Pitfalls in training and validation of deep learning systems
Pitfalls in training and validation of deep learning systems
复制标题
DOI：
10.1016/j.bpg.2020.101712
复制
发表时间：
2021-06-22
影响因子：
3.2
通讯作者：
Bisschops, Raf
中科院分区：
文献类型：
--
作者：
Eelbode, Tom;Sinonquel, Pieter;Bisschops, Raf
在过去几年中，内窥镜期刊上介绍深度学习应用的出版物数量大幅增加。深度学习在内窥镜检查的自动检测、诊断和质量改进方面显示出巨大的潜力。然而，这些作品的跨学科性质无疑使其更难以估计其价值和适用性。在这篇综述中，讨论了训练和验证深度学习系统时的陷阱和常见的不当行为，并提出了一些实用的指导方针，在获取数据和处理数据时应考虑这些指导方针，以确保系统能够在常规临床实践中推广应用。最后，提出了一些考虑因素，以确保正确的验证和比较人工智能系统。(c)2020爱思唯尔有限公司版权所有。
The number of publications in endoscopic journals that present deep learning applications has risen tremendously over the past years. Deep learning has shown great promise for automated detection, diagnosis and quality improvement in endoscopy. However, the interdisciplinary nature of these works has undoubtedly made it more difficult to estimate their value and applicability. In this review, the pitfalls and common misconducts when training and validating deep learning systems are discussed and some practical guidelines are proposed that should be taken into account when acquiring data and handling it to ensure an unbiased system that will generalize for application in routine clinical practice. Finally, some considerations are presented to ensure correct validation and comparison of AI systems. (c) 2020 Elsevier Ltd. All rights reserved.