On June 25, 2019, the researchings of Professor HOU Xiaohua and his team from the Department of Gastroenterology of Union Hospital Affiliated to TJMC, HUST, were published in Gastroenterology (Impact Factor 19.233, RANK=1), the top international journal in the field of gastroenterology, which also marked a breakthrough in the field of artificial intelligence in the diagnosis of small intestine diseases.

        After validation with a large sample, the results showed that compared with the traditional reading mode, the CNN-based image-assisted reading model could reduce the average diagnosis time from 96.6 min/case to 5.9 min/case; it could reduce the average number of manual readings from 22,654 to 578 films/case,  and could also improve the sensitivity of detecting abnormal lesions in the small intestine from 74.57% to 99.88%.

       The research results not only realize the intelligent assistance of capsule endoscopy application, but also greatly change the diagnosis mode of small intestine diseases.