AI-Assisted CT as a Clinical and Research Tool for COVID-19.
AI-Assisted CT as a Clinical and Research Tool for COVID-19.
复制标题
DOI：
10.3389/frai.2021.590189
复制
发表时间：
2021
影响因子：
4
通讯作者：
Wood BJ
中科院分区：
文献类型：
--
作者：
Tse ZTH;Hovet S;Ren H;Barrett T;Xu S;Turkbey B;Wood BJ
人们强烈支持扩大计算机断层扫描 (CT) 在 COVID-19 临床和研究场景中的作用。逆转录聚合酶链反应 (RT-PCR) 检测是 COVID-19 诊断的黄金标准，它有两个潜在的弱点：获得结果的延迟以及当需求激增时 RT-PCR 检测试剂盒可能会耗尽或完全无法使用。这篇透视文章讨论了在缺乏足够的 RT-PCR 检测试剂盒的医院中将 CT 与 RT-PCR 结合使用的潜在用途。基于英国和中国使用 CT 进行 COVID-19 诊断和筛查的情况，讨论了这种方法的先例。提出了在实现 CT 人工智能 (AI) 的潜在作用之前需要解决的障碍和挑战。潜在的作用包括更准确的临床分类、研究作用和机制的表征，以及告知临床试验反应标准作为临床结果的替代。
There is compelling support for widening the role of computed tomography (CT) for COVID-19 in clinical and research scenarios. Reverse transcription polymerase chain reaction (RT-PCR) testing, the gold standard for COVID-19 diagnosis, has two potential weaknesses: the delay in obtaining results and the possibility of RT-PCR test kits running out when demand spikes or being unavailable altogether. This perspective article discusses the potential use of CT in conjunction with RT-PCR in hospitals lacking sufficient access to RT-PCR test kits. The precedent for this approach is discussed based on the use of CT for COVID-19 diagnosis and screening in the United Kingdom and China. The hurdles and challenges are presented, which need addressing prior to realization of the potential roles for CT artificial intelligence (AI). The potential roles include a more accurate clinical classification, characterization for research roles and mechanisms, and informing clinical trial response criteria as a surrogate for clinical outcomes.