Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands.
GROW School for Oncology and Reproduction, Maastricht University, Maastricht, The Netherlands.
PLoS One. 2023 May 2;18(5):e0285121. doi: 10.1371/journal.pone.0285121. eCollection 2023.
Recently, artificial intelligence (AI)-based applications for chest imaging have emerged as potential tools to assist clinicians in the diagnosis and management of patients with coronavirus disease 2019 (COVID-19).
To develop a deep learning-based clinical decision support system for automatic diagnosis of COVID-19 on chest CT scans. Secondarily, to develop a complementary segmentation tool to assess the extent of lung involvement and measure disease severity.
The Imaging COVID-19 AI initiative was formed to conduct a retrospective multicentre cohort study including 20 institutions from seven different European countries. Patients with suspected or known COVID-19 who underwent a chest CT were included. The dataset was split on the institution-level to allow external evaluation. Data annotation was performed by 34 radiologists/radiology residents and included quality control measures. A multi-class classification model was created using a custom 3D convolutional neural network. For the segmentation task, a UNET-like architecture with a backbone Residual Network (ResNet-34) was selected.
A total of 2,802 CT scans were included (2,667 unique patients, mean [standard deviation] age = 64.6 [16.2] years, male/female ratio 1.3:1). The distribution of classes (COVID-19/Other type of pulmonary infection/No imaging signs of infection) was 1,490 (53.2%), 402 (14.3%), and 910 (32.5%), respectively. On the external test dataset, the diagnostic multiclassification model yielded high micro-average and macro-average AUC values (0.93 and 0.91, respectively). The model provided the likelihood of COVID-19 vs other cases with a sensitivity of 87% and a specificity of 94%. The segmentation performance was moderate with Dice similarity coefficient (DSC) of 0.59. An imaging analysis pipeline was developed that returned a quantitative report to the user.
We developed a deep learning-based clinical decision support system that could become an efficient concurrent reading tool to assist clinicians, utilising a newly created European dataset including more than 2,800 CT scans.
最近，基于人工智能（AI）的胸部成像应用已经成为协助临床医生诊断和管理 2019 冠状病毒病（COVID-19）患者的潜在工具。
开发一种基于深度学习的临床决策支持系统，用于自动诊断胸部 CT 扫描中的 COVID-19。其次，开发一种补充分割工具来评估肺受累程度并测量疾病严重程度。
成立了成像 COVID-19 AI 倡议，以进行一项回顾性多中心队列研究，该研究包括来自欧洲七个不同国家的 20 个机构。纳入了疑似或已知 COVID-19 并接受胸部 CT 检查的患者。数据集在机构级别上进行拆分，以允许外部评估。数据注释由 34 名放射科医生/放射科住院医师完成，并包括质量控制措施。使用定制的 3D 卷积神经网络创建了一个多类分类模型。对于分割任务，选择了具有骨干残差网络（ResNet-34）的 UNET 样架构。
共纳入 2802 例 CT 扫描（2667 例独特患者，平均[标准差]年龄为 64.6[16.2]岁，男女比例为 1.3:1）。类别的分布（COVID-19/其他类型肺部感染/无感染影像学征象）分别为 1490（53.2%）、402（14.3%）和 910（32.5%）。在外部测试数据集上，多分类诊断模型的微观平均和宏观平均 AUC 值较高（分别为 0.93 和 0.91）。该模型提供了 COVID-19 与其他病例的可能性，其敏感性为 87%，特异性为 94%。分割性能中等，Dice 相似系数（DSC）为 0.59。开发了一种成像分析管道，为用户提供定量报告。
我们开发了一种基于深度学习的临床决策支持系统，该系统可以成为一种高效的并发阅读工具，利用包括 2800 多例 CT 扫描在内的新创建的欧洲数据集来协助临床医生。
Zotero 插件
