AUTHOR=Fu Xin-yu , Mao Xin-li , Chen Ya-hong , You Ning-ning , Song Ya-qi , Zhang Li-hui , Cai Yue , Ye Xing-nan , Ye Li-ping , Li Shao-wei 

TITLE=The Feasibility of Applying Artificial Intelligence to Gastrointestinal Endoscopy to Improve the Detection Rate of Early Gastric Cancer Screening

JOURNAL=Frontiers in Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2022.886853

DOI=10.3389/fmed.2022.886853

ISSN=2296-858X

ABSTRACT=With the continuous innovation and breakthroughs associated with computer science and technology, the development of artificial intelligence technology is rapidly maturing. And it has been applied in various fields, such as multilingual translation, speech recognition, face recognition, driverless driving and so on. It's also shining in the medical field. For example, artificial intelligence trained on a cirrocumulus neural network has been applied to endoscopy and improved the quality of the procedure, effectively identifying lesions that are difficult to recognize by the naked eye. It has also helped doctors gather accurate samples, thus greatly improving the detection rate of early gastric cancer. Gastric cancer is the fifth-most common malignant tumor in the world and the second leading cause of cancer death in China. The 5-year survival rate for advanced gastric cancer is less than 30%, while the 5-year survival rate for early gastric cancer is more than 90%. Therefore, earlier screening for gastric cancer can lead to a better prognosis. However, the detection rate of early gastric cancer in China has been extremely low due to many factors, such as the presence of gastric cancer without obvious symptoms, difficulty identifying lesions by the naked eye, and a lack of experience among endoscopists. The introduction of artificial intelligence can help mitigate these shortcomings and greatly improve the accuracy of screening. According to relevant reports, the sensitivity and accuracy of artificial intelligence trained on deep cirrocumulus neural networks are better than those of endoscopists, and evaluations also take less time, which can greatly reduce the burden on endoscopists.