用改进的Wasserstein GAN生成肺部X光片，提升新冠检测准确率。
A Hybrid Approach for COVID-19 Detection: Combining Wasserstein GAN with Transfer Learning
- 设计定制 Wasserstein GAN，生成比真实数据多19%的胸部X光图像。
- 在扩增数据上训练的VGG-16模型达到99.17%分类准确率。
- 方法适用于小样本图像分析，适合医疗影像研究者参考。
新冠疫情传播迅速，早期诊断对阻断传播链至关重要。当前临床中新冠与病毒性肺炎等肺部感染影像重叠严重，且数据集有限、训练耗时长，导致模型易过拟合、泛化能力差。为解决此问题，本文提出基于GAN的数据增强方法，利用定制 Wasserstein GAN 生成更多胸部X光图像，相比真实数据增加19%。扩增后的数据用于训练四种深度学习模型：VGG-16、ResNet-50、GoogLeNet 和 MNAST。实验表明，使用扩增数据后模型分类性能显著提升，其中 VGG-16 达到最高测试准确率99.17%，其余模型分别为93.9%（ResNet-50）、94.49%（GoogLeNet）和97.75%（MNAST）。进一步对比了现有先进模型，验证了所提方法的有效性。该框架可推广至其他图像分析中小样本问题。
原文摘要 · Abstract (English)
COVID-19 is extremely contagious and its rapid growth has drawn attention towards its early diagnosis. Early diagnosis of COVID-19 enables healthcare professionals and government authorities to break the chain of transition and flatten the epidemic curve. With the number of cases accelerating across the developed world, COVID-19 induced Viral Pneumonia cases is a big challenge. Overlapping of COVID-19 cases with Viral Pneumonia and other lung infections with limited dataset and long training hours is a serious problem to cater. Limited amount of data often results in over-fitting models and due to this reason, model does not predict generalized results. To fill this gap, we proposed GAN-based approach to synthesize images which later fed into the deep learning models to classify images of COVID-19, Normal, and Viral Pneumonia. Specifically, customized Wasserstein GAN is proposed to generate 19% more Chest X-ray images as compare to the real images. This expanded dataset is then used to train four proposed deep learning models: VGG-16, ResNet-50, GoogLeNet and MNAST. The result showed that expanded dataset utilized deep learning models to deliver high classification accuracies. In particular, VGG-16 achieved highest accuracy of 99.17% among all four proposed schemes. Rest of the models like ResNet-50, GoogLeNet and MNAST delivered 93.9%, 94.49% and 97.75% testing accuracies respectively. Later, the efficiency of these models is compared with the state of art models on the basis of accuracy. Further, our proposed models can be applied to address the issue of scant datasets for any problem of image analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。