Department of Medicine, The University of British Columbia, Vancouver, Canada.
Dig Endosc. 2021 Jan;33(2):290-297. doi: 10.1111/den.13896. Epub 2020 Dec 27.
Capsule endoscopy is ideally suited to artificial intelligence-based interpretation given its reliance on pattern recognition in still images. Time saving viewing modes and lesion detection features currently available rely on machine learning algorithms, a form of artificial intelligence. Current software necessitates close human supervision given poor sensitivity relative to an expert reader. However, with the advent of deep learning, artificial intelligence is becoming increasingly reliable and will be increasingly relied upon. We review the major advances in artificial intelligence for capsule endoscopy in recent publications and briefly review artificial intelligence development for historical understanding. Importantly, recent advancements in artificial intelligence have not yet been incorporated into practice and it is immature to judge the potential of this technology based on current platforms. Remaining regulatory and standardization hurdles are being overcome and artificial intelligence-based clinical applications are likely to proliferate rapidly.
胶囊内镜非常适合基于人工智能的解释，因为它依赖于静态图像中的模式识别。节省时间的查看模式和病变检测功能目前依赖于机器学习算法，这是人工智能的一种形式。由于相对于专家读者的敏感性较差，当前的软件需要密切的人工监督。然而，随着深度学习的出现，人工智能变得越来越可靠，并将越来越多地被依赖。我们回顾了最近出版物中胶囊内镜人工智能的主要进展，并简要回顾了人工智能的发展历史，以便了解。重要的是，人工智能的最新进展尚未在实践中得到应用，基于当前平台来判断这项技术的潜力还为时过早。基于人工智能的临床应用可能会迅速普及，剩下的监管和标准化障碍正在被克服。
