Comparison of GANs for Covid-19 X-ray classification

• Luiz Felipe Cavalcanti UNIFESP
• Lilian Berton UNIFESP

DOI: https://doi.org/10.5753/eniac.2021.18238

Resumo

Image classification has been applied to several real problems. However, getting labeled data is a costly task, since it demands time, resources and experts. Furthermore, some domains like disease detection suffer from unbalanced classes. These scenarios are challenging and degrade the performance of machine learning algorithms. In these cases, we can use Data Augmentation (DA) approaches to increase the number of labeled examples in a dataset. The objective of this work is to analyze the use of Generative Adversarial Networks (GANs) as DA, which are capable of synthesizing artificial data from the original data, under an adversarial process of two neural networks. The GANs are applied in the classification of unbalanced Covid-19 radiological images. Increasing the number of images led to better accuracy for all the GANs tested, especially in the multi-label dataset, mitigating the bias for unbalanced classes.

Referências

Afonso, B., Melo, L., Oliveira, W., Sousa, S., and Berton, L. (2019). Housing prices prediction with a deep learning and random forest ensemble. In Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional, pages 389–400. SBC.

Antoniou, A., Storkey, A., and Edwards, H. (2017). Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340.

Fawzi, A., Samulowitz, H., Turaga, D., and Frossard, P. (2016). Adaptive data augmentation for image classification. In 2016 IEEE International Conference on Image Processing (ICIP), pages 3688–3692.

Frid-Adar, M., Klang, E., Amitai, M., Goldberger, J., and Greenspan, H. (2018). Synthetic data augmentation using gan for improved liver lesion classification. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pages 289–293.

Gandhi, R. T., Lynch, J. B., and del Rio, C. (2020). Mild or moderate covid-19. The New England Journal of Medicine.

Garcia, K. and Berton, L. (2021). Topic detection and sentiment analysis in twitter content related to covid-19 from brazil and the usa. Applied Soft Computing, 101:107057.

Goel, T., Murugan, R., Mirjalili, S., and Chakrabartty, D. K. (2021). Automatic screening of covid-19 using an optimized generative adversarial network. Cognitive computation, pages 1–16.

Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep learning, volume 1. MIT press Cambridge.

Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. In Advances in neural information processing systems, pages 2672–2680.

KAGGLE (2020a). Covid-19 chest xray. Disponível em: https://www.kaggle.com/bachrr/covid-chest-xray.

KAGGLE (2020b). Covid-19/pneumonia chest xray). Disponível em: https://www.kaggle.com/prashant268/chest-xray-covid19-pneumonia.

Kazeminia, S., Baur, C., Kuijper, A., van Ginneken, B., Navab, N., Albarqouni, S., and Mukhopadhyay, A. (2020). Gans for medical image analysis. Artificial Intelligence in Medicine, page 101938.

LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436–444.

Loey, M., Smarandache, F., and M Khalifa, N. E. (2020). Within the lack of chest covid-19 x-ray dataset: a novel detection model based on gan and deep transfer learning. Symmetry, 12(4):651.

Menon, S., Galita, J., Chapman, D., Gangopadhyay, A., Mangalagiri, J., Nguyen, P., Yesha, Y., Yesha, Y., Saboury, B., and Morris, M. (2020). Generating realistic covid-19 x-rays with a mean teacher+ transfer learning gan. In 2020 IEEE International Conference on Big Data (Big Data), pages 1216–1225. IEEE.

Nguyen, G., Dlugolinsky, S., Bobák, M., Tran, V., García, Á. L., Heredia, I., Malík, P., and Hluch`y, L. (2019). Machine learning and deep learning frameworks and libraries for large-scale data mining: a survey. Artificial Intelligence Review, 52(1):77–124.

Quan, T. M., Thanh, H. M., Huy, T. D., Chanh, N. D. T., Anh, N. T. P., Vu, P. H., Nam, N. H., Tuong, T. Q., Dien, V. M., Van Giang, B., et al. (2021). Xpgan: X-ray projected generative adversarial network for improving covid-19 image classification. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pages 1509–1513. IEEE.

Russell, S. and Norvig, P. (2009). Artificial Intelligence: A Modern Approach, volume 84. Prentice Hall Press, Upper Saddle River, NJ, USA, 3rd edition.

Sano, H., Malere, J., and Berton, L. (2019). Single and multiple failures diagnostics of pneumatic valves using machine learning. In Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional, pages 202–213. SBC.

Tanaka, F. H. K. d. S. and Aranha, C. (2019). Data augmentation using gans. arXiv preprint arXiv:1904.09135.

Welander, P., Karlsson, S., and Eklund, A. (2018). Generative adversarial networks for image-to-image translation on multi-contrast mr images-a comparison of cyclegan and unit. arXiv preprint arXiv:1806.07777.

Yi, X., Walia, E., and Babyn, P. (2019). Generative adversarial network in medical imaging: A review. Medical image analysis, 58:101552.