文献速递胸部DR

外部COVID-19深度学习模型在ACR AI-LAB上的验证:一个勇敢的新世界

External COVID-19 Deep Learning Model Validation on ACR AI-LAB: It's a Brave New World.
PubMed 文献 · J Am Coll Radiol · 2022-04-08

研究将外部开发的COVID-19胸部X线疾病严重程度深度学习模型加载至独立学术医学中心的ACR AI-LAB平台,对141例经逆转录聚合酶链反应确诊COVID-19患者的胸片进行模型推理,计算肺部X线严重程度(PXS)评分。结果显示PXS评分与三位放射科医师独立判读的改良肺部水肿影像评估评分平均值相关(r=0.80),且PXS评分在入院患者及3天内插管或死亡患者中显著更高。结论认为AI-LAB可相对便捷地用于本地数据测试外部COVID-19胸片AI算法,显示PXS评分模型的可泛化性。

要点

  • 外部COVID-19胸片深度学习模型可在ACR AI-LAB平台本地运行并输出PXS评分。
  • PXS评分与三位放射科医师改良肺部水肿影像评估评分平均值相关(r=0.80)。
  • 入院患者PXS评分4.0 vs 非入院1.3(P<.001),3天内插管或死亡患者5.5 vs 3.3(P=.001)。

核心结论

  • AI-LAB成功用于在本地数据上相对便捷地测试外部COVID-19胸片AI算法,显示PXS评分模型的可泛化性;为让AI模型规模化并具有临床实用性,像免费可用的AI-LAB这样促进本地测试过程的软件工具对跨越医疗系统中的AI实施差距将很重要。

研究设计与样本

  • 研究论文;外部开发的COVID-19胸片肺部疾病严重程度深度学习模型加载至独立学术医学中心的AI-LAB平台,该中心与模型训练机构不同;数据集为141例经逆转录聚合酶链反应确诊COVID-19患者的胸片图像,路由至AI-LAB进行模型推理;参考标准为三位放射科医师独立判读的改良肺部水肿影像评估评分平均值。

诊断标准与关键数值

  • 模型对每张图像计算肺部X线严重程度(PXS)评分;PXS评分与放射科医师判读的改良肺部水肿影像评估评分平均值相关(r=0.80);入院患者PXS评分4.0 vs 非入院患者1.3(P<.001);3天内插管或死亡患者PXS评分5.5 vs 未发生者3.3(P=.001)。

临床应用与阅片要点

  • 原文未据此给出推荐。

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

PURPOSE: Deploying external artificial intelligence (AI) models locally can be logistically challenging. We aimed to use the ACR AI-LAB software platform for local testing of a chest radiograph (CXR) algorithm for COVID-19 lung disease severity assessment.

METHODS: An externally developed deep learning model for COVID-19 radiographic lung disease severity assessment was loaded into the AI-LAB platform at an independent academic medical center, which was separate from the institution in which the model was trained. The data set consisted of CXR images from 141 patients with reverse transcription-polymerase chain reaction-confirmed COVID-19, which were routed to AI-LAB for model inference. The model calculated a Pulmonary X-ray Severity (PXS) score for each image. This score was correlated with the average of a radiologist-based assessment of severity, the modified Radiographic Assessment of Lung Edema score, independently interpreted by three radiologists. The associations between the PXS score and patient admission and intubation or death were assessed.

RESULTS: The PXS score deployed in AI-LAB correlated with the radiologist-determined modified Radiographic Assessment of Lung Edema score (r = 0.80). PXS score was significantly higher in patients who were admitted (4.0 versus 1.3, P < .001) or intubated or died within 3 days (5.5 versus 3.3, P = .001).

CONCLUSIONS: AI-LAB was successfully used to test an external COVID-19 CXR AI algorithm on local data with relative ease, showing generalizability of the PXS score model. For AI models to scale and be clinically useful, software tools that facilitate the local testing process, like the freely available AI-LAB, will be important to cross the AI implementation gap in health care systems.

来源:J Am Coll Radiol,查看原文。版权归原作者所有。

引用

  1. Ardestani, Li, Chea, et al. External COVID-19 Deep Learning Model Validation on ACR AI-LAB: It's a Brave New World. J Am Coll Radiol. 2022. PMID: 35483438. doi:10.1016/j.jacr.2022.03.013

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。