当前位置: X-MOL 学术Pers. Ubiquitous Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Artificial intelligence technology based on deep learning in digestive endoscopy imaging diagnosis
Personal and Ubiquitous Computing Pub Date : 2021-02-05 , DOI: 10.1007/s00779-021-01532-5
Jinling Cheng , Tao Song , Zhi Liu , Lelai Zhou , Dianmin Sun

With the continuous progress in the era of big data, artificial intelligence technology has begun to get more and more applications in medicine, and it is becoming more and more possible to use artificial intelligence in the diagnostic technology of digestive endoscopy images. This article mainly studies the progress of artificial intelligence technology in the diagnosis of gastrointestinal endoscopy. The main purpose is to add new vitality to the medical conditions that are not yet perfect. This article mainly uses digestive endoscopy to carry out a comprehensive examination of all aspects of the digestive tract under the conditions of accuracy, clarity, and other advantages. Randomly select 14 of the 50 registered patient images for corresponding gastrointestinal endoscopy. The premise is that the subjects must be tested under the same conditions. The ordinary manual detection technology adds 4 groups as the control group, and the start time of the test is the same; when conducting the experiment, the position of each group to be tested must be the same and the detection area is large enough. Finally, image simulation is carried out on the experiment. The experimental results show that the sensitivity of artificial intelligence used in the actual experiment is 95.1%, of which the most prominent data value is 97.6%. The accuracy of the digestive endoscopy is 96.6%. The sharpness of the image detected by artificial intelligence is also superior.



中文翻译:

基于深度学习的人工智能技术在消化内窥镜成像诊断中的应用

随着大数据时代的不断发展,人工智能技术已开始在医学中得到越来越多的应用,在消化内窥镜图像诊断技术中使用人工智能的可能性越来越大。本文主要研究人工智能技术在胃肠道内窥镜诊断中的进展。主要目的是为尚未完善的医疗条件增加新的活力。本文主要使用消化内窥镜在准确性,清晰度和其他优势条件下对消化道的各个方面进行全面检查。从50张已注册患者图像中随机选择14张用于相应的胃肠道内窥镜检查。前提是必须在相同条件下测试受试者。普通的手动检测技术将4组作为对照组,测试的开始时间相同。进行实验时,每个待测组的位置必须相同,检测面积要足够大。最后,在实验中进行了图像仿真。实验结果表明,实际实验中使用的人工智能灵敏度为95.1%,其中最突出的数据值为97.6%。消化内窥镜检查的准确性为96.6%。人工智能检测到的图像的清晰度也更高。每个测试组的位置必须相同,并且检测区域足够大。最后,在实验中进行了图像仿真。实验结果表明,实际实验中使用的人工智能灵敏度为95.1%,其中最突出的数据值为97.6%。消化内窥镜检查的准确性为96.6%。人工智能检测到的图像的清晰度也更高。每个测试组的位置必须相同并且检测区域足够大。最后,在实验中进行了图像仿真。实验结果表明,实际实验中使用的人工智能灵敏度为95.1%,其中最突出的数据值为97.6%。消化内窥镜检查的准确性为96.6%。人工智能检测到的图像的清晰度也更高。

更新日期:2021-02-05
down
wechat
bug