with other cancers, colorectal cancer is relatively preventable and controllable.
The key to prevention and control lies in early prevention, early screening, and early treatment. Colonoscopy is one of the most important early screening methods.
"Health Times" once reported that China needs 350,000 digestive endoscopy physicians, but the actual number is less than 40,000, and there are even fewer skilled operators.
A digestive endoscopist has to go through more than 10 years of training and experience from a novice to a proficient.
Therefore, the importance of AI medical technology in assisting clinicians and enhancing clinical capabilities has become increasingly prominent.
The relevant person in charge of Xiaohe Health revealed that the reason for the development of colonoscopy AI equipment and supporting software is to help solve the problems of the shortage of digestive endoscopy physicians in my country and the high missed diagnosis rate of traditional colonoscopy.
Xiaohe Health conducted internal research in the early days, focusing on sorting out the technical patents of ByteDance.
"After research and judgment, we finally chose colonoscopy AI technology as the first scientific research project. Through this technology, we can apply our own technical advantages to medical scenarios." The person in charge said.
In order to understand the actual needs of front-line doctors, before product development, all R&D engineers practiced in cooperative hospitals, observed operations, checked the operation process, and watched a large number of intestinal videos every day.
According to the actual situation, the engineers decided on the research and development direction of colonoscopy AI technology: in addition to assisting doctors in discovering and identifying colorectal cancer lesions, it also has functions such as bowel cleanliness assessment and automatic switching of gastroenteroscopy modes.
In addition, the colonoscope will have special reminders when entering and exiting the patient's intestinal cavity to help doctors determine whether the time meets the standard requirements; in order to better assist novice doctors, this software has also developed an auxiliary function for intestinal examination.
"Like the bowel examination auxiliary function, it can help doctors predict the direction of the colonoscopy when the bowel cavity is not visible. This is of great help to some novice doctors." The above-mentioned person in charge said that many doctors have mentioned in the investigation that improper bowel movements The endoscopic operation may cause pain, and even damage the intestinal mucosa and cause perforation.
This has also become one of the key problems solved by this AI colonoscopy software.
Wu Xiaojian, vice president of the Sixth Affiliated Hospital of Sun Yat-sen University, believes that the combination of artificial intelligence and colonoscopy is one of the current trends. Xiaohe Health's colonoscopy AI technology is sensitive and specific, two key indicators that reflect the level of medical screening. Outstanding.
If the relevant technologies are put into clinical practice on a large scale, it will greatly assist front-line doctors to improve the diagnosis efficiency of colorectal cancer, colorectal polyps and other diseases, and reduce the missed diagnosis rate.
The relevant person in charge of Xiaohe Health said that Xiaohe Health will take malignant tumors as a key project for continuous scientific research.
In the future, ByteDance will also invest more resources in technology research and development, combining medical needs with its own technological advantages to benefit more ordinary patients.