Integrated Radiological Services Ltd, Unit 110, Century Building, Brunswick Business Park, Liverpool, L3 4BJ, UK.
Radiat Prot Dosimetry. 2021 Oct 12;195(3-4):145-151. doi: 10.1093/rpd/ncab005.
This paper is concerned with the role of science and technology in helping to create change in society. Diagnostic radiology is an example of an activity that has undergone significant change due to such developments, which over the past 40 years have led to a huge increase in the volume of medical imaging data generated. However, these developments have by and large left the human elements of the radiological process (referrer, radiographer and radiologist) intact. Diagnostic radiology has now reached a stage whereby the volume of information generated cannot be fully utilised solely by employing human observers to form clinical opinions, a process that has not changed in over 100 years. In order to address this problem, the potential application of Artificial Intelligence (AI) in the form of Deep Learning (DL) techniques to diagnostic radiology indicates that the next technological development phase may already be underway. The paper outlines the historical development of AI techniques, including Machine Learning and DL Neural Networks and discusses how such developments may affect radiological practice over the coming decades. The ongoing growth in the world market for radiological services is potentially a significant driver for change. The application of AI and DL learning techniques will place quantification of diagnostic outcomes at the heart of performance evaluation and quality standards. The effect this might have on the optimisation process will be discussed and in particular the possible need for automation in order to meet more stringent and standardised performance requirements that might result from these developments. Changes in radiological practices would also impact upon patient protection including the associated scientific support requirements and these are discussed.
本文探讨了科学技术在帮助社会变革中的作用。放射诊断学就是一个因这些发展而发生重大变化的例子，在过去的 40 年中，放射诊断学产生的医学影像数据量大幅增加。然而，这些发展在很大程度上保留了放射科工作流程中的人为因素（放射科医师、放射技师和放射科医师）。放射诊断学现在已经到了这样一个阶段，仅凭人类观察者来形成临床意见，已经无法充分利用所产生的大量信息，而这一过程在 100 多年来都没有改变。为了解决这个问题，人工智能（AI）在深度学习（DL）技术中的潜在应用表明，下一个技术发展阶段可能已经在进行中。本文概述了 AI 技术的历史发展，包括机器学习和 DL 神经网络，并讨论了这些发展在未来几十年可能对放射科实践产生的影响。放射科服务的全球市场持续增长，可能是推动变革的重要因素。AI 和 DL 学习技术的应用将使诊断结果的量化成为绩效评估和质量标准的核心。本文将讨论这可能对优化过程产生的影响，特别是为了满足这些发展可能带来的更严格和标准化的性能要求，可能需要实现自动化。放射科实践的变化也将影响到患者保护，包括相关的科学支持要求，这些都将在文中进行讨论。
