Synthesis of COVID-19 chest X-rays using unpaired image-to-image translation.

Synthesis of COVID-19 chest X-rays using unpaired image-to-image translation.
复制标题

DOI:
10.1007/s13278-021-00731-5
复制
发表时间:
2021
影响因子:
2.8
通讯作者:
Hamza AB
Hamza AB
中科院分区:
其他
文献类型:
--
作者:
Zunair H;Hamza AB

文献摘要

参考文献

被引文献

相似文献

由于缺乏公开可用的2019年冠状病毒病(新冠肺炎)阳性患者胸部X光片数据集,我们利用课堂条件调整和对抗性训练,使用无监督的域自适应方法构建了首个此类开放的高保真新冠肺炎胸部X光图像合成数据集。我们的贡献是双重的。首先,当我们使用合成图像作为额外的训练集时,我们显示出使用各种深度学习结构的新冠肺炎检测的性能有相当大的改善。其次,我们展示了我们的图像合成方法如何作为数据匿名化工具,在仅对合成数据进行训练时获得类似的检测性能。此外,提出的数据生成框架为新冠肺炎检测,以及一般的医学图像分类任务提供了一个可行的解决方案。我们公开提供的基准数据集(https://github.com/hasibzunair/synthetic-covid-cxr-dataset.)由21,295张合成新冠肺炎胸部X光照片组成。从这个数据集收集的见解可以用于抗击新冠肺炎大流行的预防行动。
Motivated by the lack of publicly available datasets of chest radiographs of positive patients with coronavirus disease 2019 (COVID-19), we build the first-of-its-kind open dataset of synthetic COVID-19 chest X-ray images of high fidelity using an unsupervised domain adaptation approach by leveraging class conditioning and adversarial training. Our contributions are twofold. First, we show considerable performance improvements on COVID-19 detection using various deep learning architectures when employing synthetic images as additional training set. Second, we show how our image synthesis method can serve as a data anonymization tool by achieving comparable detection performance when trained only on synthetic data. In addition, the proposed data generation framework offers a viable solution to the COVID-19 detection in particular, and to medical image classification tasks in general. Our publicly available benchmark dataset (https://github.com/hasibzunair/synthetic-covid-cxr-dataset.) consists of 21,295 synthetic COVID-19 chest X-ray images. The insights gleaned from this dataset can be used for preventive actions in the fight against the COVID-19 pandemic.
DOI: 10.1016/s0140-6736(20)30183-5
发表时间: 2020-02-15
期刊: LANCET
影响因子: 168.9
作者:
Huang, Chaolin;Wang, Yeming;Cao, Bin
通讯作者: Cao, Bin
DOI: 10.1148/ryct.2020200034
发表时间: 2020-02-01
期刊: RADIOLOGY-CARDIOTHORACIC IMAGING
影响因子: --
作者:
Ng, Ming-Yen;Lee, Elaine Y. P.;Kuo, Michael D.
通讯作者: Kuo, Michael D.
DOI: 10.1038/nature21056
发表时间: 2017-02-02
期刊: Nature
影响因子: 64.8
作者:
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者: Thrun S
DOI: 10.1093/jamia/ocv080
发表时间: 2016-03-01
影响因子: 6.4
作者:
Demner-Fushman, Dina;Kohli, Marc D.;McDonald, Clement J.
通讯作者: McDonald, Clement J.
DOI: 10.1109/acii.2013.47
发表时间: 2013
期刊: International Conference on Affective Computing and Intelligent Interaction and workshops : [proceedings]. ACII (Conference)
影响因子: --
作者:
Jeni LA;Cohn JF;De La Torre F
通讯作者: De La Torre F