克服放射学人工智能开发与实施中的挑战:超越监督学习的解决方案综合综述
2022年韩国放射学会论坛讨论了放射学人工智能开发与实施中的多种障碍,包括标注数据有限、数据隐私与安全、数据异质性、数据不平衡、模型可解释性、过拟合及与临床工作流整合等;本综述呈现并讨论了多种可能的解决方案,如纵向与多模态数据集训练、密集训练与多任务/多模态学习、自监督对比学习、生成模型图像修改与合成、可解释AI、因果学习、联邦学习与大数据模型及数字孪生。
要点
- 标注数据有限、数据异质性与不平衡、模型可解释性及临床整合是AI落地的主要障碍。
- 综述汇总的解决方向包括纵向/多模态训练、自监督对比学习、生成模型与可解释AI等。
- 联邦学习、因果学习与数字孪生被列为超越监督学习的可能技术路径。
核心结论
- 综述针对放射学AI开发与实施中的多种挑战,呈现并讨论了包括自监督学习、生成模型、可解释AI、联邦学习与数字孪生等超越监督学习的可能解决方案。
研究设计与样本
- 综述性文章,基于2022年韩国放射学会论坛对放射学AI开发与实施挑战的讨论,检索范围与纳入文献数量原文未报告。
局限性
- 原文未报告局限性
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.
引用
- Hong GS, Jang M, Kyung S, et al. Overcoming the Challenges in the Development and Implementation of Artificial Intelligence in Radiology: A Comprehensive Review of Solutions Beyond Supervised Learning. Korean J Radiol. 2023. PMID: 37724586. doi:10.3348/kjr.2023.0393
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。