文献速递胸部CTDR

人工智能在胸部影像学中的应用

Artificial intelligence applications for thoracic imaging.
PubMed 文献 · Eur J Radiol · 2019-12-11

本文阐述人工智能在胸部影像中的应用现状与前景:深度学习特别是卷积神经网络在肺结节评估、结核或肺炎检测及弥漫性肺疾病定量等方面取得显著性能提升;胸片自动解读可检测多达14种常见异常,胸部CT在大规模肺癌筛查中应用前景广阔;AI工具进入常规临床前需前瞻性验证。

要点

  • 深度学习(尤其是卷积神经网络)在胸部影像多项任务上性能优于经典机器学习。
  • 胸片自动解读算法在孤立发现时最多可检测14种常见异常。
  • AI工具达到常规临床实施前,需要前瞻性验证。

核心结论

  • 深度学习特别是卷积神经网络的发展使胸部影像AI性能较经典机器学习技术有实质提升。
  • 胸片是深度学习自动解读近乎理想的领域,需大规模标注数据集。
  • 胸部CT是人工智能的另一主要应用领域,尤其在大规模肺癌筛查方面。
  • 放射科医生应理解、积极参与并引领人工智能驱动的新时代放射学。
  • AI工具在达到常规临床实施前将需要前瞻性验证。

研究设计与样本

  • 本文为综述,旨在提供理解机器学习方法及其可能性的有用定义,并报告胸部影像的现状与未来发展。
  • 涉及的应用包括肺结节评估、结核或肺炎检测、弥漫性肺疾病定量、胸片自动解读和胸部CT肺癌筛查。

诊断标准与关键数值

  • 当前胸片算法在异常以孤立发现存在时最多可检测14种常见异常。

临床应用与阅片要点

  • 放射科医生应理解与机器学习相关的新术语和概念,积极参与并引领人工智能驱动的放射学新时代。

局限性

  • AI工具在达到常规临床实施前将需要前瞻性验证。

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 is a hot topic in medical imaging. The development of deep learning methods and in particular the use of convolutional neural networks (CNNs), have led to substantial performance gain over the classic machine learning techniques. Multiple usages are currently being evaluated, especially for thoracic imaging, such as such as lung nodule evaluation, tuberculosis or pneumonia detection or quantification of diffuse lung diseases. Chest radiography is a near perfect domain for the development of deep learning algorithms for automatic interpretation, requiring large annotated datasets, in view of the high number of procedures and increasing data availability. Current algorithms are able to detect up to 14 common anomalies, when present as isolated findings. Chest computed tomography is another major field of application for artificial intelligence, especially in the perspective of large scale lung cancer screening. It is important for radiologists to apprehend, contribute actively and lead this new era of radiology powered by artificial intelligence. Such a perspective requires understanding new terms and concepts associated with machine learning. The objective of this paper is to provide useful definitions for understanding the methods used and their possibilities, and report current and future developments for thoracic imaging. Prospective validation of AI tools will be required before reaching routine clinical implementation.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Chassagnon G, Vakalopoulou M, Paragios N, et al. Artificial intelligence applications for thoracic imaging. Eur J Radiol. 2019. PMID: 31841881. doi:10.1016/j.ejrad.2019.108774

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。