arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.05096eess.IVcs.CVcs.LG
收藏

COVID CT-Net:使用注意力卷积网络从胸部CT图像预测新冠肺炎

COVID CT-Net: Predicting Covid-19 From Chest CT Images Using Attentional Convolutional Network

Isfahan University of Technology(伊斯法罕理工大学);Snap Inc.(Snap公司);Isfahan University of Medical Sciences(伊斯法罕医科大学);The University of Iowa(爱荷华大学)

Shakib Yazdani, Shervin Minaee, Rahele Kafieh, Narges Saeedizadeh, Milan Sonka

摘要:

新型冠状病毒病(COVID-19)大流行已在全球200多个国家引发大规模疫情,对全球许多人的健康和生活造成严重影响。截至2020年8月25日,超过2000万人感染,超过80万人死亡。计算机断层扫描(CT)图像可用作耗时的“逆转录聚合酶链反应(RT-PCR)”测试的替代方法,以检测COVID-19。在这项工作中,我们开发了一个深度学习框架来从CT图像中预测COVID-19。我们建议使用注意力卷积网络,它可以专注于胸部的感染区域,使其能够进行更准确的预测。我们在2000多张CT图像的数据集上训练了我们的模型,并报告了它在各种流行指标方面的性能,如灵敏度、特异性、曲线下面积以及精确度-召回率曲线,并取得了非常有希望的结果。我们还提供了几个测试图像的模型的注意力图的可视化,并显示我们的模型正在按预期处理感染区域。除了开发机器学习建模框架外,我们还在委员会认证的放射科医生的帮助下提供了胸部潜在感染区域的手动注释,并将其公开提供给其他研究人员。

英文摘要:

The novel corona-virus disease (COVID-19) pandemic has caused a major outbreak in more than 200 countries around the world, leading to a severe impact on the health and life of many people globally. As of Aug 25th of 2020, more than 20 million people are infected, and more than 800,000 death are reported. Computed Tomography (CT) images can be used as a as an alternative to the time-consuming "reverse transcription polymerase chain reaction (RT-PCR)" test, to detect COVID-19. In this work we developed a deep learning framework to predict COVID-19 from CT images. We propose to use an attentional convolution network, which can focus on the infected areas of chest, enabling it to perform a more accurate prediction. We trained our model on a dataset of more than 2000 CT images, and report its performance in terms of various popular metrics, such as sensitivity, specificity, area under the curve, and also precision-recall curve, and achieve very promising results. We also provide a visualization of the attention maps of the model for several test images, and show that our model is attending to the infected regions as intended. In addition to developing a machine learning modeling framework, we also provide the manual annotation of the potentionally infected regions of chest, with the help of a board-certified radiologist, and make that publicly available for other researchers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑