Generating Realistic COVID-19 x-rays with a Mean Teacher + Transfer Learning GAN
Generating Realistic COVID-19 x-rays with a Mean Teacher + Transfer Learning GAN
复制标题
DOI：
10.1109/bigdata50022.2020.9377878
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Sumeet Menon;Joshua Galita;David Chapman;A. Gangopadhyay;Jayalakshmi Mangalagiri;Phuong Nguyen;Y. Yesha;Y. Yesha;B. Saboury;Michael Morris
中科院分区：
文献类型：
--
作者：
Sumeet Menon;Joshua Galita;David Chapman;A. Gangopadhyay;Jayalakshmi Mangalagiri;Phuong Nguyen;Y. Yesha;Y. Yesha;B. Saboury;Michael Morris
COVID-19是一种新型传染病，截至2020年11月，全球有超过120万人死亡。快速检测的需求是一个高度优先事项，包括X射线图像分类在内的替代检测策略是一个很有前途的研究领域。然而，目前，COVID-19 X射线图像的公共数据集的数据量很低，这使得开发准确的图像分类器具有挑战性。最近的几篇论文利用了生成对抗网络（GAN）来增加训练数据量。但现实的合成COVID-19 X射线仍然具有挑战性。我们提出了一种新的Mean Teacher + Transfer GAN（MTT-GAN），可以生成高质量的COVID-19胸部X射线图像。为了创建一个更准确的GAN，我们采用了Kaggle肺炎x射线数据集的迁移学习，这是一个比公共COVID-19数据集大几个数量级的高度相关的数据源。此外，我们采用Mean Teacher算法作为约束，以提高训练的稳定性。我们的定性分析表明，MTT-GAN生成的X射线图像大大上级基线GAN，并且在视觉上与真实的X射线相当。尽管委员会认证的放射科医生可以区分MTT-GAN假的和真实的COVID-19 X射线，但定量分析表明，与基线GAN相比，MTT-GAN大大提高了二元COVID-19分类器和多类肺炎分类器的准确性。与文献中最近报道的类似二元和多类COVID-19筛查任务的结果相比，我们的分类准确性是有利的。
COVID-19 is a novel infectious disease responsible for over 1.2 million deaths worldwide as of November 2020. The need for rapid testing is a high priority and alternative testing strategies including x-ray image classification are a promising area of research. However, at present, public datasets for COVID-19 x-ray images have low data volumes, making it challenging to develop accurate image classifiers. Several recent papers have made use of Generative Adversarial Networks (GANs) in order to increase the training data volumes. But realistic synthetic COVID-19 x-rays remain challenging to generate. We present a novel Mean Teacher + Transfer GAN (MTT-GAN) that generates COVID-19 chest x-ray images of high quality. In order to create a more accurate GAN, we employ transfer learning from the Kaggle pneumonia x-ray dataset, a highly relevant data source orders of magnitude larger than public COVID-19 datasets. Furthermore, we employ the Mean Teacher algorithm as a constraint to improve stability of training. Our qualitative analysis shows that the MTT-GAN generates x-ray images that are greatly superior to a baseline GAN and visually comparable to real x-rays. Although board-certified radiologists can distinguish MTT-GAN fakes from real COVID-19 x-rays, quantitative analysis shows that MTT-GAN greatly improves the accuracy of both a binary COVID-19 classifier as well as a multi-class pneumonia classifier as compared to a baseline GAN. Our classification accuracy is favorable as compared to recently reported results in the literature for similar binary and multi-class COVID-19 screening tasks.