当前位置: X-MOL 学术arXiv.cs.DB › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Accelerating COVID-19 Differential Diagnosis with Explainable Ultrasound Image Analysis
arXiv - CS - Databases Pub Date : 2020-09-13 , DOI: arxiv-2009.06116
Jannis Born, Nina Wiedemann, Gabriel Br\"andle, Charlotte Buhre, Bastian Rieck, Karsten Borgwardt

Controlling the COVID-19 pandemic largely hinges upon the existence of fast, safe, and highly-available diagnostic tools. Ultrasound, in contrast to CT or X-Ray, has many practical advantages and can serve as a globally-applicable first-line examination technique. We provide the largest publicly available lung ultrasound (US) dataset for COVID-19 consisting of 106 videos from three classes (COVID-19, bacterial pneumonia, and healthy controls); curated and approved by medical experts. On this dataset, we perform an in-depth study of the value of deep learning methods for differential diagnosis of COVID-19. We propose a frame-based convolutional neural network that correctly classifies COVID-19 US videos with a sensitivity of 0.98+-0.04 and a specificity of 0.91+-08 (frame-based sensitivity 0.93+-0.05, specificity 0.87+-0.07). We further employ class activation maps for the spatio-temporal localization of pulmonary biomarkers, which we subsequently validate for human-in-the-loop scenarios in a blindfolded study with medical experts. Aiming for scalability and robustness, we perform ablation studies comparing mobile-friendly, frame- and video-based architectures and show reliability of the best model by aleatoric and epistemic uncertainty estimates. We hope to pave the road for a community effort toward an accessible, efficient and interpretable screening method and we have started to work on a clinical validation of the proposed method. Data and code are publicly available.

中文翻译:

通过可解释的超声图像分析加速 COVID-19 鉴别诊断

控制 COVID-19 大流行很大程度上取决于快速、安全和高度可用的诊断工具的存在。与 CT 或 X 射线相比,超声具有许多实际优势,可以作为全球适用的一线检查技术。我们为 COVID-19 提供了最大的公开可用肺部超声(美国)数据集,其中包含来自三类(COVID-19、细菌性肺炎和健康对照)的 106 个视频;由医学专家策划和批准。在这个数据集上,我们深入研究了深度学习方法对 COVID-19 鉴别诊断的价值。我们提出了一种基于帧的卷积神经网络,可以正确分类 COVID-19 美国视频,灵敏度为 0.98+-0.04,特异性为 0.91+-08(基于帧的灵敏度为 0.93+-0.05,特异性为 0.87+-0.07)。我们进一步使用类激活图进行肺部生物标志物的时空定位,随后我们在与医学专家的蒙眼研究中验证了人在回路场景。为了实现可扩展性和鲁棒性,我们进行了消融研究,比较了移动友好、基于帧和基于视频的架构,并通过任意和认知不确定性估计显示了最佳模型的可靠性。我们希望为社区努力铺平道路,以实现可访问、高效和可解释的筛查方法,并且我们已开始对所提出的方法进行临床验证。数据和代码是公开的。为了实现可扩展性和鲁棒性,我们进行了消融研究,比较了移动友好、基于帧和基于视频的架构,并通过任意和认知不确定性估计显示了最佳模型的可靠性。我们希望为社区努力铺平道路,以实现可访问、高效和可解释的筛查方法,并且我们已开始对所提出的方法进行临床验证。数据和代码是公开的。为了实现可扩展性和鲁棒性,我们进行了消融研究,比较了移动友好、基于帧和基于视频的架构,并通过任意和认知不确定性估计显示了最佳模型的可靠性。我们希望为社区努力铺平道路,以实现可访问、高效和可解释的筛查方法,并且我们已开始对所提出的方法进行临床验证。数据和代码是公开的。
更新日期:2020-09-15
down
wechat
bug